Files
api/api/services/docling/.gitignore
T
CC WorkerandClaude Opus 4.8 69d9c46abe
api-ci-deploy / test-build-deploy (push) Has been cancelled
feat(docling): B1 image-only OCR eval harness (overwatch-cleaned)
Eval harness for AQA A-level + GCSE-science image-only papers: finalize.py --b1-only,
RapidOCR runner (rapid_pass.py via dsync), GT fixtures (make_b1_gt.py + b1_gt_labels.json),
and fetch_b1_corpus.py to pull the eval corpus from .94 cc.examboards at runtime.

Salvaged from t_15be12ed (which timed out on iteration budget re-running OCR): exam PDFs and
generated OCR caches/reports are NOT committed (third-party copyright + reproducible) — gitignored
and fetched/generated at runtime. Baseline coverage recorded in the task evidence file.

Co-Authored-By: Claude Opus 4.8 <[email protected]>
2026-06-08 03:10:10 +00:00

6 lines
245 B
Plaintext

# B1 image-only eval corpus + pipeline outputs: fetched/generated at runtime, never committed.
# Exam-board PDFs are third-party copyright (served only via signed URLs); results/ are reproducible.
/samples/b1/
/results/b1_rapid/
/results/final/