bikeshare-daily-leakage-regression-v4
contested/defectiveCurrent calibratedOutside aggregate scope- Reference solution (oracle)
- Pass
- No-op resistance check
- Pass
- QA verdict
- taxonomy: Qualified; QA: QA-H sweep: budget fairness (>= 50% of 75-min estimate,
- Aggregate eligibility
- Excluded / other version
- Known task defect recorded
These per-version observations remain visible, but this version does not contribute to aggregate pass rates.
The task
Excerpt only; not a complete executable task specification. Task ID task_265a85be81b34483 · version 1. Selection status: not fully recorded.
Results by model and effort
This exact task version only. Every rate is passes / valid runs with a Wilson 95% interval; n≤2 remains counts only. Macro aggregation does not apply within a single task. Baselines are summarized in the quality gates, not ranked. A passed no-op resistance check means that doing nothing did not solve the task.
Current evidence
| Model / effort | Verifier result [95% Wilson] | Diagnostic labels / valid | HARNESS_ERROR · excluded | Outcome classes |
|---|---|---|---|---|
| Claude Opus 5 · default (unverified) | 5/10 · 50.0% [23.7%, 76.3%] | 10 / 10 | 5 | GOOD_FAILURE: 5 BAD_FAILURE: 0 GOOD_SUCCESS: 5 BAD_SUCCESS: 0 |
Legacy evidence
| Model / effort | Verifier result [95% Wilson] | Diagnostic labels / valid | HARNESS_ERROR · excluded | Outcome classes |
|---|
Every recorded run
17 recorded trials, including controls. Diagnostic labels do not replace verifier reward. Labels and quality checks are source declarations, not independently attested here. Internal evidence remains private; a missing public URL is shown explicitly. Records with invalid or absent rewards are not scored.
| Run / model | Date / source | Reward / eligibility | Diagnostic class / source | Resources | Evidence |
|---|---|---|---|---|---|
trial_4615b762007041ccoracle@@ | Oct 13, 2026 console | 1 · valid | GOOD_SUCCESS frozen-classifier | Tokens: — Turns: — Cost: — | Not publicly available |
trial_c685e17769cf41cbnop@@ | Oct 13, 2026 console | 0 · valid | GOOD_FAILURE frozen-classifier | Tokens: — Turns: — Cost: — | Not publicly available |
trial_8b141bbaf3ba4d44Claude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 48,916 Turns: 33 Cost: $3.0676 | Not publicly available |
trial_91f0e31dc21243f1Claude Opus 5 · default (unverified) | Oct 13, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 55,190 Turns: 35 Cost: $3.3398 | Not publicly available |
trial_cf63ff4115c94875Claude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 52,266 Turns: 31 Cost: $3.0064 | Not publicly available |
trial_10d851a604d44894Claude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 63,020 Turns: 41 Cost: $3.8709 | Not publicly available |
trial_1a0cf4d491e543ceClaude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · excludedharness_error | HARNESS_ERROR independent-review | Tokens: 0 Turns: 1 Cost: $0.0000 | Not publicly available |
trial_242938f17b0749cfClaude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 66,057 Turns: 45 Cost: $4.1815 | Not publicly available |
trial_6944daca71614d47Claude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · excludedharness_error | HARNESS_ERROR independent-review | Tokens: 0 Turns: 1 Cost: $0.0000 | Not publicly available |
trial_8ee01d52361f4f91Claude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · excludedharness_error | HARNESS_ERROR independent-review | Tokens: 0 Turns: 1 Cost: $0.0000 | Not publicly available |
trial_c1cd1c035acf4b38Claude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · excludedharness_error | HARNESS_ERROR independent-review | Tokens: 0 Turns: 1 Cost: $0.0000 | Not publicly available |
trial_cfeb046e099f4714Claude Opus 5 · default (unverified) | Oct 13, 2026 console | 0 · excludedharness_error | HARNESS_ERROR independent-review | Tokens: 0 Turns: 1 Cost: $0.0000 | Not publicly available |
trial_39a98a6d283144a8Claude Opus 5 · default (unverified) | Oct 14, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 53,330 Turns: 25 Cost: $2.8524 | Not publicly available |
trial_3b07ff4cafbf4712Claude Opus 5 · default (unverified) | Oct 14, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 66,379 Turns: 41 Cost: $3.7731 | Not publicly available |
trial_562ef87ec2294429Claude Opus 5 · default (unverified) | Oct 14, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 57,375 Turns: 44 Cost: $3.6669 | Not publicly available |
trial_7baf9c98f43d4a26Claude Opus 5 · default (unverified) | Oct 14, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 64,853 Turns: 31 Cost: $3.5408 | Not publicly available |
trial_9122e542bc214f5aClaude Opus 5 · default (unverified) | Oct 14, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 74,735 Turns: 39 Cost: $4.3853 | Not publicly available |