Traces from results/, generated by scripts/trace_site.py.
| Run | Resolved | Failure labels |
|---|---|---|
| baseline_full | 0/129 | {'NO_PATCH': 129} |
| baseline_full_v2 | 3/129 | {'NO_PATCH': 126, 'RESOLVED': 3} |
| mined_baseline | 16/151 | {'NO_PATCH': 135, 'RESOLVED': 16} |
| mined_baseline_harness | 0/151 | {'NO_PATCH': 151} |
| mined_httpx_baseline2 | 1/25 | {'NO_PATCH': 24, 'RESOLVED': 1} |
| mined_httpx_oracle2 | 1/25 | {'WRONG_FIX': 24, 'RESOLVED': 1} |
| mined_oracle | 54/151 | {'WRONG_FIX': 97, 'RESOLVED': 54} |
| or20_qwen27b_v2 | 6/20 | {'NO_PATCH': 14, 'RESOLVED': 6} |
| or20_submission | 5/20 | {'LOOP': 9, 'RESOLVED': 5, 'WRONG_FIX': 5, 'NO_PATCH': 1} |
| or_smoke | 0/1 | {'LOOP': 1} |
| oracle_full | 95/129 | {'RESOLVED': 95, 'WRONG_FIX': 34} |
| oracle_refix | 15/34 | {'WRONG_FIX': 19, 'RESOLVED': 15} |
| pod_r1_v1e | 6/20 | {'RESOLVED': 6, 'LOOP': 5, 'WRONG_FIX': 5, 'NO_PATCH': 3, 'CONTEXT': 1} |
| pod_r1_v1n | 6/20 | {'LOOP': 8, 'RESOLVED': 6, 'WRONG_FIX': 3, 'NO_PATCH': 3} |
| pod_r2_v1e | 16/45 | {'RESOLVED': 16, 'NO_PATCH': 10, 'WRONG_FIX': 10, 'LOOP': 7, 'CONTEXT': 2} |
| pod_r2_v1f | 12/45 | {'RESOLVED': 12, 'NO_PATCH': 11, 'LOOP': 9, 'WRONG_FIX': 9, 'CONTEXT': 4} |
| pod_r3_v1e | 16/45 | {'RESOLVED': 16, 'LOOP': 15, 'WRONG_FIX': 9, 'CONTEXT': 5} |
| pod_r3_v1g | 16/45 | {'RESOLVED': 16, 'LOOP': 12, 'CONTEXT': 7, 'WRONG_FIX': 7, 'NO_PATCH': 3} |
| pod_r4_v1 | 13/45 | {'LOOP': 18, 'RESOLVED': 13, 'CONTEXT': 8, 'WRONG_FIX': 4, 'NO_PATCH': 2} |
| pod_r4_v1g | 17/45 | {'RESOLVED': 17, 'WRONG_FIX': 9, 'NO_PATCH': 9, 'LOOP': 6, 'CONTEXT': 4} |
| pod_r5_v1h | 17/45 | {'RESOLVED': 17, 'WRONG_FIX': 13, 'CONTEXT': 7, 'NO_PATCH': 5, 'LOOP': 3} |
| pod_r5_v1i | 18/45 | {'RESOLVED': 18, 'WRONG_FIX': 15, 'NO_PATCH': 5, 'CONTEXT': 4, 'LOOP': 3} |
| pod_step15_v1 | 7/20 | {'RESOLVED': 7, 'LOOP': 7, 'CONTEXT': 4, 'WRONG_FIX': 2} |
| pod_step15_v1_lora | 1/20 | {'LOOP': 9, 'CONTEXT': 5, 'INTERFACE': 2, 'NO_PATCH': 2, 'RESOLVED': 1, 'WRONG_FIX': 1} |
| tpu_run2/results/eval_submission | 10/30 | {'RESOLVED': 10, 'LOOP': 10, 'WRONG_FIX': 4, 'CONTEXT': 4, 'NO_PATCH': 2} |
| tpu_run2/results/eval_submission_analyzer | 9/30 | {'WRONG_FIX': 11, 'RESOLVED': 9, 'LOOP': 5, 'NO_PATCH': 3, 'CONTEXT': 2} |
| tpu_run2/results/eval_submission_nothink | 8/30 | {'WRONG_FIX': 9, 'RESOLVED': 8, 'LOOP': 6, 'NO_PATCH': 5, 'CONTEXT': 2} |
| tpu_run3/results/eval3_submission | 11/30 | {'RESOLVED': 11, 'LOOP': 9, 'WRONG_FIX': 7, 'CONTEXT': 3} |
| tpu_run3/results/eval3_submission_v2 | 8/30 | {'RESOLVED': 8, 'NO_PATCH': 8, 'LOOP': 6, 'CONTEXT': 4, 'WRONG_FIX': 4} |
| tpu_run3/results/eval3_submission_v2t | 9/30 | {'WRONG_FIX': 11, 'RESOLVED': 9, 'LOOP': 4, 'CONTEXT': 3, 'NO_PATCH': 2, 'INTERFACE': 1} |
| tpu_run4/results/eval4_submission | 19/45 | {'RESOLVED': 19, 'LOOP': 13, 'CONTEXT': 6, 'WRONG_FIX': 5, 'NO_PATCH': 2} |
| tpu_run4/results/eval4_submission_v1b | 17/45 | {'RESOLVED': 17, 'LOOP': 13, 'WRONG_FIX': 10, 'NO_PATCH': 4, 'CONTEXT': 1} |
| tpu_run5/results/eval5_submission | 14/45 | {'LOOP': 20, 'RESOLVED': 14, 'CONTEXT': 5, 'WRONG_FIX': 4, 'NO_PATCH': 2} |
| tpu_run5/results/eval5_submission_v1s | 13/45 | {'LOOP': 21, 'RESOLVED': 13, 'WRONG_FIX': 5, 'CONTEXT': 4, 'NO_PATCH': 2} |
| tpu_run6/results/eval6_submission | 12/45 | {'LOOP': 25, 'RESOLVED': 12, 'CONTEXT': 4, 'NO_PATCH': 2, 'WRONG_FIX': 2} |
| tpu_run6/results/eval6_submission_v1r | 10/45 | {'LOOP': 21, 'RESOLVED': 10, 'CONTEXT': 7, 'WRONG_FIX': 4, 'NO_PATCH': 3} |
| tpu_run7/results/eval7_submission | 13/45 | {'LOOP': 26, 'RESOLVED': 13, 'WRONG_FIX': 2, 'CONTEXT': 2, 'NO_PATCH': 2} |
| tpu_run7/results/eval7_submission_v1n | 13/45 | {'RESOLVED': 13, 'LOOP': 13, 'WRONG_FIX': 10, 'CONTEXT': 7, 'NO_PATCH': 2} |
| tpu_run8/results/eval8_submission_v1a | 12/45 | {'LOOP': 17, 'RESOLVED': 12, 'WRONG_FIX': 8, 'CONTEXT': 5, 'NO_PATCH': 2, 'INTERFACE': 1} |
| tpu_run8/results/eval8_submission_v1e | 5/45 | {'LOOP': 25, 'RESOLVED': 5, 'WRONG_FIX': 5, 'CONTEXT': 5, 'NO_PATCH': 5} |
| tpu_run8/results/eval8_submission_v1l | 11/45 | {'LOOP': 20, 'RESOLVED': 11, 'CONTEXT': 5, 'WRONG_FIX': 5, 'NO_PATCH': 4} |
| tpu_run8/results/eval8_submission_v1n | 11/45 | {'LOOP': 20, 'RESOLVED': 11, 'CONTEXT': 6, 'WRONG_FIX': 4, 'NO_PATCH': 4} |