VuongKB/docs/specs/saga-taxonomy-redesign-plan.md

created, id, keywords, links, modified, summary, tags, title

created	id	keywords	links	modified	summary	tags	title
2026-04-14T21:13:22+00:00	b47806bc-e187-4381-bbd2-b9d5e71ea37a	schema concept type saga extraction types claim taxonomy author principle plan calibration extractor prompt as		2026-04-14T21:21:32+00:00	Architecture and implementation plan for refining Saga's concept taxonomy and extraction schemas based on scientific research into cognitive categorization, ontology design, and LLM extraction best practices. Covers MECE compliance, type descriptions, schema structure, and validation approach. Revised to fix disambiguation logic, add prompt assembly spec, restructure decision tree, and defer speculative metadata.	spec saga ingestion taxonomy redesign-plan gitea-37 gitea-38	Saga Concept Taxonomy & Extraction Schema — Redesign Plan

Saga Concept Taxonomy & Extraction Schema — Redesign Plan

Author: Atlas (Librarian & Historian) Date: 2025-07-12 (revised 2025-07-13) Status: Proposed — awaiting developer review Tracks: Gitea #37 (taxonomy refinement), Gitea #38 (collection architecture redesign) Research basis: Hermione rs_concept_taxonomy_science — 51 extracted concepts across 4 chapters

---

1. Purpose & Scope

This plan provides a grounded, phased approach for tuning Saga's concept taxonomy and extraction schemas from their current working state to a state backed by established research in cognitive science, ontology engineering, and LLM extraction design.

What this covers:

• Concept type definitions (the "what we extract" layer)
• Concept type descriptions (the "how to recognize it" layer)
• Schema structure and type ordering (the "how we organize it" layer)
• Validation and quality measurement (the "how we know it works" layer)

What this does NOT cover:

• Pipeline architecture changes (parsing, chunking, summarization — separate work)
• Coherence graph redesign (related but distinct)
• Chroma collection restructuring (Gitea #38 — this plan feeds into it)

Design philosophy: We are not rebuilding — we are tuning. The current 7-source-type, 7-schema architecture is structurally sound. The research confirms the direction and identifies specific seams that need tightening.

---

2. Research Summary — What the Science Says

The following principles are drawn from Hermione's research session, grounded in primary sources. Each principle is stated with its source and mapped to a specific implication for Saga.

2.1 Cognitive Science Foundations (Rosch 1978, Gozli 2023)

Principle — Basic-level categories: Human categorization operates at a "basic level" that maximizes both cue validity (how well features predict category membership) and category resemblance (how similar members are to each other). This is the level at which people (and by extension, LLMs) classify most reliably and quickly.

"These principles result in basic-level categories that maximize both total cue validity and category resemblance." — Rosch (1978)

Implication for Saga: Our concept types should sit at this basic level — specific enough to be actionable, general enough for reliable classification. The test: can an LLM extractor reliably assign a concept to one type without hesitation? If extraction accuracy shows high ambiguity between adjacent types, we're either too fine (too many types) or too coarse (types that serve multiple purposes).

Principle — Prototypicality effects: The degree to which an instance matches the prototype of its category directly affects processing speed, learning efficiency, and classification confidence. Atypical instances are harder to classify.

"Effects of prototypicality on processing speed, learning, item output, and natural language use are documented." — Rosch (1978)

Implication for Saga: Each concept type should have clear prototypical examples in its description. The extractor prompt should include "this IS a claim / this is NOT a claim" examples to anchor classification.

Principle — Sense vs. choice categories (Mammen/Gozli): Some categories operate by logic of types (interchangeable instances — "sense"), while others operate by logic of individuals (unique, irreplaceable instances — "choice"). Deviations from basic-level toward choice categories reveal subjectivity.

Implication for Saga: Our concept types are "sense" categories (the claim in chapter 3 is interchangeable with the claim in chapter 7 at the type level). This is correct. We should not try to make types that encode the specific instance's uniqueness — that's what the verbatim text and metadata are for.

2.2 Taxonomy & Ontology Design Best Practices

Principle — MECE is non-negotiable: Categories must be Mutually Exclusive (no concept should fit two types) and Collectively Exhaustive (every extractable concept should fit at least one type).

"Key principles: MECE categories" — NNGroup / Taxon.dev (multiple sources) "choose a simple intuitive structure — MECE categories (mutually exclusive, collectively exhaustive)" — Taxon.dev

Implication for Saga: This is the single most important audit criterion. Current areas of concern (detailed in §3.1):

• claim vs. contradiction (book schema) — a contradiction is semantically a claim that targets another view
• principle vs. framework (book schema) — a framework often is a set of principles
• claim vs. evidence (article schema) — a fact that serves as evidence is also a claim about reality

Principle — Start with a clear objective: Taxonomy design must begin by defining what problem the system solves.

"start with a clear objective — define what problem you're solving" — Taxon.dev

Implication for Saga: Our objective is clear but should be explicitly stated in the config: "Enable retrieval of source-grounded knowledge atoms by type, with sufficient precision that an agent can filter by concept_type and get results matching their intent."

Principle — Consistent, meaningful labels: Taxonomy terms must use standardized terminology from the relevant domain.

"use consistent meaningful labels — standardized terminology from the domain" — NNGroup

Implication for Saga: Our type names are already domain-standard for the most part (hypothesis, finding, method from academic research; obligation, right, exception from legal analysis). The only questionable label is contradiction — in argumentation theory, the standard term is counterargument or rebuttal, which we already use in the article schema. Consider aligning.

Principle — Iterative testing and refinement: Taxonomies must be validated against real data and refined.

"test and refine — evaluate in real-world scenarios" — Taxon.dev

Implication for Saga: We need a feedback loop — extract from a known document, classify by hand, compare to extractor output, measure agreement, adjust types. This is detailed in §5.

Principle — 10-step taxonomy building process: Content inventory → check existing standards → identify key concepts → define hierarchy → apply MECE → test with real content → label consistently → document governance → plan maintenance → deploy and monitor.

Implication for Saga: We've done steps 1-3 implicitly. Steps 4-6 are what this plan addresses. Steps 7-10 are the validation and governance covered in §5.

2.3 Ontology Design Schools (Semantic Arts)

Eight schools of ontology design were identified. The two most relevant to Saga:

Data-Centric School: Modest class counts (<500), implemented and populated, high-level domain descriptions. Equivalent class restrictions enable inference. This is closest to our current approach — a working, populated taxonomy with a small number of well-defined types.

NLP/LLM School: Machine-generated ontologies with hallucination risk. Best practice: controlled document sets + human in the loop. This is literally what we're doing — an LLM extracts concepts from documents, and the results go through Atlas for review.

Principle — Modular design: Complex systems should be broken into smaller, manageable components.

"use modular design — break into smaller manageable modules" — Semantic Arts

Implication for Saga: Our current 7-schema architecture is already modular (one schema per source type). This should be preserved. The module boundary should remain at the source-type level.

Principle — Define scope and purpose explicitly.

"define scope and purpose" — Semantic Arts

Implication for Saga: Each schema should carry an explicit scope statement describing what it's optimized to extract. Currently the schema name (book, academic_paper) implies the scope, but an explicit purpose statement would improve extractor performance.

2.4 Argumentation Theory (Visser et al. 2021)

Principle — Classification difficulty is real: Even trained annotators achieved only moderate inter-annotator agreement when classifying arguments into established typologies (Walton's 60 schemes, Wagemans' 36 types). Many arguments resisted classification entirely.

"Key insight: argument scheme annotation is difficult — inter-annotator agreement is moderate" — Visser et al. (2021)

Implication for Saga: This is a humility check. We should expect imperfect classification and design for it rather than trying to eliminate it. Specific mitigations:

• Keep type counts low (6-7 per schema is the right range — don't expand to 10+)
• Include a confidence field (already present) and use it downstream
• Include an unclassifiable or other fallback type, OR accept that some concepts will be imperfectly classified and rely on semantic search rather than type filtering for those cases
• The recommendation is to NOT add an other type — it becomes a junk drawer. Instead, accept the imperfection and document it.

Principle — Decision tree heuristics help: Providing annotators (or LLMs) with a binary decision tree improves classification consistency.

"A decision tree heuristic helps annotators classify arguments through binary questions." — Visser et al. (2021)

Implication for Saga: The extractor prompt should include a binary decision tree where each fork asks a single yes/no question. The tree should front-load the most common types so the extractor reaches the right answer quickly. See §4.3 for the full specification.

2.5 Extraction Schema Design for LLMs (LandingAI 2025)

Principle — Descriptive field names with contextual descriptions: Field names must clearly indicate what to extract. Descriptions should specify format, currency, length constraints, and examples.

"field names should clearly indicate what data to extract; descriptions provide additional context that improves accuracy — specify time formats, currency, expected length" — LandingAI (2025)

Implication for Saga: Our concept type descriptions are currently short labels ("A stated argument or position the author defends"). They should be expanded to include:

• What it looks like (linguistic cues: "typically uses declarative sentences, may include 'I argue', 'we show', 'the evidence suggests'")
• What it is NOT (disambiguation: "not a definition of a term, not a general observation")
• Examples (1-2 prototypical instances)

Principle — Mirror document structure: Schema should reflect how data appears in the source document.

"organize schema to reflect how data appears in parsed Markdown and how it will be used; use nested objects for hierarchical data; match document flow order" — LandingAI (2025)

Implication for Saga: Within each schema, types should be ordered by likelihood of occurrence in that source type. For example, in academic_paper, finding should come first (it's the most common and important), not hypothesis. In book, claim first is correct. In fiction, theme first is correct.

Principle — Strict data type specification: Prevent downstream conversion errors by specifying correct types.

"use correct types (string, number, integer, boolean, array, object) to prevent downstream conversion errors" — LandingAI (2025)

Implication for Saga: Review the concept metadata schema in config.yaml to ensure all fields have strict type declarations. The confidence field should be a float, verbatim a boolean, terms an array of strings, etc.

---

3. Current State Analysis — Where the Seams Are

3.1 MECE Audit of Each Schema

book schema — issues found

Problem	Types	Why it's not MECE	Recommended resolution
claim and contradiction overlap	claim, contradiction	A contradiction is a claim that targets another view. The extractor must decide: is this "the author's argument" or "the author's challenge to another argument"? Both are claims structurally.	Rename contradiction to counterargument (aligns with argument schema terminology used in article). Add to description: "A claim that explicitly targets and opposes another stated position. If the author simply states an unconventional view without targeting a specific alternative, classify as claim." This creates a cleaner boundary: counterargument requires a target; claim does not.
claim and principle overlap	claim, principle	Both are the author putting something forward. A claim asserts what is true; a principle prescribes what to do or how to think. The boundary can be fuzzy when a claim reads like a rule ("Practice deliberate feedback").	Sharpen the disambiguation rule. The test is: can you imagine someone following this? If yes → principle. If it's a statement about reality (even a strong one) → claim. "System 1 operates automatically" is a claim — it describes how things are. "Seek regular feedback in structured environments" is a principle — it tells you what to do.
principle and framework overlap	principle, framework	A framework (e.g., "Dual Process Theory") often contains principles (e.g., "System 1 is fast and automatic"). The boundary between "a general rule" and "a structured model of thinking" depends on scale, which is subjective.	Keep both but sharpen descriptions. principle = "a single, standalone rule or guideline." framework = "a named, multi-component system or model that organizes multiple ideas into a structured whole." Key test: can you name it? Does it have parts? If yes → framework. If it's one rule → principle.
question is a weak type	question	Open questions are rarely the primary knowledge atom a reader is searching for. They're more like metadata about what the author is investigating.	Demote but keep. Move question to the end of the type list (lowest priority). Consider whether it should be extracted at all, or whether it's better captured in section summaries. Recommendation: keep for now, monitor extraction frequency.

academic_paper schema — issues found

Problem	Types	Why it's not MECE	Recommended resolution
hypothesis and finding can overlap	hypothesis, finding	A confirmed hypothesis is reported as a finding. The same statement can be both depending on where in the paper it appears (intro = hypothesis, results = finding).	Disambiguate by tense and framing, not by position. hypothesis = "a prediction or proposition framed in future or conditional tense about what the study expects to find." finding = "an observed result framed in past tense about what the study found." Key test: is the author predicting what will happen (hypothesis) or reporting what did happen (finding)? Position in the document can be a corroborating signal if available, but tense/framing is the primary disambiguation criterion and works without structural metadata.
contribution is orphaned	contribution	Contributions are often a mix of findings, methods, and frameworks. They rarely appear as standalone knowledge atoms.	Keep but narrow. contribution = "a specific claimed novelty or advance that the authors explicitly identify as their contribution, typically in the introduction or discussion."

article schema — issues found

Problem	Types	Why it's not MECE	Recommended resolution
claim and evidence overlap	claim, evidence	A cited statistic ("60% of voters...") is evidence for a claim, but it's also a claim about reality.	Disambiguate by role in the argument. claim = "the author's own assertion or thesis." evidence = "a fact, statistic, or external source cited to support a claim." Key test: did the author produce this, or did they cite it? Author-produced → claim. Cited from elsewhere → evidence.

technical_document schema — no issues

This schema is already well-MECE. The types (definition, requirement, procedure, parameter, warning, example) have clear structural boundaries. No changes recommended.

instruction_manual schema — no issues

Similarly clean. step, prerequisite, warning, tip, troubleshooting, example are well-separated. No changes recommended.

legal_document schema — no issues

obligation, right, condition, exception, definition, penalty are standard legal ontology terms with clear boundaries. No changes recommended.

fiction schema — minor issue

Problem	Types	Why it's not MECE	Recommended resolution
relationship and character_trait can overlap	relationship, character_trait	A dynamic between characters can reveal character traits, and vice versa.	Minor — acceptable as-is. The boundary is: relationship describes the interaction between two+ characters. character_trait describes a quality of a single character. This is sufficiently distinct.

3.2 Type Ordering Audit

Current default types (the type the extractor falls back to) are generally correct:

Schema	Current default	Assessment
book	claim	✓ Correct — claims are the primary knowledge atoms
academic_paper	finding	✓ Correct — findings are what researchers search for
article	claim	✓ Correct
technical_document	definition	✓ Correct — terms and concepts are the primary referents
instruction_manual	tip	⚠️ Questionable — step may be more commonly extracted and useful
legal_document	obligation	✓ Correct
fiction	theme	✓ Correct

Recommendation: Change instruction_manual default from tip to step.

3.3 Description Quality Audit

Current descriptions are single-sentence labels. Per LandingAI's research, they should be expanded to include linguistic cues, disambiguation rules, and prototypical examples. All 7 schemas need this treatment. See §4.1 for the specification.

---

4. Architecture Design — What to Build

4.1 Enhanced Concept Type Specification Format

Each concept type in config.yaml should be upgraded from a single-line description to a structured specification:

types:
  claim:
    label: "Claim"
    short_description: "The author's own assertion, thesis, or position"
    long_description: |
      A declarative statement that the author argues for, defends, or puts forward as true.
      This is the author's voice making a case — not a cited fact, not a definition of a term,
      and not a question.
    linguistic_cues:
      - "The author argues that..."
      - "We believe..."
      - "The evidence shows..."
      - "It is clear that..."
    disambiguation:
      - "NOT a definition (use 'definition' for term explanations)"
      - "NOT a cited external fact (use 'evidence' in article schema)"
      - "NOT a general observation without argumentative force"
    prototypical_examples:
      - "System 1 operates automatically and quickly with little or no effort."
      - "Expert intuition is more reliable than we think in structured environments."
    priority: 1  # order within the schema prompt

Fields explained:

Field	Purpose	Required
label	Human-readable display name	Yes
short_description	One-line summary for compact contexts	Yes
long_description	Full description for the extractor prompt	Yes
linguistic_cues	Common phrasing patterns that signal this type	Recommended
disambiguation	Rules for what this is NOT, especially vs. adjacent types	Recommended
prototypical_examples	2-3 canonical examples from real source material	Yes
priority	Extraction priority (lower = extracted first, ties broken by this)	Yes

4.2 Schema Scope Statements

Each schema should include a scope statement that the classifier uses to select it:

schemas:
  book:
    source_types: ["book"]
    scope: |
      Optimized for long-form non-fiction where the author develops arguments,
      frameworks, and principles across chapters. Prioritizes claims and
      structured models over individual facts.
    default_type: "claim"
    types: { ... }

4.3 Decision Tree for Disambiguation

For schemas with adjacent-type ambiguity (specifically book), the extractor prompt should include a binary decision tree — a series of yes/no questions where each fork leads to either a type assignment or the next question. This directly implements Visser et al.'s finding that binary decision trees improve classification consistency.

The tree should front-load the most common types so the extractor reaches the right answer quickly.

Example for book schema:

Is the author asserting something as true or arguing a position?
  YES:
    Is there a specific alternative view they are explicitly opposing?
      YES → COUNTERARGUMENT
      NO → CLAIM
  NO:
    Is the author defining a term or concept precisely?
      YES → DEFINITION
      NO:
        Is the author presenting a named, multi-component model or system?
          YES → FRAMEWORK
          NO:
            Is the author stating a rule about what to do or what generally applies?
              YES → PRINCIPLE
              NO:
                Is the author illustrating a point with a concrete instance?
                  YES → EXAMPLE
                  NO:
                    Is the author raising something they don't answer?
                      YES → QUESTION
                      NO → CLAIM  (default fallback)

Implementation notes:

• This tree is generated from the priority ordering of types in the schema.
• The root question targets the highest-priority type's core distinction (asserting something as true → claim, the most common and important type).
• Each fork is a single yes/no question — the extractor never has to choose among 7 options simultaneously.
• The final fallback is always the schema's default_type.
• For schemas without significant ambiguity (e.g., legal_document), a decision tree is unnecessary — the standard type list suffices.

4.4 Prompt Assembly

The enhanced type specifications must be assembled into the actual LLM extraction prompt. This section specifies how.

Which fields go into the prompt, and in what order:

For each concept type in the schema, the prompt should include:

1. label — bolded header
2. long_description — full paragraph
3. linguistic_cues — bullet list (if present)
4. disambiguation — bullet list (if present)
5. prototypical_examples — numbered list (1-2 examples, not all)

Fields NOT included in the prompt: short_description (for human consumption only), priority (used for ordering only).

Token budget guidance:

A typical concept type spec assembled as above runs ~150-250 tokens. With 6-7 types per schema, that's ~1,000-1,750 tokens for the type definitions section — well within a standard extraction prompt context. If schemas grow beyond 10 types, consider using short_description instead of long_description and dropping linguistic_cues to stay within budget.

Decision tree placement:

If a decision tree is used (§4.3), it appears after the type definitions and before the extraction instructions. The prompt structure should be:

[Schema scope statement]
[Type definitions — ordered by priority]
[Decision tree for disambiguation]
[Extraction instructions — format, output schema, constraints]

Example assembled prompt fragment for book.claim:

## Claim
A declarative statement that the author argues for, defends, or puts forward as true.
This is the author's voice making a substantive case. Claims are the primary knowledge
atoms in non-fiction — they are what a reader would quote or reference when discussing
the book's arguments.

Signals: "I argue that...", "The evidence shows...", "It is clear that...", declarative
sentences asserting something as true.

Not to be confused with: definitions (explaining what a term means), cited facts (evidence
from elsewhere), challenges to specific alternatives (counterarguments), or prescriptive
rules (principles).

Examples:
1. "System 1 operates automatically and quickly with little or no effort and no sense of
   voluntary control."
2. "Expert intuition is more reliable than we think, but only in environments with regular
   feedback."

4.5 Concept Metadata Schema Additions

Phase 1 — essential addition:

concept_metadata:
  # Existing fields preserved...
  
  # New field:
  source_position:         # Where in the document structure this appeared
                           # (string: "introduction", "body", "conclusion", "methodology", "results")

source_position enables position-aware disambiguation as a corroborating signal (e.g., in academic_paper, statements in a "results" section are more likely to be finding). It is optional in Phase 1 — populated when the section structure is available from the parsed document.

Phase 4 — optional diagnostic fields:

These are deferred to Phase 4 and included only if calibration reveals systematic confusion that needs debugging:

  extraction_rationale:    # Short explanation of why this type was chosen (string, optional)
  adjacent_type_score:     # If the extractor considered a second type, record it (string, optional)

Why these are deferred: extraction_rationale adds prompt overhead for every extracted concept, and LLMs are known to confabulate post-hoc justifications rather than accurately reporting their reasoning. adjacent_type_score asks the LLM to quantify its own uncertainty — something LLMs are notably poor at. Neither field is used by the validation plan (§5), which compares against hand labels. Their value is purely for post-hoc debugging of systematic confusion patterns. They should only be added if Phase 2-3 calibration reveals a specific problem they would help diagnose.

---

5. Validation & Quality Measurement Plan

5.1 Calibration Dataset

Create a gold-standard calibration dataset:

1. Select 3-5 representative documents — prefer documents that have already been ingested so we can compare existing extractions directly against the hand annotations. One per major schema: book, academic_paper, article, plus one wild card.

2. Hand-annotate 50-100 concepts per document with type assignments, using the following process:

   • Primary annotator: Atlas (the Librarian), working from the source text and the enhanced type specifications.
   • Annotation protocol: For each concept, record the hand label, rationale, and any adjacent type considered. Use the same JSON schema the extractor produces so comparison is direct.
   • Inter-annotator check: After the primary annotation is complete, a second annotator (the user or another agent) independently labels a 20% subset (10-20 concepts per document). Measure human-human agreement on this subset. If human-human agreement is below 90%, the type definitions themselves may be ambiguous and need sharpening before measuring LLM accuracy. This addresses the meta-problem Visser et al. identified: if humans can't agree, the taxonomy is the problem, not the annotator.

3. Record disambiguation notes — for every concept where the annotator hesitated or considered an alternative type, record why. These notes are the raw material for future description improvements.

4. Store in validation/calibration/ as JSON files with schema:

   {
     "source": "Thinking, Fast and Slow",
     "section": "Ch. 1, Sec. 2",
     "verbatim": "System 1 operates automatically...",
     "hand_label": "claim",
     "rationale": "Author's direct assertion about how cognition works",
     "adjacent_considered": "definition",
     "notes": "Could be confused with definition because it describes System 1, but it's asserting a factual claim, not explaining a term"
   }
   

5.2 Inter-Rater Reliability Metric

After running the extractor against the calibration dataset:

• Measure per-type precision and recall against hand labels
• Identify the confusion matrix (which types are most commonly confused with which)
• Target: ≥85% agreement on primary type assignment
• Acceptable: ≥70% with documented confusion pairs
• Below 70% on any type pair: triggers a merge or re-description of those types

5.3 Feedback Loop

[Calibration dataset] → [Run extractor] → [Compare to hand labels]
  → [Confusion matrix] → [Adjust type descriptions]
  → [Re-run] → [Measure improvement]
  → [When stable: promote descriptions to config.yaml]

This is not a one-time exercise. As new source types are added or existing schemas are used on new document types, the calibration dataset should grow.

5.4 Governance

• Type changes require: Updated description in config.yaml + re-run against calibration dataset + update to concept-taxonomy-reference.md
• New type additions require: Justification against MECE principle (why existing types don't cover it) + calibration dataset entries
• Type removals require: Evidence from extraction logs that the type is used <2% of the time or is never the primary classification
• Review cadence: After every 5 new ingestion jobs, review type distribution and confusion patterns

---

6. Implementation Phases

Phase 1 — Foundation (config.yaml changes)

Goal: Upgrade the type specification format and rename one type, without changing any structural boundaries.

Tasks:

1. Add scope field to each of the 7 schemas in config.yaml
2. Add long_description, linguistic_cues, disambiguation, prototypical_examples, priority to each concept type in each schema
3. Rename contradiction → counterargument in book schema
4. Change instruction_manual default type from tip to step
5. Add source_position to concept metadata (optional — populated when section structure is available)
6. Update extractor prompt template to include binary decision tree for schemas with adjacent-type ambiguity (book, academic_paper, article)
7. Update prompt assembly logic to include long_description, linguistic_cues, disambiguation, and prototypical_examples for each type (see §4.4)
8. Bulk-update any existing contradiction-typed concepts in Chroma to counterargument (conditional — only if such concepts exist)
9. Update docs/specs/concept-taxonomy-reference.md to reflect all changes

Deliverable: Updated config.yaml with enhanced type specs, updated prompt template, updated reference doc, migrated legacy concepts.

Estimated effort: Small — mostly YAML editing and prompt engineering.

Phase 2 — Calibration (validation infrastructure)

Goal: Build the measurement infrastructure to validate that Phase 1 changes improve extraction quality.

Tasks:

1. Create validation/calibration/ directory structure
2. Hand-annotate calibration dataset (3-5 documents, 50-100 concepts each) — primary annotation by Atlas, 20% subset verified by a second annotator
3. Build comparison script: scripts/validate_extraction.py that takes extractor output and calibration data, produces confusion matrix and per-type metrics
4. Run baseline measurement with current extractor against calibration dataset (before Phase 1 changes, if possible — otherwise against Phase 1 output)
5. Document baseline metrics in validation/baseline_metrics.md

Deliverable: Calibration dataset, validation script, baseline metrics.

Estimated effort: Medium — annotation is the bottleneck.

Phase 3 — Iterate (tuning cycle)

Goal: Use calibration data to tune type descriptions until ≥85% agreement is achieved.

Tasks:

1. Run extractor with Phase 1 type specs against calibration dataset
2. Generate confusion matrix
3. For each confused pair, either: (a) sharpen descriptions with more specific disambiguation rules, or (b) if confusion persists across iterations, consider merging the types
4. Re-run and re-measure
5. When stable, finalize descriptions in config.yaml
6. Re-index any existing ingested concepts that were extracted with the old type specs (optional — may not be worth it if changes are description-only)

Deliverable: Finalized type specs with measured quality metrics.

Estimated effort: Medium — depends on how many iterations are needed.

Phase 4 — Extend (optional, post-validation)

Goal: Apply validated patterns to new source types or schema extensions.

Tasks:

1. If adding new source types, use the enhanced type specification format from Phase 1
2. Add calibration entries for new source types before deploying
3. Consider adding source_position-based extraction rules (e.g., in academic_paper, weight hypothesis higher in introduction sections, finding higher in results sections) — now that we have calibration data to measure whether position-awareness improves accuracy
4. If calibration revealed systematic confusion that needs deeper diagnosis, add extraction_rationale and adjacent_type_score as optional metadata fields — but only if there's a specific problem to solve

Deliverable: Extension-ready architecture.

---

7. Open Questions

These are decisions that should be made before or during Phase 1, but don't block starting the work:

1. Should we add source_position as a required extraction field? Currently proposed as optional in Phase 1. Making it required means every extraction includes section-aware position, which helps with hypothesis/finding disambiguation in academic papers. But it depends on the parsed document providing section labels consistently. Recommendation: start optional, require it if Phase 2 calibration shows position would have resolved confusions.

2. What's the threshold for creating a new schema vs. extending an existing one? If we ingest a new document type (e.g., podcast_transcript), should it get its own schema or use the closest existing one? Recommendation: start by mapping to the closest existing schema, and only create a new schema if calibration shows ≥30% of concepts don't fit any existing type cleanly.

---

8. What This Plan Does NOT Change

To be explicit about stability:

• 7 source types — keeping all 7 (book, academic_paper, article, technical_document, instruction_manual, legal_document, fiction)
• 7 schemas — keeping the one-schema-per-source-type architecture
• 7 coherence relationship types — not touched by this plan
• Pipeline architecture — parse → structure → summarize → classify → extract → index → coherence is preserved
• Chroma collections — ingested_concepts, knowledge_base, agent_memory structure preserved (Gitea #38 may address this separately)
• Type counts — staying at 6-7 types per schema (one rename, no additions or removals in Phase 1)

---

9. References

• Rosch, E. (1978). Principles of Categorization. — Basic-level categories, prototypicality, cognitive economy
• Gozli, D. (2023). On the Relative Nature of Categories. — Sense vs. choice categories, deviations from basic-level
• NNGroup / Taxon.dev — MECE taxonomy design, 10-step process, consistent labels
• Semantic Arts — 8 ontology design schools, modular design, scope definition
• Visser, S. et al. (2021). Argument Scheme Annotation. — Inter-annotator agreement, Walton's 60 schemes, Wagemans' Periodic Table, decision tree heuristics
• LandingAI (2025). LLM Extraction Schema Design. — Descriptive field names, document-mirroring, data type specificity
• Mammen, J. — Sense vs. choice categories (as discussed in Gozli 2023)
• Wagemans, J. — Periodic Table of Arguments (36 types, factorial typology)

---

Appendix A: Quick-Reference — Changes Summary

What	Current	Proposed	Phase
book.contradiction	contradiction	Rename to counterargument	1
instruction_manual default	tip	Change to step	1
Type descriptions	1-sentence label	Structured spec (long desc + cues + disambiguation + examples + priority)	1
Schema scope	Implicit (schema name)	Explicit scope field	1
Extractor prompt	Type list only	Type list + binary decision tree for ambiguous schemas	1
Prompt assembly	Not specified	Explicit field ordering and token budget guidance (§4.4)	1
Concept metadata	Current fields	Add source_position (optional)	1
Legacy data migration	Not addressed	Bulk-update contradiction → counterargument in Chroma	1
Validation infrastructure	None	Calibration dataset + comparison script + baseline metrics	2
Quality target	Not measured	≥85% type agreement vs. hand labels	3
Diagnostic metadata	Not applicable	extraction_rationale, adjacent_type_score — only if calibration reveals need	4

Appendix B: Example Enhanced Type Spec — book.claim

claim:
  label: "Claim"
  short_description: "The author's own assertion, thesis, or position"
  long_description: |
    A declarative statement that the author argues for, defends, or puts forward as true.
    This is the author's voice making a substantive case. Claims are the primary knowledge
    atoms in non-fiction — they are what a reader would quote or reference when discussing
    the book's arguments.
  linguistic_cues:
    - "I argue that..."
    - "The evidence shows..."
    - "It is clear that..."
    - "We will see that..."
    - "The key insight is..."
    - Declarative sentences in the author's voice that assert something as true
  disambiguation:
    - "NOT a definition of a term (use 'definition' — definitions explain what something means, claims assert that something is true)"
    - "NOT a cited external fact (use 'evidence' — claims are the author's own, evidence is borrowed)"
    - "NOT a challenge to a specific alternative (use 'counterargument' — counterarguments explicitly target another view)"
    - "NOT a prescriptive rule or guideline (use 'principle' — principles tell you what to do or what generally applies, claims describe what is true)"
  prototypical_examples:
    - "System 1 operates automatically and quickly with little or no effort and no sense of voluntary control."
    - "The planning fallacy describes a tendency for people to underestimate the time, costs, and risks of future actions."
    - "Expert intuition is more reliable than we think, but only in environments with regular feedback."
  priority: 1