27 items under this folder.
P2 Batch 1 Ingest Report Date: 2026-05-12 Tier: P2 — LOQ source candidates (488 handles in manifest) Sub-batches processed: p2-sub1 (50), p2-sub2 (50), p2-sub3 (50), p2-sub4 (50), remaining-group1 (55), remaining-group2 (55), remaining-group3 (55) 1.
P2 Sub-Batch 3 Ingest Report Date: 2026-05-12 Batch: 50 papers listed in P2 sub-batch 3 task 1.
P2 Sub-batch 4 Ingest Report Date: 2026-05-12 Batch: 50 papers from P2 tier Handles: FM_12412015, FM_467049, FM_10005410 through FM_10305879, FM_9965521 1.
P4 Batch 1 Ingest Report Date: 2026-05-12 Tier: P4 — post-2020 peer-reviewed, high-evidence Handles processed: 200 (sorted year-descending, positions 1–200 of 6,571) Groups: 4 parallel agents of 50 handles each 1.
P4 Batch 10 — Ingest Report Date: 2026-05-13 Handles processed: 200 (P4 year-descending, positions 3768–3967; all 2023 cohort) Source pages created: 21 False positives: 178 (89%) Summary Batch 10 spans a uniform 2023 cohort slice (FM_104xx–FM_106xx).
P4 Batch 11 — Ingest Report Date: 2026-05-13 Handles processed: 200 (P4 year-descending, positions 3968–4167; 2023 cohort) Source pages created: 41 False positives: 159 (79.5%) Summary Batch 11 is the highest-yield single batch to date (41 pages), with a false-positive rate of 79.5% — noticeably low...
P4 Batch 12 — Ingest Report (2026-05-13) Positions 4168–4367 of the P4 manifest (year-descending sort).
P4 Batch 13 — Ingest Report (2026-05-13) Positions 4368–4567 of the P4 manifest, sorted by (-year, handle). First handle: FM_9999012 (g1).
P4 Batch 5 — Ingest Report Date: 2026-05-13 Handles processed: 198 (food-matrix-filtered P4, 2025 papers, positions 400–598) Source pages created: 2 False positives / missing from filesystem: 196 Summary Batch 5 reveals a major structural obstacle: a ~400-handle corpus gap spanning roughly FM_124831...
P4 Batch 6 — Ingest Report Date: 2026-05-13 Handles processed: 199 (food-matrix-filtered P4, positions 600–799 in sorted list) Source pages created: 15 False positives: 184 (92%) Summary Batch 6 cleared positions 600–799 of the food-matrix-filtered P4 sorted list, spanning mostly 2025 papers (153) w...
P4 Batch 7 — Ingest Report Date: 2026-05-13 Handles processed: 200 (food-matrix-filtered P4, all 2024, positions 800–999) Source pages created: 16 False positives: 184 (92%) Summary Batch 7 processed the first all-2024 slice (positions 800–999).
P4 Batch 8 — Ingest Report Date: 2026-05-13 Handles processed: 200 (food-matrix-filtered P4, all 2024, positions 1000–1199) Source pages created: 14 False positives: 186 (93%) Summary Batch 8 continues the all-2024 slice.
P4 Batch 9 — Ingest Report Date: 2026-05-13 Handles processed: 200 (P4 year-descending, positions 3287–3767; 4 groups of 50) Source pages created: 20 False positives: 180 (90%) Summary Batch 9 spans the year-transition zone between the 2024 and 2023 cohorts.
Batch Report — P1 Priority Tier Ingest Date: 2026-05-12 Priority tier: P1 (HMT&C Path A concentration candidates) Original manifest P1 count: 46 rows (34 short-form handles + 12 reclassified to P5) Long-name dedup copies skipped: 3 Summary 26 new source pages created.
P4 Batch 2 — Ingest Report Date: 2026-05-12 Handles processed: 200 (FM_12964337 to FM_11848250, P4 tier, year-descending, pre-food-matrix-filter) Source pages created: 7 False positives: 193 (96.5%) Summary P4 batch 2 confirms the pattern discovered in batch 1: the unfiltered P4 year-descending sort...
P4 Batch 3 — Ingest Report Date: 2026-05-12 Handles processed: 200 (food-matrix-filtered P4 tier, year-descending; first use of food-matrix filter) Net new source pages: 2 Duplicates created and removed: 8 False positives: ~190 Summary Batch 3 was the first batch using the food-matrix-filtered P4 ha...
P4 Batch 4 — Ingest Report Date: 2026-05-12 Handles processed: 200 (food-matrix-filtered P4, 2025 papers, positions 200–400 in filtered list) Source pages created: 12 False positives: 188 (94%) Summary Batch 4 is the first batch with meaningful yield from the food-matrix-filtered strategy: 12 source...
Batch report: seasonal and geographic variance ingest — 2026-05-12 Overview Processed 95 PDFs from raw/manual-fetch/seasonal-geographic-variance/ (59 in the main folder, 36 in the auto-fetched/ subfolder).
Tier-1→3→4 Sweep Final Summary (cycles 27-35) This report documents the tier-1→3→4 autonomous-loop sweep that ran from cycle 27 (2026-05-11 fruit-juice mislabel correction) through cycle 35 (final summary).
HMTc Category 5 Beverages — Overnight Final Report — 2026-05-09 (cycles 11-20) This report covers cycles 11-20 of the autonomous /loop, which built out HMTc Category 5 Beverages from scaffold-only state (Step 0 locked architecture only) to the readiness state Karen specified: at-bar where computable...
Heavy Metal Index — Cycles 21-26 Extension Final Summary This report documents the post-cycle-20 extension run (cycles 21-26) triggered by Karen’s directive to (a) continue the re-ingest queue, (b) begin Priority 5, and (c) regenerate the gap report.
Data-Gap Wishlist — 2026-05-09 External candidate papers identified for the HMTc Category 1 data-gap cells via PubMed E-utilities queries.
Infant and Child Foods Overnight Final Report — 2026-05-09 This report covers the day-2 autonomous run under Karen’s overnight Expansion 1 directive (full 16-subcategory Category 1 scope) and Expansion 2 directive (external corpus acquisition via PubMed for data gaps).
Priority 5 — HMTc Product Category Architecture Survey (cycle 23) This report documents the cycle-23 survey of wiki/products/ for HMTc product category architecture beyond Cat 1 (Infant and Child Foods) and Cat 5 (Beverages).
Digest Ingest Final Report — 2026-05-08 This report covers the autonomous-session Digest ingest run from this evening, complementing the parallel agent’s Phase 6 Infant and Child Foods overnight final report.
Infant and Child Foods Overnight Final Report — 2026-05-08 This report consolidates everything produced overnight under Karen’s autonomous-operation directive.
Row-Fit Re-Sweep — 2026-05-08 Read-only Phase 1 sweep across all wiki/products/*.md pages, applying the row-fit determination rule from CLAUDE.md Part 6 (“trust author scope statements; over-hedging row-fit destroys the value of the source evidence inventory”).