profile-generate

原文涵盖的主题

• Profile Generate
• How to run
• --fm — foundation-model author/group profiles
• Triggers
• References

Generate Tier-1 PROF-P entity profiles for the corpus's most-cited authors who don't have a profile yet — the bulk profile-induction pass. --fm runs the FM pass (port of buildfmprofiles.py): it reads a corpus-local documentation/profiles/fm-config.yaml and scaffolds PROF-P profiles for the top-N authors of each listed FM paper plus PROF-G group profiles for team-authored releases. The FM-paper list and group specs are corpus data, not built-in: Absent file → no-op. Institutional/team author names are skipped from PROF-P. Dry-run by default. --write creates files; existing profiles are skipped. Ranks REFs by corpus in-degree (citations within the corpus, derived from the citation sidecars), takes each top REF's primary author, and skips institutional/group "authors" (team, labs, foundation, consortium, …) — those get group profiles, not PROF-P. --scan N = how many top-in-degree REFs to consider (default 60); --limit N = max profiles to generate (default 25). Generates a compact 5-section profile (summary, corpus presence, focus, co-author network, notes). affiliation is left blank for manual enrichment; corpus-refs is written as a list of REF-id strings. "generate profiles for top c

这里只展示节选，请以完整原文和当前要求为准。