Skip to content

docs: chunking/OCR re-index lever measured negligible — do not re-index#404

Merged
BigSimmo merged 2 commits into
mainfrom
claude/chunking-ocr-lever-finding
Jul 8, 2026
Merged

docs: chunking/OCR re-index lever measured negligible — do not re-index#404
BigSimmo merged 2 commits into
mainfrom
claude/chunking-ocr-lever-finding

Conversation

@BigSimmo

@BigSimmo BigSimmo commented Jul 8, 2026

Copy link
Copy Markdown
Owner

What

Records the Phase-A offline measurement of the "last high-value retrieval lever"
(table/heading-aware chunking + OCR repair → controlled re-index) so it is not re-litigated.
Docs-only. No code, no migration, no re-index, no spend.

Verdict: negligible / neutral — do not build config-gated chunking and do not re-index for this.

Evidence (live corpus sjrfecxgysukkwxsowpy, read-only, 2026-07-08)

  • noisy_unit_rate is a red herring. It is 1 - visual_units/total_units (a visual-coverage
    metric), saturated at 1.0 for all 1,779 signalled docs because visual_units = 0 corpus-wide
    — not OCR corruption. The "495 docs / dropped-letter" framing was a misread.
  • OCR corruption is negligible across the 111,991 index units: 0 hits for the exact cited
    signature (p ycho, ocial); the space+single-consonant proxy is 3.9% but 82.6% is the
    bullet-"o" glyph
    (cosmetic, words intact); the non-"o" residual excluding dose/dimension tokens
    is 84 units (0.075%), mostly legitimate (2 g IV, x 109/L, type b).
  • Table/heading-aware chunking already exists (detectHeading, isTableBlock/chunkTableBlock
    in src/lib/chunking.ts): section_path on 100% of chunks, well-bounded sizes (p90 1,239, max
    2,700; 0.6% > 2,400) — no run-on flattening. The worst dual-column scrambles are flowcharts that
    text chunking can't fix.
  • Retrieval already strong (content_mrr@10 ≈ 0.90, recall@5 = 1.0) with zero recall headroom;
    coverage ~100%, so a re-index re-embeds ~69k chunks for ~0 expected gain.

Same evidence standard and conclusion as the wrapped-dose-unit non-action (measured 0.03%, not re-indexed).

Changes

  • docs/chunking-ocr-reindex-lever-finding-2026-07-08.md — full finding.
  • docs/reindex-runbook.md — one "Do not do this" pointer at the decision point.

🤖 Generated with Claude Code

Phase-A offline measurement (live corpus, read-only) of the table/heading-aware
chunking + OCR-repair re-index lever. Verdict: negligible/neutral, do not re-index.

- noisy_unit_rate is a saturated visual-coverage metric (1 - visual_units/total_units,
  =1.0 for all 1779 signalled docs because visual_units=0), NOT OCR corruption.
- OCR corruption in the 111,991 index units is negligible: 0 cited-signature hits;
  non-"o" residual (excl. dose/dim tokens) = 84 units (0.075%), mostly legitimate.
- table/heading-aware chunking already exists in chunking.ts; section_path on 100%
  of chunks; chunks well-bounded (p90 1239, max 2700); no run-on flattening.

Same evidence standard as the wrapped-dose-unit non-action (0.03%). Adds a standalone
finding doc + a "Do not do this" pointer in the reindex runbook so it is not re-litigated.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@chatgpt-codex-connector

Copy link
Copy Markdown

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

@supabase

supabase Bot commented Jul 8, 2026

Copy link
Copy Markdown

This pull request has been ignored for the connected project sjrfecxgysukkwxsowpy because there are no changes detected in supabase directory. You can change this behaviour in Project Integrations Settings ↗︎.


Preview Branches by Supabase.
Learn more about Supabase Branching ↗︎.

@BigSimmo
BigSimmo enabled auto-merge (squash) July 8, 2026 14:58
Prettier check failed on the new lever-finding doc; no content changes.

Co-authored-by: Cursor <cursoragent@cursor.com>
@BigSimmo
BigSimmo merged commit 08f1496 into main Jul 8, 2026
6 checks passed
@BigSimmo
BigSimmo deleted the claude/chunking-ocr-lever-finding branch July 9, 2026 12:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant