weichen
1c25d65ae9
Why: The U1 controlled trial finished; its fixtures, validator, runner, per-run results, report, and renderer spike must be reviewable from the task branch, and the task card needs the final PASS/FAIL record. Evidence: results/summary.json + report.md (SELF, MiniMax official channel, CNY 3 of 200 cap); make evidence receipts for precheck, task-sync, and make test follow in this branch. Impact: Task-scoped experiment artifacts only (.task/genui-u1/); no production code changes. Refs: Documents PR #62 (proposal r2); task card feature/generative-ui-u1
98 lines
1.9 KiB
JSON
98 lines
1.9 KiB
JSON
{
|
|
"B": {
|
|
"arm": "B",
|
|
"tasks": 30,
|
|
"calls": 30,
|
|
"prompt_tok": 13565,
|
|
"completion_tok": 41000,
|
|
"cached_tok": 3456,
|
|
"cost_cny": 0.38,
|
|
"wall_s": 457.3,
|
|
"cost_cny_per_task": 0.013,
|
|
"markdown_pipe_table_on_compare": "3/3"
|
|
},
|
|
"G": {
|
|
"arm": "G",
|
|
"tasks": 30,
|
|
"calls": 42,
|
|
"prompt_tok": 43717,
|
|
"completion_tok": 220981,
|
|
"cached_tok": 16391,
|
|
"cost_cny": 2.0,
|
|
"wall_s": 1766.1,
|
|
"cost_cny_per_task": 0.067,
|
|
"valid_first": "18/30 (60%)",
|
|
"valid_final": "25/30 (83%)",
|
|
"repaired": 12,
|
|
"structure_fit": 0.66,
|
|
"source_coverage": 0.87,
|
|
"ids_provided_tasks": 25
|
|
},
|
|
"G-hs": {
|
|
"arm": "G-hs",
|
|
"tasks": 10,
|
|
"calls": 20,
|
|
"prompt_tok": 18210,
|
|
"completion_tok": 24477,
|
|
"cached_tok": 12897,
|
|
"cost_cny": 0.5,
|
|
"wall_s": 370.9,
|
|
"cost_cny_per_task": 0.05,
|
|
"valid_first": "0/10 (0%)",
|
|
"valid_final": "2/10 (20%)",
|
|
"repaired": 10,
|
|
"structure_fit": 0.89,
|
|
"source_coverage": 0.25,
|
|
"ids_provided_tasks": 2
|
|
},
|
|
"r1_divergence": [
|
|
{
|
|
"group": "facts-A",
|
|
"pair": "rc-01~rc-02",
|
|
"jaccard": 0.44,
|
|
"primary": "section|section",
|
|
"distinct": true
|
|
},
|
|
{
|
|
"group": "facts-A",
|
|
"pair": "rc-01~rc-03",
|
|
"jaccard": 0.17,
|
|
"primary": "section|markdown",
|
|
"distinct": true
|
|
},
|
|
{
|
|
"group": "facts-A",
|
|
"pair": "rc-02~rc-03",
|
|
"jaccard": 0.32,
|
|
"primary": "section|markdown",
|
|
"distinct": true
|
|
},
|
|
{
|
|
"group": "facts-B",
|
|
"pair": "rc-07~rc-08",
|
|
"jaccard": 0.26,
|
|
"primary": "section|section",
|
|
"distinct": true
|
|
},
|
|
{
|
|
"group": "facts-B",
|
|
"pair": "rc-07~rc-09",
|
|
"jaccard": 0.5,
|
|
"primary": "section|section",
|
|
"distinct": true
|
|
},
|
|
{
|
|
"group": "facts-B",
|
|
"pair": "rc-08~rc-09",
|
|
"jaccard": 0.45,
|
|
"primary": "section|section",
|
|
"distinct": true
|
|
}
|
|
],
|
|
"r1_distinct_pairs": "6/6",
|
|
"G_structure_fit_by_family": {
|
|
"research-compare": 0.54,
|
|
"requirement-input": 0.88,
|
|
"task-overview": 0.58
|
|
}
|
|
} |