Track pattern evidence and ongoing language learning
Assistant: codex Assistant-Model: gpt-6-astra Assistant-Session: 01a0cffe-206f-7323-89d3-b20ca4cf4bf9
This commit is contained in:
parent
f273a190f0
commit
b8a03a3bee
16 changed files with 3223 additions and 12 deletions
71
research/evolution/context.json
Normal file
71
research/evolution/context.json
Normal file
|
|
@ -0,0 +1,71 @@
|
|||
{
|
||||
"schema_version": 1,
|
||||
"cases": [
|
||||
{
|
||||
"id": "VC-01",
|
||||
"state": "synthetic draft",
|
||||
"ref": "research/walkthroughs/VC01-TransactionalAdministration.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-02",
|
||||
"state": "synthetic draft",
|
||||
"ref": "research/walkthroughs/VC02-OfflineFieldNotes.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-03",
|
||||
"state": "provisional",
|
||||
"ref": "research/walkthroughs/VC03-ContentPublication.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-04",
|
||||
"state": "planned",
|
||||
"ref": "research/plan/ValidationCases.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-05",
|
||||
"state": "planned",
|
||||
"ref": "research/plan/ValidationCases.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-06",
|
||||
"state": "provisional",
|
||||
"ref": "research/walkthroughs/VC06-MicrofrontendEstate.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-07",
|
||||
"state": "planned",
|
||||
"ref": "research/plan/ValidationCases.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-08",
|
||||
"state": "planned",
|
||||
"ref": "research/plan/ValidationCases.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-09",
|
||||
"state": "planned",
|
||||
"ref": "research/plan/ValidationCases.md"
|
||||
},
|
||||
{
|
||||
"id": "VC-10",
|
||||
"state": "planned",
|
||||
"ref": "research/plan/ValidationCases.md"
|
||||
}
|
||||
],
|
||||
"usefulness": {
|
||||
"named_score": 18,
|
||||
"prose_score": 18,
|
||||
"denominator": 24,
|
||||
"independent_human": false,
|
||||
"decision_time_minutes": null,
|
||||
"ref": "research/evaluations/language-pilot-01/submitted-review-01/adjudication.md",
|
||||
"limit": "One frozen development pilot with submitted model review; six matched briefs. Equal aggregate scores do not establish equivalence. Stable anchors are consumed development cases, not fresh held-out tasks.",
|
||||
"initial_unsupported_claims_each": 2,
|
||||
"adjudicated_unsupported_claim_count": null
|
||||
},
|
||||
"open_work": [
|
||||
"workplans/FEP-WP-0002-seed-language-validation.md",
|
||||
"workplans/FEP-WP-0003-contrasting-schools.md",
|
||||
"workplans/FEP-WP-0006-language-evolution.md"
|
||||
]
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue