50 lines
1.6 KiB
JSON
50 lines
1.6 KiB
JSON
|
|
{
|
||
|
|
"milestone": "training-rl",
|
||
|
|
"round": 1,
|
||
|
|
"status": "pass",
|
||
|
|
"assertionsSummary": {
|
||
|
|
"total": 20,
|
||
|
|
"passed": 20,
|
||
|
|
"failed": 0,
|
||
|
|
"blocked": 0
|
||
|
|
},
|
||
|
|
"passedAssertions": [
|
||
|
|
"VAL-TRAIN-001",
|
||
|
|
"VAL-TRAIN-002",
|
||
|
|
"VAL-TRAIN-003",
|
||
|
|
"VAL-TRAIN-004",
|
||
|
|
"VAL-TRAIN-005",
|
||
|
|
"VAL-TRAIN-006",
|
||
|
|
"VAL-TRAIN-007",
|
||
|
|
"VAL-TRAIN-008",
|
||
|
|
"VAL-TRAIN-009",
|
||
|
|
"VAL-ML-003",
|
||
|
|
"VAL-ML-006",
|
||
|
|
"VAL-ML-007",
|
||
|
|
"VAL-ML-008",
|
||
|
|
"VAL-ML-009",
|
||
|
|
"VAL-ML-010",
|
||
|
|
"VAL-ML-011",
|
||
|
|
"VAL-ML-012",
|
||
|
|
"VAL-ML-013",
|
||
|
|
"VAL-ML-014",
|
||
|
|
"VAL-JOY-004"
|
||
|
|
],
|
||
|
|
"failedAssertions": [],
|
||
|
|
"blockedAssertions": [],
|
||
|
|
"appliedUpdates": [],
|
||
|
|
"previousRound": null,
|
||
|
|
"notes": [
|
||
|
|
"VAL-TRAIN-004: Clear Ex sets exampleCount to 0 but retains previous loss value in status. Minor cosmetic issue, core behavior correct.",
|
||
|
|
"VAL-TRAIN-007: Visual preset chips work (calm-to-chaotic → 3 examples, training triggered). Heatmap bars not yet implemented (Milestone 4).",
|
||
|
|
"VAL-ML-006: Validation contract mentions 126 outputs but app defaults to visual mode (20 outputs). Tested with actual mode.",
|
||
|
|
"VAL-ML-012: Spread-aware noise verified: spread=0 gives 8.73 total output change vs spread=1 gives 0.052.",
|
||
|
|
"VAL-ML-014: Undo restores weights exactly (max diff: 0, well within 1e-4 tolerance)."
|
||
|
|
],
|
||
|
|
"flowReports": [
|
||
|
|
".factory/validation/training-rl/user-testing/flows/group1-training-controls.json",
|
||
|
|
".factory/validation/training-rl/user-testing/flows/group2-ml-core.json",
|
||
|
|
".factory/validation/training-rl/user-testing/flows/group3-rl-noise-undo.json"
|
||
|
|
]
|
||
|
|
}
|