Document completed LLM and reference expansion

docs/cli.md

@@ -20,7 +20,7 @@ a bearer token.
 
 ```text
 notarius help
-notarius run <pipeline-id> --input path/to/source.json [--config path/to/config.yml] [--only lane-a,lane-b] [--reference slot=path] [--without-reference slot]
+notarius run <pipeline-id> --input path/to/source.json [--config path/to/config.yml] [--only lane-a,lane-b] [--reference selector=path] [--without-reference selector]
 notarius config validate --config path/to/config.yml [--pipeline pipeline-id] [--only lane-a,lane-b]
 notarius pipelines list --config path/to/config.yml [--json]
 ```
@@ -46,34 +46,44 @@ Flags:
   invocation.
 - `--llm-profile id`: override every effective module binding to use one LLM
   profile.
-- `--reference slot=path`: bind a reference path to an extractor reference
-  slot. Repeatable. Use `lane.slot=path` when multiple selected lanes declare
-  the same slot.
-- `--without-reference slot`: remove a configured optional reference binding.
-  Repeatable. Use `lane.slot` when multiple selected lanes declare the same
-  slot.
+- `--reference selector=path`: bind a reference path to a chunk, extractor, or
+  normalizer reference slot. Repeatable.
+- `--without-reference selector`: remove a configured optional reference binding.
+  Repeatable. It accepts the same selector forms as `--reference`, without
+  `=path`.
 
 On success, the command prints the completed pipeline ID, approved and rejected
 artifact counts, and the output directory. If the run completes with warnings,
 the warning count is printed to stderr.
 
-Reference flags are resolved against selected artifact lanes before the run
-starts. Flat slot names are accepted only when exactly one selected lane
-declares that slot. Bound reference files are read before extraction, validated
-as UTF-8 text, and passed only to the lane extractor that declares the slot.
-Notarius infers reference media types from file extensions for provenance and
-for optional slot checks. Reference content is not written to diagnostics, logs,
-errors, or manifests.
+Reference flags are resolved against selected chunk, extractor, and normalizer
+targets before the run starts. Flat slot names are accepted only when exactly
+one selected target declares that slot. Bound reference files are read before
+pipeline work starts, validated as UTF-8 text, and recorded as provenance for
+the target that declares the slot. Runtime reference content is passed to the
+chunker, extractor, or normalizer target that declares the slot. Notarius infers
+reference media types from file extensions for provenance and for optional slot
+checks. Reference content is not written to diagnostics, logs, errors, or
+manifests.
 
 Reference binding precedence is:
 
 1. pipeline-level config `references`;
-2. lane-level config `references`;
+2. target-local config references, including legacy lane-level extractor
+   `references`;
 3. `--reference` run flags;
 4. `--without-reference` run flags.
 
-`--reference` binds or replaces one slot for one selected lane. Use
-`slot=path` when the selected lanes declare the slot unambiguously:
+`--reference` binds or replaces one slot for one selected target. Selectors are:
+
+- `slot=path`: valid when exactly one selected target declares `slot`;
+- `chunk.slot=path`: target the chunker;
+- `lane.slot=path`: valid when exactly one selected extractor or normalizer in
+  that lane declares `slot`;
+- `lane.extract.slot=path`: target a lane extractor;
+- `lane.normalize.slot=path`: target a lane normalizer.
+
+Use `slot=path` when the selected targets declare the slot unambiguously:
 
 ```sh
 go run ./cmd/notarius run dnd-session \
@@ -82,14 +92,25 @@ go run ./cmd/notarius run dnd-session \
   --reference roster=./campaign-roster.txt
 ```
 
-Use `lane.slot=path` when multiple selected lanes declare the same slot or when
-you want to target a specific lane:
+Use an explicit selector when multiple selected targets declare the same slot or
+when you want to target a specific target:
 
 ```sh
 go run ./cmd/notarius run dnd-session \
   --config examples/dnd-spells.config.yml \
   --input examples/seriatim-minimal-transcript.json \
-  --reference spells.glossary=./campaign-glossary.txt
+  --reference spells.extract.glossary=./campaign-glossary.txt
+```
+
+The same grammar can target chunk and normalize slots when the configured
+modules declare them:
+
+```sh
+go run ./cmd/notarius run dnd-session \
+  --config path/to/config.yml \
+  --input examples/seriatim-minimal-transcript.json \
+  --reference chunk.scene_guide=./campaign-scenes.txt \
+  --reference spells.normalize.normalization_notes=./normalization-notes.txt
 ```
 
 Use `--without-reference` to remove a configured optional binding for a run:

docs/config.md

@@ -124,9 +124,9 @@ Pipeline fields:
 - `artifacts`: required for pipeline resolution. It maps artifact lane IDs to
   lane definitions.
 - `output`: optional module binding. Default module is `json`.
-- `references`: optional map of extractor reference slot names to reference
-  paths. These bindings are defaults for artifact lanes whose extractor declares
-  the matching slot.
+- `references`: optional map of reference slot names to reference paths. These
+  bindings are defaults for eligible pipeline targets that declare the matching
+  slot.
 
 Artifact lane fields:
 
@@ -135,28 +135,32 @@ Artifact lane fields:
 - `normalize`: optional module binding. Default module is `noop`.
 - `validators`: optional list of module bindings. The production CLI currently
   does not register validator modules.
-- `references`: optional map of extractor reference slot names to reference
-  paths. Lane bindings override pipeline-level bindings for the same slot.
+- `references`: optional compatibility alias for extractor reference bindings.
+  Lane bindings override pipeline-level bindings for the same slot.
 
 `notarius run` and `notarius config validate --pipeline` resolve the pipeline
 against the production module catalog and fail fast for unknown or incompatible
 module keys.
 
-Reference bindings are validated against extractor-declared slots during
-pipeline resolution. Required slots must be bound after config defaults,
-lane-level bindings, and run-time `--reference` or `--without-reference`
-overrides are applied. Config-relative paths are resolved relative to the
-config file; CLI reference paths are resolved relative to the current working
-directory. Bound files must be UTF-8 text and are passed only to lane
-extractors that declare the slot. Reference media types are inferred from file
-extensions, recorded as canonical base media types, and checked only when a
-module declares `AcceptedMediaTypes`; unknown extensions are recorded as
+Reference bindings are validated against reference slots declared by eligible
+chunk, extract, and normalize targets during pipeline resolution. Required slots
+must be bound after config defaults, target-local references, lane-level
+compatibility bindings, and run-time `--reference` or `--without-reference`
+overrides are applied. Config-relative paths are resolved relative to the config
+file; CLI reference paths are resolved relative to the current working
+directory. Materialized bound files must be UTF-8 text. Materialized reference
+provenance is recorded for chunk, extractor, and normalizer targets, and runtime
+reference content is passed to the target that declares the slot. Reference
+media types are inferred from file extensions, recorded as canonical base media
+types, and checked only when a module declares
+`AcceptedMediaTypes`; unknown extensions are recorded as
 `application/octet-stream`. Reference content is not written to diagnostics,
 logs, errors, or manifests.
 
 Pipeline-level `references` are defaults. They are valid when at least one
-declared lane in the pipeline has an extractor that declares the slot. During a
-run, they apply only to selected lanes whose extractor declares the slot:
+eligible target in the full configured pipeline declares the slot, including
+chunk, extractor, and normalizer targets. During a run, they apply only to the
+selected targets that declare the slot:
 
 ```yaml
 pipelines:
@@ -170,7 +174,9 @@ pipelines:
         extract: dnd/spells
 ```
 
-Lane-level `references` override or add bindings for one lane:
+Extractor binding `references` are the canonical lane-local location. The
+legacy lane-level `references` field remains supported as an alias; when both
+bind the same slot, `extract.references` wins:
 
 ```yaml
 pipelines:
@@ -180,11 +186,27 @@ pipelines:
       glossary: ./campaign/glossary.txt
     artifacts:
       spells:
-        extract: dnd/spells
         references:
-          roster: ./campaign/session-roster.txt
+          roster: ./campaign/legacy-roster.txt
+        extract:
+          module: dnd/spells
+          references:
+            roster: ./campaign/session-roster.txt
 ```
 
+`chunk.references` and `normalize.references` are accepted in object-form
+bindings. They override pipeline-level defaults for slots declared by the chunk
+or normalizer module. Extractor-local references apply only to the extractor,
+and normalizer-local references apply only to the normalizer.
+
+Stage-local reference fields use the same map shape at:
+
+- `pipelines.<id>.chunk.references`
+- `pipelines.<id>.artifacts.<lane>.extract.references`
+- `pipelines.<id>.artifacts.<lane>.normalize.references`
+
+Each binding is valid only when that target module declares the slot.
+
 ## Module Bindings
 
 Every module binding may use shorthand:
@@ -208,6 +230,9 @@ Binding fields:
 - `module`: module key.
 - `llm_profile`: optional LLM profile ID. Empty means `default`.
 - `options`: optional module-specific settings.
+- `references`: optional reference bindings. Supported only for `chunk`,
+  `extract`, and `normalize` bindings. `input`, `merge`, validator, and
+  `output` bindings reject this field during validation.
 
 The `--llm-profile` run flag overrides every effective module binding to use
 one configured profile.

docs/integrations/json-output.md

@@ -100,8 +100,12 @@ Fields with empty values may be omitted by JSON encoding.
 
 `source_digests` contains source document digests only. Bound references are
 recorded separately under `references`, which contains provenance only:
-lane ID, slot name, origin type and URI, digest, media type, byte size, and
-binding source. Reference content is not written to durable output.
+target stage, lane ID when present, slot name, origin type and URI, digest,
+media type, byte size, and binding source. Reference content is not written to
+durable output.
+
+Reference `stage` is `chunk`, `extract`, or `normalize`. `lane_id` is omitted
+for chunk references and present for extract and normalize references.
 
 When references are bound, the manifest section has this shape:
 
@@ -109,6 +113,7 @@ When references are bound, the manifest section has this shape:
 {
   "references": [
     {
+      "stage": "extract",
       "lane_id": "spells",
       "slot_name": "roster",
       "origin_type": "file",

docs/internal/llm.md

@@ -17,8 +17,8 @@ The request contains messages, optional model override, response schema name,
 and response schema JSON. The caller supplies a pointer target for decoded
 structured output.
 
-Extractors own prompts and schemas. Provider adapters should not contain
-domain-specific prompt logic.
+Modules that call the LLM own their prompts and schemas. Provider adapters
+should not contain domain-specific prompt logic.
 
 ## Production Client Construction
 

docs/internal/modules.md

@@ -20,21 +20,24 @@ A production module package should provide:
 Module specs should describe capabilities accurately. Resolution uses specs to
 reject incompatible pipelines before execution.
 
-Extractor modules that accept auxiliary reference material must declare slots
-through both `ReferenceSlots()` and `ModuleSpec().ReferenceSlots`. The runtime
-slot list and registry metadata should match so config validation can inspect
-slots without constructing extractor instances. A slot declaration names the
-slot, whether it is required, accepted media types, whether multiple items are
-allowed, and any byte limit. Empty `AcceptedMediaTypes` means any inferred
-media type is accepted, though the file must still be UTF-8 text. When a slot
-declares accepted media types, Notarius compares the canonical base media type
-inferred from the file extension, case-insensitively and without parameters.
+Chunk, extract, and normalize modules that accept auxiliary reference material
+must declare slots through both `ReferenceSlots()` and
+`ModuleSpec().ReferenceSlots`. The runtime slot list and registry metadata
+should match so config validation can inspect slots without constructing module
+instances. A slot declaration names the slot, whether it is required, accepted
+media types, whether multiple items are allowed, and any byte limit. Empty
+`AcceptedMediaTypes` means any inferred media type is accepted, though the file
+must still be UTF-8 text. When a slot declares accepted media types, Notarius
+compares the canonical base media type inferred from the file extension,
+case-insensitively and without parameters.
 
-Reference content is delivered only to the lane extractor through
-`contracts.ExtractionRequest.References`. It is not source evidence and must not
-be converted into `SourceRef` values. If a module prompt uses references, load
-the prompt bundle with the same declared slots and render with
-`RenderUserSystemWithReferences`. Prompt templates may use the `reference`
+The resolver materializes reference content for chunk, extractor, and
+normalizer targets. Runtime delivery uses `contracts.ChunkRequest.References`,
+`contracts.ExtractionRequest.References`, and
+`contracts.NormalizeRequest.References`. Reference material is not source
+evidence and must not be converted into `SourceRef` values. If a module prompt
+uses references, load the prompt bundle with the same declared slots and render
+with `RenderUserSystemWithReferences`. Prompt templates may use the `reference`
 function for content and the `hasreference` function for conditional sections.
 Prompt metadata hashes remain based on template source, not rendered reference
 bytes.
@@ -44,6 +47,9 @@ when they need model-backed chunking. The pipeline runner validates generic
 chunk result invariants before extraction; module-owned policies may be stricter
 but must stay within the module package.
 
+Normalize modules receive the structured LLM client through
+`contracts.NormalizeRequest` when they need model-backed reconciliation.
+
 ## `seriatim` Input
 
 Package: `internal/modules/input/seriatim`

docs/internal/pipeline.md

@@ -31,32 +31,34 @@ before execution:
 The CLI writes the resolved pipeline and digest to diagnostics.
 
 Pipeline profiles and artifact lanes may include reference binding maps keyed by
-extractor reference slot name. During resolution, pipeline-level bindings act as
-defaults for selected lanes whose extractor declares the slot, lane-level
-bindings override or add lane bindings, runtime `--reference` requests override
-config bindings, and runtime unbinds remove optional bindings. Flat runtime slot
-names are resolved only when exactly one selected lane declares the slot;
-otherwise the CLI requires `lane.slot`. Resolution validates bindings against
-extractor specs and records lane-scoped binding metadata. It does not read
-reference files or include reference bytes in source digests.
+reference slot name. During resolution, pipeline-level bindings act as defaults
+for selected chunk, extractor, and normalizer targets that declare the slot;
+target-local bindings override or add bindings for that target. Runtime
+`--reference` requests override target config bindings, and runtime unbinds
+remove optional target bindings. Flat runtime slot names are resolved only when
+exactly one selected target declares the slot; otherwise the CLI requires a more
+specific selector such as `chunk.slot`, `lane.extract.slot`, or
+`lane.normalize.slot`. Resolution validates bindings against the declaring
+target specs and stores the bindings in target-aware resolved reference holders.
+It does not read reference files or include reference bytes in source digests.
 
-During run preparation, resolved file references are materialized before any
-LLM-backed pipeline work. Config bindings resolve relative to the config file,
-CLI bindings resolve relative to the current working directory, and materialized
-reference content is passed only to the matching lane extractor through
-`ExtractionRequest`. Materialization accepts UTF-8 text files, computes
-`sha256:` content digests, records file origins, infers canonical base media
-types from file extensions, enforces declared byte limits, and warns for empty
-bound files. Media-type acceptance is checked only when a slot declares
+During run preparation, resolved file references for chunk, extractor, and
+normalizer targets are materialized before any LLM-backed pipeline work. Config
+bindings resolve relative to the config file, and CLI bindings resolve relative
+to the current working directory. Materialization accepts UTF-8 text files,
+computes `sha256:` content digests, records file origins, infers canonical base
+media types from file extensions, enforces declared byte limits, and warns for
+empty bound files. Media-type acceptance is checked only when a slot declares
 `AcceptedMediaTypes`; unknown extensions are recorded as
 `application/octet-stream`. Reference content is omitted from diagnostics and
 manifests. The CLI writes provenance-only resolved reference diagnostics, and
-the run manifest records lane-scoped reference provenance separately from source
-digests.
+the run manifest records target-stage reference provenance separately from
+source digests. Runtime reference content is passed to the matching chunker,
+extractor, or normalizer request.
 
 Prompt bundles can declare reference slots and use `reference` and
 `hasreference` template functions. Bundle loading validates string-literal slot
-names against the declaration. Rendering receives a lane reference set from the
+names against the declaration. Rendering receives a target reference set from the
 caller; unbound optional slots render as empty strings, and `hasreference`
 returns true only when at least one bound item has content.
 
@@ -74,9 +76,10 @@ Every production module registers a `ModuleSpec` with:
 - `Provides`: capabilities added after that module runs;
 - `Requires`: capabilities that must already be available.
 
-Extractor specs may also declare reference slots. Slot declarations are
-available from registry metadata without constructing extractor instances.
-Non-extractor module specs must not declare reference slots.
+Chunk, extract, and normalize specs may also declare reference slots. Slot
+declarations are available from registry metadata without constructing module
+instances. Input, merge, validate, and output specs must not declare reference
+slots.
 
 Capability checks prevent incompatible pipeline composition before a run starts.
 
@@ -114,10 +117,10 @@ The runner:
 ## Chunk Results
 
 Chunkers implement `contracts.Chunker` and receive a `contracts.ChunkRequest`
-with the validated source document, the structured LLM client, the configured
-LLM profile, module options, and run metadata. Deterministic and LLM-backed
-chunkers use the same contract; provider construction stays outside chunk
-modules.
+with the validated source document, reference set, structured LLM client, the
+configured LLM profile, module options, and run metadata. Deterministic and
+LLM-backed chunkers use the same contract; provider construction stays outside
+chunk modules.
 
 After `Chunk` returns, the runner appends chunker warnings before returning any
 chunker error. When chunking succeeds, the runner validates generic chunk

docs/operations.md

@@ -63,9 +63,9 @@ Implemented diagnostics artifacts:
   path, selected lanes, run ID, and pipeline digest when available.
 - `effective-config.json`: resolved config with API keys redacted.
 - `resolved-pipeline.json`: resolved module bindings and pipeline digest.
-- `resolved-references.json`: lane-scoped resolved reference provenance,
-  including origin, digest, media type, byte size, and binding source, without
-  reference content.
+- `resolved-references.json`: resolved reference provenance, including target
+  stage, lane ID when present, origin, digest, media type, byte size, and
+  binding source, without reference content.
 - `run-manifest.json`: the same run manifest written to durable output when it
   is available, including top-level module metadata when present.
 - `warnings.json`: warning list.

docs/roadmap/future.md

@@ -8,11 +8,6 @@ future work only.
 
 - Additional input adapters, such as Markdown or note-export formats.
 - Additional D&D extractors beyond spell casts.
-- First-class LLM access for all LLM-eligible pipeline stages: `chunk`,
-  `extract`, and `normalize`.
-- Expand reference support beyond extractors to `chunk` and `normalize`
-  modules, using the same declared-slot model and preserving stage-specific
-  ownership boundaries.
 - Add non-file reference producers, such as prior-run artifacts, derived
   summaries, or entity registries, without changing module-facing reference
   item contracts.

docs/roadmap/implementation.md

@@ -1,463 +1,21 @@
-# LLM And Stage Reference Expansion Implementation Plan
+# LLM And Reference Expansion Completed
 
-## Purpose
+This roadmap item is implemented.
 
-Implement these future roadmap items:
+Notarius now supports first-class LLM access for chunk, extract, and normalize
+modules, plus target-aware reference declaration, binding, CLI override,
+materialization, provenance, and runtime delivery for chunker, extractor, and
+normalizer targets.
 
-- First-class LLM access for all LLM-eligible pipeline stages: `chunk`,
-  `extract`, and `normalize`.
-- Expand reference support beyond extractors to `chunk` and `normalize`
-  modules, using the same declared-slot model and preserving stage-specific
-  ownership boundaries.
+Current behavior is documented in:
 
-This is a decision-complete implementation plan for an LLM coding agent. Follow
-the stages in order. Keep current-behavior docs unchanged until the
-corresponding behavior exists. Do not implement token budgeting, non-file
-reference producers, structured references, retrieval, or multiple effective LLM
-profiles in this pass.
+- [CLI Reference](../cli.md)
+- [Configuration](../config.md)
+- [Pipeline Internals](../internal/pipeline.md)
+- [Module Internals](../internal/modules.md)
+- [JSON Output](../integrations/json-output.md)
+- [Troubleshooting](../troubleshooting.md)
 
-## Target Behavior
-
-LLM access:
-
-- `contracts.ChunkRequest`, `contracts.ExtractionRequest`, and
-  `contracts.NormalizeRequest` all carry `LLMClient`, `LLMProfile`, `Options`,
-  and `Metadata`.
-- The runner passes the configured structured LLM client to chunkers,
-  extractors, and normalizers.
-- The existing single-effective-LLM-profile CLI restriction remains in place.
-
-References:
-
-- `chunk`, `extract`, and `normalize` modules can declare reference slots.
-- The framework treats references as opaque UTF-8 text plus provenance. Stage
-  modules own slot names and semantics.
-- Reference slots are declared in both runtime module contracts and
-  `ModuleSpec.ReferenceSlots`, so config and pipeline validation can inspect
-  slots without constructing modules.
-- `ModuleSpec.ReferenceSlots` is valid only for `chunk`, `extract`, and
-  `normalize` modules. `input`, `merge`, `validate`, and `output` modules must
-  not declare reference slots.
-- Pipeline-level `references` remain defaults. A pipeline-level binding is
-  valid when any declared eligible module in the pipeline declares the slot. In
-  a run, it is applied only to selected targets that declare the slot.
-- Stage-local reference bindings override pipeline-level defaults for that
-  target.
-- CLI `--reference` and `--without-reference` can target chunk, extract, and
-  normalize references explicitly, while preserving existing unambiguous flat
-  forms.
-- Reference materialization still accepts file producers only, validates UTF-8,
-  infers media types from extensions, enforces optional `AcceptedMediaTypes` and
-  `MaxBytes`, warns for empty files, and never writes content to diagnostics,
-  logs, errors, or manifests.
-- Manifest and diagnostics provenance identifies the reference target stage and,
-  for lane-owned stages, the lane ID.
-
-## Target Config Shape
-
-Keep existing config compatibility and add stage-specific binding locations:
-
-```yaml
-pipelines:
-  dnd-session:
-    input: seriatim
-    references:
-      campaign_context: ./campaign/context.md
-    chunk:
-      module: dnd/scenes
-      references:
-        scene_guide: ./campaign/scenes.md
-    artifacts:
-      spells:
-        extract: dnd/spells
-        references:
-          glossary: ./campaign/glossary.md
-        normalize:
-          module: noop
-          references:
-            normalization_notes: ./campaign/normalization.md
-```
-
-Compatibility rule:
-
-- Existing `artifacts.<lane>.references` remains supported as an alias for
-  extractor references.
-- New `artifacts.<lane>.extract.references` is the canonical extract-stage
-  location.
-- If both the legacy lane-level `references` map and
-  `extract.references` bind the same slot, `extract.references` wins. This keeps
-  migration deterministic and avoids breaking existing configs.
-
-`chunk.references` and `normalize.references` are supported only when their
-module binding uses object form. Scalar bindings continue to work when no
-stage-local references are needed.
-
-## Target CLI Reference Selectors
-
-Preserve existing valid forms and add explicit stage selectors:
-
-- `slot=path`: valid only when exactly one selected reference target across
-  chunk, selected extractors, and selected normalizers declares `slot`.
-- `chunk.slot=path`: targets the singleton chunk module.
-- `lane.slot=path`: valid only when exactly one selected module in that lane,
-  extract or normalize, declares `slot`.
-- `lane.extract.slot=path`: targets a lane extractor.
-- `lane.normalize.slot=path`: targets a lane normalizer.
-
-`--without-reference` accepts the same selector forms without `=path`.
-
-Ambiguous selectors must fail before any LLM call and should name the ambiguous
-targets and the more specific selector forms.
-
-## Stage 1: Contract And Registry Expansion
-
-Add reference declaration support to chunkers and normalizers and LLM delivery
-to normalizers. This stage should not change config shape or runtime reference
-resolution yet.
-
-Implementation steps:
-
-- Add `References contracts.ReferenceSet` to `contracts.ChunkRequest`.
-- Add `LLMClient contracts.StructuredLLMClient` and
-  `References contracts.ReferenceSet` to `contracts.NormalizeRequest`.
-- Add `ReferenceSlots() []ReferenceSlot` to `contracts.Chunker` and
-  `contracts.Normalizer`.
-- Update every concrete chunker and normalizer plus all test fakes to implement
-  `ReferenceSlots()`. Existing modules without references should return `nil`.
-- Change `validateModuleSpec` so `ModuleSpec.ReferenceSlots` is allowed for
-  `StageChunk`, `StageExtract`, and `StageNormalize`, and rejected for all other
-  stages.
-- Add registry/module tests proving:
-  - chunker specs may declare valid reference slots;
-  - normalizer specs may declare valid reference slots;
-  - extractor specs still may declare valid reference slots;
-  - input, merge, validate, and output specs reject reference slots;
-  - invalid slot names, duplicate slots, and negative `MaxBytes` are rejected
-    for all eligible stages.
-- Add production registration tests comparing runtime `ReferenceSlots()` with
-  registered `ModuleSpec.ReferenceSlots` for chunkers, extractors, and
-  normalizers that declare slots. Modules with no slots should be covered by
-  simple nil/empty assertions.
-
-Verification:
-
-- `go test ./internal/framework/contracts`
-- `go test ./internal/framework/pipeline`
-- `go test ./internal/modules/chunk/...`
-- `go test ./internal/modules/normalize/...`
-- `go test ./...`
-
-## Stage 2: Resolved Reference Target Model
-
-Replace extractor-only resolved reference storage with a target-aware model.
-Keep external config and CLI behavior unchanged in this stage where possible.
-
-Implementation steps:
-
-- Introduce a target model in `internal/framework/pipeline`, for example:
-  - target stage: `chunk`, `extract`, or `normalize`;
-  - optional lane ID for lane-owned targets;
-  - module key;
-  - reference bindings;
-  - materialized `ReferenceSet`.
-- Add a resolved chunk reference holder to `ResolvedPipeline`.
-- Split lane reference storage into extract and normalize holders on
-  `ResolvedArtifactLane`.
-- Keep JSON field names deterministic and redaction-friendly. Do not expose
-  reference content through resolved pipeline JSON.
-- Update `CloneReferenceSet`, `ReferenceProvenance`, redacted effective config,
-  resolved-pipeline diagnostics, and any affected tests for the target-aware
-  model.
-- Preserve existing extractor behavior by mapping old lane extractor references
-  into the new extract target.
-- Keep the pipeline digest deterministic and based on resolved reference
-  bindings, not materialized reference bytes. Materialized reference digests
-  remain manifest provenance.
-
-Verification:
-
-- `go test ./internal/framework/pipeline`
-- `go test ./internal/core/config`
-- `go test ./internal/core/diagnostics`
-- `go test ./...`
-
-## Stage 3: Config Parsing And Validation
-
-Add stage-local reference fields while preserving existing configs.
-
-Implementation steps:
-
-- Extend the file config module binding object to accept `references`.
-- Add `References map[string]string` to `pipeline.ModuleBinding`, or use a
-  narrower equivalent if the implementation can do so without duplicating
-  binding parsing. If added to `ModuleBinding`, validation must reject
-  references on non-eligible stages.
-- Apply file config references from:
-  - `pipelines.<id>.chunk.references`;
-  - `pipelines.<id>.artifacts.<lane>.extract.references`;
-  - `pipelines.<id>.artifacts.<lane>.normalize.references`;
-  - existing `pipelines.<id>.artifacts.<lane>.references` as an extract-stage
-    compatibility alias.
-- Validate reference maps for empty names, duplicate-after-trim names, and empty
-  sources at each new location.
-- Reject references on `input`, `merge`, validators, and `output` bindings with
-  clear config errors.
-- Preserve existing `llm_profile` validation for chunk, extract, and normalize
-  bindings. No new LLM profile semantics are introduced in this pass.
-- Add config tests for:
-  - parsing `chunk.references`;
-  - parsing `extract.references`;
-  - parsing `normalize.references`;
-  - legacy lane `references` compatibility;
-  - duplicate conflicts where `extract.references` overrides legacy lane
-    references for the same slot;
-  - rejection of references on unsupported module binding locations;
-  - redaction/effective config cloning for all new reference maps.
-
-Verification:
-
-- `go test ./internal/core/config`
-- `go test ./internal/framework/pipeline`
-- `go test ./...`
-
-## Stage 4: Pipeline Resolution
-
-Resolve reference bindings against all eligible stage targets and selected lanes
-without constructing modules.
-
-Implementation steps:
-
-- During `ResolvePipeline`, collect declared reference slots from:
-  - the configured chunker spec;
-  - every declared artifact lane extractor spec;
-  - every declared artifact lane normalizer spec.
-- Keep pipeline-level reference validation broad: a pipeline-level binding is
-  valid if any declared eligible target in the full pipeline declares that slot,
-  even when `--only` selects lanes that do not consume it.
-- During a selected run, apply pipeline-level defaults only to:
-  - the singleton chunk target if its chunker declares the slot;
-  - selected extractor targets that declare the slot;
-  - selected normalizer targets that declare the slot.
-- Apply stage-local references after pipeline defaults:
-  - chunk-local references override chunk pipeline defaults;
-  - extract-local references override extract pipeline defaults;
-  - normalize-local references override normalize pipeline defaults.
-- Enforce required slots independently per selected target after defaults,
-  local references, CLI overrides, and CLI unbinds.
-- Keep lane-local strictness: extract-local references must be declared by that
-  lane's extractor, and normalize-local references must be declared by that
-  lane's normalizer.
-- Return clear errors that name pipeline ID, stage, lane ID when present, slot,
-  and module key.
-- Add pipeline tests for:
-  - pipeline default consumed by chunk only;
-  - pipeline default consumed by extract only;
-  - pipeline default consumed by normalize only;
-  - one pipeline default consumed by several eligible targets;
-  - valid pipeline default declared only by an unselected lane target;
-  - unknown pipeline-level slot rejected when no declared target has it;
-  - extract-local reference rejected by normalizer-only slot;
-  - normalize-local reference rejected by extractor-only slot;
-  - required chunk reference missing;
-  - required normalize reference missing;
-  - local overrides over pipeline defaults for each eligible stage.
-
-Verification:
-
-- `go test ./internal/framework/pipeline`
-- `go test ./internal/core/config`
-- `go test ./...`
-
-## Stage 5: CLI Reference Selectors
-
-Extend CLI reference override and unbind resolution to target chunk, extract,
-and normalize references.
-
-Implementation steps:
-
-- Replace extractor-only CLI reference target lookup with target-aware lookup
-  over the resolved eligible targets for the selected run.
-- Support selector forms listed in "Target CLI Reference Selectors".
-- Preserve existing behavior for unambiguous `slot` and `lane.slot` forms.
-- Reject ambiguous `slot` and `lane.slot` forms with a message naming matching
-  targets and suggesting `chunk.slot`, `lane.extract.slot`, or
-  `lane.normalize.slot` as appropriate.
-- Reject selectors that target an unselected lane during `--only` runs.
-- Reject selectors for stages that do not declare the slot.
-- Keep `--reference` empty-path rejection and `--without-reference` optional
-  unbinding semantics.
-- Add CLI tests for:
-  - `chunk.slot=path`;
-  - `lane.extract.slot=path`;
-  - `lane.normalize.slot=path`;
-  - flat slot resolution across exactly one target;
-  - lane slot resolution across exactly one lane-local target;
-  - ambiguous flat slot across chunk and extract;
-  - ambiguous lane slot across extract and normalize;
-  - unbind forms for chunk, extract, and normalize;
-  - unbind leaving required chunk or normalize slot missing;
-  - `--only` with an unselected lane selector.
-
-Verification:
-
-- `go test ./internal/cli`
-- `go test ./internal/framework/pipeline`
-- `go test ./...`
-
-## Stage 6: Materialization And Provenance
-
-Materialize references for chunk, extract, and normalize targets with one shared
-implementation.
-
-Implementation steps:
-
-- Refactor materialization so it accepts a resolved target plus that target's
-  declared slots, rather than assuming an extractor lane.
-- Reuse the existing file behavior:
-  - config paths relative to the config file;
-  - CLI paths relative to the current working directory;
-  - UTF-8 validation for all files;
-  - extension-based media type inference;
-  - optional `AcceptedMediaTypes` enforcement;
-  - optional `MaxBytes` enforcement;
-  - empty-file warning;
-  - `sha256:` content digest.
-- Store materialized reference sets on the resolved chunk target, extract
-  targets, and normalize targets.
-- Update warnings to include target context in `Scope`, such as:
-  - `pipeline.<id>.chunk.reference.<slot>`;
-  - `pipeline.<id>.lane.<lane>.extract.reference.<slot>`;
-  - `pipeline.<id>.lane.<lane>.normalize.reference.<slot>`.
-- Update manifest and diagnostics provenance to include:
-  - `stage`: `chunk`, `extract`, or `normalize`;
-  - `lane_id`: omitted for chunk and present for extract/normalize;
-  - `slot_name`;
-  - origin type and URI;
-  - digest;
-  - media type;
-  - size bytes;
-  - binding source.
-- Keep reference content out of manifests, diagnostics, logs, and errors.
-- Add tests for materialization and provenance for all three eligible stages,
-  including media-type rejection and UTF-8 rejection on non-extractor targets.
-
-Verification:
-
-- `go test ./internal/framework/pipeline`
-- `go test ./internal/core/artifacts`
-- `go test ./internal/core/diagnostics`
-- `go test ./internal/modules/output/json`
-- `go test ./internal/cli`
-- `go test ./...`
-
-## Stage 7: Runner Delivery
-
-Deliver LLM clients and references to eligible stage modules at runtime.
-
-Implementation steps:
-
-- Pass `CloneReferenceSet` of the materialized chunk reference set into
-  `contracts.ChunkRequest.References`.
-- Continue passing `LLMClient` into `contracts.ChunkRequest`.
-- Continue passing extract references and `LLMClient` into
-  `contracts.ExtractionRequest`.
-- Pass `LLMClient` and `CloneReferenceSet` of the materialized normalize
-  reference set into `contracts.NormalizeRequest`.
-- Ensure normalizers receive their configured `LLMProfile`, options, and
-  metadata as they do today.
-- Add runner tests proving:
-  - chunkers receive LLM client and chunk references;
-  - extractors still receive LLM client and extract references;
-  - normalizers receive LLM client and normalize references;
-  - reference sets are cloned before delivery so modules cannot mutate resolved
-    pipeline state;
-  - missing LLM client still fails only when a module actually uses it, matching
-    existing chunk/extract behavior.
-- Update the walking skeleton to exercise LLM-backed normalize access if a small
-  fake normalizer can do so without making the fixture noisy.
-
-Verification:
-
-- `go test ./internal/framework/pipeline`
-- `go test ./...`
-
-## Stage 8: Prompt Helpers And Module Usage
-
-Make prompt reference helpers usable by chunk and normalize modules, then update
-production modules only where needed.
-
-Implementation steps:
-
-- Confirm `internal/framework/prompt` reference rendering is contract-based and
-  not extractor-specific. If any naming or error text says extractor-only,
-  generalize it to module/stage language.
-- Add prompt tests rendering references for a fake chunker or normalizer prompt
-  bundle if existing tests cover only extractor usage.
-- Update production chunkers and normalizers:
-  - `generic` chunker: no reference slots.
-  - `dnd/scenes` chunker: no reference slots in this pass unless a clear
-    module-owned slot already exists.
-  - `noop` normalizer: no reference slots.
-- Do not invent a new production normalize module in this pass. The goal is
-  framework support, not a domain normalizer.
-
-Verification:
-
-- `go test ./internal/framework/prompt`
-- `go test ./internal/modules/chunk/...`
-- `go test ./internal/modules/normalize/...`
-- `go test ./...`
-
-## Stage 9: Documentation And Examples
-
-After behavior is implemented and tested, update canonical docs and examples.
-
-Implementation steps:
-
-- Update `docs/cli.md` with the expanded `--reference` and
-  `--without-reference` selector grammar and examples.
-- Update `docs/config.md` with `chunk.references`,
-  `artifacts.<lane>.extract.references`, `artifacts.<lane>.normalize.references`,
-  and the legacy `artifacts.<lane>.references` compatibility rule.
-- Update `docs/internal/modules.md` with module-author guidance for
-  `ReferenceSlots()` on chunkers, extractors, and normalizers, plus LLM access
-  expectations for chunk, extract, and normalize.
-- Update `docs/internal/pipeline.md` with target-aware reference resolution,
-  materialization, provenance, and runtime delivery.
-- Update `docs/integrations/json-output.md` with the new reference provenance
-  shape including `stage` and optional `lane_id`.
-- Update `docs/troubleshooting.md` with ambiguous selector examples for chunk,
-  extract, and normalize targets.
-- Update maintained examples only if they can remain small and validated. Do
-  not add speculative reference files for chunk or normalize modules without a
-  production module that actually declares those slots.
-- Update `docs/roadmap/future.md` by removing or revising the two completed
-  items while leaving still-deferred work such as token budgeting and non-file
-  producers.
-- Replace this implementation plan with a concise completed-note document after
-  implementation is finished.
-
-Verification:
-
-- `rg -n "chunk.references|normalize.references|lane.extract.slot|lane.normalize.slot" docs/cli.md docs/config.md docs/internal docs/integrations docs/troubleshooting.md`
-- `go test ./...`
-- `go vet ./...`
-- `go build ./cmd/notarius`
-
-## Final Acceptance Criteria
-
-The feature is complete when:
-
-- chunkers, extractors, and normalizers can declare reference slots through
-  runtime contracts and registry specs;
-- normalizers receive the structured LLM client at runtime;
-- config can bind references at pipeline, chunk, extract, and normalize levels;
-- CLI reference overrides and unbinds can target chunk, extract, and normalize
-  references without ambiguous selector behavior;
-- pipeline resolution validates all reference bindings before any LLM call;
-- materialization and provenance work uniformly for chunk, extract, and
-  normalize references;
-- reference manifest entries identify stage and lane context;
-- existing extractor reference behavior remains backward compatible;
-- canonical docs describe only implemented behavior;
-- `go test ./...`, `go vet ./...`, and `go build ./cmd/notarius` pass.
+Deferred reference work remains tracked in [Future Work](future.md), including
+non-file reference producers, token budgeting, structured references, and
+reference preprocessing or retrieval.

docs/troubleshooting.md

@@ -107,10 +107,10 @@ go run ./cmd/notarius run dnd-session \
 Symptoms include:
 
 - `reference slot "..." is not declared`
-- `reference slot "..." is declared by multiple selected lanes`
+- `reference slot "..." is declared by multiple selected targets`
 - `required reference slot "..." is not bound`
-- `--reference must use slot=path or lane.slot=path`
-- `--without-reference must use slot or lane.slot`
+- `--reference must use slot=path`
+- `--without-reference must use a reference selector without =path`
 - `read "...": no such file`
 - `must be UTF-8 text`
 - `media type "..." is not accepted`
@@ -118,17 +118,24 @@ Symptoms include:
 
 Fix:
 
-- Confirm the selected extractor declares the slot. The implemented
-  `dnd/spells` extractor declares optional `roster` and `glossary` slots.
-- Use `lane.slot=path` when more than one selected lane declares the same slot.
-- Use `--without-reference slot` to remove optional config bindings; do not pass
-  an empty `--reference slot=`.
+- Confirm the selected chunker, extractor, or normalizer declares the slot. The
+  implemented `dnd/spells` extractor declares optional `roster` and `glossary`
+  slots.
+- Use a specific selector when more than one selected target declares the same
+  slot. Examples include `chunk.context=./context.txt`,
+  `spells.extract.context=./extract-context.txt`, and
+  `spells.normalize.context=./normalize-context.txt`.
+- `lane.slot=path` is valid only when exactly one selected extractor or
+  normalizer in that lane declares the slot. If both do, use
+  `lane.extract.slot=path` or `lane.normalize.slot=path`.
+- Use `--without-reference selector` to remove optional config bindings; do not
+  pass an empty `--reference selector=`.
 - Check whether a path came from config or CLI. Config paths are relative to
   the config file. CLI reference paths are relative to the current working
   directory.
 - Ensure the file is readable UTF-8 text and within any byte limit declared by
-  the extractor.
-- If the extractor narrows accepted media types, use a file extension that
+  the declaring module.
+- If the declaring module narrows accepted media types, use a file extension that
   infers an accepted type such as `text/markdown` or `application/json`.
   Unknown extensions infer `application/octet-stream`.
 - If diagnostics are retained, inspect `resolved-pipeline.json`,

internal/cli/run.go

@@ -25,7 +25,7 @@ const defaultOutputRoot = "./notarius-output"
 
 const usage = `Usage:
   notarius help
-  notarius run <pipeline-id> --input path/to/source.json [--config path/to/config.yml] [--only lane-a,lane-b] [--reference slot=path] [--without-reference slot]
+  notarius run <pipeline-id> --input path/to/source.json [--config path/to/config.yml] [--only lane-a,lane-b] [--reference selector=path] [--without-reference selector]
   notarius config validate --config path/to/config.yml [--pipeline pipeline-id] [--only lane-a,lane-b]
   notarius pipelines list --config path/to/config.yml [--json]
 `
@@ -97,8 +97,8 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
 	llmProfile := fs.String("llm-profile", "", "LLM profile override")
 	referenceFlags := stringListFlag{}
 	withoutReferenceFlags := stringListFlag{}
-	fs.Var(&referenceFlags, "reference", "reference binding, as slot=path or lane.slot=path")
-	fs.Var(&withoutReferenceFlags, "without-reference", "unbind a reference, as slot or lane.slot")
+	fs.Var(&referenceFlags, "reference", "reference binding, as slot=path, chunk.slot=path, lane.slot=path, lane.extract.slot=path, or lane.normalize.slot=path")
+	fs.Var(&withoutReferenceFlags, "without-reference", "unbind a reference, using the same selector forms as --reference")
 	if err := fs.Parse(reorderRunArgs(args)); err != nil {
 		fmt.Fprintf(stderr, "notarius: %v\n", err)
 		return 2
@@ -712,13 +712,17 @@ func (flag *stringListFlag) Set(value string) error {
 }
 
 type cliReferenceRequest struct {
-	LaneID   string
-	SlotName string
+	Selector cliReferenceSelector
 	Source   string
 }
 
 type cliReferenceUnbindRequest struct {
+	Selector cliReferenceSelector
+}
+
+type cliReferenceSelector struct {
 	LaneID   string
+	Stage    pipeline.ModuleStage
 	SlotName string
 }
 
@@ -735,13 +739,12 @@ func parseReferenceFlags(values []string) ([]cliReferenceRequest, error) {
 		if strings.TrimSpace(source) == "" {
 			return nil, fmt.Errorf("--reference path must not be empty; use --without-reference to unbind")
 		}
-		laneID, slotName, err := parseReferenceSelector(name, "--reference")
+		selector, err := parseReferenceSelector(name, "--reference")
 		if err != nil {
 			return nil, err
 		}
 		requests = append(requests, cliReferenceRequest{
-			LaneID:   laneID,
-			SlotName: slotName,
+			Selector: selector,
 			Source:   strings.TrimSpace(source),
 		})
 	}
@@ -755,39 +758,51 @@ func parseReferenceUnbindFlags(values []string) ([]cliReferenceUnbindRequest, er
 	requests := make([]cliReferenceUnbindRequest, 0, len(values))
 	for _, raw := range values {
 		if strings.Contains(raw, "=") {
-			return nil, fmt.Errorf("--without-reference must use slot or lane.slot")
+			return nil, fmt.Errorf("--without-reference must use a reference selector without =path")
 		}
-		laneID, slotName, err := parseReferenceSelector(raw, "--without-reference")
+		selector, err := parseReferenceSelector(raw, "--without-reference")
 		if err != nil {
 			return nil, err
 		}
 		requests = append(requests, cliReferenceUnbindRequest{
-			LaneID:   laneID,
-			SlotName: slotName,
+			Selector: selector,
 		})
 	}
 	return requests, nil
 }
 
-func parseReferenceSelector(raw string, flagName string) (string, string, error) {
+func parseReferenceSelector(raw string, flagName string) (cliReferenceSelector, error) {
 	selector := strings.TrimSpace(raw)
 	if selector == "" {
-		return "", "", fmt.Errorf("%s reference slot must not be empty", flagName)
+		return cliReferenceSelector{}, fmt.Errorf("%s reference slot must not be empty", flagName)
 	}
-	if strings.Count(selector, ".") > 1 {
-		return "", "", fmt.Errorf("%s must use slot or lane.slot", flagName)
-	}
-	laneID := ""
-	slotName := selector
-	if strings.Contains(selector, ".") {
-		before, after, _ := strings.Cut(selector, ".")
-		laneID = strings.TrimSpace(before)
-		slotName = strings.TrimSpace(after)
-		if laneID == "" || slotName == "" {
-			return "", "", fmt.Errorf("%s must use non-empty lane.slot values", flagName)
+	parts := strings.Split(selector, ".")
+	for _, part := range parts {
+		if strings.TrimSpace(part) == "" {
+			return cliReferenceSelector{}, fmt.Errorf("%s must use non-empty reference selector values", flagName)
 		}
 	}
-	return laneID, slotName, nil
+	switch len(parts) {
+	case 1:
+		return cliReferenceSelector{SlotName: strings.TrimSpace(parts[0])}, nil
+	case 2:
+		first := strings.TrimSpace(parts[0])
+		slotName := strings.TrimSpace(parts[1])
+		if first == string(pipeline.StageChunk) {
+			return cliReferenceSelector{Stage: pipeline.StageChunk, SlotName: slotName}, nil
+		}
+		return cliReferenceSelector{LaneID: first, SlotName: slotName}, nil
+	case 3:
+		laneID := strings.TrimSpace(parts[0])
+		stage := pipeline.ModuleStage(strings.TrimSpace(parts[1]))
+		slotName := strings.TrimSpace(parts[2])
+		if stage != pipeline.StageExtract && stage != pipeline.StageNormalize {
+			return cliReferenceSelector{}, fmt.Errorf("%s lane-qualified selector must use lane.extract.slot or lane.normalize.slot", flagName)
+		}
+		return cliReferenceSelector{LaneID: laneID, Stage: stage, SlotName: slotName}, nil
+	default:
+		return cliReferenceSelector{}, fmt.Errorf("%s must use slot, chunk.slot, lane.slot, lane.extract.slot, or lane.normalize.slot", flagName)
+	}
 }
 
 func resolveCLIReferenceRequests(
@@ -802,20 +817,21 @@ func resolveCLIReferenceRequests(
 		return nil, nil, nil
 	}
 
-	selected, err := selectedReferenceLanes(cfg, pipelineID, only, catalog)
+	targets, err := selectedReferenceTargets(cfg, pipelineID, only, catalog)
 	if err != nil {
 		return nil, nil, err
 	}
 
 	overrides := make([]pipeline.ReferenceBinding, 0, len(referenceRequests))
 	for _, request := range referenceRequests {
-		laneID, err := resolveCLIReferenceLane(selected, request.LaneID, request.SlotName)
+		target, err := resolveCLIReferenceTarget(targets, request.Selector)
 		if err != nil {
 			return nil, nil, err
 		}
 		overrides = append(overrides, pipeline.ReferenceBinding{
-			LaneID:        laneID,
-			SlotName:      request.SlotName,
+			Stage:         target.stage,
+			LaneID:        target.laneID,
+			SlotName:      request.Selector.SlotName,
 			Source:        request.Source,
 			BindingSource: contracts.ReferenceBindingSourceCLI,
 		})
@@ -823,25 +839,28 @@ func resolveCLIReferenceRequests(
 
 	unbinds := make([]pipeline.ReferenceUnbind, 0, len(unbindRequests))
 	for _, request := range unbindRequests {
-		laneID, err := resolveCLIReferenceLane(selected, request.LaneID, request.SlotName)
+		target, err := resolveCLIReferenceTarget(targets, request.Selector)
 		if err != nil {
 			return nil, nil, err
 		}
 		unbinds = append(unbinds, pipeline.ReferenceUnbind{
-			LaneID:   laneID,
-			SlotName: request.SlotName,
+			Stage:    target.stage,
+			LaneID:   target.laneID,
+			SlotName: request.Selector.SlotName,
 		})
 	}
 
 	return overrides, unbinds, nil
 }
 
-type selectedReferenceLane struct {
-	id    string
-	slots map[string]struct{}
+type selectedReferenceTarget struct {
+	laneID string
+	stage  pipeline.ModuleStage
+	module string
+	slots  map[string]struct{}
 }
 
-func selectedReferenceLanes(cfg config.Config, pipelineID string, only []string, catalog pipeline.ModuleCatalog) ([]selectedReferenceLane, error) {
+func selectedReferenceTargets(cfg config.Config, pipelineID string, only []string, catalog pipeline.ModuleCatalog) ([]selectedReferenceTarget, error) {
 	profile, ok := lookupCLIReferencePipeline(cfg.Pipelines, pipelineID)
 	if !ok {
 		return nil, fmt.Errorf("pipeline %q is not configured", strings.TrimSpace(pipelineID))
@@ -882,27 +901,55 @@ func selectedReferenceLanes(cfg config.Config, pipelineID string, only []string,
 	}
 	sort.Strings(selectedIDs)
 
-	selected := make([]selectedReferenceLane, 0, len(selectedIDs))
+	targets := make([]selectedReferenceTarget, 0, 1+len(selectedIDs)*2)
+	chunk := pipeline.Binding(profile.Chunk.Module)
+	chunk.Module = strings.TrimSpace(profile.Chunk.Module)
+	if chunk.Module == "" {
+		chunk.Module = pipeline.DefaultChunkModule
+	}
+	chunkSpec, err := cliReferenceChunkerSpec(catalog, chunk.Module)
+	if err != nil {
+		return nil, fmt.Errorf("pipeline %q chunk module %q: %w", strings.TrimSpace(pipelineID), chunk.Module, err)
+	}
+	targets = append(targets, selectedReferenceTarget{
+		stage:  pipeline.StageChunk,
+		module: chunk.Module,
+		slots:  referenceSlotSet(chunkSpec.ReferenceSlots),
+	})
+
 	for _, laneID := range selectedIDs {
 		lane := lanesByID[laneID]
 		extractModule := strings.TrimSpace(lane.Extract.Module)
 		if extractModule == "" {
 			return nil, fmt.Errorf("pipeline %q lane %q extract module must not be empty", strings.TrimSpace(pipelineID), laneID)
 		}
-		if catalog.Extractors == nil {
-			return nil, fmt.Errorf("pipeline %q lane %q extract module %q: module %q is not registered", strings.TrimSpace(pipelineID), laneID, extractModule, extractModule)
+		extractSpec, err := cliReferenceExtractorSpec(catalog, extractModule)
+		if err != nil {
+			return nil, fmt.Errorf("pipeline %q lane %q extract module %q: %w", strings.TrimSpace(pipelineID), laneID, extractModule, err)
 		}
-		spec, ok := catalog.Extractors.Spec(extractModule)
-		if !ok {
-			return nil, fmt.Errorf("pipeline %q lane %q extract module %q: module %q is not registered", strings.TrimSpace(pipelineID), laneID, extractModule, extractModule)
+		targets = append(targets, selectedReferenceTarget{
+			laneID: laneID,
+			stage:  pipeline.StageExtract,
+			module: extractModule,
+			slots:  referenceSlotSet(extractSpec.ReferenceSlots),
+		})
+
+		normalizeModule := strings.TrimSpace(lane.Normalize.Module)
+		if normalizeModule == "" {
+			normalizeModule = pipeline.DefaultNormalizeModule
 		}
-		slotSet := make(map[string]struct{}, len(spec.ReferenceSlots))
-		for _, slot := range spec.ReferenceSlots {
-			slotSet[slot.Name] = struct{}{}
+		normalizeSpec, err := cliReferenceNormalizerSpec(catalog, normalizeModule)
+		if err != nil {
+			return nil, fmt.Errorf("pipeline %q lane %q normalize module %q: %w", strings.TrimSpace(pipelineID), laneID, normalizeModule, err)
 		}
-		selected = append(selected, selectedReferenceLane{id: laneID, slots: slotSet})
+		targets = append(targets, selectedReferenceTarget{
+			laneID: laneID,
+			stage:  pipeline.StageNormalize,
+			module: normalizeModule,
+			slots:  referenceSlotSet(normalizeSpec.ReferenceSlots),
+		})
 	}
-	return selected, nil
+	return targets, nil
 }
 
 func lookupCLIReferencePipeline(profiles map[string]pipeline.PipelineProfile, pipelineID string) (pipeline.PipelineProfile, bool) {
@@ -915,37 +962,152 @@ func lookupCLIReferencePipeline(profiles map[string]pipeline.PipelineProfile, pi
 	return pipeline.PipelineProfile{}, false
 }
 
-func resolveCLIReferenceLane(selected []selectedReferenceLane, requestedLaneID string, slotName string) (string, error) {
-	slotName = strings.TrimSpace(slotName)
-	requestedLaneID = strings.TrimSpace(requestedLaneID)
-	if requestedLaneID != "" {
-		for _, lane := range selected {
-			if lane.id == requestedLaneID {
-				if _, ok := lane.slots[slotName]; !ok {
-					return "", fmt.Errorf("reference slot %q is not declared by selected lane %q", slotName, requestedLaneID)
+func cliReferenceChunkerSpec(catalog pipeline.ModuleCatalog, module string) (pipeline.ModuleSpec, error) {
+	if catalog.Chunkers == nil {
+		return pipeline.ModuleSpec{}, fmt.Errorf("module %q is not registered", module)
+	}
+	spec, ok := catalog.Chunkers.Spec(module)
+	if !ok {
+		return pipeline.ModuleSpec{}, fmt.Errorf("module %q is not registered", module)
+	}
+	return spec, nil
+}
+
+func cliReferenceExtractorSpec(catalog pipeline.ModuleCatalog, module string) (pipeline.ModuleSpec, error) {
+	if catalog.Extractors == nil {
+		return pipeline.ModuleSpec{}, fmt.Errorf("module %q is not registered", module)
+	}
+	spec, ok := catalog.Extractors.Spec(module)
+	if !ok {
+		return pipeline.ModuleSpec{}, fmt.Errorf("module %q is not registered", module)
+	}
+	return spec, nil
+}
+
+func cliReferenceNormalizerSpec(catalog pipeline.ModuleCatalog, module string) (pipeline.ModuleSpec, error) {
+	if catalog.Normalizers == nil {
+		return pipeline.ModuleSpec{}, fmt.Errorf("module %q is not registered", module)
+	}
+	spec, ok := catalog.Normalizers.Spec(module)
+	if !ok {
+		return pipeline.ModuleSpec{}, fmt.Errorf("module %q is not registered", module)
+	}
+	return spec, nil
+}
+
+func referenceSlotSet(slots []contracts.ReferenceSlot) map[string]struct{} {
+	slotSet := make(map[string]struct{}, len(slots))
+	for _, slot := range slots {
+		slotSet[slot.Name] = struct{}{}
+	}
+	return slotSet
+}
+
+func resolveCLIReferenceTarget(targets []selectedReferenceTarget, selector cliReferenceSelector) (selectedReferenceTarget, error) {
+	slotName := strings.TrimSpace(selector.SlotName)
+	if slotName == "" {
+		return selectedReferenceTarget{}, fmt.Errorf("reference slot must not be empty")
+	}
+	if selector.Stage == pipeline.StageChunk {
+		for _, target := range targets {
+			if target.stage != pipeline.StageChunk {
+				continue
+			}
+			if _, ok := target.slots[slotName]; !ok {
+				return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by chunk module %q", slotName, target.module)
+			}
+			return target, nil
+		}
+		return selectedReferenceTarget{}, fmt.Errorf("reference chunk target is not selected")
+	}
+	if selector.Stage == pipeline.StageExtract || selector.Stage == pipeline.StageNormalize {
+		for _, target := range targets {
+			if target.laneID == selector.LaneID && target.stage == selector.Stage {
+				if _, ok := target.slots[slotName]; !ok {
+					return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by selected %s target %q", slotName, selector.Stage, targetLabel(target))
 				}
-				return requestedLaneID, nil
+				return target, nil
 			}
 		}
-		return "", fmt.Errorf("reference lane %q is not selected", requestedLaneID)
+		return selectedReferenceTarget{}, fmt.Errorf("reference lane %q is not selected", selector.LaneID)
 	}
+	if strings.TrimSpace(selector.LaneID) != "" {
+		return resolveCLIReferenceLaneTarget(targets, strings.TrimSpace(selector.LaneID), slotName)
+	}
+	return resolveCLIReferenceFlatTarget(targets, slotName)
+}
 
-	matches := make([]string, 0, 1)
-	for _, lane := range selected {
-		if _, ok := lane.slots[slotName]; ok {
-			matches = append(matches, lane.id)
+func resolveCLIReferenceLaneTarget(targets []selectedReferenceTarget, laneID string, slotName string) (selectedReferenceTarget, error) {
+	laneSelected := false
+	matches := make([]selectedReferenceTarget, 0, 2)
+	for _, target := range targets {
+		if target.laneID != laneID {
+			continue
+		}
+		laneSelected = true
+		if _, ok := target.slots[slotName]; ok {
+			matches = append(matches, target)
+		}
+	}
+	if !laneSelected {
+		return selectedReferenceTarget{}, fmt.Errorf("reference lane %q is not selected", laneID)
+	}
+	switch len(matches) {
+	case 0:
+		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by selected lane %q", slotName, laneID)
+	case 1:
+		return matches[0], nil
+	default:
+		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is declared by multiple selected targets in lane %q (%s); use %s.extract.%s or %s.normalize.%s", slotName, laneID, targetList(matches), laneID, slotName, laneID, slotName)
+	}
+}
+
+func resolveCLIReferenceFlatTarget(targets []selectedReferenceTarget, slotName string) (selectedReferenceTarget, error) {
+	matches := make([]selectedReferenceTarget, 0, 2)
+	for _, target := range targets {
+		if _, ok := target.slots[slotName]; ok {
+			matches = append(matches, target)
 		}
 	}
 	switch len(matches) {
 	case 0:
-		return "", fmt.Errorf("reference slot %q is not declared by any selected lane", slotName)
+		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by any selected reference target", slotName)
 	case 1:
 		return matches[0], nil
 	default:
-		return "", fmt.Errorf("reference slot %q is declared by multiple selected lanes (%s); use lane.slot", slotName, strings.Join(matches, ", "))
+		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is declared by multiple selected targets (%s); use a more specific selector such as %s", slotName, targetList(matches), selectorSuggestions(matches, slotName))
 	}
 }
 
+func targetList(targets []selectedReferenceTarget) string {
+	labels := make([]string, 0, len(targets))
+	for _, target := range targets {
+		labels = append(labels, targetLabel(target))
+	}
+	sort.Strings(labels)
+	return strings.Join(labels, ", ")
+}
+
+func targetLabel(target selectedReferenceTarget) string {
+	if target.stage == pipeline.StageChunk {
+		return "chunk"
+	}
+	return target.laneID + "." + string(target.stage)
+}
+
+func selectorSuggestions(targets []selectedReferenceTarget, slotName string) string {
+	suggestions := make([]string, 0, len(targets))
+	for _, target := range targets {
+		if target.stage == pipeline.StageChunk {
+			suggestions = append(suggestions, "chunk."+slotName)
+			continue
+		}
+		suggestions = append(suggestions, target.laneID+"."+string(target.stage)+"."+slotName)
+	}
+	sort.Strings(suggestions)
+	return strings.Join(suggestions, " or ")
+}
+
 func sortedPipelineIDs(cfg config.Config) []string {
 	ids := make([]string, 0, len(cfg.Pipelines))
 	for id := range cfg.Pipelines {

internal/cli/run_test.go

@@ -769,7 +769,7 @@ func TestRunPipelineReferenceFlagBindsUnambiguousSlot(t *testing.T) {
 		t.Fatalf("RunWithOptions() code = %d stderr=%q, want read input failure after resolution", code, stderr.String())
 	}
 	resolved := readResolvedPipeline(t, diagnosticsDir)
-	refs := resolved.ArtifactLanes[0].References
+	refs := resolved.ArtifactLanes[0].ExtractReferences.Bindings
 	want := []pipeline.ReferenceBinding{
 		{LaneID: "events", SlotName: "roster", Source: referencePath, BindingSource: contracts.ReferenceBindingSourceCLI},
 	}
@@ -810,12 +810,199 @@ func TestRunPipelineReferenceFlagBindsLaneQualifiedSlot(t *testing.T) {
 	}
 	resolved := readResolvedPipeline(t, diagnosticsDir)
 	events := resolvedArtifactLane(t, resolved, "events")
-	if len(events.References) != 0 {
-		t.Fatalf("events references = %#v, want none", events.References)
+	if len(events.ExtractReferences.Bindings) != 0 {
+		t.Fatalf("events references = %#v, want none", events.ExtractReferences.Bindings)
 	}
 	notes := resolvedArtifactLane(t, resolved, "notes")
-	if len(notes.References) != 1 || notes.References[0].Source != referencePath {
-		t.Fatalf("notes references = %#v, want lane-qualified binding", notes.References)
+	if len(notes.ExtractReferences.Bindings) != 1 || notes.ExtractReferences.Bindings[0].Source != referencePath {
+		t.Fatalf("notes references = %#v, want lane-qualified binding", notes.ExtractReferences.Bindings)
+	}
+}
+
+func TestRunPipelineReferenceFlagBindsChunkQualifiedSlot(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAML("example", "events"))
+	inputPath := filepath.Join(t.TempDir(), "missing.json")
+	referencePath := writeFile(t, "scenes.md", "Scenes\n")
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--reference", "chunk.scene_guide=" + referencePath,
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
+			Key:      "generic",
+			Stage:    pipeline.StageChunk,
+			Requires: []string{"source"},
+			Provides: []string{"chunks"},
+			ReferenceSlots: []contracts.ReferenceSlot{
+				{Name: "scene_guide"},
+			},
+		}),
+	})
+
+	if code != 1 || !strings.Contains(stderr.String(), "read input") {
+		t.Fatalf("RunWithOptions() code = %d stderr=%q, want read input failure after resolution", code, stderr.String())
+	}
+	resolved := readResolvedPipeline(t, diagnosticsDir)
+	refs := resolved.ChunkReferences.Bindings
+	want := []pipeline.ReferenceBinding{
+		{SlotName: "scene_guide", Source: referencePath, BindingSource: contracts.ReferenceBindingSourceCLI},
+	}
+	if !reflect.DeepEqual(refs, want) {
+		t.Fatalf("chunk references = %#v, want %#v", refs, want)
+	}
+}
+
+func TestRunPipelineReferenceFlagBindsExplicitExtractSlot(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAML("example", "events"))
+	inputPath := filepath.Join(t.TempDir(), "missing.json")
+	referencePath := writeFile(t, "roster.yml", "Aria\n")
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--reference", "events.extract.roster=" + referencePath,
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
+			Key:      "fake/extract",
+			Stage:    pipeline.StageExtract,
+			Requires: []string{"chunks"},
+			Provides: []string{"artifact"},
+			ReferenceSlots: []contracts.ReferenceSlot{
+				{Name: "roster"},
+			},
+		}),
+	})
+
+	if code != 1 || !strings.Contains(stderr.String(), "read input") {
+		t.Fatalf("RunWithOptions() code = %d stderr=%q, want read input failure after resolution", code, stderr.String())
+	}
+	resolved := readResolvedPipeline(t, diagnosticsDir)
+	refs := resolved.ArtifactLanes[0].ExtractReferences.Bindings
+	want := []pipeline.ReferenceBinding{
+		{LaneID: "events", SlotName: "roster", Source: referencePath, BindingSource: contracts.ReferenceBindingSourceCLI},
+	}
+	if !reflect.DeepEqual(refs, want) {
+		t.Fatalf("extract references = %#v, want %#v", refs, want)
+	}
+}
+
+func TestRunPipelineReferenceFlagBindsExplicitNormalizeSlot(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAML("example", "events"))
+	inputPath := filepath.Join(t.TempDir(), "missing.json")
+	referencePath := writeFile(t, "normalize.md", "Normalize\n")
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--reference", "events.normalize.notes=" + referencePath,
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
+			Key:      "noop",
+			Stage:    pipeline.StageNormalize,
+			Requires: []string{"merged"},
+			Provides: []string{"normalized"},
+			ReferenceSlots: []contracts.ReferenceSlot{
+				{Name: "notes"},
+			},
+		}),
+	})
+
+	if code != 1 || !strings.Contains(stderr.String(), "read input") {
+		t.Fatalf("RunWithOptions() code = %d stderr=%q, want read input failure after resolution", code, stderr.String())
+	}
+	resolved := readResolvedPipeline(t, diagnosticsDir)
+	refs := resolved.ArtifactLanes[0].NormalizeReferences.Bindings
+	want := []pipeline.ReferenceBinding{
+		{LaneID: "events", SlotName: "notes", Source: referencePath, BindingSource: contracts.ReferenceBindingSourceCLI},
+	}
+	if !reflect.DeepEqual(refs, want) {
+		t.Fatalf("normalize references = %#v, want %#v", refs, want)
+	}
+}
+
+func TestRunPipelineReferenceFlagBindsFlatSlotAcrossOneTarget(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAML("example", "events"))
+	inputPath := filepath.Join(t.TempDir(), "missing.json")
+	referencePath := writeFile(t, "normalize.md", "Normalize\n")
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--reference", "notes=" + referencePath,
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
+			Key:      "noop",
+			Stage:    pipeline.StageNormalize,
+			Requires: []string{"merged"},
+			Provides: []string{"normalized"},
+			ReferenceSlots: []contracts.ReferenceSlot{
+				{Name: "notes"},
+			},
+		}),
+	})
+
+	if code != 1 || !strings.Contains(stderr.String(), "read input") {
+		t.Fatalf("RunWithOptions() code = %d stderr=%q, want read input failure after resolution", code, stderr.String())
+	}
+	resolved := readResolvedPipeline(t, diagnosticsDir)
+	if refs := resolved.ArtifactLanes[0].NormalizeReferences.Bindings; len(refs) != 1 || refs[0].Source != referencePath {
+		t.Fatalf("normalize references = %#v, want flat binding", refs)
+	}
+}
+
+func TestRunPipelineReferenceFlagBindsLaneSlotAcrossOneTarget(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAML("example", "events"))
+	inputPath := filepath.Join(t.TempDir(), "missing.json")
+	referencePath := writeFile(t, "normalize.md", "Normalize\n")
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--reference", "events.notes=" + referencePath,
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
+			Key:      "noop",
+			Stage:    pipeline.StageNormalize,
+			Requires: []string{"merged"},
+			Provides: []string{"normalized"},
+			ReferenceSlots: []contracts.ReferenceSlot{
+				{Name: "notes"},
+			},
+		}),
+	})
+
+	if code != 1 || !strings.Contains(stderr.String(), "read input") {
+		t.Fatalf("RunWithOptions() code = %d stderr=%q, want read input failure after resolution", code, stderr.String())
+	}
+	resolved := readResolvedPipeline(t, diagnosticsDir)
+	if refs := resolved.ArtifactLanes[0].NormalizeReferences.Bindings; len(refs) != 1 || refs[0].Source != referencePath {
+		t.Fatalf("normalize references = %#v, want lane-qualified binding", refs)
 	}
 }
 
@@ -847,11 +1034,99 @@ func TestRunPipelineReferenceFlagRejectsAmbiguousFlatSlot(t *testing.T) {
 	if code != 1 {
 		t.Fatalf("RunWithOptions() code = %d, want 1", code)
 	}
-	if !strings.Contains(stderr.String(), "multiple selected lanes") || !strings.Contains(stderr.String(), "lane.slot") {
+	if !strings.Contains(stderr.String(), "multiple selected targets") || !strings.Contains(stderr.String(), "events.extract.roster") || !strings.Contains(stderr.String(), "notes.extract.roster") {
 		t.Fatalf("stderr = %q, want ambiguous reference error", stderr.String())
 	}
 }
 
+func TestRunPipelineReferenceFlagRejectsAmbiguousFlatSlotAcrossChunkAndExtract(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAML("example", "events"))
+	inputPath := writeSeriatimInput(t)
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--reference", "context=./context.md",
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t,
+			pipeline.ModuleSpec{
+				Key:      "generic",
+				Stage:    pipeline.StageChunk,
+				Requires: []string{"source"},
+				Provides: []string{"chunks"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "context"},
+				},
+			},
+			pipeline.ModuleSpec{
+				Key:      "fake/extract",
+				Stage:    pipeline.StageExtract,
+				Requires: []string{"chunks"},
+				Provides: []string{"artifact"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "context"},
+				},
+			},
+		),
+	})
+
+	if code != 1 {
+		t.Fatalf("RunWithOptions() code = %d, want 1", code)
+	}
+	if !strings.Contains(stderr.String(), "multiple selected targets") || !strings.Contains(stderr.String(), "chunk.context") || !strings.Contains(stderr.String(), "events.extract.context") {
+		t.Fatalf("stderr = %q, want ambiguous chunk/extract reference error", stderr.String())
+	}
+}
+
+func TestRunPipelineReferenceFlagRejectsAmbiguousLaneSlotAcrossExtractAndNormalize(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAML("example", "events"))
+	inputPath := writeSeriatimInput(t)
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--reference", "events.context=./context.md",
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t,
+			pipeline.ModuleSpec{
+				Key:      "fake/extract",
+				Stage:    pipeline.StageExtract,
+				Requires: []string{"chunks"},
+				Provides: []string{"artifact"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "context"},
+				},
+			},
+			pipeline.ModuleSpec{
+				Key:      "noop",
+				Stage:    pipeline.StageNormalize,
+				Requires: []string{"merged"},
+				Provides: []string{"normalized"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "context"},
+				},
+			},
+		),
+	})
+
+	if code != 1 {
+		t.Fatalf("RunWithOptions() code = %d, want 1", code)
+	}
+	if !strings.Contains(stderr.String(), "multiple selected targets in lane") || !strings.Contains(stderr.String(), "events.extract.context") || !strings.Contains(stderr.String(), "events.normalize.context") {
+		t.Fatalf("stderr = %q, want ambiguous lane reference error", stderr.String())
+	}
+}
+
 func TestRunPipelineReferenceFlagsRejectMalformedValues(t *testing.T) {
 	tests := []struct {
 		name string
@@ -861,8 +1136,9 @@ func TestRunPipelineReferenceFlagsRejectMalformedValues(t *testing.T) {
 		{name: "missing equals", args: []string{"--reference", "roster"}, want: "slot=path"},
 		{name: "empty path", args: []string{"--reference", "roster="}, want: "path must not be empty"},
 		{name: "empty slot", args: []string{"--reference", "=./roster.yml"}, want: "slot must not be empty"},
-		{name: "too many selector parts", args: []string{"--reference", "a.b.c=./roster.yml"}, want: "lane.slot"},
-		{name: "unbind with equals", args: []string{"--without-reference", "roster=./roster.yml"}, want: "slot or lane.slot"},
+		{name: "unsupported explicit stage", args: []string{"--reference", "a.b.c=./roster.yml"}, want: "lane.extract.slot or lane.normalize.slot"},
+		{name: "too many selector parts", args: []string{"--reference", "a.b.c.d=./roster.yml"}, want: "slot, chunk.slot, lane.slot, lane.extract.slot, or lane.normalize.slot"},
+		{name: "unbind with equals", args: []string{"--without-reference", "roster=./roster.yml"}, want: "without =path"},
 	}
 
 	for _, test := range tests {
@@ -885,6 +1161,72 @@ func TestRunPipelineReferenceFlagsRejectMalformedValues(t *testing.T) {
 	}
 }
 
+func TestRunPipelineWithoutReferenceRemovesConfigBindingsForEligibleTargets(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAMLWithPipelineReferences("example", "events", map[string]string{
+		"context": "./config-context.md",
+		"notes":   "./config-notes.md",
+		"roster":  "./config-roster.yml",
+	}))
+	inputPath := filepath.Join(t.TempDir(), "missing.json")
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--without-reference", "chunk.context",
+		"--without-reference", "events.extract.roster",
+		"--without-reference", "events.normalize.notes",
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t,
+			pipeline.ModuleSpec{
+				Key:      "generic",
+				Stage:    pipeline.StageChunk,
+				Requires: []string{"source"},
+				Provides: []string{"chunks"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "context"},
+				},
+			},
+			pipeline.ModuleSpec{
+				Key:      "fake/extract",
+				Stage:    pipeline.StageExtract,
+				Requires: []string{"chunks"},
+				Provides: []string{"artifact"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "roster"},
+				},
+			},
+			pipeline.ModuleSpec{
+				Key:      "noop",
+				Stage:    pipeline.StageNormalize,
+				Requires: []string{"merged"},
+				Provides: []string{"normalized"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "notes"},
+				},
+			},
+		),
+	})
+
+	if code != 1 || !strings.Contains(stderr.String(), "read input") {
+		t.Fatalf("RunWithOptions() code = %d stderr=%q, want read input failure after resolution", code, stderr.String())
+	}
+	resolved := readResolvedPipeline(t, diagnosticsDir)
+	if refs := resolved.ChunkReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("chunk references = %#v, want none", refs)
+	}
+	if refs := resolved.ArtifactLanes[0].ExtractReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("extract references = %#v, want none", refs)
+	}
+	if refs := resolved.ArtifactLanes[0].NormalizeReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("normalize references = %#v, want none", refs)
+	}
+}
+
 func TestRunPipelineWithoutReferenceRemovesOptionalConfigBinding(t *testing.T) {
 	configPath := writeTestConfig(t, testConfigYAMLWithReferences("example", "events", map[string]string{"roster": "./config-roster.yml"}))
 	inputPath := filepath.Join(t.TempDir(), "missing.json")
@@ -914,11 +1256,112 @@ func TestRunPipelineWithoutReferenceRemovesOptionalConfigBinding(t *testing.T) {
 		t.Fatalf("RunWithOptions() code = %d stderr=%q, want read input failure after resolution", code, stderr.String())
 	}
 	resolved := readResolvedPipeline(t, diagnosticsDir)
-	if refs := resolved.ArtifactLanes[0].References; len(refs) != 0 {
+	if refs := resolved.ArtifactLanes[0].ExtractReferences.Bindings; len(refs) != 0 {
 		t.Fatalf("references = %#v, want unbound optional slot", refs)
 	}
 }
 
+func TestRunPipelineWithoutReferenceFailsWhenRequiredChunkSlotWouldBeMissing(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAMLWithPipelineReferences("example", "events", map[string]string{"context": "./config-context.md"}))
+	inputPath := writeSeriatimInput(t)
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--without-reference", "chunk.context",
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
+			Key:      "generic",
+			Stage:    pipeline.StageChunk,
+			Requires: []string{"source"},
+			Provides: []string{"chunks"},
+			ReferenceSlots: []contracts.ReferenceSlot{
+				{Name: "context", Required: true},
+			},
+		}),
+	})
+
+	if code != 1 {
+		t.Fatalf("RunWithOptions() code = %d, want 1", code)
+	}
+	if !strings.Contains(stderr.String(), "required reference slot") || !strings.Contains(stderr.String(), "context") {
+		t.Fatalf("stderr = %q, want required chunk reference error", stderr.String())
+	}
+}
+
+func TestRunPipelineWithoutReferenceFailsWhenRequiredNormalizeSlotWouldBeMissing(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAMLWithPipelineReferences("example", "events", map[string]string{"notes": "./config-notes.md"}))
+	inputPath := writeSeriatimInput(t)
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--diagnostics-dir", diagnosticsDir,
+		"--without-reference", "events.normalize.notes",
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
+			Key:      "noop",
+			Stage:    pipeline.StageNormalize,
+			Requires: []string{"merged"},
+			Provides: []string{"normalized"},
+			ReferenceSlots: []contracts.ReferenceSlot{
+				{Name: "notes", Required: true},
+			},
+		}),
+	})
+
+	if code != 1 {
+		t.Fatalf("RunWithOptions() code = %d, want 1", code)
+	}
+	if !strings.Contains(stderr.String(), "required reference slot") || !strings.Contains(stderr.String(), "notes") {
+		t.Fatalf("stderr = %q, want required normalize reference error", stderr.String())
+	}
+}
+
+func TestRunPipelineReferenceFlagRejectsUnselectedLaneSelector(t *testing.T) {
+	configPath := writeTestConfig(t, testConfigYAML("example", "events", "notes"))
+	inputPath := writeSeriatimInput(t)
+	referencePath := writeFile(t, "notes.yml", "Notes\n")
+	diagnosticsDir := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{
+		"run", "example",
+		"--config", configPath,
+		"--input", inputPath,
+		"--only", "events",
+		"--diagnostics-dir", diagnosticsDir,
+		"--reference", "notes.extract.roster=" + referencePath,
+	}, &stdout, &stderr, Options{
+		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
+			Key:      "fake/extract",
+			Stage:    pipeline.StageExtract,
+			Requires: []string{"chunks"},
+			Provides: []string{"artifact"},
+			ReferenceSlots: []contracts.ReferenceSlot{
+				{Name: "roster"},
+			},
+		}),
+	})
+
+	if code != 1 {
+		t.Fatalf("RunWithOptions() code = %d, want 1", code)
+	}
+	if !strings.Contains(stderr.String(), `reference lane "notes" is not selected`) {
+		t.Fatalf("stderr = %q, want unselected lane error", stderr.String())
+	}
+}
+
 func TestRunPipelineWithoutReferenceFailsWhenRequiredSlotWouldBeMissing(t *testing.T) {
 	configPath := writeTestConfig(t, testConfigYAMLWithReferences("example", "events", map[string]string{"roster": "./config-roster.yml"}))
 	inputPath := writeSeriatimInput(t)
@@ -1609,6 +2052,27 @@ func testConfigYAMLWithReferences(pipelineID string, laneID string, references m
 	return b.String()
 }
 
+func testConfigYAMLWithPipelineReferences(pipelineID string, laneID string, references map[string]string) string {
+	var b strings.Builder
+	b.WriteString("version: 1\n")
+	b.WriteString("pipelines:\n")
+	b.WriteString("  " + pipelineID + ":\n")
+	b.WriteString("    input: fake/input\n")
+	b.WriteString("    references:\n")
+	keys := make([]string, 0, len(references))
+	for key := range references {
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+	for _, key := range keys {
+		b.WriteString("      " + key + ": " + references[key] + "\n")
+	}
+	b.WriteString("    artifacts:\n")
+	b.WriteString("      " + laneID + ":\n")
+	b.WriteString("        extract: fake/extract\n")
+	return b.String()
+}
+
 func testConfigYAMLWithReferencesAndDiagnostics(pipelineID string, laneID string, diagnosticsDir string, references map[string]string) string {
 	var b strings.Builder
 	b.WriteString("version: 1\n")
@@ -1961,6 +2425,10 @@ func (fakeRunChunker) Key() string {
 	return "generic"
 }
 
+func (fakeRunChunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (fakeRunChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	return contracts.ChunkResult{
 		Chunks: []contracts.SourceChunk{
@@ -2024,6 +2492,10 @@ func (fakeRunNormalizer) Key() string {
 	return "noop"
 }
 
+func (fakeRunNormalizer) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (fakeRunNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
 	return contracts.NormalizeResult{Candidates: append([]artifacts.ArtifactCandidate(nil), req.Candidates...)}, nil
 }

internal/core/artifacts/artifacts.go

@@ -49,7 +49,8 @@ type LLMProfileManifest struct {
 }
 
 type ReferenceProvenance struct {
-	LaneID        string `json:"lane_id"`
+	Stage         string `json:"stage,omitempty"`
+	LaneID        string `json:"lane_id,omitempty"`
 	SlotName      string `json:"slot_name"`
 	OriginType    string `json:"origin_type"`
 	OriginURI     string `json:"origin_uri,omitempty"`

internal/core/artifacts/artifacts_test.go

@@ -187,6 +187,7 @@ func TestRunManifestIncludesReferenceProvenance(t *testing.T) {
 	manifest := RunManifest{
 		References: []ReferenceProvenance{
 			{
+				Stage:         "extract",
 				LaneID:        "events",
 				SlotName:      "roster",
 				OriginType:    "file",
@@ -212,7 +213,7 @@ func TestRunManifestIncludesReferenceProvenance(t *testing.T) {
 		t.Fatalf("len(References) = %d, want 1", len(got.References))
 	}
 	reference := got.References[0]
-	if reference.LaneID != "events" || reference.SlotName != "roster" || reference.OriginType != "file" || reference.OriginURI != "file:///tmp/roster.txt" {
+	if reference.Stage != "extract" || reference.LaneID != "events" || reference.SlotName != "roster" || reference.OriginType != "file" || reference.OriginURI != "file:///tmp/roster.txt" {
 		t.Fatalf("reference provenance = %#v, want lane-scoped origin details", reference)
 	}
 	if reference.Digest != "sha256:reference" || reference.MediaType != "text/plain; charset=utf-8" || reference.SizeBytes != 12 || reference.BindingSource != "config" {

internal/core/config/config.go

@@ -114,6 +114,7 @@ func cloneModuleBinding(in pipeline.ModuleBinding) pipeline.ModuleBinding {
 	if len(in.Options) > 0 {
 		out.Options = cloneOptions(in.Options)
 	}
+	out.References = cloneStringMap(in.References)
 	return out
 }
 

internal/core/config/file_config.go

@@ -99,6 +99,7 @@ type fileModuleBinding struct {
 	Module     string
 	LLMProfile string
 	Options    map[string]any
+	References map[string]string
 }
 
 func (b *fileModuleBinding) UnmarshalYAML(node *yaml.Node) error {
@@ -133,6 +134,12 @@ func (b *fileModuleBinding) UnmarshalYAML(node *yaml.Node) error {
 					return err
 				}
 				b.Options = normalizeOptions(options)
+			case "references":
+				var references map[string]string
+				if err := valueNode.Decode(&references); err != nil {
+					return err
+				}
+				b.References = references
 			default:
 				return fmt.Errorf("field %s not found in module binding", keyNode.Value)
 			}
@@ -148,6 +155,7 @@ func (b fileModuleBinding) toPipelineBinding() pipeline.ModuleBinding {
 		Module:     strings.TrimSpace(b.Module),
 		LLMProfile: strings.TrimSpace(b.LLMProfile),
 		Options:    cloneOptions(b.Options),
+		References: normalizedStringMap(b.References),
 	}
 }
 
@@ -217,6 +225,19 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
 		if _, _, err := normalizedMapKeys(filePipeline.References, fmt.Sprintf("pipeline %q reference slot", pipelineID)); err != nil {
 			return err
 		}
+		if filePipeline.Chunk != nil {
+			if _, _, err := normalizedMapKeys(filePipeline.Chunk.References, fmt.Sprintf("pipeline %q chunk reference slot", pipelineID)); err != nil {
+				return err
+			}
+		}
+		if _, _, err := normalizedMapKeys(filePipeline.Input.References, fmt.Sprintf("pipeline %q input reference slot", pipelineID)); err != nil {
+			return err
+		}
+		if filePipeline.Output != nil {
+			if _, _, err := normalizedMapKeys(filePipeline.Output.References, fmt.Sprintf("pipeline %q output reference slot", pipelineID)); err != nil {
+				return err
+			}
+		}
 		for rawLaneID, fileLane := range filePipeline.Artifacts {
 			laneID := strings.TrimSpace(rawLaneID)
 			if laneID == "" {
@@ -225,6 +246,24 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
 			if _, _, err := normalizedMapKeys(fileLane.References, fmt.Sprintf("pipeline %q lane %q reference slot", pipelineID, laneID)); err != nil {
 				return err
 			}
+			if _, _, err := normalizedMapKeys(fileLane.Extract.References, fmt.Sprintf("pipeline %q lane %q extract reference slot", pipelineID, laneID)); err != nil {
+				return err
+			}
+			if fileLane.Merge != nil {
+				if _, _, err := normalizedMapKeys(fileLane.Merge.References, fmt.Sprintf("pipeline %q lane %q merge reference slot", pipelineID, laneID)); err != nil {
+					return err
+				}
+			}
+			if fileLane.Normalize != nil {
+				if _, _, err := normalizedMapKeys(fileLane.Normalize.References, fmt.Sprintf("pipeline %q lane %q normalize reference slot", pipelineID, laneID)); err != nil {
+					return err
+				}
+			}
+			for i, validator := range fileLane.Validators {
+				if _, _, err := normalizedMapKeys(validator.References, fmt.Sprintf("pipeline %q lane %q validator[%d] reference slot", pipelineID, laneID, i)); err != nil {
+					return err
+				}
+			}
 		}
 	}
 
@@ -280,8 +319,10 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
 		}
 		for _, laneID := range laneIDs {
 			fileLane := filePipeline.Artifacts[rawLaneIDs[laneID]]
+			extract := fileLane.Extract.toPipelineBinding()
+			extract.References = mergeStringMaps(normalizedStringMap(fileLane.References), extract.References)
 			lane := pipeline.ArtifactLaneProfile{
-				Extract:    fileLane.Extract.toPipelineBinding(),
+				Extract:    extract,
 				References: normalizedStringMap(fileLane.References),
 			}
 			if fileLane.Merge != nil {
@@ -353,6 +394,20 @@ func normalizedStringMap(values map[string]string) map[string]string {
 	return out
 }
 
+func mergeStringMaps(base map[string]string, override map[string]string) map[string]string {
+	if len(base) == 0 && len(override) == 0 {
+		return nil
+	}
+	out := make(map[string]string, len(base)+len(override))
+	for key, value := range base {
+		out[key] = value
+	}
+	for key, value := range override {
+		out[key] = value
+	}
+	return out
+}
+
 func resolveAPIKeyEnv(envName string, lookup func(string) (string, bool)) (string, error) {
 	name := strings.TrimSpace(envName)
 	if name == "" {

internal/core/config/file_config_test.go

@@ -169,6 +169,53 @@ pipelines:
 	}
 }
 
+func TestParseFileConfigStageLocalReferenceMaps(t *testing.T) {
+	cfg := parseAndApplyConfig(t, `
+version: 1
+pipelines:
+  example:
+    input: fake/input
+    chunk:
+      module: generic
+      references:
+        " scene_guide ": " ./scenes.md "
+    artifacts:
+      events:
+        extract:
+          module: fake/extract
+          references:
+            " glossary ": " ./glossary.md "
+            " roster ": " ./extract-roster.yml "
+        references:
+          roster: ./legacy-roster.yml
+          lore: ./lore.md
+        normalize:
+          module: noop
+          references:
+            " normalization_notes ": " ./normalization.md "
+`)
+
+	profile := cfg.Pipelines["example"]
+	if !reflect.DeepEqual(profile.Chunk.References, map[string]string{"scene_guide": "./scenes.md"}) {
+		t.Fatalf("chunk references = %#v, want trimmed map", profile.Chunk.References)
+	}
+	lane := profile.Artifacts["events"]
+	if !reflect.DeepEqual(lane.References, map[string]string{"lore": "./lore.md", "roster": "./legacy-roster.yml"}) {
+		t.Fatalf("legacy lane references = %#v, want trimmed map", lane.References)
+	}
+	wantExtract := map[string]string{
+		"glossary": "./glossary.md",
+		"lore":     "./lore.md",
+		"roster":   "./extract-roster.yml",
+	}
+	if !reflect.DeepEqual(lane.Extract.References, wantExtract) {
+		t.Fatalf("extract references = %#v, want legacy merged with extract override %#v", lane.Extract.References, wantExtract)
+	}
+	if !reflect.DeepEqual(lane.Normalize.References, map[string]string{"normalization_notes": "./normalization.md"}) {
+		t.Fatalf("normalize references = %#v, want trimmed map", lane.Normalize.References)
+	}
+}
+
 func TestParseFileConfigValidatorMixedBindingForms(t *testing.T) {
 	cfg := parseAndApplyConfig(t, `
 version: 1
@@ -357,6 +404,56 @@ pipelines:
 `,
 			want: `pipeline "example" lane "events" reference slot`,
 		},
+		{
+			name: "chunk",
+			raw: `
+version: 1
+pipelines:
+  example:
+    input: fake/input
+    chunk:
+      module: generic
+      references:
+        roster: ./first.yml
+        " roster ": ./second.yml
+`,
+			want: `pipeline "example" chunk reference slot`,
+		},
+		{
+			name: "extract",
+			raw: `
+version: 1
+pipelines:
+  example:
+    input: fake/input
+    artifacts:
+      events:
+        extract:
+          module: fake/extract
+          references:
+            roster: ./first.yml
+            " roster ": ./second.yml
+`,
+			want: `pipeline "example" lane "events" extract reference slot`,
+		},
+		{
+			name: "normalize",
+			raw: `
+version: 1
+pipelines:
+  example:
+    input: fake/input
+    artifacts:
+      events:
+        extract: fake/extract
+        normalize:
+          module: noop
+          references:
+            roster: ./first.yml
+            " roster ": ./second.yml
+`,
+			want: `pipeline "example" lane "events" normalize reference slot`,
+		},
 	}
 
 	for _, tc := range tests {

internal/core/config/redaction.go

@@ -34,6 +34,7 @@ func cloneResolvedPipeline(in pipeline.ResolvedPipeline) pipeline.ResolvedPipeli
 	out := in
 	out.Input = cloneModuleBinding(in.Input)
 	out.Chunk = cloneModuleBinding(in.Chunk)
+	out.ChunkReferences = pipeline.CloneReferenceTarget(in.ChunkReferences)
 	out.Output = cloneModuleBinding(in.Output)
 	if len(in.ArtifactLanes) > 0 {
 		out.ArtifactLanes = make([]pipeline.ResolvedArtifactLane, len(in.ArtifactLanes))
@@ -49,8 +50,8 @@ func cloneResolvedArtifactLane(in pipeline.ResolvedArtifactLane) pipeline.Resolv
 	out.Extract = cloneModuleBinding(in.Extract)
 	out.Merge = cloneModuleBinding(in.Merge)
 	out.Normalize = cloneModuleBinding(in.Normalize)
-	out.References = append([]pipeline.ReferenceBinding(nil), in.References...)
-	out.ReferenceSet = pipeline.CloneReferenceSet(in.ReferenceSet)
+	out.ExtractReferences = pipeline.CloneReferenceTarget(in.ExtractReferences)
+	out.NormalizeReferences = pipeline.CloneReferenceTarget(in.NormalizeReferences)
 	if len(in.Validators) > 0 {
 		out.Validators = make([]pipeline.ModuleBinding, len(in.Validators))
 		for i, binding := range in.Validators {

internal/core/config/redaction_test.go

@@ -67,20 +67,46 @@ func TestEffectiveConfigRedactedDiagnosticsPayloadRedactsAndCopies(t *testing.T)
 	lane := cfg.Pipelines["example"].Artifacts["events"]
 	lane.Extract.Options = map[string]any{"temperature": 0.2}
 	lane.References = map[string]string{"roster": "./roster.yml"}
+	lane.Extract.References = map[string]string{"glossary": "./glossary.md"}
+	lane.Normalize.References = map[string]string{"notes": "./normalize.md"}
 	cfg.Pipelines["example"].Artifacts["events"] = lane
+	pipelineProfile := cfg.Pipelines["example"]
+	pipelineProfile.Chunk.References = map[string]string{"scene_guide": "./scene.md"}
+	cfg.Pipelines["example"] = pipelineProfile
 
 	effective, err := cfg.Resolve(ResolveInput{
 		PipelineID: "example",
 		Only:       []string{"events"},
-		Catalog: fakeCatalog(t, pipeline.ModuleSpec{
-			Key:      "fake/extract",
-			Stage:    pipeline.StageExtract,
-			Requires: []string{"chunks"},
-			Provides: []string{"artifact"},
-			ReferenceSlots: []contracts.ReferenceSlot{
-				{Name: "roster"},
+		Catalog: fakeCatalog(t,
+			pipeline.ModuleSpec{
+				Key:      "generic",
+				Stage:    pipeline.StageChunk,
+				Requires: []string{"source"},
+				Provides: []string{"chunks"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "scene_guide"},
+				},
 			},
-		}),
+			pipeline.ModuleSpec{
+				Key:      "fake/extract",
+				Stage:    pipeline.StageExtract,
+				Requires: []string{"chunks"},
+				Provides: []string{"artifact"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "glossary"},
+					{Name: "roster"},
+				},
+			},
+			pipeline.ModuleSpec{
+				Key:      "noop",
+				Stage:    pipeline.StageNormalize,
+				Requires: []string{"merged"},
+				Provides: []string{"normalized"},
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "notes"},
+				},
+			},
+		),
 	})
 	if err != nil {
 		t.Fatalf("Resolve: %v", err)
@@ -108,8 +134,52 @@ func TestEffectiveConfigRedactedDiagnosticsPayloadRedactsAndCopies(t *testing.T)
 	if effective.ResolvedPipeline.ArtifactLanes[0].Extract.Options["temperature"] != 0.2 {
 		t.Fatalf("expected resolved pipeline options to be copied")
 	}
-	payload.ResolvedPipeline.ArtifactLanes[0].References[0].Source = "./changed.yml"
-	if effective.ResolvedPipeline.ArtifactLanes[0].References[0].Source != "./roster.yml" {
+	payload.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.Bindings[0].Source = "./changed.yml"
+	if referenceBindingSource(effective.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.Bindings, "roster") != "./roster.yml" {
 		t.Fatalf("expected resolved pipeline references to be copied")
 	}
+	payload.ResolvedPipeline.Chunk.References["scene_guide"] = "./changed-scene.md"
+	if effective.ResolvedPipeline.Chunk.References["scene_guide"] != "./scene.md" {
+		t.Fatalf("expected chunk references to be copied")
+	}
+	payload.ResolvedPipeline.ArtifactLanes[0].Extract.References["glossary"] = "./changed-glossary.md"
+	if effective.ResolvedPipeline.ArtifactLanes[0].Extract.References["glossary"] != "./glossary.md" {
+		t.Fatalf("expected extract references to be copied")
+	}
+	payload.ResolvedPipeline.ArtifactLanes[0].Normalize.References["notes"] = "./changed-normalize.md"
+	if effective.ResolvedPipeline.ArtifactLanes[0].Normalize.References["notes"] != "./normalize.md" {
+		t.Fatalf("expected normalize references to be copied")
+	}
+
+	effective.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet = contracts.ReferenceSet{
+		Slots: map[string]contracts.ResolvedReferenceSlot{
+			"roster": {
+				Slot: contracts.ReferenceSlot{Name: "roster"},
+				Items: []contracts.ReferenceItem{
+					{
+						SlotName: "roster",
+						Content:  []byte("reference content"),
+					},
+				},
+			},
+		},
+	}
+	payload, ok = effective.RedactedDiagnosticsPayload().(EffectiveConfig)
+	if !ok {
+		t.Fatalf("expected EffectiveConfig payload, got %T", effective.RedactedDiagnosticsPayload())
+	}
+	payload.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0].Content[0] = 'X'
+	got := effective.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0].Content
+	if string(got) != "reference content" {
+		t.Fatalf("expected materialized reference content to be copied, got %q", got)
+	}
+}
+
+func referenceBindingSource(bindings []pipeline.ReferenceBinding, slotName string) string {
+	for _, binding := range bindings {
+		if binding.SlotName == slotName {
+			return binding.Source
+		}
+	}
+	return ""
 }

internal/core/config/validation.go

@@ -89,13 +89,13 @@ func validatePipelineProfiles(profiles map[string]pipeline.PipelineProfile, llmP
 		if profile.ID != "" && strings.TrimSpace(profile.ID) != id {
 			return fmt.Errorf("pipeline %q profile id %q does not match map key", id, profile.ID)
 		}
-		if err := validateBindingLLMProfile(id, "", "input", profile.Input, llmProfiles); err != nil {
+		if err := validateBinding(id, "", "input", profile.Input, llmProfiles, false); err != nil {
 			return err
 		}
-		if err := validateBindingLLMProfile(id, "", "chunk", profile.Chunk, llmProfiles); err != nil {
+		if err := validateBinding(id, "", "chunk", profile.Chunk, llmProfiles, true); err != nil {
 			return err
 		}
-		if err := validateBindingLLMProfile(id, "", "output", profile.Output, llmProfiles); err != nil {
+		if err := validateBinding(id, "", "output", profile.Output, llmProfiles, false); err != nil {
 			return err
 		}
 		if err := validateReferenceMap(id, "", profile.References); err != nil {
@@ -109,17 +109,17 @@ func validatePipelineProfiles(profiles map[string]pipeline.PipelineProfile, llmP
 			if err := validateReferenceMap(id, laneID, lane.References); err != nil {
 				return err
 			}
-			if err := validateBindingLLMProfile(id, laneID, "extract", lane.Extract, llmProfiles); err != nil {
+			if err := validateBinding(id, laneID, "extract", lane.Extract, llmProfiles, true); err != nil {
 				return err
 			}
-			if err := validateBindingLLMProfile(id, laneID, "merge", lane.Merge, llmProfiles); err != nil {
+			if err := validateBinding(id, laneID, "merge", lane.Merge, llmProfiles, false); err != nil {
 				return err
 			}
-			if err := validateBindingLLMProfile(id, laneID, "normalize", lane.Normalize, llmProfiles); err != nil {
+			if err := validateBinding(id, laneID, "normalize", lane.Normalize, llmProfiles, true); err != nil {
 				return err
 			}
 			for i, validator := range lane.Validators {
-				if err := validateBindingLLMProfile(id, laneID, fmt.Sprintf("validator[%d]", i), validator, llmProfiles); err != nil {
+				if err := validateBinding(id, laneID, fmt.Sprintf("validator[%d]", i), validator, llmProfiles, false); err != nil {
 					return err
 				}
 			}
@@ -128,33 +128,64 @@ func validatePipelineProfiles(profiles map[string]pipeline.PipelineProfile, llmP
 	return nil
 }
 
+func validateBinding(
+	pipelineID string,
+	laneID string,
+	slot string,
+	binding pipeline.ModuleBinding,
+	profiles map[string]LLMProfile,
+	referencesAllowed bool,
+) error {
+	if err := validateBindingLLMProfile(pipelineID, laneID, slot, binding, profiles); err != nil {
+		return err
+	}
+	if len(binding.References) == 0 {
+		return nil
+	}
+	if !referencesAllowed {
+		if laneID != "" {
+			return fmt.Errorf("pipeline %q lane %q %s references are not supported", pipelineID, laneID, slot)
+		}
+		return fmt.Errorf("pipeline %q %s references are not supported", pipelineID, slot)
+	}
+	return validateReferenceMapForContext(pipelineID, laneID, slot, binding.References)
+}
+
 func validateReferenceMap(pipelineID string, laneID string, references map[string]string) error {
+	return validateReferenceMapForContext(pipelineID, laneID, "", references)
+}
+
+func validateReferenceMapForContext(pipelineID string, laneID string, slot string, references map[string]string) error {
 	seen := make(map[string]struct{}, len(references))
 	for rawSlotName, rawSource := range references {
 		slotName := strings.TrimSpace(rawSlotName)
 		if slotName == "" {
-			if laneID != "" {
-				return fmt.Errorf("pipeline %q lane %q reference slot name must not be empty", pipelineID, laneID)
-			}
-			return fmt.Errorf("pipeline %q reference slot name must not be empty", pipelineID)
+			return fmt.Errorf("%s reference slot name must not be empty", referenceContext(pipelineID, laneID, slot))
 		}
 		if _, ok := seen[slotName]; ok {
-			if laneID != "" {
-				return fmt.Errorf("pipeline %q lane %q reference slot %q is duplicated after trimming", pipelineID, laneID, slotName)
-			}
-			return fmt.Errorf("pipeline %q reference slot %q is duplicated after trimming", pipelineID, slotName)
+			return fmt.Errorf("%s reference slot %q is duplicated after trimming", referenceContext(pipelineID, laneID, slot), slotName)
 		}
 		seen[slotName] = struct{}{}
 		if strings.TrimSpace(rawSource) == "" {
-			if laneID != "" {
-				return fmt.Errorf("pipeline %q lane %q reference slot %q source must not be empty", pipelineID, laneID, slotName)
-			}
-			return fmt.Errorf("pipeline %q reference slot %q source must not be empty", pipelineID, slotName)
+			return fmt.Errorf("%s reference slot %q source must not be empty", referenceContext(pipelineID, laneID, slot), slotName)
 		}
 	}
 	return nil
 }
 
+func referenceContext(pipelineID string, laneID string, slot string) string {
+	if laneID != "" && slot != "" {
+		return fmt.Sprintf("pipeline %q lane %q %s", pipelineID, laneID, slot)
+	}
+	if laneID != "" {
+		return fmt.Sprintf("pipeline %q lane %q", pipelineID, laneID)
+	}
+	if slot != "" {
+		return fmt.Sprintf("pipeline %q %s", pipelineID, slot)
+	}
+	return fmt.Sprintf("pipeline %q", pipelineID)
+}
+
 func validateBindingLLMProfile(
 	pipelineID string,
 	laneID string,

internal/core/config/validation_test.go

@@ -122,6 +122,74 @@ func TestValidateRejectsInvalidReferenceMaps(t *testing.T) {
 		mutate func(Config) Config
 		want   []string
 	}{
+		{
+			name: "empty chunk slot",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				profile.Chunk.References = map[string]string{" ": "./roster.yml"}
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "chunk", "reference slot", "empty"},
+		},
+		{
+			name: "empty chunk source",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				profile.Chunk.References = map[string]string{"roster": " "}
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "chunk", "roster", "source", "empty"},
+		},
+		{
+			name: "empty extract slot",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				lane := profile.Artifacts["events"]
+				lane.Extract.References = map[string]string{" ": "./roster.yml"}
+				profile.Artifacts["events"] = lane
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "events", "extract", "reference slot", "empty"},
+		},
+		{
+			name: "empty extract source",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				lane := profile.Artifacts["events"]
+				lane.Extract.References = map[string]string{"roster": " "}
+				profile.Artifacts["events"] = lane
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "events", "extract", "roster", "source", "empty"},
+		},
+		{
+			name: "empty normalize slot",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				lane := profile.Artifacts["events"]
+				lane.Normalize.References = map[string]string{" ": "./roster.yml"}
+				profile.Artifacts["events"] = lane
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "events", "normalize", "reference slot", "empty"},
+		},
+		{
+			name: "empty normalize source",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				lane := profile.Artifacts["events"]
+				lane.Normalize.References = map[string]string{"roster": " "}
+				profile.Artifacts["events"] = lane
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "events", "normalize", "roster", "source", "empty"},
+		},
 		{
 			name: "empty pipeline slot",
 			mutate: func(cfg Config) Config {
@@ -183,6 +251,76 @@ func TestValidateRejectsInvalidReferenceMaps(t *testing.T) {
 	}
 }
 
+func TestValidateRejectsReferencesOnUnsupportedBindings(t *testing.T) {
+	tests := []struct {
+		name   string
+		mutate func(Config) Config
+		want   []string
+	}{
+		{
+			name: "input",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				profile.Input.References = map[string]string{"roster": "./roster.yml"}
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "input", "references", "not supported"},
+		},
+		{
+			name: "merge",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				lane := profile.Artifacts["events"]
+				lane.Merge.References = map[string]string{"roster": "./roster.yml"}
+				profile.Artifacts["events"] = lane
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "events", "merge", "references", "not supported"},
+		},
+		{
+			name: "validator",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				lane := profile.Artifacts["events"]
+				lane.Validators = []pipeline.ModuleBinding{{
+					Module:     "fake/validator",
+					References: map[string]string{"roster": "./roster.yml"},
+				}}
+				profile.Artifacts["events"] = lane
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "events", "validator[0]", "references", "not supported"},
+		},
+		{
+			name: "output",
+			mutate: func(cfg Config) Config {
+				profile := cfg.Pipelines["example"]
+				profile.Output.References = map[string]string{"roster": "./roster.yml"}
+				cfg.Pipelines["example"] = profile
+				return cfg
+			},
+			want: []string{"example", "output", "references", "not supported"},
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			err := tc.mutate(validConfig()).Validate()
+			if err == nil {
+				t.Fatal("Validate() error = nil, want error")
+			}
+			for _, want := range tc.want {
+				if !strings.Contains(err.Error(), want) {
+					t.Fatalf("Validate() error = %q, want substring %q", err.Error(), want)
+				}
+			}
+		})
+	}
+}
+
 func TestValidateRejectsEmptyIDs(t *testing.T) {
 	tests := []struct {
 		name   string

internal/framework/contracts/composition_test.go

@@ -162,6 +162,10 @@ func (chunker compositionChunker) Key() string {
 	return "generic-chunker"
 }
 
+func (chunker compositionChunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (chunker compositionChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	if req.Source == nil {
 		return contracts.ChunkResult{}, errors.New("source document is required")
@@ -264,6 +268,10 @@ func (normalizer compositionNormalizer) Key() string {
 	return "generic-normalizer"
 }
 
+func (normalizer compositionNormalizer) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (normalizer compositionNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
 	return contracts.NormalizeResult{Candidates: req.Candidates}, nil
 }

internal/framework/contracts/contracts.go

@@ -58,6 +58,7 @@ type SourceChunk struct {
 
 type ChunkRequest struct {
 	Source     *source.SourceDocument `json:"-"`
+	References ReferenceSet           `json:"references,omitempty"`
 	LLMClient  StructuredLLMClient    `json:"-"`
 	LLMProfile string                 `json:"llm_profile,omitempty"`
 	Options    map[string]any         `json:"options,omitempty"`
@@ -71,6 +72,7 @@ type ChunkResult struct {
 
 type Chunker interface {
 	Key() string
+	ReferenceSlots() []ReferenceSlot
 	Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error)
 }
 
@@ -165,6 +167,8 @@ type NormalizeRequest struct {
 	Source     *source.SourceDocument        `json:"-"`
 	LaneID     string                        `json:"lane_id"`
 	Candidates []artifacts.ArtifactCandidate `json:"candidates"`
+	References ReferenceSet                  `json:"references,omitempty"`
+	LLMClient  StructuredLLMClient           `json:"-"`
 	LLMProfile string                        `json:"llm_profile,omitempty"`
 	Options    map[string]any                `json:"options,omitempty"`
 	Metadata   map[string]any                `json:"metadata,omitempty"`
@@ -177,6 +181,7 @@ type NormalizeResult struct {
 
 type Normalizer interface {
 	Key() string
+	ReferenceSlots() []ReferenceSlot
 	Normalize(ctx context.Context, req NormalizeRequest) (NormalizeResult, error)
 }
 

internal/framework/contracts/contracts_test.go

@@ -378,6 +378,10 @@ func (chunker fakeChunker) Key() string {
 	return chunker.key
 }
 
+func (chunker fakeChunker) ReferenceSlots() []ReferenceSlot {
+	return nil
+}
+
 func (chunker fakeChunker) Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error) {
 	return ChunkResult{
 		Chunks: []SourceChunk{
@@ -400,6 +404,10 @@ func (chunker *recordingChunker) Key() string {
 	return chunker.key
 }
 
+func (chunker *recordingChunker) ReferenceSlots() []ReferenceSlot {
+	return nil
+}
+
 func (chunker *recordingChunker) Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error) {
 	chunker.request = req
 	return fakeChunker{key: chunker.key}.Chunk(ctx, req)
@@ -487,6 +495,10 @@ func (normalizer fakeNormalizer) Key() string {
 	return normalizer.key
 }
 
+func (normalizer fakeNormalizer) ReferenceSlots() []ReferenceSlot {
+	return nil
+}
+
 func (normalizer fakeNormalizer) Normalize(ctx context.Context, req NormalizeRequest) (NormalizeResult, error) {
 	return NormalizeResult{Candidates: req.Candidates}, nil
 }

internal/framework/pipeline/chunker_registry_test.go

@@ -330,6 +330,10 @@ func (chunker registryChunker) Key() string {
 	return chunker.key
 }
 
+func (chunker registryChunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (chunker registryChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	return contracts.ChunkResult{}, nil
 }
@@ -354,6 +358,10 @@ func (normalizer registryNormalizer) Key() string {
 	return normalizer.key
 }
 
+func (normalizer registryNormalizer) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (normalizer registryNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
 	return contracts.NormalizeResult{}, nil
 }

internal/framework/pipeline/module.go

@@ -87,7 +87,7 @@ func validateModuleSpec(kind string, expectedStage ModuleStage, spec ModuleSpec)
 	if spec.Stage != expectedStage {
 		return fmt.Errorf("%s %q must use %q stage, got %q", kind, spec.Key, expectedStage, spec.Stage)
 	}
-	if spec.Stage != StageExtract && len(spec.ReferenceSlots) > 0 {
+	if !referenceSlotStage(spec.Stage) && len(spec.ReferenceSlots) > 0 {
 		return fmt.Errorf("%s %q must not declare reference slots", kind, spec.Key)
 	}
 	if err := validateReferenceSlots(spec.ReferenceSlots); err != nil {
@@ -96,6 +96,10 @@ func validateModuleSpec(kind string, expectedStage ModuleStage, spec ModuleSpec)
 	return nil
 }
 
+func referenceSlotStage(stage ModuleStage) bool {
+	return stage == StageChunk || stage == StageExtract || stage == StageNormalize
+}
+
 func sortedRegistryKeys[C any](constructors map[string]C) []string {
 	if len(constructors) == 0 {
 		return nil

internal/framework/pipeline/module_test.go

@@ -7,19 +7,117 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 )
 
-func TestValidateModuleSpecRejectsReferenceSlotsForNonExtractors(t *testing.T) {
-	err := validateModuleSpec("chunker", StageChunk, ModuleSpec{
-		Key:   "generic",
-		Stage: StageChunk,
-		ReferenceSlots: []contracts.ReferenceSlot{
-			{Name: "roster"},
-		},
-	})
-
-	if err == nil {
-		t.Fatal("validateModuleSpec() error = nil, want error")
+func TestValidateModuleSpecAllowsReferenceSlotsForEligibleStages(t *testing.T) {
+	tests := []struct {
+		name  string
+		kind  string
+		stage ModuleStage
+	}{
+		{name: "chunker", kind: "chunker", stage: StageChunk},
+		{name: "extractor", kind: "extractor", stage: StageExtract},
+		{name: "normalizer", kind: "normalizer", stage: StageNormalize},
 	}
-	if !strings.Contains(err.Error(), "reference slots") {
-		t.Fatalf("validateModuleSpec() error = %q, want reference slots context", err.Error())
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			spec := normalizeModuleSpec(ModuleSpec{
+				Key:   "module",
+				Stage: test.stage,
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "roster", Description: "Character roster", MaxBytes: 1024},
+				},
+			})
+			err := validateModuleSpec(test.kind, test.stage, spec)
+			if err != nil {
+				t.Fatalf("validateModuleSpec() error = %v, want nil", err)
+			}
+		})
+	}
+}
+
+func TestValidateModuleSpecRejectsReferenceSlotsForIneligibleStages(t *testing.T) {
+	tests := []struct {
+		name  string
+		kind  string
+		stage ModuleStage
+	}{
+		{name: "input", kind: "input adapter", stage: StageInput},
+		{name: "merge", kind: "merger", stage: StageMerge},
+		{name: "validate", kind: "validator", stage: StageValidate},
+		{name: "output", kind: "output encoder", stage: StageOutput},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			spec := normalizeModuleSpec(ModuleSpec{
+				Key:   "module",
+				Stage: test.stage,
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "roster"},
+				},
+			})
+			err := validateModuleSpec(test.kind, test.stage, spec)
+			if err == nil {
+				t.Fatal("validateModuleSpec() error = nil, want error")
+			}
+			if !strings.Contains(err.Error(), "reference slots") {
+				t.Fatalf("validateModuleSpec() error = %q, want reference slots context", err.Error())
+			}
+		})
+	}
+}
+
+func TestValidateModuleSpecRejectsInvalidReferenceSlotsForEligibleStages(t *testing.T) {
+	invalidSlots := []struct {
+		name  string
+		slots []contracts.ReferenceSlot
+		want  string
+	}{
+		{
+			name:  "empty name",
+			slots: []contracts.ReferenceSlot{{Name: " "}},
+			want:  "name",
+		},
+		{
+			name: "duplicate name after trim",
+			slots: []contracts.ReferenceSlot{
+				{Name: "roster"},
+				{Name: " roster "},
+			},
+			want: "duplicated",
+		},
+		{
+			name:  "negative max bytes",
+			slots: []contracts.ReferenceSlot{{Name: "roster", MaxBytes: -1}},
+			want:  "max_bytes",
+		},
+	}
+	eligibleStages := []struct {
+		name  string
+		kind  string
+		stage ModuleStage
+	}{
+		{name: "chunk", kind: "chunker", stage: StageChunk},
+		{name: "extract", kind: "extractor", stage: StageExtract},
+		{name: "normalize", kind: "normalizer", stage: StageNormalize},
+	}
+
+	for _, stage := range eligibleStages {
+		for _, invalid := range invalidSlots {
+			t.Run(stage.name+"/"+invalid.name, func(t *testing.T) {
+				spec := normalizeModuleSpec(ModuleSpec{
+					Key:            "module",
+					Stage:          stage.stage,
+					ReferenceSlots: invalid.slots,
+				})
+				err := validateModuleSpec(stage.kind, stage.stage, spec)
+				if err == nil {
+					t.Fatal("validateModuleSpec() error = nil, want error")
+				}
+				if !strings.Contains(err.Error(), invalid.want) {
+					t.Fatalf("validateModuleSpec() error = %q, want %q", err.Error(), invalid.want)
+				}
+			})
+		}
 	}
 }

internal/framework/pipeline/profile.go

@@ -20,9 +20,10 @@ const (
 )
 
 type ModuleBinding struct {
-	Module     string         `json:"module"`
-	LLMProfile string         `json:"llm_profile,omitempty"`
-	Options    map[string]any `json:"options,omitempty"`
+	Module     string            `json:"module"`
+	LLMProfile string            `json:"llm_profile,omitempty"`
+	Options    map[string]any    `json:"options,omitempty"`
+	References map[string]string `json:"references,omitempty"`
 }
 
 type ArtifactLaneProfile struct {
@@ -49,34 +50,45 @@ type ResolveOptions struct {
 }
 
 type ReferenceBinding struct {
-	LaneID        string `json:"lane_id,omitempty"`
-	SlotName      string `json:"slot_name"`
-	Source        string `json:"source"`
-	BindingSource string `json:"binding_source,omitempty"`
+	Stage         ModuleStage `json:"stage,omitempty"`
+	LaneID        string      `json:"lane_id,omitempty"`
+	SlotName      string      `json:"slot_name"`
+	Source        string      `json:"source"`
+	BindingSource string      `json:"binding_source,omitempty"`
 }
 
 type ReferenceUnbind struct {
-	LaneID   string `json:"lane_id"`
-	SlotName string `json:"slot_name"`
+	Stage    ModuleStage `json:"stage,omitempty"`
+	LaneID   string      `json:"lane_id,omitempty"`
+	SlotName string      `json:"slot_name"`
 }
 
-type ResolvedArtifactLane struct {
-	ID           string
-	Extract      ModuleBinding
-	Merge        ModuleBinding
-	Normalize    ModuleBinding
-	Validators   []ModuleBinding
-	References   []ReferenceBinding     `json:"references,omitempty"`
+type ResolvedReferenceTarget struct {
+	Stage        ModuleStage            `json:"stage"`
+	LaneID       string                 `json:"lane_id,omitempty"`
+	Module       string                 `json:"module"`
+	Bindings     []ReferenceBinding     `json:"bindings,omitempty"`
 	ReferenceSet contracts.ReferenceSet `json:"-"`
 }
 
+type ResolvedArtifactLane struct {
+	ID                  string
+	Extract             ModuleBinding
+	Merge               ModuleBinding
+	Normalize           ModuleBinding
+	Validators          []ModuleBinding
+	ExtractReferences   ResolvedReferenceTarget `json:"extract_references"`
+	NormalizeReferences ResolvedReferenceTarget `json:"normalize_references"`
+}
+
 type ResolvedPipeline struct {
-	ID            string
-	Digest        string
-	Input         ModuleBinding
-	Chunk         ModuleBinding
-	ArtifactLanes []ResolvedArtifactLane
-	Output        ModuleBinding
+	ID              string
+	Digest          string
+	Input           ModuleBinding
+	Chunk           ModuleBinding
+	ChunkReferences ResolvedReferenceTarget `json:"chunk_references"`
+	ArtifactLanes   []ResolvedArtifactLane
+	Output          ModuleBinding
 }
 
 type ModuleCatalog struct {
@@ -135,15 +147,28 @@ func ResolvePipeline(profile PipelineProfile, options ResolveOptions, catalog Mo
 	if len(selectedLaneIDs) == 0 {
 		return ResolvedPipeline{}, fmt.Errorf("pipeline %q must select at least one artifact lane", pipelineID)
 	}
-	if err := validatePipelineReferenceDefaults(pipelineID, profile.References, lanesByID, catalog); err != nil {
+	if err := validatePipelineReferenceDefaults(pipelineID, profile.References, chunkSpec, lanesByID, catalog); err != nil {
 		return ResolvedPipeline{}, err
 	}
 
+	chunkReferences, err := resolveReferenceTargetBindings(referenceResolutionTarget{
+		PipelineID:         pipelineID,
+		Stage:              StageChunk,
+		Module:             chunk.Module,
+		Slots:              chunkSpec.ReferenceSlots,
+		PipelineReferences: profile.References,
+		LocalReferences:    chunk.References,
+		Options:            options,
+	})
+	if err != nil {
+		return ResolvedPipeline{}, err
+	}
 	resolved := ResolvedPipeline{
-		ID:     pipelineID,
-		Input:  input,
-		Chunk:  chunk,
-		Output: resolveBinding(profile.Output, DefaultOutputModule),
+		ID:              pipelineID,
+		Input:           input,
+		Chunk:           chunk,
+		ChunkReferences: referenceTarget(StageChunk, "", chunk.Module, chunkReferences),
+		Output:          resolveBinding(profile.Output, DefaultOutputModule),
 	}
 	outputCapabilities := capabilities.clone()
 
@@ -202,11 +227,21 @@ func resolveArtifactLane(
 	if missing, ok := capabilities.missing(extractSpec.Requires); ok {
 		return ResolvedArtifactLane{}, nil, capabilityError(pipelineID, laneID, StageExtract, lane.Extract.Module, missing)
 	}
-	references, err := resolveReferenceBindings(pipelineID, laneID, lane.Extract.Module, extractSpec.ReferenceSlots, pipelineReferences, profile.References, options)
+	extractReferences := mergeReferenceMaps(profile.References, lane.Extract.References)
+	references, err := resolveReferenceTargetBindings(referenceResolutionTarget{
+		PipelineID:         pipelineID,
+		LaneID:             laneID,
+		Stage:              StageExtract,
+		Module:             lane.Extract.Module,
+		Slots:              extractSpec.ReferenceSlots,
+		PipelineReferences: pipelineReferences,
+		LocalReferences:    extractReferences,
+		Options:            options,
+	})
 	if err != nil {
 		return ResolvedArtifactLane{}, nil, err
 	}
-	lane.References = references
+	lane.ExtractReferences = referenceTarget(StageExtract, laneID, lane.Extract.Module, references)
 	capabilities.add(extractSpec.Provides...)
 
 	mergeSpec, err := mergerSpec(catalog, lane.Merge.Module)
@@ -225,6 +260,20 @@ func resolveArtifactLane(
 	if missing, ok := capabilities.missing(normalizeSpec.Requires); ok {
 		return ResolvedArtifactLane{}, nil, capabilityError(pipelineID, laneID, StageNormalize, lane.Normalize.Module, missing)
 	}
+	normalizeReferences, err := resolveReferenceTargetBindings(referenceResolutionTarget{
+		PipelineID:         pipelineID,
+		LaneID:             laneID,
+		Stage:              StageNormalize,
+		Module:             lane.Normalize.Module,
+		Slots:              normalizeSpec.ReferenceSlots,
+		PipelineReferences: pipelineReferences,
+		LocalReferences:    lane.Normalize.References,
+		Options:            options,
+	})
+	if err != nil {
+		return ResolvedArtifactLane{}, nil, err
+	}
+	lane.NormalizeReferences = referenceTarget(StageNormalize, laneID, lane.Normalize.Module, normalizeReferences)
 	capabilities.add(normalizeSpec.Provides...)
 
 	for _, validator := range lane.Validators {
@@ -241,9 +290,33 @@ func resolveArtifactLane(
 	return lane, capabilities, nil
 }
 
+func referenceTarget(stage ModuleStage, laneID string, module string, bindings []ReferenceBinding) ResolvedReferenceTarget {
+	return ResolvedReferenceTarget{
+		Stage:    stage,
+		LaneID:   strings.TrimSpace(laneID),
+		Module:   strings.TrimSpace(module),
+		Bindings: append([]ReferenceBinding(nil), bindings...),
+	}
+}
+
+func mergeReferenceMaps(base map[string]string, override map[string]string) map[string]string {
+	if len(base) == 0 && len(override) == 0 {
+		return nil
+	}
+	out := make(map[string]string, len(base)+len(override))
+	for key, value := range base {
+		out[key] = value
+	}
+	for key, value := range override {
+		out[key] = value
+	}
+	return out
+}
+
 func validatePipelineReferenceDefaults(
 	pipelineID string,
 	pipelineReferences map[string]string,
+	chunkSpec ModuleSpec,
 	lanesByID map[string]ArtifactLaneProfile,
 	catalog ModuleCatalog,
 ) error {
@@ -255,7 +328,10 @@ func validatePipelineReferenceDefaults(
 		return nil
 	}
 
-	declaredByAnyLane := make(map[string]struct{}, len(normalizedPipelineReferences))
+	declaredByAnyTarget := make(map[string]struct{}, len(normalizedPipelineReferences))
+	for _, slot := range chunkSpec.ReferenceSlots {
+		declaredByAnyTarget[slot.Name] = struct{}{}
+	}
 	for _, laneID := range sortedArtifactLaneProfileKeys(lanesByID) {
 		laneProfile := lanesByID[laneID]
 		extract := resolveBinding(laneProfile.Extract, "")
@@ -267,29 +343,41 @@ func validatePipelineReferenceDefaults(
 			return moduleLookupError(pipelineID, laneID, StageExtract, extract.Module, err)
 		}
 		for _, slot := range extractSpec.ReferenceSlots {
-			declaredByAnyLane[slot.Name] = struct{}{}
+			declaredByAnyTarget[slot.Name] = struct{}{}
+		}
+
+		normalize := resolveBinding(laneProfile.Normalize, DefaultNormalizeModule)
+		normalizeSpec, err := normalizerSpec(catalog, normalize.Module)
+		if err != nil {
+			return moduleLookupError(pipelineID, laneID, StageNormalize, normalize.Module, err)
+		}
+		for _, slot := range normalizeSpec.ReferenceSlots {
+			declaredByAnyTarget[slot.Name] = struct{}{}
 		}
 	}
 
 	for _, slotName := range sortedStringMapKeys(normalizedPipelineReferences) {
-		if _, ok := declaredByAnyLane[slotName]; !ok {
-			return fmt.Errorf("pipeline %q reference slot %q is not declared by any artifact lane", pipelineID, slotName)
+		if _, ok := declaredByAnyTarget[slotName]; !ok {
+			return fmt.Errorf("pipeline %q reference slot %q is not declared by any eligible reference target", pipelineID, slotName)
 		}
 	}
 	return nil
 }
 
-func resolveReferenceBindings(
-	pipelineID string,
-	laneID string,
-	extractorModule string,
-	slots []contracts.ReferenceSlot,
-	pipelineReferences map[string]string,
-	laneReferences map[string]string,
-	options ResolveOptions,
-) ([]ReferenceBinding, error) {
-	slotByName := make(map[string]contracts.ReferenceSlot, len(slots))
-	for _, slot := range slots {
+type referenceResolutionTarget struct {
+	PipelineID         string
+	LaneID             string
+	Stage              ModuleStage
+	Module             string
+	Slots              []contracts.ReferenceSlot
+	PipelineReferences map[string]string
+	LocalReferences    map[string]string
+	Options            ResolveOptions
+}
+
+func resolveReferenceTargetBindings(target referenceResolutionTarget) ([]ReferenceBinding, error) {
+	slotByName := make(map[string]contracts.ReferenceSlot, len(target.Slots))
+	for _, slot := range target.Slots {
 		slotByName[slot.Name] = slot
 	}
 
@@ -298,16 +386,16 @@ func resolveReferenceBindings(
 		slotName = strings.TrimSpace(slotName)
 		source = strings.TrimSpace(source)
 		if slotName == "" {
-			return fmt.Errorf("pipeline %q lane %q reference slot name must not be empty", pipelineID, laneID)
+			return fmt.Errorf("%s reference slot name must not be empty", referenceTargetErrorContext(target))
 		}
 		if source == "" {
-			return fmt.Errorf("pipeline %q lane %q reference slot %q source must not be empty", pipelineID, laneID, slotName)
+			return fmt.Errorf("%s reference slot %q source must not be empty", referenceTargetErrorContext(target), slotName)
 		}
 		if _, ok := slotByName[slotName]; !ok {
-			return fmt.Errorf("pipeline %q lane %q reference slot %q is not declared by extractor %q", pipelineID, laneID, slotName, extractorModule)
+			return fmt.Errorf("%s reference slot %q is not declared by %s module %q", referenceTargetErrorContext(target), slotName, target.Stage, target.Module)
 		}
 		bindings[slotName] = ReferenceBinding{
-			LaneID:        laneID,
+			LaneID:        target.LaneID,
 			SlotName:      slotName,
 			Source:        source,
 			BindingSource: bindingSource,
@@ -315,7 +403,7 @@ func resolveReferenceBindings(
 		return nil
 	}
 
-	normalizedPipelineReferences, err := normalizedReferenceMap(pipelineReferences, fmt.Sprintf("pipeline %q reference slot", pipelineID))
+	normalizedPipelineReferences, err := normalizedReferenceMap(target.PipelineReferences, fmt.Sprintf("pipeline %q reference slot", target.PipelineID))
 	if err != nil {
 		return nil, err
 	}
@@ -328,22 +416,22 @@ func resolveReferenceBindings(
 		}
 	}
 
-	normalizedLaneReferences, err := normalizedReferenceMap(laneReferences, fmt.Sprintf("pipeline %q lane %q reference slot", pipelineID, laneID))
+	normalizedLocalReferences, err := normalizedReferenceMap(target.LocalReferences, referenceTargetSlotLabel(target))
 	if err != nil {
 		return nil, err
 	}
-	for _, slotName := range sortedStringMapKeys(normalizedLaneReferences) {
-		if err := addBinding(slotName, normalizedLaneReferences[slotName], contracts.ReferenceBindingSourceConfig); err != nil {
+	for _, slotName := range sortedStringMapKeys(normalizedLocalReferences) {
+		if err := addBinding(slotName, normalizedLocalReferences[slotName], contracts.ReferenceBindingSourceConfig); err != nil {
 			return nil, err
 		}
 	}
 
-	for _, override := range options.ReferenceOverrides {
-		optionLaneID := strings.TrimSpace(override.LaneID)
-		if optionLaneID == "" {
-			return nil, fmt.Errorf("pipeline %q reference override lane id must not be empty", pipelineID)
+	for _, override := range target.Options.ReferenceOverrides {
+		match, err := referenceOverrideMatchesTarget(target, override)
+		if err != nil {
+			return nil, err
 		}
-		if optionLaneID != laneID {
+		if !match {
 			continue
 		}
 		source := override.BindingSource
@@ -355,38 +443,94 @@ func resolveReferenceBindings(
 		}
 	}
 
-	for _, unbind := range options.ReferenceUnbinds {
-		optionLaneID := strings.TrimSpace(unbind.LaneID)
-		if optionLaneID == "" {
-			return nil, fmt.Errorf("pipeline %q reference unbind lane id must not be empty", pipelineID)
+	for _, unbind := range target.Options.ReferenceUnbinds {
+		match, err := referenceUnbindMatchesTarget(target, unbind)
+		if err != nil {
+			return nil, err
 		}
-		if optionLaneID != laneID {
+		if !match {
 			continue
 		}
 		slotName := strings.TrimSpace(unbind.SlotName)
 		if slotName == "" {
-			return nil, fmt.Errorf("pipeline %q lane %q reference unbind slot name must not be empty", pipelineID, laneID)
+			return nil, fmt.Errorf("%s reference unbind slot name must not be empty", referenceTargetErrorContext(target))
 		}
 		if _, ok := slotByName[slotName]; !ok {
-			return nil, fmt.Errorf("pipeline %q lane %q reference slot %q is not declared", pipelineID, laneID, slotName)
+			return nil, fmt.Errorf("%s reference slot %q is not declared", referenceTargetErrorContext(target), slotName)
 		}
 		delete(bindings, slotName)
 	}
 
-	for _, slot := range slots {
+	for _, slot := range target.Slots {
 		if slot.Required {
 			if _, ok := bindings[slot.Name]; !ok {
-				return nil, fmt.Errorf("pipeline %q lane %q required reference slot %q is not bound", pipelineID, laneID, slot.Name)
+				return nil, fmt.Errorf("%s required reference slot %q is not bound", referenceTargetErrorContext(target), slot.Name)
 			}
 		}
 	}
 
+	return sortedReferenceBindings(bindings), nil
+}
+
+func referenceOverrideMatchesTarget(target referenceResolutionTarget, override ReferenceBinding) (bool, error) {
+	stage, laneID, err := normalizeReferenceOptionTarget(target.PipelineID, "override", override.Stage, override.LaneID)
+	if err != nil {
+		return false, err
+	}
+	return stage == target.Stage && laneID == target.LaneID, nil
+}
+
+func referenceUnbindMatchesTarget(target referenceResolutionTarget, unbind ReferenceUnbind) (bool, error) {
+	stage, laneID, err := normalizeReferenceOptionTarget(target.PipelineID, "unbind", unbind.Stage, unbind.LaneID)
+	if err != nil {
+		return false, err
+	}
+	return stage == target.Stage && laneID == target.LaneID, nil
+}
+
+func normalizeReferenceOptionTarget(pipelineID string, operation string, stage ModuleStage, laneID string) (ModuleStage, string, error) {
+	stage = ModuleStage(strings.TrimSpace(string(stage)))
+	if stage == "" {
+		stage = StageExtract
+	}
+	laneID = strings.TrimSpace(laneID)
+
+	switch stage {
+	case StageChunk:
+		if laneID != "" {
+			return "", "", fmt.Errorf("pipeline %q reference %s for chunk must not include a lane id", pipelineID, operation)
+		}
+	case StageExtract, StageNormalize:
+		if laneID == "" {
+			return "", "", fmt.Errorf("pipeline %q reference %s lane id must not be empty", pipelineID, operation)
+		}
+	default:
+		return "", "", fmt.Errorf("pipeline %q reference %s stage %q is not supported", pipelineID, operation, stage)
+	}
+	return stage, laneID, nil
+}
+
+func sortedReferenceBindings(bindings map[string]ReferenceBinding) []ReferenceBinding {
 	keys := sortedReferenceBindingKeys(bindings)
 	resolved := make([]ReferenceBinding, 0, len(keys))
 	for _, slotName := range keys {
 		resolved = append(resolved, bindings[slotName])
 	}
-	return resolved, nil
+	return resolved
+}
+
+func referenceTargetErrorContext(target referenceResolutionTarget) string {
+	if target.LaneID != "" {
+		return fmt.Sprintf("pipeline %q lane %q %s module %q", target.PipelineID, target.LaneID, target.Stage, target.Module)
+	}
+	return fmt.Sprintf("pipeline %q %s module %q", target.PipelineID, target.Stage, target.Module)
+}
+
+func referenceTargetSlotLabel(target referenceResolutionTarget) string {
+	if target.LaneID != "" {
+		return fmt.Sprintf("pipeline %q lane %q %s reference slot", target.PipelineID, target.LaneID, target.Stage)
+	}
+	return fmt.Sprintf("pipeline %q %s reference slot", target.PipelineID, target.Stage)
 }
 
 func normalizedReferenceMap(values map[string]string, keyName string) (map[string]string, error) {
@@ -460,6 +604,7 @@ func resolveBinding(binding ModuleBinding, defaultModule string) ModuleBinding {
 		Module:     module,
 		LLMProfile: llmProfile,
 		Options:    cloneOptions(binding.Options),
+		References: normalizeReferenceMap(binding.References),
 	}
 }
 
@@ -488,6 +633,25 @@ func cloneOptions(options map[string]any) map[string]any {
 	return copied
 }
 
+func normalizeReferenceMap(values map[string]string) map[string]string {
+	if len(values) == 0 {
+		return nil
+	}
+	out := make(map[string]string, len(values))
+	keys := make([]string, 0, len(values))
+	rawByNormalized := make(map[string]string, len(values))
+	for rawKey := range values {
+		key := strings.TrimSpace(rawKey)
+		rawByNormalized[key] = rawKey
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+	for _, key := range keys {
+		out[key] = strings.TrimSpace(values[rawByNormalized[key]])
+	}
+	return out
+}
+
 func selectedArtifactLanes(pipelineID string, artifacts map[string]ArtifactLaneProfile, options ResolveOptions) (map[string]ArtifactLaneProfile, []string, error) {
 	lanesByID := make(map[string]ArtifactLaneProfile, len(artifacts))
 	for rawLaneID, lane := range artifacts {
@@ -532,17 +696,19 @@ func selectedArtifactLanes(pipelineID string, artifacts map[string]ArtifactLaneP
 
 func resolvedPipelineDigest(resolved ResolvedPipeline) (string, error) {
 	withoutDigest := struct {
-		ID            string
-		Input         ModuleBinding
-		Chunk         ModuleBinding
-		ArtifactLanes []ResolvedArtifactLane
-		Output        ModuleBinding
+		ID              string
+		Input           ModuleBinding
+		Chunk           ModuleBinding
+		ChunkReferences ResolvedReferenceTarget
+		ArtifactLanes   []ResolvedArtifactLane
+		Output          ModuleBinding
 	}{
-		ID:            resolved.ID,
-		Input:         resolved.Input,
-		Chunk:         resolved.Chunk,
-		ArtifactLanes: resolved.ArtifactLanes,
-		Output:        resolved.Output,
+		ID:              resolved.ID,
+		Input:           resolved.Input,
+		Chunk:           resolved.Chunk,
+		ChunkReferences: resolved.ChunkReferences,
+		ArtifactLanes:   resolved.ArtifactLanes,
+		Output:          resolved.Output,
 	}
 	encoded, err := json.Marshal(withoutDigest)
 	if err != nil {

internal/framework/pipeline/profile_test.go

@@ -154,19 +154,131 @@ func TestResolvePipelineAppliesReferenceBindings(t *testing.T) {
 	}
 
 	events := resolvedLane(t, resolved.ArtifactLanes, "events")
+	if events.ExtractReferences.Stage != StageExtract || events.ExtractReferences.LaneID != "events" || events.ExtractReferences.Module != "event-extractor" {
+		t.Fatalf("extract reference target = %#v, want event extractor target", events.ExtractReferences)
+	}
+	if events.NormalizeReferences.Stage != StageNormalize || events.NormalizeReferences.LaneID != "events" || events.NormalizeReferences.Module != DefaultNormalizeModule {
+		t.Fatalf("normalize reference target = %#v, want event normalizer target", events.NormalizeReferences)
+	}
+	if resolved.ChunkReferences.Stage != StageChunk || resolved.ChunkReferences.Module != DefaultChunkModule {
+		t.Fatalf("chunk reference target = %#v, want chunk target", resolved.ChunkReferences)
+	}
 	want := []ReferenceBinding{
 		{LaneID: "events", SlotName: "lore", Source: "./lore.md", BindingSource: contracts.ReferenceBindingSourceConfig},
 		{LaneID: "events", SlotName: "roster", Source: "./lane-roster.yml", BindingSource: contracts.ReferenceBindingSourceConfig},
 	}
-	if !reflect.DeepEqual(events.References, want) {
-		t.Fatalf("events references = %#v, want %#v", events.References, want)
+	if !reflect.DeepEqual(events.ExtractReferences.Bindings, want) {
+		t.Fatalf("events references = %#v, want %#v", events.ExtractReferences.Bindings, want)
 	}
 	summaries := resolvedLane(t, resolved.ArtifactLanes, "summaries")
-	if len(summaries.References) != 0 {
-		t.Fatalf("summaries references = %#v, want none", summaries.References)
+	if len(summaries.ExtractReferences.Bindings) != 0 {
+		t.Fatalf("summaries references = %#v, want none", summaries.ExtractReferences.Bindings)
 	}
 }
 
+func TestResolvePipelineAppliesPipelineReferenceDefaultToChunkTarget(t *testing.T) {
+	profile := baselineProfile()
+	profile.References = map[string]string{"scene_guide": "./scenes.md"}
+	catalog := newProfileCatalogWithOverrides(t, ModuleSpec{
+		Key:            "generic",
+		Stage:          StageChunk,
+		Requires:       []string{"source"},
+		Provides:       []string{"chunk"},
+		ReferenceSlots: []contracts.ReferenceSlot{{Name: "scene_guide"}},
+	})
+
+	resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	want := []ReferenceBinding{{SlotName: "scene_guide", Source: "./scenes.md", BindingSource: contracts.ReferenceBindingSourceConfig}}
+	if !reflect.DeepEqual(resolved.ChunkReferences.Bindings, want) {
+		t.Fatalf("chunk references = %#v, want %#v", resolved.ChunkReferences.Bindings, want)
+	}
+	if refs := resolved.ArtifactLanes[0].ExtractReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("extract references = %#v, want none", refs)
+	}
+	if refs := resolved.ArtifactLanes[0].NormalizeReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("normalize references = %#v, want none", refs)
+	}
+}
+
+func TestResolvePipelineAppliesPipelineReferenceDefaultToExtractorTarget(t *testing.T) {
+	profile := baselineProfile()
+	profile.References = map[string]string{"roster": "./roster.yml"}
+	catalog := newProfileCatalogWithOverrides(t, ModuleSpec{
+		Key:            "event-extractor",
+		Stage:          StageExtract,
+		Requires:       []string{"chunk"},
+		Provides:       []string{"candidate"},
+		ReferenceSlots: []contracts.ReferenceSlot{{Name: "roster"}},
+	})
+
+	resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	want := []ReferenceBinding{{LaneID: "events", SlotName: "roster", Source: "./roster.yml", BindingSource: contracts.ReferenceBindingSourceConfig}}
+	if !reflect.DeepEqual(resolved.ArtifactLanes[0].ExtractReferences.Bindings, want) {
+		t.Fatalf("extract references = %#v, want %#v", resolved.ArtifactLanes[0].ExtractReferences.Bindings, want)
+	}
+	if refs := resolved.ChunkReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("chunk references = %#v, want none", refs)
+	}
+	if refs := resolved.ArtifactLanes[0].NormalizeReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("normalize references = %#v, want none", refs)
+	}
+}
+
+func TestResolvePipelineAppliesPipelineReferenceDefaultToNormalizerTarget(t *testing.T) {
+	profile := baselineProfile()
+	profile.References = map[string]string{"normalization_notes": "./normalize.md"}
+	catalog := newProfileCatalogWithOverrides(t, ModuleSpec{
+		Key:            "noop",
+		Stage:          StageNormalize,
+		Requires:       []string{"merged"},
+		Provides:       []string{"normalized"},
+		ReferenceSlots: []contracts.ReferenceSlot{{Name: "normalization_notes"}},
+	})
+
+	resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	want := []ReferenceBinding{{LaneID: "events", SlotName: "normalization_notes", Source: "./normalize.md", BindingSource: contracts.ReferenceBindingSourceConfig}}
+	if !reflect.DeepEqual(resolved.ArtifactLanes[0].NormalizeReferences.Bindings, want) {
+		t.Fatalf("normalize references = %#v, want %#v", resolved.ArtifactLanes[0].NormalizeReferences.Bindings, want)
+	}
+	if refs := resolved.ChunkReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("chunk references = %#v, want none", refs)
+	}
+	if refs := resolved.ArtifactLanes[0].ExtractReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("extract references = %#v, want none", refs)
+	}
+}
+
+func TestResolvePipelineAppliesOnePipelineReferenceDefaultToMultipleTargets(t *testing.T) {
+	profile := baselineProfile()
+	profile.References = map[string]string{"context": "./context.md"}
+	catalog := newProfileCatalogWithOverrides(t,
+		ModuleSpec{Key: "generic", Stage: StageChunk, Requires: []string{"source"}, Provides: []string{"chunk"}, ReferenceSlots: []contracts.ReferenceSlot{{Name: "context"}}},
+		ModuleSpec{Key: "event-extractor", Stage: StageExtract, Requires: []string{"chunk"}, Provides: []string{"candidate"}, ReferenceSlots: []contracts.ReferenceSlot{{Name: "context"}}},
+		ModuleSpec{Key: "noop", Stage: StageNormalize, Requires: []string{"merged"}, Provides: []string{"normalized"}, ReferenceSlots: []contracts.ReferenceSlot{{Name: "context"}}},
+	)
+
+	resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	assertBindingSource(t, resolved.ChunkReferences.Bindings, "context", "./context.md")
+	assertBindingSource(t, resolved.ArtifactLanes[0].ExtractReferences.Bindings, "context", "./context.md")
+	assertBindingSource(t, resolved.ArtifactLanes[0].NormalizeReferences.Bindings, "context", "./context.md")
+}
+
 func TestResolvePipelineAllowsPipelineReferenceDeclaredOnlyByUnselectedLane(t *testing.T) {
 	profile := multiLaneProfile()
 	profile.References = map[string]string{"notes_context": "./notes.md"}
@@ -184,11 +296,39 @@ func TestResolvePipelineAllowsPipelineReferenceDeclaredOnlyByUnselectedLane(t *t
 	if err != nil {
 		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
 	}
-	if refs := resolved.ArtifactLanes[0].References; len(refs) != 0 {
+	if refs := resolved.ArtifactLanes[0].ExtractReferences.Bindings; len(refs) != 0 {
 		t.Fatalf("selected lane references = %#v, want none", refs)
 	}
 }
 
+func TestResolvePipelineAllowsPipelineReferenceDeclaredOnlyByUnselectedNormalizer(t *testing.T) {
+	profile := multiLaneProfile()
+	profile.References = map[string]string{"notes_context": "./notes.md"}
+	lane := profile.Artifacts["notes"]
+	lane.Normalize = Binding("note-normalizer")
+	profile.Artifacts["notes"] = lane
+	catalog := newProfileCatalogWithOverrides(t, ModuleSpec{
+		Key:      "note-normalizer",
+		Stage:    StageNormalize,
+		Requires: []string{"merged"},
+		Provides: []string{"normalized"},
+		ReferenceSlots: []contracts.ReferenceSlot{
+			{Name: "notes_context"},
+		},
+	})
+
+	resolved, err := ResolvePipeline(profile, ResolveOptions{Only: []string{"events"}}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+	if refs := resolved.ArtifactLanes[0].ExtractReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("selected extract references = %#v, want none", refs)
+	}
+	if refs := resolved.ArtifactLanes[0].NormalizeReferences.Bindings; len(refs) != 0 {
+		t.Fatalf("selected normalize references = %#v, want none", refs)
+	}
+}
+
 func TestResolvePipelineRejectsPipelineReferenceNotDeclaredByAnyLane(t *testing.T) {
 	profile := multiLaneProfile()
 	profile.References = map[string]string{"missing": "./missing.md"}
@@ -213,6 +353,106 @@ func TestResolvePipelineRejectsUndeclaredReferenceSlot(t *testing.T) {
 	assertErrorContains(t, err, "events", "missing", "not declared")
 }
 
+func TestResolvePipelineRejectsExtractLocalReferenceDeclaredOnlyByNormalizer(t *testing.T) {
+	profile := baselineProfile()
+	lane := profile.Artifacts["events"]
+	lane.Extract.References = map[string]string{"normalization_notes": "./normalize.md"}
+	profile.Artifacts["events"] = lane
+	catalog := newProfileCatalogWithOverrides(t, ModuleSpec{
+		Key:            "noop",
+		Stage:          StageNormalize,
+		Requires:       []string{"merged"},
+		Provides:       []string{"normalized"},
+		ReferenceSlots: []contracts.ReferenceSlot{{Name: "normalization_notes"}},
+	})
+
+	_, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "baseline", "events", "extract", "event-extractor", "normalization_notes", "not declared")
+}
+
+func TestResolvePipelineRejectsNormalizeLocalReferenceDeclaredOnlyByExtractor(t *testing.T) {
+	profile := baselineProfile()
+	lane := profile.Artifacts["events"]
+	lane.Normalize.References = map[string]string{"roster": "./roster.yml"}
+	profile.Artifacts["events"] = lane
+	catalog := newProfileCatalogWithOverrides(t, ModuleSpec{
+		Key:            "event-extractor",
+		Stage:          StageExtract,
+		Requires:       []string{"chunk"},
+		Provides:       []string{"candidate"},
+		ReferenceSlots: []contracts.ReferenceSlot{{Name: "roster"}},
+	})
+
+	_, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "baseline", "events", "normalize", "noop", "roster", "not declared")
+}
+
+func TestResolvePipelineRequiresBoundChunkReference(t *testing.T) {
+	catalog := newProfileCatalogWithOverrides(t, ModuleSpec{
+		Key:            "generic",
+		Stage:          StageChunk,
+		Requires:       []string{"source"},
+		Provides:       []string{"chunk"},
+		ReferenceSlots: []contracts.ReferenceSlot{{Name: "scene_guide", Required: true}},
+	})
+
+	_, err := ResolvePipeline(baselineProfile(), ResolveOptions{}, catalog)
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "baseline", "chunk", "generic", "required", "scene_guide", "not bound")
+}
+
+func TestResolvePipelineRequiresBoundNormalizeReference(t *testing.T) {
+	catalog := newProfileCatalogWithOverrides(t, ModuleSpec{
+		Key:            "noop",
+		Stage:          StageNormalize,
+		Requires:       []string{"merged"},
+		Provides:       []string{"normalized"},
+		ReferenceSlots: []contracts.ReferenceSlot{{Name: "normalization_notes", Required: true}},
+	})
+
+	_, err := ResolvePipeline(baselineProfile(), ResolveOptions{}, catalog)
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "baseline", "events", "normalize", "noop", "required", "normalization_notes", "not bound")
+}
+
+func TestResolvePipelineLocalReferencesOverridePipelineDefaultsForEligibleTargets(t *testing.T) {
+	profile := baselineProfile()
+	profile.References = map[string]string{
+		"context":             "./shared-context.md",
+		"roster":              "./shared-roster.yml",
+		"normalization_notes": "./shared-normalize.md",
+	}
+	profile.Chunk.References = map[string]string{"context": "./chunk-context.md"}
+	lane := profile.Artifacts["events"]
+	lane.Extract.References = map[string]string{"roster": "./extract-roster.yml"}
+	lane.Normalize.References = map[string]string{"normalization_notes": "./local-normalize.md"}
+	profile.Artifacts["events"] = lane
+	catalog := newProfileCatalogWithOverrides(t,
+		ModuleSpec{Key: "generic", Stage: StageChunk, Requires: []string{"source"}, Provides: []string{"chunk"}, ReferenceSlots: []contracts.ReferenceSlot{{Name: "context"}}},
+		ModuleSpec{Key: "event-extractor", Stage: StageExtract, Requires: []string{"chunk"}, Provides: []string{"candidate"}, ReferenceSlots: []contracts.ReferenceSlot{{Name: "roster"}}},
+		ModuleSpec{Key: "noop", Stage: StageNormalize, Requires: []string{"merged"}, Provides: []string{"normalized"}, ReferenceSlots: []contracts.ReferenceSlot{{Name: "normalization_notes"}}},
+	)
+
+	resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	assertBindingSource(t, resolved.ChunkReferences.Bindings, "context", "./chunk-context.md")
+	assertBindingSource(t, resolved.ArtifactLanes[0].ExtractReferences.Bindings, "roster", "./extract-roster.yml")
+	assertBindingSource(t, resolved.ArtifactLanes[0].NormalizeReferences.Bindings, "normalization_notes", "./local-normalize.md")
+}
+
 func TestResolvePipelineRequiresBoundReferenceSlotsForSelectedLanes(t *testing.T) {
 	catalog := newProfileCatalogWithOverride(t, ModuleSpec{
 		Key:      "event-extractor",
@@ -284,7 +524,7 @@ func TestResolvePipelineUsesReferenceSlotsFromSpecWithoutConstructingExtractor(t
 	if err != nil {
 		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
 	}
-	if got := resolved.ArtifactLanes[0].References[0].Source; got != "./roster.yml" {
+	if got := resolved.ArtifactLanes[0].ExtractReferences.Bindings[0].Source; got != "./roster.yml" {
 		t.Fatalf("reference source = %q, want ./roster.yml", got)
 	}
 }
@@ -649,6 +889,21 @@ func assertErrorContains(t *testing.T, err error, values ...string) {
 	}
 }
 
+func assertBindingSource(t *testing.T, bindings []ReferenceBinding, slotName string, source string) {
+	t.Helper()
+
+	for _, binding := range bindings {
+		if binding.SlotName != slotName {
+			continue
+		}
+		if binding.Source != source {
+			t.Fatalf("binding %q source = %q, want %q in %#v", slotName, binding.Source, source, bindings)
+		}
+		return
+	}
+	t.Fatalf("binding %q not found in %#v", slotName, bindings)
+}
+
 func newProfileCatalog(t *testing.T) ModuleCatalog {
 	t.Helper()
 
@@ -660,19 +915,29 @@ func newProfileCatalog(t *testing.T) ModuleCatalog {
 func newProfileCatalogWithOverride(t *testing.T, override ModuleSpec) ModuleCatalog {
 	t.Helper()
 
+	return newProfileCatalogWithOverrides(t, override)
+}
+
+func newProfileCatalogWithOverrides(t *testing.T, overrides ...ModuleSpec) ModuleCatalog {
+	t.Helper()
+
 	specs := defaultProfileSpecs()
-	for index, spec := range specs {
-		if spec.Stage == override.Stage && spec.Key == override.Key {
-			specs[index] = override
-			catalog := emptyProfileCatalog()
-			registerProfileSpecs(t, catalog, specs...)
-			return catalog
+	for _, override := range overrides {
+		replaced := false
+		for index, spec := range specs {
+			if spec.Stage == override.Stage && spec.Key == override.Key {
+				specs[index] = override
+				replaced = true
+				break
+			}
+		}
+		if !replaced {
+			specs = append(specs, override)
 		}
 	}
 
 	catalog := emptyProfileCatalog()
 	registerProfileSpecs(t, catalog, specs...)
-	registerProfileSpecs(t, catalog, override)
 	return catalog
 }
 

internal/framework/pipeline/references.go

@@ -29,40 +29,52 @@ type ReferenceMaterializationOptions struct {
 
 func MaterializeReferences(resolved ResolvedPipeline, catalog ModuleCatalog, options ReferenceMaterializationOptions) (ResolvedPipeline, []contracts.Warning, error) {
 	out := resolved
+	out.ChunkReferences = CloneReferenceTarget(resolved.ChunkReferences)
+	chunkReferenceSet, chunkWarnings, err := materializeReferenceTarget(resolved.ID, resolved.ChunkReferences, catalog, options)
+	if err != nil {
+		return ResolvedPipeline{}, nil, err
+	}
+	out.ChunkReferences.ReferenceSet = chunkReferenceSet
+	warnings := append([]contracts.Warning(nil), chunkWarnings...)
 	if len(resolved.ArtifactLanes) == 0 {
-		return out, nil, nil
+		return out, warnings, nil
 	}
 
-	warnings := []contracts.Warning(nil)
 	out.ArtifactLanes = make([]ResolvedArtifactLane, len(resolved.ArtifactLanes))
 	for i, lane := range resolved.ArtifactLanes {
 		materializedLane := lane
-		referenceSet, laneWarnings, err := materializeLaneReferences(resolved.ID, lane, catalog, options)
+		materializedLane.ExtractReferences = CloneReferenceTarget(lane.ExtractReferences)
+		materializedLane.NormalizeReferences = CloneReferenceTarget(lane.NormalizeReferences)
+		extractReferenceSet, laneWarnings, err := materializeReferenceTarget(resolved.ID, lane.ExtractReferences, catalog, options)
 		if err != nil {
 			return ResolvedPipeline{}, nil, err
 		}
-		materializedLane.ReferenceSet = referenceSet
-		out.ArtifactLanes[i] = materializedLane
+		materializedLane.ExtractReferences.ReferenceSet = extractReferenceSet
 		warnings = append(warnings, laneWarnings...)
+
+		normalizeReferenceSet, laneWarnings, err := materializeReferenceTarget(resolved.ID, lane.NormalizeReferences, catalog, options)
+		if err != nil {
+			return ResolvedPipeline{}, nil, err
+		}
+		materializedLane.NormalizeReferences.ReferenceSet = normalizeReferenceSet
+		warnings = append(warnings, laneWarnings...)
+		out.ArtifactLanes[i] = materializedLane
 	}
 	return out, warnings, nil
 }
 
-func materializeLaneReferences(
+func materializeReferenceTarget(
 	pipelineID string,
-	lane ResolvedArtifactLane,
+	target ResolvedReferenceTarget,
 	catalog ModuleCatalog,
 	options ReferenceMaterializationOptions,
 ) (contracts.ReferenceSet, []contracts.Warning, error) {
-	if len(lane.References) == 0 {
+	if len(target.Bindings) == 0 {
 		return contracts.ReferenceSet{}, nil, nil
 	}
-	if catalog.Extractors == nil {
-		return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q extract module %q: module %q is not registered", pipelineID, lane.ID, lane.Extract.Module, lane.Extract.Module)
-	}
-	spec, ok := catalog.Extractors.Spec(lane.Extract.Module)
-	if !ok {
-		return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q extract module %q: module %q is not registered", pipelineID, lane.ID, lane.Extract.Module, lane.Extract.Module)
+	spec, err := referenceTargetSpec(target, catalog)
+	if err != nil {
+		return contracts.ReferenceSet{}, nil, fmt.Errorf("%s: %w", referenceTargetContext(pipelineID, target), err)
 	}
 
 	slotByName := make(map[string]contracts.ReferenceSlot, len(spec.ReferenceSlots))
@@ -70,38 +82,38 @@ func materializeLaneReferences(
 		slotByName[slot.Name] = slot
 	}
 
-	set := contracts.ReferenceSet{Slots: make(map[string]contracts.ResolvedReferenceSlot, len(lane.References))}
+	set := contracts.ReferenceSet{Slots: make(map[string]contracts.ResolvedReferenceSlot, len(target.Bindings))}
 	var warnings []contracts.Warning
-	for _, binding := range lane.References {
+	for _, binding := range target.Bindings {
 		slotName := strings.TrimSpace(binding.SlotName)
 		slot, ok := slotByName[slotName]
 		if !ok {
-			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q is not declared by extractor %q", pipelineID, lane.ID, slotName, lane.Extract.Module)
+			return contracts.ReferenceSet{}, nil, fmt.Errorf("%s reference slot %q is not declared by %s module %q", referenceTargetContext(pipelineID, target), slotName, target.Stage, target.Module)
 		}
 
 		path, err := referencePath(binding, options)
 		if err != nil {
-			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q: %w", pipelineID, lane.ID, slotName, binding.Source, err)
+			return contracts.ReferenceSet{}, nil, fmt.Errorf("%s reference slot %q path %q: %w", referenceTargetContext(pipelineID, target), slotName, binding.Source, err)
 		}
 		content, err := os.ReadFile(path)
 		if err != nil {
-			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q read %q: %w", pipelineID, lane.ID, slotName, path, err)
+			return contracts.ReferenceSet{}, nil, fmt.Errorf("%s reference slot %q read %q: %w", referenceTargetContext(pipelineID, target), slotName, path, err)
 		}
 		if !utf8.Valid(content) {
-			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q must be UTF-8 text", pipelineID, lane.ID, slotName, path)
+			return contracts.ReferenceSet{}, nil, fmt.Errorf("%s reference slot %q path %q must be UTF-8 text", referenceTargetContext(pipelineID, target), slotName, path)
 		}
 		mediaType := referenceMediaTypeForPath(path)
 		if !referenceMediaTypeAccepted(mediaType, slot.AcceptedMediaTypes) {
-			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q media type %q is not accepted", pipelineID, lane.ID, slotName, path, mediaType)
+			return contracts.ReferenceSet{}, nil, fmt.Errorf("%s reference slot %q path %q media type %q is not accepted", referenceTargetContext(pipelineID, target), slotName, path, mediaType)
 		}
 		if slot.MaxBytes > 0 && int64(len(content)) > slot.MaxBytes {
-			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q is %d bytes, limit %d", pipelineID, lane.ID, slotName, path, len(content), slot.MaxBytes)
+			return contracts.ReferenceSet{}, nil, fmt.Errorf("%s reference slot %q path %q is %d bytes, limit %d", referenceTargetContext(pipelineID, target), slotName, path, len(content), slot.MaxBytes)
 		}
 		if len(content) == 0 {
 			warnings = append(warnings, contracts.Warning{
-				Scope:      fmt.Sprintf("pipeline.%s.lane.%s.reference.%s", pipelineID, lane.ID, slotName),
+				Scope:      referenceWarningScope(pipelineID, target, slotName),
 				ReasonCode: "empty_reference",
-				Message:    fmt.Sprintf("reference slot %q for lane %q is bound to an empty file", slotName, lane.ID),
+				Message:    fmt.Sprintf("reference slot %q for %s is bound to an empty file", slotName, referenceTargetLabel(target)),
 			})
 		}
 
@@ -122,6 +134,40 @@ func materializeLaneReferences(
 	return set, warnings, nil
 }
 
+func referenceTargetSpec(target ResolvedReferenceTarget, catalog ModuleCatalog) (ModuleSpec, error) {
+	switch target.Stage {
+	case StageChunk:
+		return registrySpec(catalog.Chunkers, target.Module)
+	case StageExtract:
+		return registrySpec(catalog.Extractors, target.Module)
+	case StageNormalize:
+		return registrySpec(catalog.Normalizers, target.Module)
+	default:
+		return ModuleSpec{}, fmt.Errorf("reference target stage %q is not supported", target.Stage)
+	}
+}
+
+func referenceTargetContext(pipelineID string, target ResolvedReferenceTarget) string {
+	if target.LaneID != "" {
+		return fmt.Sprintf("pipeline %q lane %q %s module %q", pipelineID, target.LaneID, target.Stage, target.Module)
+	}
+	return fmt.Sprintf("pipeline %q %s module %q", pipelineID, target.Stage, target.Module)
+}
+
+func referenceTargetLabel(target ResolvedReferenceTarget) string {
+	if target.LaneID != "" {
+		return fmt.Sprintf("lane %q %s target", target.LaneID, target.Stage)
+	}
+	return fmt.Sprintf("%s target", target.Stage)
+}
+
+func referenceWarningScope(pipelineID string, target ResolvedReferenceTarget, slotName string) string {
+	if target.LaneID != "" {
+		return fmt.Sprintf("pipeline.%s.lane.%s.%s.reference.%s", pipelineID, target.LaneID, target.Stage, slotName)
+	}
+	return fmt.Sprintf("pipeline.%s.%s.reference.%s", pipelineID, target.Stage, slotName)
+}
+
 func referenceMediaTypeForPath(path string) string {
 	extension := strings.ToLower(filepath.Ext(path))
 	mediaType := mime.TypeByExtension(extension)
@@ -230,31 +276,47 @@ func CloneReferenceSet(in contracts.ReferenceSet) contracts.ReferenceSet {
 	return out
 }
 
+func CloneReferenceTarget(in ResolvedReferenceTarget) ResolvedReferenceTarget {
+	out := in
+	out.Bindings = append([]ReferenceBinding(nil), in.Bindings...)
+	out.ReferenceSet = CloneReferenceSet(in.ReferenceSet)
+	return out
+}
+
 func ReferenceProvenance(resolved ResolvedPipeline) []artifacts.ReferenceProvenance {
 	provenance := []artifacts.ReferenceProvenance{}
+	provenance = append(provenance, referenceTargetProvenance(resolved.ChunkReferences)...)
 	for _, lane := range resolved.ArtifactLanes {
-		if len(lane.ReferenceSet.Slots) == 0 {
-			continue
-		}
-		slotNames := make([]string, 0, len(lane.ReferenceSet.Slots))
-		for slotName := range lane.ReferenceSet.Slots {
-			slotNames = append(slotNames, slotName)
-		}
-		sort.Strings(slotNames)
-		for _, slotName := range slotNames {
-			slot := lane.ReferenceSet.Slots[slotName]
-			for _, item := range slot.Items {
-				provenance = append(provenance, artifacts.ReferenceProvenance{
-					LaneID:        lane.ID,
-					SlotName:      item.SlotName,
-					OriginType:    item.Origin.Type,
-					OriginURI:     item.Origin.URI,
-					Digest:        item.Digest,
-					MediaType:     item.MediaType,
-					SizeBytes:     item.SizeBytes,
-					BindingSource: item.BindingSource,
-				})
-			}
+		provenance = append(provenance, referenceTargetProvenance(lane.ExtractReferences)...)
+		provenance = append(provenance, referenceTargetProvenance(lane.NormalizeReferences)...)
+	}
+	return provenance
+}
+
+func referenceTargetProvenance(target ResolvedReferenceTarget) []artifacts.ReferenceProvenance {
+	if len(target.ReferenceSet.Slots) == 0 {
+		return nil
+	}
+	provenance := []artifacts.ReferenceProvenance{}
+	slotNames := make([]string, 0, len(target.ReferenceSet.Slots))
+	for slotName := range target.ReferenceSet.Slots {
+		slotNames = append(slotNames, slotName)
+	}
+	sort.Strings(slotNames)
+	for _, slotName := range slotNames {
+		slot := target.ReferenceSet.Slots[slotName]
+		for _, item := range slot.Items {
+			provenance = append(provenance, artifacts.ReferenceProvenance{
+				Stage:         string(target.Stage),
+				LaneID:        target.LaneID,
+				SlotName:      item.SlotName,
+				OriginType:    item.Origin.Type,
+				OriginURI:     item.Origin.URI,
+				Digest:        item.Digest,
+				MediaType:     item.MediaType,
+				SizeBytes:     item.SizeBytes,
+				BindingSource: item.BindingSource,
+			})
 		}
 	}
 	return provenance

internal/framework/pipeline/references_test.go

@@ -4,6 +4,8 @@ import (
 	"encoding/json"
 	"os"
 	"path/filepath"
+	"reflect"
+	"sort"
 	"strings"
 	"testing"
 
@@ -54,12 +56,12 @@ func TestMaterializeReferencesResolvesPathsAndDigestsContent(t *testing.T) {
 		t.Fatalf("MaterializeReferences(second) error = %v, want nil", err)
 	}
 
-	referenceSet := first.ArtifactLanes[0].ReferenceSet
+	referenceSet := first.ArtifactLanes[0].ExtractReferences.ReferenceSet
 	roster := referenceSet.Slots["roster"].Items[0]
 	if string(roster.Content) != "config text" {
 		t.Fatalf("roster content = %q, want config text", roster.Content)
 	}
-	if roster.Digest != referenceDigest([]byte("config text")) || roster.Digest != second.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0].Digest {
+	if roster.Digest != referenceDigest([]byte("config text")) || roster.Digest != second.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0].Digest {
 		t.Fatalf("roster digest = %q, want stable digest", roster.Digest)
 	}
 	if roster.BindingSource != contracts.ReferenceBindingSourceConfig {
@@ -87,10 +89,10 @@ func TestMaterializeReferencesResolvesPathsAndDigestsContent(t *testing.T) {
 	if len(provenance) != 2 {
 		t.Fatalf("ReferenceProvenance() = %#v, want two entries", provenance)
 	}
-	if provenance[0].LaneID != "events" || provenance[0].SlotName != "glossary" || provenance[0].Digest != glossary.Digest {
+	if provenance[0].Stage != string(StageExtract) || provenance[0].LaneID != "events" || provenance[0].SlotName != "glossary" || provenance[0].Digest != glossary.Digest {
 		t.Fatalf("ReferenceProvenance()[0] = %#v, want sorted glossary provenance", provenance[0])
 	}
-	if provenance[1].LaneID != "events" || provenance[1].SlotName != "roster" || provenance[1].Digest != roster.Digest {
+	if provenance[1].Stage != string(StageExtract) || provenance[1].LaneID != "events" || provenance[1].SlotName != "roster" || provenance[1].Digest != roster.Digest {
 		t.Fatalf("ReferenceProvenance()[1] = %#v, want roster provenance", provenance[1])
 	}
 
@@ -103,6 +105,66 @@ func TestMaterializeReferencesResolvesPathsAndDigestsContent(t *testing.T) {
 	}
 }
 
+func TestMaterializeReferencesStoresSetsAndProvenanceForAllTargets(t *testing.T) {
+	configDir := t.TempDir()
+	writeReferenceFile(t, filepath.Join(configDir, "chunk.txt"), []byte("chunk text"))
+	writeReferenceFile(t, filepath.Join(configDir, "extract.txt"), []byte("extract text"))
+	writeReferenceFile(t, filepath.Join(configDir, "normalize.txt"), []byte("normalize text"))
+
+	profile := baselineProfile()
+	profile.References = map[string]string{
+		"scene_guide":         "chunk.txt",
+		"roster":              "extract.txt",
+		"normalization_notes": "normalize.txt",
+	}
+	catalog := referenceCatalogForTargets(t,
+		[]contracts.ReferenceSlot{{Name: "scene_guide"}},
+		[]contracts.ReferenceSlot{{Name: "roster"}},
+		[]contracts.ReferenceSlot{{Name: "normalization_notes"}},
+	)
+	resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	materialized, warnings, err := MaterializeReferences(resolved, catalog, ReferenceMaterializationOptions{
+		ConfigPath: filepath.Join(configDir, "config.yml"),
+	})
+	if err != nil {
+		t.Fatalf("MaterializeReferences() error = %v, want nil", err)
+	}
+	if len(warnings) != 0 {
+		t.Fatalf("warnings = %#v, want none", warnings)
+	}
+
+	chunkItem := materialized.ChunkReferences.ReferenceSet.Slots["scene_guide"].Items[0]
+	if string(chunkItem.Content) != "chunk text" {
+		t.Fatalf("chunk content = %q, want chunk text", chunkItem.Content)
+	}
+	extractItem := materialized.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0]
+	if string(extractItem.Content) != "extract text" {
+		t.Fatalf("extract content = %q, want extract text", extractItem.Content)
+	}
+	normalizeItem := materialized.ArtifactLanes[0].NormalizeReferences.ReferenceSet.Slots["normalization_notes"].Items[0]
+	if string(normalizeItem.Content) != "normalize text" {
+		t.Fatalf("normalize content = %q, want normalize text", normalizeItem.Content)
+	}
+
+	provenance := ReferenceProvenance(materialized)
+	if len(provenance) != 3 {
+		t.Fatalf("ReferenceProvenance() = %#v, want three entries", provenance)
+	}
+	if provenance[0].Stage != string(StageChunk) || provenance[0].LaneID != "" || provenance[0].SlotName != "scene_guide" || provenance[0].Digest != chunkItem.Digest {
+		t.Fatalf("ReferenceProvenance()[0] = %#v, want chunk scene guide provenance", provenance[0])
+	}
+	if provenance[1].Stage != string(StageExtract) || provenance[1].LaneID != "events" || provenance[1].SlotName != "roster" || provenance[1].Digest != extractItem.Digest {
+		t.Fatalf("ReferenceProvenance()[1] = %#v, want extract roster provenance", provenance[1])
+	}
+	if provenance[2].Stage != string(StageNormalize) || provenance[2].LaneID != "events" || provenance[2].SlotName != "normalization_notes" || provenance[2].Digest != normalizeItem.Digest {
+		t.Fatalf("ReferenceProvenance()[2] = %#v, want normalize notes provenance", provenance[2])
+	}
+}
+
 func TestMaterializeReferencesRejectsNonUTF8Content(t *testing.T) {
 	configDir := t.TempDir()
 	path := filepath.Join(configDir, "bad.txt")
@@ -117,6 +179,20 @@ func TestMaterializeReferencesRejectsNonUTF8Content(t *testing.T) {
 	}
 }
 
+func TestMaterializeReferencesRejectsNonUTF8ContentForChunkTarget(t *testing.T) {
+	configDir := t.TempDir()
+	path := filepath.Join(configDir, "bad.txt")
+	writeReferenceFile(t, path, []byte{0xff, 0xfe})
+
+	resolved := resolvedPipelineWithTargetReference(t, StageChunk, "", "scene_guide", "bad.txt", contracts.ReferenceBindingSourceConfig, contracts.ReferenceSlot{Name: "scene_guide"})
+	_, _, err := MaterializeReferences(resolved, referenceCatalogForTargets(t, []contracts.ReferenceSlot{{Name: "scene_guide"}}, nil, nil), ReferenceMaterializationOptions{
+		ConfigPath: filepath.Join(configDir, "config.yml"),
+	})
+	if err == nil || !strings.Contains(err.Error(), "chunk") || !strings.Contains(err.Error(), "UTF-8") || !strings.Contains(err.Error(), "scene_guide") || !strings.Contains(err.Error(), path) {
+		t.Fatalf("error = %v, want chunk UTF-8 path error", err)
+	}
+}
+
 func TestMaterializeReferencesAllowsAnyMediaTypeWhenSlotDoesNotRestrictIt(t *testing.T) {
 	configDir := t.TempDir()
 	path := filepath.Join(configDir, "roster.reference")
@@ -129,7 +205,7 @@ func TestMaterializeReferencesAllowsAnyMediaTypeWhenSlotDoesNotRestrictIt(t *tes
 	if err != nil {
 		t.Fatalf("MaterializeReferences() error = %v, want nil", err)
 	}
-	item := materialized.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0]
+	item := materialized.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0]
 	if item.MediaType != unknownMediaType {
 		t.Fatalf("MediaType = %q, want %q", item.MediaType, unknownMediaType)
 	}
@@ -148,7 +224,7 @@ func TestMaterializeReferencesAcceptsDeclaredMarkdownMediaType(t *testing.T) {
 	if err != nil {
 		t.Fatalf("MaterializeReferences() error = %v, want nil", err)
 	}
-	item := materialized.ArtifactLanes[0].ReferenceSet.Slots["glossary"].Items[0]
+	item := materialized.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["glossary"].Items[0]
 	if item.MediaType != "text/markdown" {
 		t.Fatalf("MediaType = %q, want text/markdown", item.MediaType)
 	}
@@ -167,7 +243,7 @@ func TestMaterializeReferencesAcceptsDeclaredJSONMediaType(t *testing.T) {
 	if err != nil {
 		t.Fatalf("MaterializeReferences() error = %v, want nil", err)
 	}
-	item := materialized.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0]
+	item := materialized.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0]
 	if item.MediaType != "application/json" {
 		t.Fatalf("MediaType = %q, want application/json", item.MediaType)
 	}
@@ -201,12 +277,27 @@ func TestMaterializeReferencesMatchesAcceptedMediaTypesIgnoringParameters(t *tes
 	if err != nil {
 		t.Fatalf("MaterializeReferences() error = %v, want nil", err)
 	}
-	item := materialized.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0]
+	item := materialized.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0]
 	if item.MediaType != referenceMediaType {
 		t.Fatalf("MediaType = %q, want %q", item.MediaType, referenceMediaType)
 	}
 }
 
+func TestMaterializeReferencesRejectsUnacceptedMediaTypeForNormalizeTarget(t *testing.T) {
+	configDir := t.TempDir()
+	path := filepath.Join(configDir, "notes.json")
+	writeReferenceFile(t, path, []byte(`{"notes":true}`))
+
+	slot := contracts.ReferenceSlot{Name: "normalization_notes", AcceptedMediaTypes: []string{"text/markdown"}}
+	resolved := resolvedPipelineWithTargetReference(t, StageNormalize, "events", "normalization_notes", "notes.json", contracts.ReferenceBindingSourceConfig, slot)
+	_, _, err := MaterializeReferences(resolved, referenceCatalogForTargets(t, nil, nil, []contracts.ReferenceSlot{slot}), ReferenceMaterializationOptions{
+		ConfigPath: filepath.Join(configDir, "config.yml"),
+	})
+	if err == nil || !strings.Contains(err.Error(), "normalize") || !strings.Contains(err.Error(), "media type") || !strings.Contains(err.Error(), "application/json") || !strings.Contains(err.Error(), "normalization_notes") {
+		t.Fatalf("error = %v, want normalize media type rejection", err)
+	}
+}
+
 func TestMaterializeReferencesWarnsForEmptyFiles(t *testing.T) {
 	configDir := t.TempDir()
 	path := filepath.Join(configDir, "empty.txt")
@@ -222,12 +313,51 @@ func TestMaterializeReferencesWarnsForEmptyFiles(t *testing.T) {
 	if len(warnings) != 1 || warnings[0].ReasonCode != "empty_reference" {
 		t.Fatalf("warnings = %#v, want empty reference warning", warnings)
 	}
-	item := materialized.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0]
+	item := materialized.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0]
 	if item.SizeBytes != 0 || item.Digest != referenceDigest(nil) {
 		t.Fatalf("empty item = %#v, want zero size and empty digest", item)
 	}
 }
 
+func TestMaterializeReferencesWarningScopesIncludeTargetContext(t *testing.T) {
+	configDir := t.TempDir()
+	writeReferenceFile(t, filepath.Join(configDir, "chunk.txt"), nil)
+	writeReferenceFile(t, filepath.Join(configDir, "extract.txt"), nil)
+	writeReferenceFile(t, filepath.Join(configDir, "normalize.txt"), nil)
+
+	profile := baselineProfile()
+	profile.References = map[string]string{
+		"scene_guide":         "chunk.txt",
+		"roster":              "extract.txt",
+		"normalization_notes": "normalize.txt",
+	}
+	catalog := referenceCatalogForTargets(t,
+		[]contracts.ReferenceSlot{{Name: "scene_guide"}},
+		[]contracts.ReferenceSlot{{Name: "roster"}},
+		[]contracts.ReferenceSlot{{Name: "normalization_notes"}},
+	)
+	resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	_, warnings, err := MaterializeReferences(resolved, catalog, ReferenceMaterializationOptions{
+		ConfigPath: filepath.Join(configDir, "config.yml"),
+	})
+	if err != nil {
+		t.Fatalf("MaterializeReferences() error = %v, want nil", err)
+	}
+	got := warningScopes(warnings)
+	want := []string{
+		"pipeline.baseline.chunk.reference.scene_guide",
+		"pipeline.baseline.lane.events.extract.reference.roster",
+		"pipeline.baseline.lane.events.normalize.reference.normalization_notes",
+	}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("warning scopes = %#v, want %#v", got, want)
+	}
+}
+
 func TestMaterializeReferencesEnforcesMaxBytes(t *testing.T) {
 	configDir := t.TempDir()
 	path := filepath.Join(configDir, "large.txt")
@@ -244,31 +374,99 @@ func TestMaterializeReferencesEnforcesMaxBytes(t *testing.T) {
 }
 
 func resolvedPipelineWithReference(t *testing.T, slotName, source, bindingSource string, slot contracts.ReferenceSlot) ResolvedPipeline {
+	t.Helper()
+	return resolvedPipelineWithTargetReference(t, StageExtract, "events", slotName, source, bindingSource, slot)
+}
+
+func resolvedPipelineWithTargetReference(t *testing.T, stage ModuleStage, laneID string, slotName, source, bindingSource string, slot contracts.ReferenceSlot) ResolvedPipeline {
 	t.Helper()
 	profile := baselineProfile()
-	lane := profile.Artifacts["events"]
-	lane.References = map[string]string{slotName: source}
-	profile.Artifacts["events"] = lane
-	catalog := referenceCatalog(t, []contracts.ReferenceSlot{slot})
+	switch stage {
+	case StageChunk:
+		profile.Chunk.References = map[string]string{slotName: source}
+	case StageExtract:
+		lane := profile.Artifacts[laneID]
+		lane.References = map[string]string{slotName: source}
+		profile.Artifacts[laneID] = lane
+	case StageNormalize:
+		lane := profile.Artifacts[laneID]
+		lane.Normalize.References = map[string]string{slotName: source}
+		profile.Artifacts[laneID] = lane
+	default:
+		t.Fatalf("unsupported reference target stage %q", stage)
+	}
+	catalog := referenceCatalogForStage(t, stage, []contracts.ReferenceSlot{slot})
 	resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
 	if err != nil {
 		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
 	}
 	if bindingSource != contracts.ReferenceBindingSourceConfig {
-		resolved.ArtifactLanes[0].References[0].BindingSource = bindingSource
+		switch stage {
+		case StageChunk:
+			resolved.ChunkReferences.Bindings[0].BindingSource = bindingSource
+		case StageExtract:
+			resolved.ArtifactLanes[0].ExtractReferences.Bindings[0].BindingSource = bindingSource
+		case StageNormalize:
+			resolved.ArtifactLanes[0].NormalizeReferences.Bindings[0].BindingSource = bindingSource
+		}
 	}
 	return resolved
 }
 
 func referenceCatalog(t *testing.T, slots []contracts.ReferenceSlot) ModuleCatalog {
 	t.Helper()
-	return newProfileCatalogWithOverride(t, ModuleSpec{
-		Key:            "event-extractor",
-		Stage:          StageExtract,
-		Requires:       []string{"chunk"},
-		Provides:       []string{"candidate"},
-		ReferenceSlots: slots,
-	})
+	return referenceCatalogForStage(t, StageExtract, slots)
+}
+
+func referenceCatalogForStage(t *testing.T, stage ModuleStage, slots []contracts.ReferenceSlot) ModuleCatalog {
+	t.Helper()
+	switch stage {
+	case StageChunk:
+		return referenceCatalogForTargets(t, slots, nil, nil)
+	case StageExtract:
+		return referenceCatalogForTargets(t, nil, slots, nil)
+	case StageNormalize:
+		return referenceCatalogForTargets(t, nil, nil, slots)
+	default:
+		t.Fatalf("unsupported reference target stage %q", stage)
+		return ModuleCatalog{}
+	}
+}
+
+func referenceCatalogForTargets(t *testing.T, chunkSlots, extractSlots, normalizeSlots []contracts.ReferenceSlot) ModuleCatalog {
+	t.Helper()
+	return newProfileCatalogWithOverrides(t,
+		ModuleSpec{
+			Key:            "generic",
+			Stage:          StageChunk,
+			Requires:       []string{"source"},
+			Provides:       []string{"chunk"},
+			ReferenceSlots: chunkSlots,
+		},
+		ModuleSpec{
+			Key:            "event-extractor",
+			Stage:          StageExtract,
+			Requires:       []string{"chunk"},
+			Provides:       []string{"candidate"},
+			ReferenceSlots: extractSlots,
+		},
+		ModuleSpec{
+			Key:            "noop",
+			Stage:          StageNormalize,
+			Requires:       []string{"merged"},
+			Provides:       []string{"normalized"},
+			ReferenceSlots: normalizeSlots,
+		},
+	)
+}
+
+func warningScopes(warnings []contracts.Warning) []string {
+	scopes := make([]string, 0, len(warnings))
+	for _, warning := range warnings {
+		scopes = append(scopes, warning.Scope)
+	}
+	sort.Strings(scopes)
+	return scopes
 }
 
 func writeReferenceFile(t *testing.T, path string, content []byte) {

internal/framework/pipeline/registry_integration_test.go

@@ -118,6 +118,10 @@ func (chunker integrationChunker) Key() string {
 	return "chunk"
 }
 
+func (chunker integrationChunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (chunker integrationChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	return contracts.ChunkResult{
 		Chunks: []contracts.SourceChunk{
@@ -186,6 +190,10 @@ func (normalizer integrationNormalizer) Key() string {
 	return "normalize"
 }
 
+func (normalizer integrationNormalizer) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (normalizer integrationNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
 	return contracts.NormalizeResult{Candidates: req.Candidates}, nil
 }

internal/framework/pipeline/runner.go

@@ -95,6 +95,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
 	attachModuleManifestMetadata(&output, "chunker", chunker)
 	chunkResult, err := chunker.Chunk(ctx, contracts.ChunkRequest{
 		Source:     doc,
+		References: CloneReferenceSet(input.Pipeline.ChunkReferences.ReferenceSet),
 		LLMClient:  input.LLMClient,
 		LLMProfile: input.Pipeline.Chunk.LLMProfile,
 		Options:    cloneOptions(input.Pipeline.Chunk.Options),
@@ -186,7 +187,7 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
 		result, err := extractor.Extract(ctx, contracts.ExtractionRequest{
 			Source:     doc,
 			Chunk:      &chunk,
-			References: CloneReferenceSet(lane.ReferenceSet),
+			References: CloneReferenceSet(lane.ExtractReferences.ReferenceSet),
 			LLMClient:  input.LLMClient,
 			LLMProfile: lane.Extract.LLMProfile,
 			Options:    cloneOptions(lane.Extract.Options),
@@ -224,6 +225,8 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
 		Source:     doc,
 		LaneID:     lane.ID,
 		Candidates: mergeResult.Candidates,
+		References: CloneReferenceSet(lane.NormalizeReferences.ReferenceSet),
+		LLMClient:  input.LLMClient,
 		LLMProfile: lane.Normalize.LLMProfile,
 		Options:    cloneOptions(lane.Normalize.Options),
 		Metadata:   input.Metadata,

internal/framework/pipeline/runner_test.go

@@ -464,6 +464,10 @@ func TestRunExecutesChunksAndPassesChunkAndLLMClient(t *testing.T) {
 	if len(extractor.seenLLMClients) != 2 || extractor.seenLLMClients[0] == nil || extractor.seenLLMClients[1] == nil {
 		t.Fatalf("seen LLM clients = %#v, want client for each chunk", extractor.seenLLMClients)
 	}
+	normalizer := modules.normalizers["normalize"]
+	if len(normalizer.requests) != 1 || normalizer.requests[0].LLMClient == nil {
+		t.Fatalf("normalizer LLM client = %#v, want client on normalize request", normalizer.requests)
+	}
 	if extractor.seenMetadata[0]["request"] != "test" {
 		t.Fatalf("seen metadata = %#v, want request metadata", extractor.seenMetadata)
 	}
@@ -562,24 +566,7 @@ func TestRunPassesModuleBindingConfigToStageRequests(t *testing.T) {
 func TestRunPassesLaneReferencesToExtractorRequests(t *testing.T) {
 	modules := defaultRunnerModules()
 	pipeline := resolvedPipeline()
-	pipeline.ArtifactLanes[0].ReferenceSet = contracts.ReferenceSet{
-		Slots: map[string]contracts.ResolvedReferenceSlot{
-			"roster": {
-				Slot: contracts.ReferenceSlot{Name: "roster"},
-				Items: []contracts.ReferenceItem{
-					{
-						SlotName:      "roster",
-						MediaType:     "text/plain; charset=utf-8",
-						Content:       []byte("reference text"),
-						Digest:        "sha256:test",
-						Origin:        contracts.ReferenceOrigin{Type: "file", URI: "file:///tmp/reference.txt"},
-						SizeBytes:     int64(len("reference text")),
-						BindingSource: contracts.ReferenceBindingSourceConfig,
-					},
-				},
-			},
-		},
-	}
+	pipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet = testReferenceSet("roster", "reference text")
 
 	_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: pipeline})
 	if err != nil {
@@ -592,11 +579,60 @@ func TestRunPassesLaneReferencesToExtractorRequests(t *testing.T) {
 		t.Fatalf("reference content = %q, want reference text", item.Content)
 	}
 	item.Content[0] = 'R'
-	if got := string(pipeline.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0].Content); got != "reference text" {
+	if got := string(pipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["roster"].Items[0].Content); got != "reference text" {
 		t.Fatalf("runner mutated reference set content = %q", got)
 	}
 }
 
+func TestRunPassesChunkReferencesToChunkerRequest(t *testing.T) {
+	modules := defaultRunnerModules()
+	pipeline := resolvedPipeline()
+	pipeline.ChunkReferences.ReferenceSet = testReferenceSet("scene_guide", "chunk reference text")
+
+	_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: pipeline})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+
+	req := modules.chunker.requests[0]
+	item := req.References.Slots["scene_guide"].Items[0]
+	if string(item.Content) != "chunk reference text" {
+		t.Fatalf("chunk reference content = %q, want chunk reference text", item.Content)
+	}
+	item.Content[0] = 'C'
+	if got := string(pipeline.ChunkReferences.ReferenceSet.Slots["scene_guide"].Items[0].Content); got != "chunk reference text" {
+		t.Fatalf("runner mutated chunk reference set content = %q", got)
+	}
+}
+
+func TestRunPassesNormalizeReferencesToNormalizerRequest(t *testing.T) {
+	modules := defaultRunnerModules()
+	pipeline := resolvedPipeline()
+	pipeline.ArtifactLanes[0].NormalizeReferences.ReferenceSet = testReferenceSet("normalization_notes", "normalize reference text")
+
+	_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: pipeline})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+
+	req := modules.normalizers["normalize"].requests[0]
+	item := req.References.Slots["normalization_notes"].Items[0]
+	if string(item.Content) != "normalize reference text" {
+		t.Fatalf("normalize reference content = %q, want normalize reference text", item.Content)
+	}
+	item.Content[0] = 'N'
+	if got := string(pipeline.ArtifactLanes[0].NormalizeReferences.ReferenceSet.Slots["normalization_notes"].Items[0].Content); got != "normalize reference text" {
+		t.Fatalf("runner mutated normalize reference set content = %q", got)
+	}
+}
+
+func TestRunAllowsNilLLMClientWhenModulesDoNotUseIt(t *testing.T) {
+	_, err := New(newRunnerRegistries(t, defaultRunnerModules())).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil with nil LLM client when modules do not use it", err)
+	}
+}
+
 func TestRunIncludesInputWarnings(t *testing.T) {
 	modules := defaultRunnerModules()
 	warning := contracts.Warning{Scope: "reference", ReasonCode: "empty_reference", Message: "empty reference"}
@@ -961,7 +997,25 @@ func TestRunReturnsFailedManifestWhenOutputEncoderFails(t *testing.T) {
 
 func TestRunManifestIncludesPipelineAndLaneDetails(t *testing.T) {
 	resolved := resolvedPipelineWithValidators("configured")
-	resolved.ArtifactLanes[0].ReferenceSet = contracts.ReferenceSet{
+	resolved.ChunkReferences.ReferenceSet = contracts.ReferenceSet{
+		Slots: map[string]contracts.ResolvedReferenceSlot{
+			"scene_guide": {
+				Slot: contracts.ReferenceSlot{Name: "scene_guide"},
+				Items: []contracts.ReferenceItem{
+					{
+						SlotName:      "scene_guide",
+						MediaType:     "text/plain; charset=utf-8",
+						Content:       []byte("chunk reference content"),
+						Digest:        "sha256:chunk-reference",
+						Origin:        contracts.ReferenceOrigin{Type: "file", URI: "file:///tmp/scene-guide.txt"},
+						SizeBytes:     int64(len("chunk reference content")),
+						BindingSource: contracts.ReferenceBindingSourceCLI,
+					},
+				},
+			},
+		},
+	}
+	resolved.ArtifactLanes[0].ExtractReferences.ReferenceSet = contracts.ReferenceSet{
 		Slots: map[string]contracts.ResolvedReferenceSlot{
 			"roster": {
 				Slot: contracts.ReferenceSlot{Name: "roster"},
@@ -979,6 +1033,24 @@ func TestRunManifestIncludesPipelineAndLaneDetails(t *testing.T) {
 			},
 		},
 	}
+	resolved.ArtifactLanes[0].NormalizeReferences.ReferenceSet = contracts.ReferenceSet{
+		Slots: map[string]contracts.ResolvedReferenceSlot{
+			"normalization_notes": {
+				Slot: contracts.ReferenceSlot{Name: "normalization_notes"},
+				Items: []contracts.ReferenceItem{
+					{
+						SlotName:      "normalization_notes",
+						MediaType:     "text/plain; charset=utf-8",
+						Content:       []byte("normalize reference content"),
+						Digest:        "sha256:normalize-reference",
+						Origin:        contracts.ReferenceOrigin{Type: "file", URI: "file:///tmp/normalize.txt"},
+						SizeBytes:     int64(len("normalize reference content")),
+						BindingSource: contracts.ReferenceBindingSourceConfig,
+					},
+				},
+			},
+		},
+	}
 
 	output, err := New(newRunnerRegistries(t, nil)).Run(context.Background(), RunInput{Pipeline: resolved})
 	if err != nil {
@@ -995,15 +1067,26 @@ func TestRunManifestIncludesPipelineAndLaneDetails(t *testing.T) {
 	if !reflect.DeepEqual(manifest.SourceDigests, []string{"sha256:source"}) {
 		t.Fatalf("SourceDigests = %#v, want source digest", manifest.SourceDigests)
 	}
-	if len(manifest.References) != 1 {
-		t.Fatalf("References = %#v, want one reference provenance entry", manifest.References)
+	if len(manifest.References) != 3 {
+		t.Fatalf("References = %#v, want three reference provenance entries", manifest.References)
 	}
-	reference := manifest.References[0]
-	if reference.LaneID != "alpha" || reference.SlotName != "roster" || reference.Digest != "sha256:reference" {
-		t.Fatalf("reference provenance = %#v, want lane slot digest", reference)
+	chunkReference := manifest.References[0]
+	if chunkReference.Stage != string(StageChunk) || chunkReference.LaneID != "" || chunkReference.SlotName != "scene_guide" || chunkReference.Digest != "sha256:chunk-reference" {
+		t.Fatalf("chunk reference provenance = %#v, want chunk slot digest", chunkReference)
 	}
-	if reference.OriginType != "file" || reference.OriginURI != "file:///tmp/roster.txt" || reference.MediaType != "text/plain; charset=utf-8" || reference.SizeBytes != int64(len("reference content")) || reference.BindingSource != contracts.ReferenceBindingSourceConfig {
-		t.Fatalf("reference provenance = %#v, want origin/media/size/source", reference)
+	if chunkReference.OriginType != "file" || chunkReference.OriginURI != "file:///tmp/scene-guide.txt" || chunkReference.MediaType != "text/plain; charset=utf-8" || chunkReference.SizeBytes != int64(len("chunk reference content")) || chunkReference.BindingSource != contracts.ReferenceBindingSourceCLI {
+		t.Fatalf("chunk reference provenance = %#v, want origin/media/size/source", chunkReference)
+	}
+	extractReference := manifest.References[1]
+	if extractReference.Stage != string(StageExtract) || extractReference.LaneID != "alpha" || extractReference.SlotName != "roster" || extractReference.Digest != "sha256:reference" {
+		t.Fatalf("extract reference provenance = %#v, want lane slot digest", extractReference)
+	}
+	if extractReference.OriginType != "file" || extractReference.OriginURI != "file:///tmp/roster.txt" || extractReference.MediaType != "text/plain; charset=utf-8" || extractReference.SizeBytes != int64(len("reference content")) || extractReference.BindingSource != contracts.ReferenceBindingSourceConfig {
+		t.Fatalf("extract reference provenance = %#v, want origin/media/size/source", extractReference)
+	}
+	normalizeReference := manifest.References[2]
+	if normalizeReference.Stage != string(StageNormalize) || normalizeReference.LaneID != "alpha" || normalizeReference.SlotName != "normalization_notes" || normalizeReference.Digest != "sha256:normalize-reference" {
+		t.Fatalf("normalize reference provenance = %#v, want lane slot digest", normalizeReference)
 	}
 	if manifest.ValidationStatus != "approved" {
 		t.Fatalf("ValidationStatus = %q, want approved", manifest.ValidationStatus)
@@ -1157,16 +1240,19 @@ func TestRunRejectsNilDefaultValidator(t *testing.T) {
 
 func resolvedPipeline() ResolvedPipeline {
 	return ResolvedPipeline{
-		ID:     "pipeline-1",
-		Digest: "sha256:pipeline",
-		Input:  Binding("input"),
-		Chunk:  Binding("chunk"),
+		ID:              "pipeline-1",
+		Digest:          "sha256:pipeline",
+		Input:           Binding("input"),
+		Chunk:           Binding("chunk"),
+		ChunkReferences: referenceTarget(StageChunk, "", "chunk", nil),
 		ArtifactLanes: []ResolvedArtifactLane{
 			{
-				ID:        "alpha",
-				Extract:   Binding("extract-alpha"),
-				Merge:     Binding("merge"),
-				Normalize: Binding("normalize"),
+				ID:                  "alpha",
+				Extract:             Binding("extract-alpha"),
+				Merge:               Binding("merge"),
+				Normalize:           Binding("normalize"),
+				ExtractReferences:   referenceTarget(StageExtract, "alpha", "extract-alpha", nil),
+				NormalizeReferences: referenceTarget(StageNormalize, "alpha", "normalize", nil),
 			},
 		},
 		Output: Binding("output"),
@@ -1181,6 +1267,27 @@ func resolvedPipelineWithValidators(validators ...string) ResolvedPipeline {
 	return pipeline
 }
 
+func testReferenceSet(slotName string, content string) contracts.ReferenceSet {
+	return contracts.ReferenceSet{
+		Slots: map[string]contracts.ResolvedReferenceSlot{
+			slotName: {
+				Slot: contracts.ReferenceSlot{Name: slotName},
+				Items: []contracts.ReferenceItem{
+					{
+						SlotName:      slotName,
+						MediaType:     "text/plain; charset=utf-8",
+						Content:       []byte(content),
+						Digest:        "sha256:test",
+						Origin:        contracts.ReferenceOrigin{Type: "file", URI: "file:///tmp/reference.txt"},
+						SizeBytes:     int64(len(content)),
+						BindingSource: contracts.ReferenceBindingSourceConfig,
+					},
+				},
+			},
+		},
+	}
+}
+
 type runnerModules struct {
 	input           *runnerInputAdapter
 	chunker         *runnerChunker
@@ -1314,6 +1421,10 @@ func (chunker *runnerChunker) Key() string {
 	return chunker.key
 }
 
+func (chunker *runnerChunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (chunker *runnerChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	chunker.requests = append(chunker.requests, req)
 	return contracts.ChunkResult{
@@ -1421,6 +1532,10 @@ func (normalizer *runnerNormalizer) Key() string {
 	return normalizer.key
 }
 
+func (normalizer *runnerNormalizer) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (normalizer *runnerNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
 	normalizer.requests = append(normalizer.requests, req)
 	candidates := append([]artifacts.ArtifactCandidate(nil), normalizer.result...)

internal/framework/pipeline/testdata/walking_skeleton_output.json

@@ -1,7 +1,7 @@
 {
   "manifest": {
     "pipeline_id": "walking-skeleton",
-    "pipeline_digest": "sha256:5df1e501a2307ef75bbfeb59d315b3710571d52e5466a9c7f8320248740e6fca",
+    "pipeline_digest": "sha256:25084e39a0cadace375c896551d1752413755c1a6772f6b24cfe91c029ea2631",
     "validation_status": "approved",
     "artifact_lanes": [
       {

internal/framework/pipeline/walking_skeleton_test.go

@@ -43,8 +43,8 @@ func TestWalkingSkeletonFixture(t *testing.T) {
 		t.Fatalf("ContentType = %q, want application/json", output.OutputFiles[0].ContentType)
 	}
 	assertStructuralJSONEqual(t, output.OutputFiles[0].Bytes, expectedBytes)
-	if llmClient.calls != 2 {
-		t.Fatalf("LLM calls = %d, want chunk count 2", llmClient.calls)
+	if llmClient.calls != 3 {
+		t.Fatalf("LLM calls = %d, want extractor calls plus normalizer call", llmClient.calls)
 	}
 }
 
@@ -216,6 +216,10 @@ func (chunker walkingSkeletonChunker) Key() string {
 	return "fake/chunk"
 }
 
+func (chunker walkingSkeletonChunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (chunker walkingSkeletonChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	if len(req.Source.Units) < 3 {
 		return contracts.ChunkResult{}, fmt.Errorf("fixture source must contain at least three units")
@@ -336,7 +340,20 @@ func (normalizer walkingSkeletonNormalizer) Key() string {
 	return DefaultNormalizeModule
 }
 
+func (normalizer walkingSkeletonNormalizer) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (normalizer walkingSkeletonNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
+	var response struct {
+		Call int `json:"call"`
+	}
+	if _, err := req.LLMClient.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
+		StageName:          "fake/normalize",
+		ResponseSchemaName: "fake_normalize",
+	}, &response); err != nil {
+		return contracts.NormalizeResult{}, err
+	}
 	return contracts.NormalizeResult{Candidates: req.Candidates}, nil
 }
 

internal/framework/prompt/render_test.go

@@ -97,6 +97,57 @@ func TestRenderUserSystemWithReferencesRendersDeclaredSlots(t *testing.T) {
 	}
 }
 
+func TestRenderUserSystemWithReferencesSupportsChunkRequestData(t *testing.T) {
+	bundle := loadReferenceBundle(t,
+		[]contracts.ReferenceSlot{{Name: "scene_guide"}},
+		`Chunk system has guide={{ hasreference "scene_guide" }}`,
+		`Source={{ .SourceID }} Guide={{ reference "scene_guide" }}`,
+	)
+	references := contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{
+		"scene_guide": {
+			Slot: contracts.ReferenceSlot{Name: "scene_guide"},
+			Items: []contracts.ReferenceItem{
+				{SlotName: "scene_guide", Content: []byte("Keep combat scenes separate.")},
+			},
+		},
+	}}
+
+	system, user, _, err := bundle.RenderUserSystemWithReferences(map[string]any{"SourceID": "session-alpha"}, references)
+	if err != nil {
+		t.Fatalf("RenderUserSystemWithReferences: %v", err)
+	}
+	if !strings.Contains(system, "has guide=true") {
+		t.Fatalf("system = %q, want chunk reference presence", system)
+	}
+	if !strings.Contains(user, "Source=session-alpha") || !strings.Contains(user, "Keep combat scenes separate.") {
+		t.Fatalf("user = %q, want chunk request data and reference content", user)
+	}
+}
+
+func TestRenderUserSystemWithReferencesSupportsNormalizeRequestData(t *testing.T) {
+	bundle := loadReferenceBundle(t,
+		[]contracts.ReferenceSlot{{Name: "normalization_notes"}},
+		`Normalize system`,
+		`Lane={{ .LaneID }} Notes={{ reference "normalization_notes" }}`,
+	)
+	references := contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{
+		"normalization_notes": {
+			Slot: contracts.ReferenceSlot{Name: "normalization_notes"},
+			Items: []contracts.ReferenceItem{
+				{SlotName: "normalization_notes", Content: []byte("Prefer canonical item names.")},
+			},
+		},
+	}}
+
+	_, user, _, err := bundle.RenderUserSystemWithReferences(map[string]any{"LaneID": "spells"}, references)
+	if err != nil {
+		t.Fatalf("RenderUserSystemWithReferences: %v", err)
+	}
+	if !strings.Contains(user, "Lane=spells") || !strings.Contains(user, "Prefer canonical item names.") {
+		t.Fatalf("user = %q, want normalize request data and reference content", user)
+	}
+}
+
 func TestRenderUserSystemReferenceHasReferenceRequiresContent(t *testing.T) {
 	bundle := loadReferenceBundle(t,
 		[]contracts.ReferenceSlot{{Name: "roster"}},

internal/modules/chunk/dnd/scenes/chunker.go

@@ -34,6 +34,10 @@ func (c *Chunker) Key() string {
 	return Key
 }
 
+func (c *Chunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (c *Chunker) ManifestMetadata() map[string]any {
 	promptMetadata := scenesPromptBundle.Metadata()
 	metadata := map[string]any{

internal/modules/chunk/dnd/scenes/chunker_test.go

@@ -57,6 +57,9 @@ func TestNewModuleSpecAndRegister(t *testing.T) {
 	if built.Key() != Key {
 		t.Fatalf("built Key() = %q, want %q", built.Key(), Key)
 	}
+	if slots := built.ReferenceSlots(); len(slots) != 0 {
+		t.Fatalf("ReferenceSlots() = %#v, want none", slots)
+	}
 }
 
 func TestRegisterNilRegistryReturnsError(t *testing.T) {

internal/modules/chunk/generic/chunker.go

@@ -31,6 +31,10 @@ func (c *Chunker) Key() string {
 	return Key
 }
 
+func (c *Chunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	if c == nil {
 		return contracts.ChunkResult{}, chunkerErrorf("chunker must not be nil")

internal/modules/chunk/generic/chunker_test.go

@@ -41,6 +41,9 @@ func TestModuleSpecAndRegister(t *testing.T) {
 	if chunker.Key() != Key {
 		t.Fatalf("Key() = %q, want %q", chunker.Key(), Key)
 	}
+	if slots := chunker.ReferenceSlots(); len(slots) != 0 {
+		t.Fatalf("ReferenceSlots() = %#v, want none", slots)
+	}
 }
 
 func TestChunkUsesDefaultsForSingleChunk(t *testing.T) {

internal/modules/extract/dnd/spells/config_test.go

@@ -236,6 +236,10 @@ func (dndSpellsChunker) Key() string {
 	return "fake/chunk"
 }
 
+func (dndSpellsChunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (dndSpellsChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	return contracts.ChunkResult{
 		Chunks: []contracts.SourceChunk{

internal/modules/extract/dnd/spells/runner_test.go

@@ -114,7 +114,7 @@ func TestRunnerPassesRosterAndGlossaryReferencesToDNDSpellsPrompt(t *testing.T)
 	raw := readDNDSpellsFixture(t)
 	expectedDoc := parseDNDSpellsFixture(t, raw)
 	resolved := resolveDNDSpellsPipeline(t)
-	resolved.ResolvedPipeline.ArtifactLanes[0].ReferenceSet = dndSpellsReferenceSet(
+	resolved.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet = dndSpellsReferenceSet(
 		"Aria: party cleric\nBorin: fighter",
 		"Fire Bolt: evocation cantrip",
 	)
@@ -168,7 +168,7 @@ func TestRunnerPassesRosterAndGlossaryReferencesToDNDSpellsPrompt(t *testing.T)
 func TestRunnerDoesNotExtractSpellMentionedOnlyInRoster(t *testing.T) {
 	raw := readDNDSpellsFixture(t)
 	resolved := resolveDNDSpellsPipeline(t)
-	resolved.ResolvedPipeline.ArtifactLanes[0].ReferenceSet = dndSpellsReferenceSet(
+	resolved.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet = dndSpellsReferenceSet(
 		"Mira: wizard who can cast Lightning Bolt",
 		"",
 	)

internal/modules/input/seriatim/config_test.go

@@ -209,6 +209,8 @@ type fakeChunker struct{}
 
 func (fakeChunker) Key() string { return "fake/chunk" }
 
+func (fakeChunker) ReferenceSlots() []contracts.ReferenceSlot { return nil }
+
 func (fakeChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	return contracts.ChunkResult{}, nil
 }

internal/modules/input/seriatim/runner_test.go

@@ -157,6 +157,10 @@ func (runnerSeriatimChunker) Key() string {
 	return "fake/chunk"
 }
 
+func (runnerSeriatimChunker) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (runnerSeriatimChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
 	return contracts.ChunkResult{
 		Chunks: []contracts.SourceChunk{

internal/modules/normalize/noop/normalizer.go

@@ -25,6 +25,10 @@ func (n *Normalizer) Key() string {
 	return Key
 }
 
+func (n *Normalizer) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (n *Normalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
 	if n == nil {
 		return contracts.NormalizeResult{}, normalizerErrorf("normalizer must not be nil")

internal/modules/normalize/noop/normalizer_test.go

@@ -34,6 +34,13 @@ func TestModuleSpecAndRegister(t *testing.T) {
 	if !reflect.DeepEqual(spec, want) {
 		t.Fatalf("registered spec = %#v, want %#v", spec, want)
 	}
+	normalizer, err := registry.Build(Key)
+	if err != nil {
+		t.Fatalf("Build(%q) error = %v, want nil", Key, err)
+	}
+	if slots := normalizer.ReferenceSlots(); len(slots) != 0 {
+		t.Fatalf("ReferenceSlots() = %#v, want none", slots)
+	}
 }
 
 func TestNormalizePassesThroughOrderAndValues(t *testing.T) {

internal/modules/output/json/encoder_test.go

@@ -148,6 +148,7 @@ func TestEncodeIncludesManifestReferences(t *testing.T) {
 			RunID: "run-1",
 			References: []artifacts.ReferenceProvenance{
 				{
+					Stage:         "extract",
 					LaneID:        "events",
 					SlotName:      "roster",
 					OriginType:    "file",