coulomb/frontend-patterns
5
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Close local review loose ends and record blocked workplan gates

Browse source 
Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0e241-8285-7a63-8c0c-51c9cb824dc3
This commit is contained in:
tegwick 2026-09-27 17:20:43 +02:00
parent bcdb02323c
commit 7295172f1e
20 changed files with 510 additions and 95 deletions
Download patch file Download diff file Expand all files Collapse all files

6
research/evolution/README.md
View file

@ -36,6 +36,10 @@ The baseline is an author-model metadata assessment; no independent human review
implied. `assessed_at` does not reset `last_substantive_review_date`: the latter is
unknown until the evidence review's date and scope have been reconciled. Open limits
include counterexamples and contexts still untested. Supersession is explicit.
Current profiles require `substantive_review_ref` and `substantive_review_scope` for
a known substantive date. The [reconciliation](../reviews/ReviewDateReconciliation.md)
records original evidence-review dates; a synthesis or metadata refresh does not
renew them. Historical snapshots retain their original schema-v1 assessments.
## Closing a bounded cycle
@ -73,7 +77,7 @@ Snapshot creation pins committed candidate content and refuses to overwrite a fi
| Dimension | Observation to collect | Current limit |
| --- | --- | --- |
| Applicability | Reviewed decisions and failure contexts across the ten validation cases | Four synthetic/provisional walkthroughs; six planned |
| Trustworthiness | Scoped evidence, independent full-contract uses, unresolved contradictions, provenance and review age | Independent recurrence and substantive-review ages unassessed |
| Trustworthiness | Scoped evidence, independent full-contract uses, unresolved contradictions, provenance and review age | Independent recurrence unassessed; dated evidence-review provenance reconciled |
| Usefulness | Constraint misses, unsupported recommendations, decision quality and time against equivalent prose | Frozen small model-reviewed pilot; human gate open |
| Coherence | Ambiguous selections, redundant candidates and unjustified relations found/resolved in reviews | No measured baseline; reconciliation/copy overlap remains open |
| Maintainability | Reference checks, overdue review obligations, remaining gaps and effort per revision | Local links/hash checks automated; age/backlog estimates not yet measured |