Open_Ultra_SAST/benchmarks/measurements/2026-10-07-search-pilot-shiftleft-sql-vuln.jsonl

{"type": "search", "pair_index": 5, "side": "vulnerable", "repo_digest": "97f40e58e334d3e3768ff6efdc43e0d77e6dd602066bbb9e971da2de748502db", "revision_digest": "d4ec744e0583e7829f60dc21e1ef9d5e728a98b720454983c98229062fe29fb9", "family": "injection", "language": "python", "dry_run": false, "fixed_effect_observed": null, "outcome": "inconclusive", "end_reason": "exhausted", "end_detail": null, "task_metrics": [{"task_id": "task-1", "step": "explore", "reserved": 0.25402256, "settled": 0.055590271999999996, "model_calls": 11, "tokens_in": 127597, "tokens_out": 2721, "warnings": 0, "wall_seconds": 80.42255735804792, "end": "ok"}, {"task_id": "task-2", "step": "reason", "reserved": 0.008167279999999999, "settled": 0.0006852720000000007, "model_calls": 1, "tokens_in": 1605, "tokens_out": 232, "warnings": 0, "wall_seconds": 2.017971262917854, "end": "ok"}, {"task_id": "task-3", "step": "explore", "reserved": 0.9702088, "settled": 0.21953697599999994, "model_calls": 27, "tokens_in": 489939, "tokens_out": 10769, "warnings": 0, "wall_seconds": 224.3654310530983, "end": "ok"}, {"task_id": "task-4", "step": "verify", "reserved": 0.0, "settled": 0.0, "model_calls": 0, "tokens_in": 0, "tokens_out": 0, "warnings": 0, "wall_seconds": 124.59446250996552, "end": "inconclusive"}, {"task_id": "task-5", "step": "explore", "reserved": 0.5723880799999996, "settled": 0.12660894400000006, "model_calls": 19, "tokens_in": 282821, "tokens_out": 7095, "warnings": 0, "wall_seconds": 148.36880350508727, "end": "ok"}, {"task_id": "task-6", "step": "verify", "reserved": 0.0, "settled": 0.0, "model_calls": 0, "tokens_in": 0, "tokens_out": 0, "warnings": 0, "wall_seconds": 130.4221933099907, "end": "inconclusive"}, {"task_id": "task-7", "step": "explore", "reserved": 0.3159450800000001, "settled": 0.06586890399999995, "model_calls": 14, "tokens_in": 146606, "tokens_out": 5039, "warnings": 0, "wall_seconds": 101.10444235103205, "end": "ok"}, {"task_id": "task-8", "step": "verify", "reserved": 0.0, "settled": 0.0, "model_calls": 0, "tokens_in": 0, "tokens_out": 0, "warnings": 0, "wall_seconds": 125.7246343609877, "end": "inconclusive"}, {"task_id": "task-9", "step": "reason", "reserved": 0.010021000000000058, "settled": 0.0018490720000000072, "model_calls": 1, "tokens_in": 4028, "tokens_out": 306, "warnings": 0, "wall_seconds": 2.24352009606082, "end": "ok"}], "executor_task_metrics": [{"executor_task": 1, "reserved": 0.25402256, "settled": 0.055590271999999996, "model_calls": 11, "tokens_in": 127597, "tokens_out": 2721, "warnings": 0, "wall_seconds": 80.42253009497654, "end": "ok"}, {"executor_task": 2, "reserved": 0.9702088, "settled": 0.21953697599999994, "model_calls": 27, "tokens_in": 489939, "tokens_out": 10769, "warnings": 0, "wall_seconds": 224.36539215198718, "end": "ok"}, {"executor_task": 3, "reserved": 0.0, "settled": 0.0, "model_calls": 0, "tokens_in": 0, "tokens_out": 0, "warnings": 0, "wall_seconds": 44.740287419059314, "end": "ok"}, {"executor_task": 4, "reserved": 0.0, "settled": 0.0, "model_calls": 0, "tokens_in": 0, "tokens_out": 0, "warnings": 0, "wall_seconds": 42.399635116918944, "end": "ok"}, {"executor_task": 5, "reserved": 0.5723880799999996, "settled": 0.12660894400000006, "model_calls": 19, "tokens_in": 282821, "tokens_out": 7095, "warnings": 0, "wall_seconds": 148.36876758094877, "end": "ok"}, {"executor_task": 6, "reserved": 0.0, "settled": 0.0, "model_calls": 0, "tokens_in": 0, "tokens_out": 0, "warnings": 0, "wall_seconds": 43.50505479099229, "end": "ok"}, {"executor_task": 7, "reserved": 0.0, "settled": 0.0, "model_calls": 0, "tokens_in": 0, "tokens_out": 0, "warnings": 0, "wall_seconds": 45.80030226195231, "end": "ok"}, {"executor_task": 8, "reserved": 0.3159450800000001, "settled": 0.06586890399999995, "model_calls": 14, "tokens_in": 146606, "tokens_out": 5039, "warnings": 0, "wall_seconds": 101.10441223706584, "end": "ok"}, {"executor_task": 9, "reserved": 0.0, "settled": 0.0, "model_calls": 0, "tokens_in": 0, "tokens_out": 0, "warnings": 0, "wall_seconds": 41.84932579402812, "end": "ok"}, {"executor_task": 10, "reserved
{"type": "summary", "end_reason": "completed", "aborted_reason": null, "skipped_pairs": [], "searches": 1, "dry_run": false, "side": "vulnerable", "ceiling_usd": 1.5, "purpose": "feasibility_only", "advantages": ["known_location", "labelled_family", "runnable_project_selection_bias"], "fixed_effects_observed": 0, "outcomes": {"inconclusive": 1}, "spend": {"reserved": 2.1307528, "settled": 0.47013943999999996}, "model_calls": 73, "tokens_in": 1052596, "tokens_out": 26162, "tasks_submitted": 16, "wall_seconds": 940.2328626200324}