llm-ingestion-pipeline-secu.../docs
Kjell Tore Guttormsen 4a9cfd2bbe docs: reframe novelty claim to composite write-time contract (review MAJOR #3)
Replace the unverified/absolute novelty statement with the defensible
four-part-contract form, verified against a focused adversarial PyPI+GitHub
survey (2026-07-15):

- BRIEF §11: 'assumed, not verified' -> verified survey with sources. Names
  aig-guardian (real, query-time; blurs only the minimal-dep-library
  differentiator), GuardLLM (nearest neighbour, runtime hardening, no
  scan-before-persist / capability isolation / fail-secure), and ipi-scanner
  (orphaned placeholder repo, recorded for honesty not as prior art).
- README: differentiator moved from 'library vs hosted/model' to the full
  four-part write-time contract.
- PLAN §27-31: drop the unverifiable 'the first' superlative.

Also promotes the v1.0 session plan (PLAN-v1.md) and the cross-model review
(review-2026-07.md) into docs/ on the open/ mirror, referenced by PLAN.md's
re-sequencing addendum.
2026-07-15 09:22:38 +02:00
..
BRIEF.md docs: reframe novelty claim to composite write-time contract (review MAJOR #3) 2026-07-15 09:22:38 +02:00
OKF-INGESTION-BRIEF.md docs(okf): capture OKF-ingestion security brief as v0.2 future work 2026-07-06 07:07:09 +02:00
PLAN-v1.md docs: reframe novelty claim to composite write-time contract (review MAJOR #3) 2026-07-15 09:22:38 +02:00
PLAN.md docs: reframe novelty claim to composite write-time contract (review MAJOR #3) 2026-07-15 09:22:38 +02:00
review-2026-07.md docs: reframe novelty claim to composite write-time contract (review MAJOR #3) 2026-07-15 09:22:38 +02:00