dsrh-paper-reader

DSRH PaperReader

Use this skill to analyze a born-digital research paper. Keep every important technical statement traceable to evidence returned by the DSRH paper tools.

Procedure

1. Ingest the PDF with mcp__dsrh-science__dsrh_paper_ingest. Do not claim success if the result reports degraded or metadata-only mode.
2. Inspect metadata and the section tree before reading. Read abstract, introduction, methods, experiments, ablations, results, limitations, and references when present.
3. Search for the method name, datasets, baselines, metrics, training details, and limitation language. Retrieve exact evidence records for material claims.
4. Inspect extracted figure and table metadata. Explain only what captions and nearby evidence support; do not infer unseen visual content.
5. Build an evidence map before synthesis. Distinguish Reported by authors, Author interpretation, and DSRH inference in the report.
6. Report missing, ambiguous, malformed, or scan-only content explicitly. Never invent experiments, datasets, equations, metrics, ablations, or conclusions.

Output

Cover research problem, motivation, contributions, method, architecture, modules, equations, training, datasets, metrics, baselines, results, ablations, figures, limitations, reproducibility, follow-up opportunities, and an evidence map. Omit a section only when the paper lacks the information, and state that absence.

For core facts, cite evidence ids in brackets, for example [paper_ab12cd34:p006:s03:c014]. Use the policy and report schema in references/evidence-policy.md and references/paper-analysis-schema.md.