Research Assistant
147f5b77e1
docs: add convergence architecture spec/plans and dense-parent hardening spec/plan
2026-06-23 14:29:18 +08:00
Research Assistant
fb28eca1fe
fix: converge figure ownership arbitration and add VFS8CBW2 dense-composite diagnostics
2026-06-23 02:42:22 +08:00
Research Assistant
224882f697
fix: govern local figure pairing and ownership fallbacks
2026-06-22 22:15:39 +08:00
Research Assistant
410151ea8e
fix: reuse rebuild metadata and object extraction work
2026-06-22 22:15:25 +08:00
Research Assistant
5bbe40d08b
fix: reject weak isolated layout clusters
2026-06-22 22:15:12 +08:00
Research Assistant
6522dc9aef
docs: update PROJECT-MANAGEMENT with 2HEUD5P9 rebuild findings
2026-06-22 02:50:37 +08:00
Research Assistant
db69961c7c
feat: convert body-zone footnotes with distinct font to callout
2026-06-22 01:51:10 +08:00
Research Assistant
69f6a82b52
docs: update PROJECT-MANAGEMENT with figure merge refactor + heading/backmatter fixes + cover page plan
2026-06-22 01:44:52 +08:00
Research Assistant
4cd0cf3d54
fix: heading detection, backmatter, table consumed, footnote reorder, figure crop + audit fixtures
2026-06-22 01:28:55 +08:00
Research Assistant
da2e018b19
feat: figure merge clustering spec + fixes for caption dedup and structural gate
...
- Add global-distance-clustering figure merge design spec
- Fix ocr_roles.py: body_zone body_paragraph no longer promoted to
figure_caption_candidate (prevents body mentions from entering legend pipeline)
- Fix ocr_document.py: preserve subsection_heading, reference_item,
table_caption from structural-gate demotion
- Update PROJECT-MANAGEMENT.md with edge-case analysis
- Add ocr-vision-audit-master.md for CODE vs VISION separation
- Update SKILL.md dispatch rules with trust boundaries
2026-06-21 21:32:30 +08:00
Research Assistant
70a7978de8
feat: complete OCR-v2 readiness gates + blind audit validation
...
- Gate 1: completeness signals for page text coverage
- Gate 2: DW figure ownership generalization with strict regression
- Gate 3: reference boundary enforcement from structure
- Gate 4: layout coverage taxonomy in audit/coverage_ledger.json
- diff_audit.py: canonical role alias mapping + auto-normalize truth_role
- ocr_structural_gate.py: table caption text-evidence fallback
- ocr-canonical-roles.md: canonical role list for audit workflow
- ocr-truth-audit.md: pre-flight checklist enforces canonical roles
- Blind audit: 5 unseen papers across domains, all PASS with coverage
2026-06-19 00:35:21 +08:00
Research Assistant
7e0b69b3ff
docs: add OCR real-paper regression design
2026-06-14 21:13:39 +08:00
Research Assistant
123234b93b
docs: add OCR-v2 closure gap remediation plan
2026-06-14 11:41:05 +08:00
Research Assistant
711bb3c86a
docs: add OCR real-paper regression harness implementation plan
2026-06-13 15:22:45 +08:00
Research Assistant
c65ff39c4d
docs: add fixture layout, debug bundle, segment-order, and consumption refinements
2026-06-13 15:20:17 +08:00
Research Assistant
9cb8fb7b04
docs: apply 6 spec refinements for agent execution readiness
2026-06-13 15:16:54 +08:00
Research Assistant
df82820e66
docs: add consumption assertion field to fixture schema
2026-06-13 15:11:45 +08:00
Research Assistant
da00c083e6
docs: add audited OCR-v2 failure families
2026-06-13 15:04:02 +08:00
Research Assistant
e1ecf125ce
docs: add OCR production-path regression design
2026-06-13 14:40:15 +08:00
Research Assistant
d9f76917e9
style: ruff format after OCR role gate implementation
2026-06-12 15:11:33 +08:00
Research Assistant
03e3966183
docs: document OCR structural role gate
2026-06-12 15:09:59 +08:00
Research Assistant
eb3b73ae78
docs: prune superseded OCR worktree plans
2026-06-09 12:55:05 +08:00
Research Assistant
b33ac572e4
docs: add real-paper audit report — pre-proof, author matching, inner text, ambiguous figures
2026-06-08 18:47:26 +08:00
Research Assistant
0aab860cf2
feat: OCR risk convergence — scored figure/table matching, layout confidence, insert scorer, health uncertainty metrics
...
- Figure matching: nearest-asset → scored multi-candidate selection with ambiguous state
- Table matching: vertical-nearest → score-based selection with prev/next page window
- Layout confidence: PageLayoutProfile gains confidence/evidence; eligible-body block filter
- Tail reorder: guarded by layout + tail confidence (low confidence preserves raw order)
- Structured insert: direct promotion → scorer + candidate + fallback state
- Health: adds 14 uncertainty metrics (ambiguous matches, unresolved clusters, forced inserts, low tail confidence)
- Audit: docs/ocr/high-risk-rule-audit.md documents 8 hard-rule decisions mapped to plans
- Spec + 6 implementation plans for agentic execution
2026-06-08 13:43:48 +08:00
Research Assistant
acd28d321e
test: make OCR real-paper regressions reproducible
2026-06-08 12:13:11 +08:00
Research Assistant
a3c8dab389
docs: audit OCR production route and mark experimental modules
2026-06-08 12:13:07 +08:00
Research Assistant
c974ba7480
fix: remove open-ended authors text heuristics, anchor to page-1 zone only
2026-06-06 13:28:46 +08:00
Research Assistant
43087401c1
docs: mark completed tasks in document analysis plan, keep only delta tasks
2026-06-06 12:23:08 +08:00
Research Assistant
687332d126
docs: correct span_metadata source to PDF (not PaddleOCR), revise plan
2026-06-06 11:42:14 +08:00
Research Assistant
bdb3eae8ac
docs: add unified span metadata spec and integration plan
2026-06-06 11:06:39 +08:00
Research Assistant
7c278fbc60
fix(ocr): properly cluster multi-panel figures — role assignment, cluster bbox crop, render visibility
2026-06-06 10:08:42 +08:00
Research Assistant
c235dbdc68
feat(ocr): journal layout generalization, OCR diagnostics, and debug scripts
2026-06-06 00:46:49 +08:00
Research Assistant
f9b5fb0541
feat(ocr): journal layout generalization — structured boundary, container regime, legend validation
...
- Task 1: TailBoundary namedtuple with body_end/backmatter_start/references_start
- Task 2: _classify_backmatter_form — 'container' (PeerJ) vs 'flat' (Frontiers) regime
- Task 3: _attach_container_bodies, _container_child flag for ### child headings
- Task 4: Style-family classification already complete
- Task 6: _is_formal_legend threshold raised to 100, more axis_words added,
low-confidence fallback with legend_uncertain flag for rejected captions
- 2GN9LMCW: authors correct, furniture suppressed, heading hierarchy,
container child headings, Figure 4 uncertain
- 7C8829BD: 26/26 markers, correct tail order, no regression
- 296/296 tests pass
2026-06-05 23:48:56 +08:00
Research Assistant
d52ea37e92
feat(ocr): tail regime remediation + style-aware heading profiles + boundary detection
...
- Task: Bidirectional body/backmatter boundary detection (forward/backward spine + tail spread reconciliation)
- Task: Style-aware heading profiles from PDF span_metadata (extract, cluster, disambiguate)
- Task: Lock tests for tail-candidate overreach, cross-page continuation, style-aware heading detection
- 296/296 tests pass, real-paper 7C8829BD verified
2026-06-05 22:47:13 +08:00
Research Assistant
1779b8b0ff
docs: add legacy OCR backfill and sync integration plan
2026-06-05 12:49:01 +08:00
Research Assistant
5f31d2924f
docs: add OCR phase4.1 cleanup and phase5 plan
2026-06-05 12:00:22 +08:00
Research Assistant
f3fe86038e
docs: add OCR structured pipeline phase4 plan
2026-06-05 10:56:54 +08:00
Research Assistant
1963a091fc
docs: add OCR structured pipeline phase3 plan
2026-06-05 01:01:50 +08:00
Research Assistant
cca983d517
docs: add OCR structured pipeline phase2 plan
2026-06-04 23:44:12 +08:00
Research Assistant
feb6129cd2
docs: add OCR structured pipeline phase1 plan
2026-06-04 22:49:01 +08:00
Research Assistant
bef8360cbd
docs: add OCR structured pipeline design spec
2026-06-04 22:41:52 +08:00
Research Assistant
2ab524aecf
feat: ocr reading-order fixes, single-source fulltext, redo closed-loop, release notes & manual
2026-06-01 18:12:31 +08:00
Research Assistant
5abdd51ca7
docs: describe layered OCR reading-order pipeline
2026-06-01 00:02:45 +08:00
Research Assistant
03ad9ce64f
feat: stabilize paperforge query planning
2026-05-27 21:20:15 +08:00
Research Assistant
3619fe264f
Revert "test: clean up brittle and low-value tests"
...
This reverts commit 5ad9a54a66
2026-05-24 19:59:24 +08:00
Research Assistant
5ad9a54a66
test: clean up brittle and low-value tests
...
- Remove 4 broken Python test files (ld_deep x3, path_normalization)
- Fix 2 vector_db tests to use correct mock target (get_collection)
- Remove 2 JS test files (settings-panels, vector-ready — trivial)
- Trim 3 buildRuntimeInstallCommand tests from errors.test.ts
- Narrow CI unit-tests to only run tests/unit/ (gate-level)
2026-05-24 19:59:14 +08:00
Research Assistant
51e78676e9
chore(plugin): finalize TS migration -- delete legacy testable.js
2026-05-24 17:33:22 +08:00
Research Assistant
1b0aecf48e
docs: add pdf annotation layer design spec and implementation plan
2026-05-20 15:33:13 +08:00
Research Assistant
cc5fa0658f
fix: add return type annotation to main() and indent=2 to early-exit json.dump calls
2026-05-19 14:41:06 +08:00
Research Assistant
19c28a8b91
chore: commit session work before hotfix switch
2026-05-18 22:47:30 +08:00
