paper-trail-acquire
Troisième passe du pipeline cible refondu. Lance la cascade PDF (10 sources : Crossref OA + arXiv + OpenAlex + Unpaywall + HAL + CORE + éditeur par DOI +…
Ingest the citations of one SOTA into the registry. Extracts bibliographic sections, parses citations via the citation-parser sub-agent, resolves DOI via Crossref/S2, deduplicates against the registry, creates new candidate refs, and substitutes free-text citations with
$ npx -y skills add roomi-fields/paper-trail --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/paper-trail-ingestContext preview
What this command does when you run it.
Ingest the citations of one SOTA into the registry. Extracts bibliographic sections, parses citations via the citation-parser sub-agent, resolves DOI via Crossref/S2, deduplicates against the registry, creates new candidate refs, and substitutes free-text citations with
description: Ingest the citations of one SOTA into the registry. Extracts bibliographic sections, parses citations via the citation-parser sub-agent, resolves DOI via Crossref/S2, deduplicates against the registry, creates new candidate refs, and substitutes free-text citations with [[wikilinks]]. Required first step to make a legacy SOTA conform to the paper-trail pipeline.
Étape 1 du pipeline cible : convertit un SOTA écrit en texte libre en un SOTA conforme (wikilinks vers refs registre).
/paper-trail:ingest <SOTA-path> # dry-run par défaut /paper-trail:ingest <SOTA-path> --apply # applique
1. **Vérifie git initialisé** dans le vault (sinon refuse — propose `pipeline ingest --init-git` la première fois).
2. **Extrait les sections bibliographiques** :
python3 -m pipeline ingest <SOTA-path> --extract-only
Retourne sur stdout un JSON `[{header, is_excluded, raw_text, ...}]`.
3. **Pour chaque section non exclue**, invoque le sub-agent `citation-parser` :
Agent(subagent_type="citation-parser", prompt=<contenu_section_brut>)
Le sub-agent retourne un JSON `[{author, year, title, doi?, raw, ...}]`.
4. **Consolide** tous les JSON de citations en un seul fichier `/tmp/citations_<sota_stem>.json`.
5. **Lance l'ingestion** :
python3 -m pipeline ingest <SOTA-path> \
--citations-json /tmp/citations_<sota_stem>.json [--apply]Sans `--apply` : montre ce qui serait ingéré (dry-run). Avec `--apply` : commit git auto, crée refs candidates, substitue le texte par `[[wikilinks]]`.
6. **Présente le récap intermédiaire** : N nouvelles refs créées, N réutilisées, N substitutions, N skipped (low confidence), N erreurs.
7. **Sweep automatique des textbooks incomplets** (uniquement si `--apply`) :
python3 -m pipeline resolve-textbooks --list > /tmp/textbook_candidates_<sota_stem>.json
Agent(subagent_type="textbook-resolver",
prompt=<contenu de /tmp/textbook_candidates_<sota_stem>.json>)applique :
python3 -m pipeline resolve-textbooks \
--apply-from /tmp/textbook_decisions_<sota_stem>.jsonrègles documentées (`agents/textbook-resolver.md`) — merge / complete / blocked. Les `blocked` restent visibles via `pipeline doctor`.
8. **Récap final consolidé** : ingestion + sweep textbooks.
9. **Si --apply réussit**, propose à l'utilisateur :
`pipeline run --loop` (étape 2 du pipeline)
"regex-matched headers".
un retry ciblé sur la section qui a échoué.
Anti-hallucination plugin for academic research in Claude Code. Create literature reviews and papers guaranteed without fabricated citations.
Troisième passe du pipeline cible refondu. Lance la cascade PDF (10 sources : Crossref OA + arXiv + OpenAlex + Unpaywall + HAL + CORE + éditeur par DOI +…
Batch audit of every SOTA in the vault. For each SOTA, identifies refs that are page1_validated (technical OK) but not yet sota_cited_confirmed (content…
Per-citation audit of an academic article (LaTeX or Markdown). Produces RECEIPTS.md classifying each citation as VALID/ADJUST/INVALID/UNVERIFIABLE. Optional…
Audit a SOTA's bibliography. Classify each cited ref by validation state. Optional --purge removes citations to retracted refs from the SOTA (with .bak backup).
Acquire PDFs via the 8-source cascade (11 with opt-in extended sources) for a single ref by slug, or a batch filtered by state. Validates page 1 anti-homonymy…
Inspect a single reference in detail (identity, PDF status, acquisition history with verdicts, citation context in vault, state transitions) and decide its…