StellarCrowandClaude Fable 5.1
439e83a4cb
Second and third rounds on the dossier pipeline, reviewed locally before commit. Retrieval - wayback_pass.py: retries every BLOCKED/DEAD/THIN/ERROR linked source through the Wayback Machine; blocks carry the snapshot date, archive URL and the live verdict. 143 slots retried: 93 fetched, 37 no snapshot, 12 script shells, 1 PDF. - fetch_sources.py: fetch_wayback() helper. - add_extra_sources.py: files staged extra_* finds (web search, not on the DB record) into the store with a provenance note. - Cases re-sourced by web search: 248 (Oslo: Document.no, Avisa Oslo, NRK; the linked Le Parisien piece is case 242 and is marked OFF-CASE), 258 Kharkiv, 260 Singapore, 358 Bangkok, 365 Las Vegas, 388 Verneuil-sur-Seine, 390 Zoersel, 430 Homestead. 341 of 364 cases now hold a fetched article; 11, 66 and 399 have no public text source (podcast, police video, direct victim report). Trimming - auto_trim.py: case-anchored furniture cut for UNTRIMMED blocks. Finds the body run that mentions the case, merges across subheadings and short furniture gaps, drops teasers, share bars, date/URL/caption lines and subscription pitches; refuses pages with no record term or almost no body. 302 blocks trimmed; 16 left on auto-trim-review.md (7 OFF-CASE suspects). Every cut is labelled AUTO-TRIMMED, UNREVIEWED in the dossier; the full extract stays in staging/. Decisions with anchors in trim-decisions-auto.json. - build_cases.py / verify_all.py: banners for auto-trimmed and archived blocks, staged-file check extended to Wayback blocks, flag legend under the record. Detention rule - README "Definitions": the DB field `kidnappings` is the DETENTION violence type (victim, guard, staff or relative held to force submission or execute the theft), distinct from the Kidnapping scenario (taken away and held). - detention-flag-review.md / detention-flag-corrections.json: 40 records reviewed with evidence; 30 set-to-1 proposals accepted by the owner on 2026-09-06 (listed in corrections-approved.md), 10 still open. - apply_detention_wording.py: "Violence Used" in the 70 reviewed summaries now names detention explicitly (62 of 70 labelled), supported by the summary's own text; idempotent; supersedes the batch scripts' wording. Worklist and docs - sofia-worklist.md: 248 decisions, detention rule item replacing the old "no abduction" item, fresh-search section for the textless cases. - README-START-HERE.md: progress notes, run commands, next steps. - Bug fixed in passing: Wayback blocks stored in-memory text with carriage returns; now stored as read back from disk. verify_all.py PASSES (2321 checks). Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01GZZENdTLzNGsbNy4DyF1yt
1.4 KiB
1.4 KiB
Auto-trim review list
Three kinds of entry. TOO SMALL blocks were left UNTRIMMED because the trimmer found almost no body text on a large page. OFF-CASE? blocks were left UNTRIMMED because no term from the record appears on the page; the linked URL may be the wrong source. WEAK blocks were trimmed but on one or two hits only, usually because the record is thin; confirm the page is about this case. The full extract stays in staging/ either way.
- case 258
extra_1Ukrinform: WEAK anchor: trimmed on only 1 case-term hit(s); confirm the page is about this case https://www.ukrinform.ua/rubric-regions/4048428-trimali-colovika-u-pidvali-j-vidibrali-97-tisac-u-harkovi-zatrimali-troh-vikradaciv.html - case 258
extra_2Hromadske Radio: WEAK anchor: trimmed on only 1 case-term hit(s); confirm the page is about this case https://hromadske.radio/news/2025/10/17/v-tsentri-kharkova-troie-napadnykiv-vykraly-cholovika-y-vidibraly-u-noho-mayzhe-100-tysiach-dolariv - case 258
extra_4ATN: WEAK anchor: trimmed on only 1 case-term hit(s); confirm the page is about this case https://atn.ua/kharkiv/kharkiv-ianyna-trymaly-v-pidvali-ta-vybyvaly-hroshi-sered-napadnykiv-vijskovyj-490170 - case 390
extra_2NNieuws: WEAK anchor: trimmed on only 2 case-term hit(s); confirm the page is about this case https://nnieuws.be/artikel/inbraak-met-geweld-zoersel-vrouw-van-60-vastgebonden-eigen-huis