frontend-patterns/research/bench/Admission.md
tegwick fc8a7dbb49 Set up source-grounded frontend research workflows with infospace-bench
Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0cffe-206f-7323-89d3-b20ca4cf4bf9
2026-09-24 09:47:22 +02:00

35 lines
2.2 KiB
Markdown

# Admission from experimental artifacts
The runner never writes to `canon/` or `patterns/`. A model critique is evidence
for a reviewer, not approval to promote. FEP-WP-0002-T01 owns the final metadata
contract; this mapping is provisional until that task resolves the open schema issues.
| Experimental representation | Repository representation |
| --- | --- |
| `source/source.md` plus SHA-256 and bibliography | SourceCatalog entry and source-review record |
| Claim C01 scoped by workspace and source | Claim citation: review path + C01 + original locator |
| Candidate P01 scoped by workspace | CandidateCatalog row; reviewed stable FEP ID only upon admission |
| Candidate Definition/Solution sections | PatternSchema prose with reviewed frontmatter |
| Relation proposal between local candidate IDs | Canonical typed relation between stable pattern IDs |
| Generated critique pass/revise/unknown | Input to a named reviewer; not evidence maturity |
For each promotion, write a review under `research/reviews/` with:
- reviewer, date and whether it is a self-review;
- source workspace, digests and source claim locators;
- candidate IDs mapped to existing/new stable FEP IDs, with merge/split/reject reasons;
- checks against the current pattern schema and at least two competing forces;
- known uses and counterexamples, marking missing evidence explicitly;
- relation endpoints, direction and rationale; prerequisites kept distinct;
- evidence maturity, quality constraints and unresolved questions;
- disposition and links to the changed catalog/pattern files and follow-up tasks.
Synthetic fixtures cannot establish known uses or satisfy evidence admission.
Do not infer recurrence from one source. Draft patterns may retain hypothesis
maturity; do not silently raise it because a model gave a favorable critique.
Cross-source patterns should retain all source-specific candidate mappings.
For later bench graph inspection, materialize reviewed candidates as `kind: entity`
artifacts with a Definition section and a preserved canonical ID, and relations as
typed Subject/Predicate/Object artifacts whose endpoints resolve. This graph-export
adapter remains part of FEP-WP-0004; proposal tables are not a graph export.