csag-extractionlisted

# CSAG extraction skill ## Goal Convert a manuscript into a **CSAG `PaperExtraction`** instance that is: - **Schema-valid** (LinkML: `assets/csag.yaml`) - **Evidence-grounded** (TextSpans for key objects) - **Canonical** (support/refute only via `EvidenceLink`, chains via `InferenceStep`) - **Conditional** (every Assertion has ≥1 Context) ## Files in this skill - `assets/csag.yaml` — authoritative schema - `assets/csag_qa_templates.yaml` — QA template catalog - `references/CSAG_PLAYBOOK.md` — detailed extraction guide + edge cases ## Quick Reference | Task | Action | |------|--------| | Extract paper | Build one `PaperExtraction` per manuscript, not per search hit. | | Ground claims | Attach important assertions, evidence, and links to TextSpans. | | Validate schema | Run `scripts/validate_paper_extraction.py` before finalizing. | | Review quality | Run `scripts/csag_quality_report.py --strict` and resolve issues. | ## Non‑negotiable invariants 1) **Every Assertion MUST have ≥1 Context** (schema-enforced). 2) **Support/refute polarity ONLY in `EvidenceLink`**. 3) **Contradictions/qualification ONLY in `AssertionRelation`**. 4) **Reasoning chains ONLY as `InferenceStep`**. 5) Ground important objects to TextSpans. 6) Every Assertion MUST have `normalization_status`: - `raw` / `partially_normalized` / `fully_normalized` ## Extraction scope The extraction scope is the **full manuscript**: title, abstract, introduction, methods, results, discussion, conclusion, and