Faza 0 pilot: rebuild activities.db from 5-file extraction

Browse Source

61 chunks × LLM subagent extraction yielded 1780 raw activities;
build_database dedup + hallucination check yielded 1732 in DB.

Pilot metrics vs plan acceptance thresholds:
- hallucinated drops      : 19/1780 = 1.07%  (threshold ≤ 2%)
- schema-rejected files   : 0/61              (threshold ≥ 0.9 valid)
- chunks needing re-extract: 13/61 (paraphrased excerpts 75-90/100)
- % with rules            : 99.9%
- extraction_confidence high: 1712/1732 = 98.8%

OCR decision: NOT NEEDED. The Cartea_Mare scanned-PDF candidate
extracted 151 pages / 38k words of real text via pdfplumber alone.

Pilot files:
- 1000 Fantastic Scout Games (EN, 278pg, 18 chunks → 946 activities)
- dragon.sleepdeprived.ca/games mirror (EN, 498pg, 31 chunks → 531)
- Cartea Mare a Jocurilor (RO, 151pg, 10 chunks → 284)
- Activităţi şi jocuri ... .doc (RO, 7pg, 1 chunk → 19, needs_review)
- Amazing Race templates zip (graphics only, 0 activities — expected)

The old activities.db was backed up to .bak before atomic swap.
tests/ still green (71 passed).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

Claude Agent

2026-05-20 07:43:42 +00:00

parent 66ae831c36

commit 3d9f266696

1 changed files with 0 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

data/activities.db

Binary file not shown.