User Tools

Site Tools


provenance:design:website_classification

Old Revisions

These are the older revisons of the current document. To revert to an old revision, select it from below, click Edit this page and save it.

  • 2026/09/21 14:40 provenance:design:website_classification – Review follow-ups: 12.8's 'task item exists' bullet closed by 12.14, and 12.14's page-sweep claim corrected (provenance:statistics:annotation carries the raw string, not a fold row). Authored by Claude karel.kubicek.claude +421 B (current)
  • 2026/09/21 14:34 Show differences to current revisions provenance:design:website_classification – LLM model-family fold extended as a rule (space/decimal after GPT, o-series): 12.5a re-derived from report_llm_currency.mjs, 12.9 output block regenerated, new 12.14. Authored by Claude karel.kubicek.claude +6.3 KB
  • 2026/09/21 13:45 Show differences to current revisions provenance:design:website_classification – Quote-check refresh 2026-09-21: regenerated llm_currency_quotecheck output block; 6 FAIL -> 6 rescued from the PDF, 0 fail in both renderings. Authored by Claude karel.kubicek.claude +3.1 KB
  • 2026/09/17 07:23 Show differences to current revisions provenance:design:website_classification – Markup rendering sweep: wrap escapes, CLI flag typography, and heading quotes. Authored by Claude. karel.kubicek.claude +378 B
  • 2026/09/03 22:35 Show differences to current revisions provenance:design:website_classification – Record in section 12.12 finding 4 that the resolvable-model figure was propagated twice (20.3% then 19.4%). Authored by Claude karel.kubicek.claude +210 B
  • 2026/09/03 22:35 Show differences to current revisions provenance:design:website_classification – Add section 12.13 (re-review of the figures): the reproducibility buckets were counting models a paper only compared against (A+B 36/20.3% -> 34/19.4%), the twelve-paper curated-database enumeration named eleven, and the targetDetail probe's \bpage\b miss karel.kubicek.claude +6.4 KB
  • 2026/09/03 22:17 Show differences to current revisions provenance:design:website_classification – Add sections 12.1-12.12: LLM-classification currency, 2026-09-03. Every query with its denominator, the decision to lead the LLM section with corpus evidence rather than the preprint, the retraction of the curated-database 'open sources returning' reading karel.kubicek.claude +114.1 KB
  • 2026/08/12 10:07 Show differences to current revisions provenance:design:website_classification – Add section 10: the Fable review pass, the windowed-guard defect it exposed (29 corpus figures stale outside the audited heading window across six pages), the hardened check_page_numbers.mjs, and the page-specific fixes. Authored by Claude. karel.kubicek.claude +2.2 KB
  • 2026/08/12 09:42 Show differences to current revisions provenance:design:website_classification – Create provenance page for design:website_classification: the 424 -> 330 population narrowing, the resource fold's 20 -> 40 -> 33 residue and what was deliberately left, two report-script bugs, all five new LLM website-category quotes verified, and the 4, karel.kubicek.claude +17.8 KB
provenance/design/website_classification.txt · Last modified: by karel.kubicek.claude