| Dispatched | Branch | Model | Commit | Pass count | Gate | Cost |
|---|---|---|---|---|---|---|
| 2026-07-08T07:12:56.901Z | claude/eval-cost-estimate-calibration | claude-sonnet-4-6 | d984cd2 | 1/1 across 1 scenarios | pass | $0.0015 |
| 2026-07-07T21:09:02.078Z | main | claude-sonnet-4-6 | 29818b2 | 1/1 across 1 scenarios | pass | $0.0015 |
| 2026-07-07T21:04:52.684Z | main | claude-sonnet-4-6 | 10b443e | 1/1 across 1 scenarios | pass | $0.0015 |
| 2026-07-07T18:09:30.470Z | claude/verify-pr586-eval-report-1u9938 | claude-sonnet-4-6 | 2697a1c | 1/1 across 1 scenarios | pass | $0.0014 |
Main-branch runs only. Watch line marks cost.watch_level_usd.
Open with #compare=<idA>,<idB>.
stats contract — alpha 0.05, one-sided true, paired test sign, multiplicity holm, MDE 84.9999pp, wilson z 1.96
| Scenario | Contract | N | Pass | Wilson CI | Quality | Cost/run | Model abandoned | Outcomes | Gate |
|---|---|---|---|---|---|---|---|---|---|
| 08-first-cycle-bootstrap | cycle_intent | 1 | 1/1 (100.0%) | [20.7%, 100.0%] | cycle_theme_adherence: 1.00 [1.00, 1.00] | $0.0015 | iteration cap: 0 (0.0%) stopped early: 0 (0.0%) |
submitted: 1 |
ok delta: +0.0pp p: 1.000 |
| Scenario | Non-submitted | Rate | By kind |
|---|---|---|---|
| 08-first-cycle-bootstrap | 0/1 | 0.0% | — |
Dialogue drill-in: query ai_turn_logs where eval_run_id = '9edcaffa-7224-4d13-a4e3-aabbf4d57e03'; per-turn artifact real-eval-d984cd2.
stats contract — alpha 0.05, one-sided true, paired test sign, multiplicity holm, MDE 84.9999pp, wilson z 1.96
| Scenario | Contract | N | Pass | Wilson CI | Quality | Cost/run | Model abandoned | Outcomes | Gate |
|---|---|---|---|---|---|---|---|---|---|
| 08-first-cycle-bootstrap | cycle_intent | 1 | 1/1 (100.0%) | [20.7%, 100.0%] | cycle_theme_adherence: 1.00 [1.00, 1.00] | $0.0015 | iteration cap: 0 (0.0%) stopped early: 0 (0.0%) |
submitted: 1 |
ok delta: +0.0pp p: 1.000 |
| Scenario | Non-submitted | Rate | By kind |
|---|---|---|---|
| 08-first-cycle-bootstrap | 0/1 | 0.0% | — |
Dialogue drill-in: query ai_turn_logs where eval_run_id = '7c837873-cb92-4874-82c3-219f44d2422f'; per-turn artifact real-eval-29818b2.
stats contract — alpha 0.05, one-sided true, paired test sign, multiplicity none, MDE 84.9999pp, wilson z 1.96
| Scenario | Contract | N | Pass | Wilson CI | Quality | Cost/run | Model abandoned | Outcomes | Gate |
|---|---|---|---|---|---|---|---|---|---|
| 08-first-cycle-bootstrap | cycle_intent | 1 | 1/1 (100.0%) | [20.7%, 100.0%] | cycle_theme_adherence: 0.50 [0.50, 0.50] | $0.0015 | iteration cap: 0 (0.0%) stopped early: 0 (0.0%) |
submitted: 1 |
ok delta: — p: — |
| Scenario | Non-submitted | Rate | By kind |
|---|---|---|---|
| 08-first-cycle-bootstrap | 0/1 | 0.0% | — |
Dialogue drill-in: query ai_turn_logs where eval_run_id = '585c76bc-f828-4231-b7df-6bb20f8189c4'; per-turn artifact real-eval-10b443e.
stats contract — alpha 0.05, one-sided true, paired test sign, multiplicity none, MDE 84.9999pp, wilson z 1.96
| Scenario | Contract | N | Pass | Wilson CI | Quality | Cost/run | Model abandoned | Outcomes | Gate |
|---|---|---|---|---|---|---|---|---|---|
| 08-first-cycle-bootstrap | cycle_intent | 1 | 1/1 (100.0%) | [20.7%, 100.0%] | cycle_theme_adherence: 1.00 [1.00, 1.00] | $0.0014 | iteration cap: 0 (0.0%) stopped early: 0 (0.0%) |
submitted: 1 |
ok delta: — p: — |
| Scenario | Non-submitted | Rate | By kind |
|---|---|---|---|
| 08-first-cycle-bootstrap | 0/1 | 0.0% | — |
Dialogue drill-in: query ai_turn_logs where eval_run_id = '10a014b1-9313-48f0-b45a-6ddee89ca867'; per-turn artifact real-eval-2697a1c.