board: E-OCR-CTC-SIMPLETEXT-1 + E-OCR-P6-GOLDEN-1 — the CTC correction + P6 golden suite shipped#664
Conversation
…e-anchored 8/8 Co-Authored-By: Claude <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016b33swuXE23hKtqxsHu9p1
…plan complete through P6 Co-Authored-By: Claude <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016b33swuXE23hKtqxsHu9p1
|
Warning Review limit reached
Next review available in: 42 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
What
Board-only (two prepended EPIPHANIES entries; companion to tesseract-rs #20):
E-OCR-CTC-SIMPLETEXT-1— the arc's biggest correctness finding: every recognizer text anchor was decoded withsimple_text=true, but eng.lstm'sO1c111head isNT_SOFTMAX= softmax activation with CTC loss → realSimpleTextOutput()is false. Both sides of every parity diff carried the same wrong flag (unfalsifiable on noise fixtures); the first rendered corpus page exposed it as systematic repeats. Entry carries the full 9-stage live-bisect method (gdb pix dump, argmax fingerprint, production beam params from registers), the fix (Network::simple_text_output()derived from the tree), and the 8/8 re-anchor. Transferable lessons: decode-semantics bugs need TEXT falsifiers; oracle config comments are claims, not facts.E-OCR-P6-GOLDEN-1— P6 shipped (hermetic corpus, tiered harness with the never-blur discipline operationalized, CER report: pages mean 0.0153 vs gt, perf report, CI wiring). The pdf-to-text-ocr-v1 plan is complete through P6. Meta-finding: the corpus paid for itself on first contact.(The branch also carries the earlier
E-OCR-LINEFEED-1entry if #661 merged without it — all three entries are append-only prepends to the same file.)🤖 Generated with Claude Code
https://claude.ai/code/session_016b33swuXE23hKtqxsHu9p1
Generated by Claude Code