fund_rfid_data/.gitignore
Florian Herzog 09798eb27a Add LLM grounding pipeline: current-source fetch, alias + LLM role-check matching
Ensures text<->gold agreement for the text->triple dataset:
- fetch: newest full prospectus book + later 497 supplements (time-aligned with
  the current N-CEN gold; fixes stale 'largest book' picking 2-5yr-old filings)
- grounding: fast alias matcher (name present, variant-tolerant) AND an LLM
  role-check (llm_extract.py match mode, via local Ollama or remote vLLM server)
  that verifies the entity plays that ROLE -- catches right-name/wrong-role cases
  a lexical matcher over-keeps. Validated with a strong model; ~93% of gold names
  are present once granularity+currency are fixed.
- llm_extract.py: extract (baseline) + match (grounding) modes, sliding-window
  with retrieval pre-filter, claim dedup, retry, ollama/vllm backends
- build_rdf_dataset.py: --grounding alias|llm|name|context|none, whole-trust
  samples now filtered, MIN_PROSE stub guard

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-09 13:45:32 +02:00

47 lines
918 B
Plaintext

# ---- Large / derived data (reproducible via build_rdf_dataset.py) ----
# Raw prospectus prose fetched from EDGAR (GBs)
data/rdf_poc/prose/
# Generated training samples and splits (embed raw SEC text, 100s of MB)
data/rdf_poc/samples.jsonl
data/rdf_poc/samples_full.jsonl
data/rdf_poc/train.jsonl
data/rdf_poc/val.jsonl
data/rdf_poc/test.jsonl
# LLM match inputs/outputs (embed raw text / large)
data/rdf_poc/match_input.jsonl
data/rdf_poc/match_all.jsonl
# diagnostic / scratch files
data/rdf_poc/_*.jsonl
# prose backups from iterative fetch-strategy changes
data/rdf_poc/prose_*_bak/
# Raw SEC bulk downloads (re-downloadable from sec.gov)
data/ncen/
data/nport/
data/xbrl_rr/
# SQLite working DB
fund_data.db
fund_data.db-shm
fund_data.db-wal
# Archives
*.zip
# Python
__pycache__/
*.pyc
*.pyo
# LaTeX build artifacts
*.aux
*.log
*.out
*.toc
*.fls
*.fdb_latexmk
*.synctex.gz
# OS / editor
.DS_Store
.claude/