{ "scope": "Retrospective correction of auxiliary physical-line annotation overlaps only. Use unchanged saved source replies, trajectories and payloads. Do not rerun a model, rebuild a graph, select new tasks or change official scores.", "protocol_sha256": "12abf234264f904a4b54d4df6615fae1d2b9b6210eed671fdb926644ec96bf43", "normalizer": "Pinned official contextbench.parsers.Gold.line_spans_init(), inclusive merged intervals", "model_calls": 0, "official_scores_changed": false, "affected_annotation_path_tasks_of_24": [ "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2" ], "source_attribution_24": { "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "language": "python", "categories": { "grep": { "replies": 2, "unique_physical": 26, "first_exposure_physical": 26, "first_exposure_annotated": 25, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 1, "unique_annotated_absent_from_native": 1 }, "completion_grep": { "replies": 1, "unique_physical": 56, "first_exposure_physical": 56, "first_exposure_annotated": 43, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 40, "unique_annotated_absent_from_native": 27 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 3, "unique_physical": 143, "first_exposure_physical": 138, "first_exposure_annotated": 65, "repeated_line_deliveries": 5, "unique_physical_absent_from_native": 103, "unique_annotated_absent_from_native": 30 }, "completion_read": { "replies": 1, "unique_physical": 4, "first_exposure_physical": 4, "first_exposure_annotated": 4, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 4248, "read": 226 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 56, "lost_annotated": 43 }, "without_any_completion": { "lost_physical": 60, "lost_annotated": 47 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "language": "typescript", "categories": { "grep": { "replies": 8, "unique_physical": 109, "first_exposure_physical": 109, "first_exposure_annotated": 0, "repeated_line_deliveries": 1, "unique_physical_absent_from_native": 57, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 5, "unique_physical": 234, "first_exposure_physical": 230, "first_exposure_annotated": 0, "repeated_line_deliveries": 87, "unique_physical_absent_from_native": 97, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 52, "first_exposure_physical": 52, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 12, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 6, "unique_physical": 385, "first_exposure_physical": 302, "first_exposure_annotated": 50, "repeated_line_deliveries": 83, "unique_physical_absent_from_native": 90, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 1, "unique_physical": 101, "first_exposure_physical": 101, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 96, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 25555, "read": 3317 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 201, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 302, "lost_annotated": 0 } } }, { "instance_id": "SWE-PolyBench__typescript__maintenance__bugfix__4f3cb6be", "language": "typescript", "categories": { "grep": { "replies": 5, "unique_physical": 59, "first_exposure_physical": 52, "first_exposure_annotated": 1, "repeated_line_deliveries": 7, "unique_physical_absent_from_native": 26, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 2, "unique_physical": 161, "first_exposure_physical": 152, "first_exposure_annotated": 2, "repeated_line_deliveries": 9, "unique_physical_absent_from_native": 105, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 4, "unique_physical": 425, "first_exposure_physical": 380, "first_exposure_annotated": 56, "repeated_line_deliveries": 45, "unique_physical_absent_from_native": 30, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 2, "unique_physical": 64, "first_exposure_physical": 64, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 57, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 15819, "read": 3273 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 117, "lost_annotated": 2 }, "without_any_completion": { "lost_physical": 180, "lost_annotated": 2 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__60bc9e86", "language": "python", "categories": { "grep": { "replies": 2, "unique_physical": 5, "first_exposure_physical": 5, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 2, "unique_physical": 160, "first_exposure_physical": 160, "first_exposure_annotated": 71, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 49, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 1, "unique_physical": 30, "first_exposure_physical": 30, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 13287 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 160, "lost_annotated": 71 }, "without_any_completion": { "lost_physical": 160, "lost_annotated": 71 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "language": "c", "categories": { "grep": { "replies": 11, "unique_physical": 111, "first_exposure_physical": 108, "first_exposure_annotated": 14, "repeated_line_deliveries": 4, "unique_physical_absent_from_native": 64, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 8, "unique_physical": 598, "first_exposure_physical": 450, "first_exposure_annotated": 40, "repeated_line_deliveries": 148, "unique_physical_absent_from_native": 217, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 7, "unique_physical": 1000, "first_exposure_physical": 972, "first_exposure_annotated": 404, "repeated_line_deliveries": 28, "unique_physical_absent_from_native": 150, "unique_annotated_absent_from_native": 40 }, "completion_read": { "replies": 3, "unique_physical": 220, "first_exposure_physical": 218, "first_exposure_annotated": 174, "repeated_line_deliveries": 2, "unique_physical_absent_from_native": 155, "unique_annotated_absent_from_native": 119 } }, "completion_characters": { "grep": 35791, "read": 6410 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 438, "lost_annotated": 40 }, "without_any_completion": { "lost_physical": 656, "lost_annotated": 214 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "language": "c", "categories": { "grep": { "replies": 4, "unique_physical": 17, "first_exposure_physical": 16, "first_exposure_annotated": 9, "repeated_line_deliveries": 1, "unique_physical_absent_from_native": 1, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 4, "unique_physical": 511, "first_exposure_physical": 502, "first_exposure_annotated": 152, "repeated_line_deliveries": 9, "unique_physical_absent_from_native": 15, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 2, "unique_physical": 88, "first_exposure_physical": 88, "first_exposure_annotated": 88, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 11, "unique_annotated_absent_from_native": 11 } }, "completion_characters": { "grep": 5813 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 88, "lost_annotated": 88 }, "without_any_completion": { "lost_physical": 88, "lost_annotated": 88 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "language": "cpp", "categories": { "grep": { "replies": 3, "unique_physical": 40, "first_exposure_physical": 40, "first_exposure_annotated": 11, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 1, "unique_physical": 320, "first_exposure_physical": 300, "first_exposure_annotated": 196, "repeated_line_deliveries": 20, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 1, "unique_physical": 35, "first_exposure_physical": 35, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 7, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 2522 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 35, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 35, "lost_annotated": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "language": "go", "categories": { "grep": { "replies": 4, "unique_physical": 26, "first_exposure_physical": 26, "first_exposure_annotated": 9, "repeated_line_deliveries": 1, "unique_physical_absent_from_native": 14, "unique_annotated_absent_from_native": 1 }, "completion_grep": { "replies": 3, "unique_physical": 309, "first_exposure_physical": 309, "first_exposure_annotated": 65, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 227, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 132, "first_exposure_physical": 132, "first_exposure_annotated": 132, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 49, "unique_annotated_absent_from_native": 49 }, "read": { "replies": 2, "unique_physical": 153, "first_exposure_physical": 38, "first_exposure_annotated": 27, "repeated_line_deliveries": 115, "unique_physical_absent_from_native": 35, "unique_annotated_absent_from_native": 30 }, "completion_read": { "replies": 2, "unique_physical": 25, "first_exposure_physical": 6, "first_exposure_annotated": 1, "repeated_line_deliveries": 19, "unique_physical_absent_from_native": 21, "unique_annotated_absent_from_native": 19 } }, "completion_characters": { "grep": 15404, "read": 910 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 309, "lost_annotated": 65 }, "without_any_completion": { "lost_physical": 315, "lost_annotated": 66 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "language": "java", "categories": { "grep": { "replies": 6, "unique_physical": 38, "first_exposure_physical": 38, "first_exposure_annotated": 16, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 4, "unique_physical": 231, "first_exposure_physical": 231, "first_exposure_annotated": 95, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 117, "unique_annotated_absent_from_native": 50 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 5, "unique_physical": 296, "first_exposure_physical": 281, "first_exposure_annotated": 50, "repeated_line_deliveries": 15, "unique_physical_absent_from_native": 10, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 3, "unique_physical": 65, "first_exposure_physical": 52, "first_exposure_annotated": 25, "repeated_line_deliveries": 13, "unique_physical_absent_from_native": 40, "unique_annotated_absent_from_native": 23 } }, "completion_characters": { "grep": 28801, "read": 3365 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 211, "lost_annotated": 75 }, "without_any_completion": { "lost_physical": 273, "lost_annotated": 110 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__2fb50735", "language": "typescript", "categories": { "grep": { "replies": 3, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 2, "unique_physical": 400, "first_exposure_physical": 400, "first_exposure_annotated": 20, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 99, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 1, "unique_physical": 5, "first_exposure_physical": 5, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 5, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 15, "first_exposure_physical": 15, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 12, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "read": 143 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 0, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 5, "lost_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "language": "cpp", "categories": { "grep": { "replies": 4, "unique_physical": 26, "first_exposure_physical": 26, "first_exposure_annotated": 7, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 16, "unique_annotated_absent_from_native": 2 }, "completion_grep": { "replies": 1, "unique_physical": 8, "first_exposure_physical": 8, "first_exposure_annotated": 8, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 4, "unique_physical": 241, "first_exposure_physical": 226, "first_exposure_annotated": 117, "repeated_line_deliveries": 15, "unique_physical_absent_from_native": 20, "unique_annotated_absent_from_native": 20 } }, "completion_characters": { "grep": 682 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 0, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 0, "lost_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__e43d9aa5", "language": "cpp", "categories": { "grep": { "replies": 4, "unique_physical": 76, "first_exposure_physical": 73, "first_exposure_annotated": 1, "repeated_line_deliveries": 4, "unique_physical_absent_from_native": 52, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 2, "unique_physical": 27, "first_exposure_physical": 27, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 27, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 4, "unique_physical": 177, "first_exposure_physical": 169, "first_exposure_annotated": 43, "repeated_line_deliveries": 8, "unique_physical_absent_from_native": 30, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 2401 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 27, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 27, "lost_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "language": "c", "categories": { "grep": { "replies": 6, "unique_physical": 122, "first_exposure_physical": 117, "first_exposure_annotated": 9, "repeated_line_deliveries": 6, "unique_physical_absent_from_native": 11, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 5, "unique_physical": 305, "first_exposure_physical": 290, "first_exposure_annotated": 1, "repeated_line_deliveries": 15, "unique_physical_absent_from_native": 169, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 15, "unique_physical": 707, "first_exposure_physical": 655, "first_exposure_annotated": 170, "repeated_line_deliveries": 52, "unique_physical_absent_from_native": 30, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 4, "unique_physical": 175, "first_exposure_physical": 175, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 170, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 23673, "read": 7847 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 289, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 464, "lost_annotated": 0 } } }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "language": "javascript", "categories": { "grep": { "replies": 7, "unique_physical": 72, "first_exposure_physical": 72, "first_exposure_annotated": 17, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 20, "unique_annotated_absent_from_native": 1 }, "completion_grep": { "replies": 3, "unique_physical": 263, "first_exposure_physical": 263, "first_exposure_annotated": 63, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 151, "unique_annotated_absent_from_native": 6 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 7, "unique_physical": 830, "first_exposure_physical": 757, "first_exposure_annotated": 127, "repeated_line_deliveries": 73, "unique_physical_absent_from_native": 101, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 3, "unique_physical": 60, "first_exposure_physical": 38, "first_exposure_annotated": 4, "repeated_line_deliveries": 22, "unique_physical_absent_from_native": 33, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 15403, "read": 2379 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 206, "lost_annotated": 6 }, "without_any_completion": { "lost_physical": 265, "lost_annotated": 31 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "language": "rust", "categories": { "grep": { "replies": 9, "unique_physical": 30, "first_exposure_physical": 25, "first_exposure_annotated": 6, "repeated_line_deliveries": 5, "unique_physical_absent_from_native": 2, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 8, "unique_physical": 442, "first_exposure_physical": 407, "first_exposure_annotated": 85, "repeated_line_deliveries": 51, "unique_physical_absent_from_native": 111, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 16, "first_exposure_physical": 16, "first_exposure_annotated": 2, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 10, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 6, "unique_physical": 789, "first_exposure_physical": 693, "first_exposure_annotated": 90, "repeated_line_deliveries": 96, "unique_physical_absent_from_native": 70, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 4, "unique_physical": 95, "first_exposure_physical": 71, "first_exposure_annotated": 5, "repeated_line_deliveries": 24, "unique_physical_absent_from_native": 59, "unique_annotated_absent_from_native": 5 } }, "completion_characters": { "grep": 29178, "read": 4663 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 304, "lost_annotated": 68 }, "without_any_completion": { "lost_physical": 398, "lost_annotated": 73 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__03fdad45", "language": "rust", "categories": { "grep": { "replies": 4, "unique_physical": 50, "first_exposure_physical": 50, "first_exposure_annotated": 3, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 6, "unique_annotated_absent_from_native": 2 }, "completion_grep": { "replies": 3, "unique_physical": 314, "first_exposure_physical": 314, "first_exposure_annotated": 2, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 221, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 12, "first_exposure_physical": 12, "first_exposure_annotated": 5, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 5, "unique_physical": 255, "first_exposure_physical": 166, "first_exposure_annotated": 5, "repeated_line_deliveries": 89, "unique_physical_absent_from_native": 11, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 3, "unique_physical": 14, "first_exposure_physical": 14, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 5, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 17172, "read": 782 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 251, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 265, "lost_annotated": 0 } } }, { "instance_id": "SWE-PolyBench__javascript__maintenance__bugfix__f4541fb1", "language": "javascript", "categories": { "grep": { "replies": 4, "unique_physical": 84, "first_exposure_physical": 84, "first_exposure_annotated": 14, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 51, "unique_annotated_absent_from_native": 1 }, "completion_grep": { "replies": 1, "unique_physical": 35, "first_exposure_physical": 35, "first_exposure_annotated": 35, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 2, "unique_physical": 527, "first_exposure_physical": 514, "first_exposure_annotated": 184, "repeated_line_deliveries": 13, "unique_physical_absent_from_native": 96, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 1, "unique_physical": 6, "first_exposure_physical": 6, "first_exposure_annotated": 3, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 3279, "read": 178 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 35, "lost_annotated": 35 }, "without_any_completion": { "lost_physical": 41, "lost_annotated": 38 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__16860730", "language": "rust", "categories": { "grep": { "replies": 7, "unique_physical": 106, "first_exposure_physical": 101, "first_exposure_annotated": 22, "repeated_line_deliveries": 5, "unique_physical_absent_from_native": 42, "unique_annotated_absent_from_native": 8 }, "completion_grep": { "replies": 6, "unique_physical": 509, "first_exposure_physical": 509, "first_exposure_annotated": 53, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 357, "unique_annotated_absent_from_native": 23 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 13, "unique_physical": 2188, "first_exposure_physical": 2150, "first_exposure_annotated": 336, "repeated_line_deliveries": 38, "unique_physical_absent_from_native": 189, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 6, "unique_physical": 493, "first_exposure_physical": 445, "first_exposure_annotated": 0, "repeated_line_deliveries": 48, "unique_physical_absent_from_native": 428, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 37954, "read": 21374 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 446, "lost_annotated": 23 }, "without_any_completion": { "lost_physical": 938, "lost_annotated": 41 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "language": "java", "categories": { "grep": { "replies": 3, "unique_physical": 29, "first_exposure_physical": 28, "first_exposure_annotated": 26, "repeated_line_deliveries": 1, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 3, "unique_physical": 129, "first_exposure_physical": 129, "first_exposure_annotated": 91, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 1, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 2, "unique_physical": 204, "first_exposure_physical": 134, "first_exposure_annotated": 134, "repeated_line_deliveries": 70, "unique_physical_absent_from_native": 21, "unique_annotated_absent_from_native": 21 }, "completion_read": { "replies": 1, "unique_physical": 11, "first_exposure_physical": 3, "first_exposure_annotated": 3, "repeated_line_deliveries": 8, "unique_physical_absent_from_native": 3, "unique_annotated_absent_from_native": 3 } }, "completion_characters": { "grep": 14162, "read": 428 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 60, "lost_annotated": 22 }, "without_any_completion": { "lost_physical": 71, "lost_annotated": 33 } } }, { "instance_id": "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "language": "go", "categories": { "grep": { "replies": 2, "unique_physical": 13, "first_exposure_physical": 13, "first_exposure_annotated": 1, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 2, "unique_physical": 100, "first_exposure_physical": 100, "first_exposure_annotated": 12, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 3, "unique_physical": 214, "first_exposure_physical": 207, "first_exposure_annotated": 1, "repeated_line_deliveries": 7, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 2, "unique_physical": 76, "first_exposure_physical": 64, "first_exposure_annotated": 0, "repeated_line_deliveries": 12, "unique_physical_absent_from_native": 44, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 5630, "read": 2929 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 88, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 163, "lost_annotated": 11 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__8b7cc5e0", "language": "java", "categories": { "grep": { "replies": 6, "unique_physical": 21, "first_exposure_physical": 21, "first_exposure_annotated": 1, "repeated_line_deliveries": 1, "unique_physical_absent_from_native": 15, "unique_annotated_absent_from_native": 1 }, "completion_grep": { "replies": 5, "unique_physical": 226, "first_exposure_physical": 226, "first_exposure_annotated": 23, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 185, "unique_annotated_absent_from_native": 23 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 2, "unique_physical": 180, "first_exposure_physical": 152, "first_exposure_annotated": 0, "repeated_line_deliveries": 28, "unique_physical_absent_from_native": 40, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 2, "unique_physical": 40, "first_exposure_physical": 26, "first_exposure_annotated": 0, "repeated_line_deliveries": 14, "unique_physical_absent_from_native": 19, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 24144, "read": 2131 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 188, "lost_annotated": 23 }, "without_any_completion": { "lost_physical": 228, "lost_annotated": 23 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "language": "go", "categories": { "grep": { "replies": 5, "unique_physical": 15, "first_exposure_physical": 11, "first_exposure_annotated": 4, "repeated_line_deliveries": 4, "unique_physical_absent_from_native": 2, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 1, "unique_physical": 127, "first_exposure_physical": 127, "first_exposure_annotated": 36, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 131, "first_exposure_physical": 131, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 32, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 6, "unique_physical": 414, "first_exposure_physical": 410, "first_exposure_annotated": 39, "repeated_line_deliveries": 4, "unique_physical_absent_from_native": 10, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 4, "unique_physical": 148, "first_exposure_physical": 19, "first_exposure_annotated": 0, "repeated_line_deliveries": 254, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 5587, "read": 8457 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 0, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 144, "lost_annotated": 35 } } }, { "instance_id": "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2", "language": "javascript", "categories": { "grep": { "replies": 2, "unique_physical": 33, "first_exposure_physical": 33, "first_exposure_annotated": 3, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 22, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 1, "unique_physical": 95, "first_exposure_physical": 95, "first_exposure_annotated": 7, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 88, "unique_annotated_absent_from_native": 0 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 3, "unique_physical": 320, "first_exposure_physical": 307, "first_exposure_annotated": 237, "repeated_line_deliveries": 13, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 5782 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 88, "lost_annotated": 0 }, "without_any_completion": { "lost_physical": 88, "lost_annotated": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__42c77239", "language": "python", "categories": { "grep": { "replies": 4, "unique_physical": 22, "first_exposure_physical": 22, "first_exposure_annotated": 5, "repeated_line_deliveries": 1, "unique_physical_absent_from_native": 6, "unique_annotated_absent_from_native": 0 }, "completion_grep": { "replies": 4, "unique_physical": 261, "first_exposure_physical": 261, "first_exposure_annotated": 74, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 173, "unique_annotated_absent_from_native": 8 }, "graph": { "replies": 1, "unique_physical": 0, "first_exposure_physical": 0, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 0, "unique_annotated_absent_from_native": 0 }, "read": { "replies": 2, "unique_physical": 70, "first_exposure_physical": 67, "first_exposure_annotated": 28, "repeated_line_deliveries": 3, "unique_physical_absent_from_native": 20, "unique_annotated_absent_from_native": 0 }, "completion_read": { "replies": 1, "unique_physical": 37, "first_exposure_physical": 37, "first_exposure_annotated": 0, "repeated_line_deliveries": 0, "unique_physical_absent_from_native": 37, "unique_annotated_absent_from_native": 0 } }, "completion_characters": { "grep": 18747, "read": 2166 }, "fixed_trace_removal": { "without_grep_completion": { "lost_physical": 261, "lost_annotated": 74 }, "without_any_completion": { "lost_physical": 298, "lost_annotated": 74 } } } ], "categories": { "completion_grep": { "first_exposure_annotated": 894, "first_exposure_physical": 4502, "repeated_line_deliveries": 310, "replies": 73, "unique_annotated_absent_from_native": 148, "unique_physical": 4713, "unique_physical_absent_from_native": 2353 }, "completion_read": { "first_exposure_annotated": 219, "first_exposure_physical": 1348, "repeated_line_deliveries": 416, "replies": 44, "unique_annotated_absent_from_native": 169, "unique_physical": 1639, "unique_physical_absent_from_native": 1172 }, "graph": { "first_exposure_annotated": 139, "first_exposure_physical": 358, "repeated_line_deliveries": 0, "replies": 24, "unique_annotated_absent_from_native": 49, "unique_physical": 358, "unique_physical_absent_from_native": 115 }, "grep": { "first_exposure_annotated": 204, "first_exposure_physical": 1096, "repeated_line_deliveries": 41, "replies": 115, "unique_annotated_absent_from_native": 17, "unique_physical": 1130, "unique_physical_absent_from_native": 408 }, "read": { "first_exposure_annotated": 2531, "first_exposure_physical": 9950, "repeated_line_deliveries": 829, "replies": 109, "unique_annotated_absent_from_native": 141, "unique_physical": 10779, "unique_physical_absent_from_native": 1170 } }, "fixed_trace_removal": { "without_grep_completion": { "lost_annotated": 635, "lost_physical": 3858 }, "without_any_completion": { "lost_annotated": 957, "lost_physical": 5464 } } }, "final_source_24": { "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "language": "python", "added_physical": 143, "lost_physical": 44, "added_annotated": 57, "lost_annotated": 8, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "language": "typescript", "added_physical": 350, "lost_physical": 293, "added_annotated": 0, "lost_annotated": 30, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "SWE-PolyBench__typescript__maintenance__bugfix__4f3cb6be", "language": "typescript", "added_physical": 211, "lost_physical": 477, "added_annotated": 0, "lost_annotated": 0, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__60bc9e86", "language": "python", "added_physical": 49, "lost_physical": 78, "added_annotated": 0, "lost_annotated": 0, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "language": "c", "added_physical": 586, "lost_physical": 459, "added_annotated": 159, "lost_annotated": 24, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "language": "c", "added_physical": 27, "lost_physical": 177, "added_annotated": 11, "lost_annotated": 159, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "language": "cpp", "added_physical": 7, "lost_physical": 43, "added_annotated": 0, "lost_annotated": 0, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "language": "go", "added_physical": 297, "lost_physical": 31, "added_annotated": 50, "lost_annotated": 20, "graph_new_annotated_at_delivery": 132, "graph_new_annotated_also_read_by_native": 83, "graph_new_annotated_not_read_by_native": 49 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "language": "java", "added_physical": 167, "lost_physical": 190, "added_annotated": 73, "lost_annotated": 28, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__2fb50735", "language": "typescript", "added_physical": 116, "lost_physical": 206, "added_annotated": 0, "lost_annotated": 0, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "language": "cpp", "added_physical": 34, "lost_physical": 97, "added_annotated": 20, "lost_annotated": 45, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__e43d9aa5", "language": "cpp", "added_physical": 108, "lost_physical": 55, "added_annotated": 0, "lost_annotated": 6, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "language": "c", "added_physical": 378, "lost_physical": 234, "added_annotated": 0, "lost_annotated": 28, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "language": "javascript", "added_physical": 304, "lost_physical": 162, "added_annotated": 7, "lost_annotated": 1, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "language": "rust", "added_physical": 252, "lost_physical": 214, "added_annotated": 5, "lost_annotated": 10, "graph_new_annotated_at_delivery": 2, "graph_new_annotated_also_read_by_native": 2, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__03fdad45", "language": "rust", "added_physical": 243, "lost_physical": 104, "added_annotated": 2, "lost_annotated": 0, "graph_new_annotated_at_delivery": 5, "graph_new_annotated_also_read_by_native": 5, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "SWE-PolyBench__javascript__maintenance__bugfix__f4541fb1", "language": "javascript", "added_physical": 147, "lost_physical": 164, "added_annotated": 1, "lost_annotated": 7, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__16860730", "language": "rust", "added_physical": 1015, "lost_physical": 836, "added_annotated": 31, "lost_annotated": 28, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "language": "java", "added_physical": 25, "lost_physical": 51, "added_annotated": 24, "lost_annotated": 35, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "language": "go", "added_physical": 44, "lost_physical": 1, "added_annotated": 0, "lost_annotated": 0, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__8b7cc5e0", "language": "java", "added_physical": 258, "lost_physical": 84, "added_annotated": 24, "lost_annotated": 0, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "language": "go", "added_physical": 44, "lost_physical": 67, "added_annotated": 0, "lost_annotated": 16, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2", "language": "javascript", "added_physical": 110, "lost_physical": 21, "added_annotated": 0, "lost_annotated": 10, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__42c77239", "language": "python", "added_physical": 236, "lost_physical": 116, "added_annotated": 8, "lost_annotated": 9, "graph_new_annotated_at_delivery": 0, "graph_new_annotated_also_read_by_native": 0, "graph_new_annotated_not_read_by_native": 0 } ], "totals": { "added_annotated": 472, "added_physical": 5151, "graph_new_annotated_also_read_by_native": 90, "graph_new_annotated_at_delivery": 139, "graph_new_annotated_not_read_by_native": 49, "lost_annotated": 464, "lost_physical": 4204 } }, "fixed_query_graph_replay": { "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "language": "python", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "no_unseen_neighbors": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "no_unseen_neighbors": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "language": "typescript", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "source_returned": 5 }, "new_physical_at_delivery": 52, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 12, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 5 }, "new_physical_at_delivery": 52, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 12, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-PolyBench__typescript__maintenance__bugfix__4f3cb6be", "language": "typescript", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__60bc9e86", "language": "python", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 4, "source_not_returned": 1 }, "new_physical_at_delivery": 90, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 88, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "language": "c", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 1 }, "new_physical_at_delivery": 202, "new_annotated_at_delivery": 202, "new_physical_absent_from_native": 145, "new_annotated_absent_from_native": 145 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "language": "c", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "language": "cpp", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_not_returned": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "language": "go", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "source_returned": 1 }, "new_physical_at_delivery": 132, "new_annotated_at_delivery": 132, "new_physical_absent_from_native": 49, "new_annotated_absent_from_native": 49 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 1 }, "new_physical_at_delivery": 132, "new_annotated_at_delivery": 132, "new_physical_absent_from_native": 49, "new_annotated_absent_from_native": 49 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "language": "java", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__2fb50735", "language": "typescript", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "source_returned": 3 }, "new_physical_at_delivery": 15, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 12, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 3 }, "new_physical_at_delivery": 15, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 12, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "language": "cpp", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 1 }, "new_physical_at_delivery": 1, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 1, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__e43d9aa5", "language": "cpp", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 5 }, "new_physical_at_delivery": 5, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 3, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "language": "c", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 2, "source_not_returned": 2 }, "new_physical_at_delivery": 99, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 48, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "language": "javascript", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "no_definition_at_line": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "no_definition_at_line": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "language": "rust", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "source_returned": 5 }, "new_physical_at_delivery": 16, "new_annotated_at_delivery": 2, "new_physical_absent_from_native": 10, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 5 }, "new_physical_at_delivery": 16, "new_annotated_at_delivery": 2, "new_physical_absent_from_native": 10, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__03fdad45", "language": "rust", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "source_returned": 2 }, "new_physical_at_delivery": 12, "new_annotated_at_delivery": 5, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 2 }, "new_physical_at_delivery": 12, "new_annotated_at_delivery": 5, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-PolyBench__javascript__maintenance__bugfix__f4541fb1", "language": "javascript", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "no_returned_neighbors": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "no_returned_neighbors": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__16860730", "language": "rust", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 1 }, "new_physical_at_delivery": 19, "new_annotated_at_delivery": 15, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "language": "java", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "language": "go", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "no_unseen_neighbors": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "no_unseen_neighbors": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__8b7cc5e0", "language": "java", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "language": "go", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "source_returned": 1 }, "new_physical_at_delivery": 131, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 32, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 1 }, "new_physical_at_delivery": 131, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 32, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2", "language": "javascript", "artifacts": { "prior": { "available": true, "queries": 1, "statuses": { "no_definition_at_line": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "no_returned_neighbors": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__42c77239", "language": "python", "artifacts": { "prior": { "available": false, "queries": 1, "statuses": { "graph_unavailable": 1 }, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "composed": { "available": true, "queries": 1, "statuses": { "source_returned": 2, "source_not_returned": 1 }, "new_physical_at_delivery": 158, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 156, "new_annotated_absent_from_native": 0 } } } ], "totals": { "prior": { "new_annotated_absent_from_native": 49, "new_annotated_at_delivery": 139, "new_physical_absent_from_native": 115, "new_physical_at_delivery": 358, "queries": 24 }, "composed": { "new_annotated_absent_from_native": 194, "new_annotated_at_delivery": 356, "new_physical_absent_from_native": 556, "new_physical_at_delivery": 932, "queries": 24 } } }, "late_anchor_probe": { "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "language": "python", "graph_available": true, "observed_callable_candidates": 20, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 32, "new_annotated_at_delivery": 21, "new_physical_absent_from_native": 30, "new_annotated_absent_from_native": 19 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 30, "new_annotated_at_delivery": 19, "new_physical_absent_from_native": 30, "new_annotated_absent_from_native": 19 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "language": "typescript", "graph_available": true, "observed_callable_candidates": 47, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 14, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 14, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 14, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 14, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 133, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 133, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-PolyBench__typescript__maintenance__bugfix__4f3cb6be", "language": "typescript", "graph_available": false, "observed_callable_candidates": 0, "policies": { "early_first": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__60bc9e86", "language": "python", "graph_available": true, "observed_callable_candidates": 12, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 127, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 125, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 125, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 125, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "language": "c", "graph_available": true, "observed_callable_candidates": 100, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 26, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 26, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 26, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 26, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "language": "c", "graph_available": false, "observed_callable_candidates": 0, "policies": { "early_first": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "language": "cpp", "graph_available": true, "observed_callable_candidates": 43, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "language": "go", "graph_available": true, "observed_callable_candidates": 12, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 148, "new_annotated_at_delivery": 145, "new_physical_absent_from_native": 53, "new_annotated_absent_from_native": 50 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 76, "new_annotated_at_delivery": 50, "new_physical_absent_from_native": 76, "new_annotated_absent_from_native": 50 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 76, "new_annotated_at_delivery": 50, "new_physical_absent_from_native": 76, "new_annotated_absent_from_native": 50 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "language": "java", "graph_available": false, "observed_callable_candidates": 0, "policies": { "early_first": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__2fb50735", "language": "typescript", "graph_available": true, "observed_callable_candidates": 37, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 36, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 36, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 36, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 36, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 31, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 31, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "language": "cpp", "graph_available": true, "observed_callable_candidates": 11, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 15, "new_annotated_at_delivery": 1, "new_physical_absent_from_native": 14, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 14, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 14, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 14, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 14, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__e43d9aa5", "language": "cpp", "graph_available": true, "observed_callable_candidates": 17, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 3, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 3, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 3, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 3, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 15, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 15, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "language": "c", "graph_available": true, "observed_callable_candidates": 45, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 147, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 96, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 134, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 134, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 37, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 37, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "language": "javascript", "graph_available": true, "observed_callable_candidates": 6, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 38, "new_annotated_at_delivery": 9, "new_physical_absent_from_native": 23, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 23, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 23, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 23, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 23, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "language": "rust", "graph_available": true, "observed_callable_candidates": 78, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 46, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 45, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 45, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 45, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 137, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 137, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__03fdad45", "language": "rust", "graph_available": true, "observed_callable_candidates": 44, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 104, "new_annotated_at_delivery": 2, "new_physical_absent_from_native": 55, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 55, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 55, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-PolyBench__javascript__maintenance__bugfix__f4541fb1", "language": "javascript", "graph_available": true, "observed_callable_candidates": 5, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__16860730", "language": "rust", "graph_available": true, "observed_callable_candidates": 148, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 102, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 102, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 102, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 102, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 19, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 19, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "language": "java", "graph_available": false, "observed_callable_candidates": 0, "policies": { "early_first": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "language": "go", "graph_available": true, "observed_callable_candidates": 4, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 138, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 138, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 138, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 138, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 138, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 138, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__8b7cc5e0", "language": "java", "graph_available": false, "observed_callable_candidates": 0, "policies": { "early_first": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 0, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "language": "go", "graph_available": true, "observed_callable_candidates": 8, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 131, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 32, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 32, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 32, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 150, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 150, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2", "language": "javascript", "graph_available": true, "observed_callable_candidates": 4, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 0, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 24, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 24, "new_annotated_absent_from_native": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__42c77239", "language": "python", "graph_available": true, "observed_callable_candidates": 33, "policies": { "early_first": { "queries": 2, "new_physical_at_delivery": 214, "new_annotated_at_delivery": 11, "new_physical_absent_from_native": 212, "new_annotated_absent_from_native": 11 }, "late_same_anchor": { "queries": 2, "new_physical_at_delivery": 212, "new_annotated_at_delivery": 11, "new_physical_absent_from_native": 212, "new_annotated_absent_from_native": 11 }, "late_issue_anchor": { "queries": 2, "new_physical_at_delivery": 5, "new_annotated_at_delivery": 0, "new_physical_absent_from_native": 5, "new_annotated_absent_from_native": 0 } } } ], "totals": { "early_first": { "new_annotated_absent_from_native": 80, "new_annotated_at_delivery": 189, "new_physical_absent_from_native": 1004, "new_physical_at_delivery": 1321, "queries": 38 }, "late_same_anchor": { "new_annotated_absent_from_native": 80, "new_annotated_at_delivery": 80, "new_physical_absent_from_native": 1065, "new_physical_at_delivery": 1065, "queries": 38 }, "late_issue_anchor": { "new_annotated_absent_from_native": 50, "new_annotated_at_delivery": 50, "new_physical_absent_from_native": 802, "new_physical_at_delivery": 802, "queries": 38 } } }, "prepared_graph_prefix_replay": { "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "language": "python", "available": { "prior": true, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 31, "statuses": { "source_returned": 2 } }, "outgoing": { "new_physical_lines": 1, "statuses": { "source_returned": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 31, "statuses": { "source_returned": 2 } }, "outgoing": { "new_physical_lines": 1, "statuses": { "source_returned": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 32, "new_annotated_physical_lines": 21 }, "prepared": { "new_physical_lines": 32, "new_annotated_physical_lines": 21 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "language": "typescript", "available": { "prior": true, "prepared": false }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } }, "outgoing": { "new_physical_lines": 14, "statuses": { "source_returned": 5 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 14, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "SWE-PolyBench__typescript__maintenance__bugfix__4f3cb6be", "language": "typescript", "available": { "prior": false, "prepared": false }, "directions": {}, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__60bc9e86", "language": "python", "available": { "prior": false, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 90, "statuses": { "source_returned": 4, "source_not_returned": 1 } }, "outgoing": { "new_physical_lines": 37, "statuses": { "source_returned": 2 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 127, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "language": "c", "available": { "prior": false, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "no_unseen_neighbors": 1 } }, "outgoing": { "new_physical_lines": 26, "statuses": { "source_returned": 5 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 26, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "language": "c", "available": { "prior": false, "prepared": false }, "directions": {}, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "language": "cpp", "available": { "prior": false, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "source_not_returned": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "source_not_returned": 3 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "language": "go", "available": { "prior": true, "prepared": false }, "directions": { "prior": { "incoming": { "new_physical_lines": 132, "statuses": { "source_returned": 1, "source_not_returned": 1 } }, "outgoing": { "new_physical_lines": 16, "statuses": { "source_returned": 5 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 148, "new_annotated_physical_lines": 145 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "language": "java", "available": { "prior": false, "prepared": false }, "directions": {}, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__2fb50735", "language": "typescript", "available": { "prior": true, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 36, "statuses": { "source_returned": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 36, "statuses": { "source_returned": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 36, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 36, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "language": "cpp", "available": { "prior": false, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 1, "statuses": { "source_returned": 1 } }, "outgoing": { "new_physical_lines": 14, "statuses": { "source_returned": 3 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 15, "new_annotated_physical_lines": 1 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__e43d9aa5", "language": "cpp", "available": { "prior": false, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } }, "outgoing": { "new_physical_lines": 3, "statuses": { "source_returned": 3 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 3, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "language": "c", "available": { "prior": false, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 99, "statuses": { "source_returned": 2, "source_not_returned": 2 } }, "outgoing": { "new_physical_lines": 48, "statuses": { "source_returned": 5 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 147, "new_annotated_physical_lines": 0 } } }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "language": "javascript", "available": { "prior": true, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } }, "outgoing": { "new_physical_lines": 38, "statuses": { "source_returned": 3 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } }, "outgoing": { "new_physical_lines": 38, "statuses": { "source_returned": 3 } } } }, "union_directions": { "prior": { "new_physical_lines": 38, "new_annotated_physical_lines": 9 }, "prepared": { "new_physical_lines": 38, "new_annotated_physical_lines": 9 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "language": "rust", "available": { "prior": true, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "no_unseen_neighbors": 1 } }, "outgoing": { "new_physical_lines": 46, "statuses": { "source_returned": 5 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "no_unseen_neighbors": 1 } }, "outgoing": { "new_physical_lines": 46, "statuses": { "source_returned": 5 } } } }, "union_directions": { "prior": { "new_physical_lines": 46, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 46, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__03fdad45", "language": "rust", "available": { "prior": true, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 90, "statuses": { "source_not_returned": 1, "source_returned": 4 } }, "outgoing": { "new_physical_lines": 14, "statuses": { "source_returned": 2 } } }, "prepared": { "incoming": { "new_physical_lines": 90, "statuses": { "source_not_returned": 1, "source_returned": 4 } }, "outgoing": { "new_physical_lines": 14, "statuses": { "source_returned": 2 } } } }, "union_directions": { "prior": { "new_physical_lines": 104, "new_annotated_physical_lines": 2 }, "prepared": { "new_physical_lines": 104, "new_annotated_physical_lines": 2 } } }, { "instance_id": "SWE-PolyBench__javascript__maintenance__bugfix__f4541fb1", "language": "javascript", "available": { "prior": true, "prepared": false }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__16860730", "language": "rust", "available": { "prior": false, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "no_unseen_neighbors": 1 } }, "outgoing": { "new_physical_lines": 102, "statuses": { "source_returned": 5 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 102, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "language": "java", "available": { "prior": false, "prepared": false }, "directions": {}, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "language": "go", "available": { "prior": true, "prepared": false }, "directions": { "prior": { "incoming": { "new_physical_lines": 83, "statuses": { "source_returned": 1 } }, "outgoing": { "new_physical_lines": 55, "statuses": { "source_returned": 5 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 138, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__8b7cc5e0", "language": "java", "available": { "prior": false, "prepared": false }, "directions": {}, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "language": "go", "available": { "prior": true, "prepared": false }, "directions": { "prior": { "incoming": { "new_physical_lines": 131, "statuses": { "source_returned": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "no_unseen_neighbors": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 131, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2", "language": "javascript", "available": { "prior": true, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "no_definition_at_line": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "no_definition_at_line": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 0, "statuses": { "no_returned_neighbors": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "no_unseen_neighbors": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__42c77239", "language": "python", "available": { "prior": false, "prepared": true }, "directions": { "prior": { "incoming": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } }, "outgoing": { "new_physical_lines": 0, "statuses": { "graph_unavailable": 1 } } }, "prepared": { "incoming": { "new_physical_lines": 158, "statuses": { "source_returned": 2, "source_not_returned": 1 } }, "outgoing": { "new_physical_lines": 56, "statuses": { "source_returned": 4, "source_not_returned": 1 } } } }, "union_directions": { "prior": { "new_physical_lines": 0, "new_annotated_physical_lines": 0 }, "prepared": { "new_physical_lines": 214, "new_annotated_physical_lines": 11 } } } ], "totals": { "prior": { "new_annotated_physical_lines": 177, "new_physical_lines": 687 }, "prepared": { "new_annotated_physical_lines": 44, "new_physical_lines": 890 } } }, "completion_replays": { "replay": { "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-PolyBench__typescript__maintenance__bugfix__4f3cb6be", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__60bc9e86", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "lost_physical": 0, "lost_annotated": 0, "added_physical": 50, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__2fb50735", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__e43d9aa5", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "lost_physical": 0, "lost_annotated": 0, "added_physical": 13, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__03fdad45", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-PolyBench__javascript__maintenance__bugfix__f4541fb1", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__16860730", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__8b7cc5e0", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__42c77239", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } ], "totals": { "added_annotated": 0, "added_physical": 63, "lost_annotated": 0, "lost_physical": 0 } }, "replay-preserve-selection": { "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-PolyBench__typescript__maintenance__bugfix__4f3cb6be", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__60bc9e86", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__2fb50735", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__e43d9aa5", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__03fdad45", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-PolyBench__javascript__maintenance__bugfix__f4541fb1", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__16860730", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__8b7cc5e0", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__42c77239", "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } ], "totals": { "added_annotated": 0, "added_physical": 0, "lost_annotated": 0, "lost_physical": 0 } } }, "initial_downstream_packing": { "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "SWE-PolyBench__typescript__maintenance__bugfix__4f3cb6be", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__60bc9e86", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__cdbc5890", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 50, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 50, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__2fb50735", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__7c9ef76c", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__e43d9aa5", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__0f495035", "budgets": { "16384": { "lost_physical": 14, "lost_annotated": 0, "added_physical": 13, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 13, "added_annotated": 0 } } }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__03fdad45", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "SWE-PolyBench__javascript__maintenance__bugfix__f4541fb1", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__16860730", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__747c7f60", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__go__maintenance__bugfix__6d48775e", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__8b7cc5e0", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__997c7afd", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "Multi-SWE-Bench__javascript__maintenance__bugfix__98bbaed2", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } }, { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__42c77239", "budgets": { "16384": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 }, "32768": { "lost_physical": 0, "lost_annotated": 0, "added_physical": 0, "added_annotated": 0 } } } ], "totals": { "16384": { "added_annotated": 0, "added_physical": 63, "lost_annotated": 0, "lost_physical": 14 }, "32768": { "added_annotated": 0, "added_physical": 63, "lost_annotated": 0, "lost_physical": 0 } } }, "late_graph_8_gate": { "protocol_sha256": "e73c676224ee7b2cef73ae44f3ed6ab9672cc4ccb599ad423a8ea51c7b627b91", "analysis_sha256": "f5b94f6c7f68530de07ea1222effbff1471fb9cc7fecf47c6ebbb2906891aed9", "all_frozen_runtime_and_inputs_match": true, "gates": { "all_selected_tasks_finish_and_score": true, "all_usage_metered": true, "every_available_graph_called": true, "at_most_two_graph_calls_per_task": true, "graph_anchors_were_previously_observed_after_two_source_replies": true, "at_least_two_languages_receive_annotated_graph_source_absent_from_native": false, "primary_recall_point_increased": true, "primary_f1_point_not_lower": true }, "passed": false, "graph_adoption": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "language": "python", "graph_available": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0, "counts": { "calls": 1, "confirmed_responses": 1, "returned_physical_lines": 0, "no_unseen_neighbors": 1 }, "queries": [ { "source_replies_before": 3, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_annotated_absent_from_native": 0, "statuses": { "no_unseen_neighbors": 1 } } ] }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "language": "typescript", "graph_available": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0, "counts": { "calls": 1, "confirmed_responses": 1, "returned_physical_lines": 0, "source_not_returned": 1 }, "queries": [ { "source_replies_before": 13, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_annotated_absent_from_native": 0, "statuses": { "source_not_returned": 1 } } ] }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "language": "c", "graph_available": true, "new_physical_lines": 200, "new_annotated_lines": 200, "new_physical_absent_from_native": 197, "new_annotated_absent_from_native": 197, "counts": { "calls": 1, "confirmed_responses": 1, "returned_physical_lines": 200, "source_returned": 1 }, "queries": [ { "source_replies_before": 15, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 200, "new_annotated_lines": 200, "new_annotated_absent_from_native": 197, "statuses": { "source_returned": 1 } } ] }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "language": "cpp", "graph_available": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0, "counts": { "calls": 1, "confirmed_responses": 1, "returned_physical_lines": 0, "source_not_returned": 1 }, "queries": [ { "source_replies_before": 3, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_annotated_absent_from_native": 0, "statuses": { "source_not_returned": 1 } } ] }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "language": "go", "graph_available": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0, "counts": { "calls": 1, "confirmed_responses": 1, "returned_physical_lines": 0, "no_unseen_neighbors": 1 }, "queries": [ { "source_replies_before": 3, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_annotated_absent_from_native": 0, "statuses": { "no_unseen_neighbors": 1 } } ] }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "language": "java", "graph_available": false, "new_physical_lines": 0, "new_annotated_lines": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0, "counts": { "calls": 1, "confirmed_responses": 1, "returned_physical_lines": 0, "graph_unavailable": 1 }, "queries": [ { "source_replies_before": 9, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_annotated_absent_from_native": 0, "statuses": { "graph_unavailable": 1 } } ] }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "language": "javascript", "graph_available": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_physical_absent_from_native": 0, "new_annotated_absent_from_native": 0, "counts": { "calls": 2, "confirmed_responses": 2, "returned_physical_lines": 0, "no_definition_at_line": 2 }, "queries": [ { "source_replies_before": 13, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_annotated_absent_from_native": 0, "statuses": { "no_definition_at_line": 1 } }, { "source_replies_before": 13, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 0, "new_annotated_lines": 0, "new_annotated_absent_from_native": 0, "statuses": { "no_definition_at_line": 1 } } ] }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "language": "rust", "graph_available": true, "new_physical_lines": 20, "new_annotated_lines": 0, "new_physical_absent_from_native": 15, "new_annotated_absent_from_native": 0, "counts": { "calls": 1, "confirmed_responses": 1, "returned_physical_lines": 20, "source_returned": 6 }, "queries": [ { "source_replies_before": 10, "anchor_previously_observed": true, "confirmed": true, "new_physical_lines": 20, "new_annotated_lines": 0, "new_annotated_absent_from_native": 0, "statuses": { "source_returned": 6 } } ] } ], "primary_metrics": { "recall": { "baseline": 0.39854522032438433, "candidate": 0.4162128649381706, "difference": 0.017667644613786265, "paired_bootstrap_95_interval": [ -0.0436286937237943, 0.08226140049602329 ] }, "precision": { "baseline": 0.34139459196207783, "candidate": 0.3456469534940558, "difference": 0.004252361531977935, "paired_bootstrap_95_interval": [ -0.09686873487212115, 0.10347369645560842 ] }, "f1": { "baseline": 0.32846291218941726, "candidate": 0.3529206038528339, "difference": 0.02445769166341666, "paired_bootstrap_95_interval": [ -0.010614238100404731, 0.07064668308772286 ] } }, "sdk_reported_estimate_usd": 6.796706500000001, "scope": "Development selection only; no independent validation, causal source-set effect, Pass@1 or leaderboard claim.", "diagnostic_correction": "Overlap counts corrected after frozen analysis using official path normalization. Original protocol, scores and first gate file remain unchanged; this amendment does not relax a gate." }, "earlier_8_source_attribution": { "development-functions": { "n_tasks": 8, "totals": { "completed_grep": { "new_physical_lines": 1901, "annotated_lines": 381, "responses_adding_source": 26, "annotated_fraction": 0.20042083114150447 }, "completed_read": { "new_physical_lines": 584, "annotated_lines": 108, "responses_adding_source": 18, "annotated_fraction": 0.18493150684931506 }, "original_grep": { "new_physical_lines": 451, "annotated_lines": 80, "responses_adding_source": 32, "annotated_fraction": 0.17738359201773837 }, "original_read": { "new_physical_lines": 4409, "annotated_lines": 1035, "responses_adding_source": 39, "annotated_fraction": 0.23474710818779768 } }, "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "categories": { "original_grep": { "new_physical_lines": 15, "annotated_lines": 14, "responses_adding_source": 1 }, "completed_grep": { "new_physical_lines": 64, "annotated_lines": 51, "responses_adding_source": 1 }, "original_read": { "new_physical_lines": 123, "annotated_lines": 37, "responses_adding_source": 2 }, "completed_read": { "new_physical_lines": 35, "annotated_lines": 35, "responses_adding_source": 1 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "categories": { "original_grep": { "new_physical_lines": 65, "annotated_lines": 0, "responses_adding_source": 5 }, "completed_grep": { "new_physical_lines": 158, "annotated_lines": 0, "responses_adding_source": 3 }, "original_read": { "new_physical_lines": 611, "annotated_lines": 60, "responses_adding_source": 7 }, "completed_read": { "new_physical_lines": 98, "annotated_lines": 0, "responses_adding_source": 2 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "categories": { "original_grep": { "new_physical_lines": 105, "annotated_lines": 17, "responses_adding_source": 6 }, "completed_grep": { "new_physical_lines": 420, "annotated_lines": 41, "responses_adding_source": 5 }, "original_read": { "new_physical_lines": 989, "annotated_lines": 328, "responses_adding_source": 7 }, "completed_read": { "new_physical_lines": 89, "annotated_lines": 10, "responses_adding_source": 4 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "categories": { "original_grep": { "new_physical_lines": 49, "annotated_lines": 11, "responses_adding_source": 1 }, "completed_grep": { "new_physical_lines": 35, "annotated_lines": 0, "responses_adding_source": 1 }, "original_read": { "new_physical_lines": 310, "annotated_lines": 196, "responses_adding_source": 1 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "categories": { "original_grep": { "new_physical_lines": 12, "annotated_lines": 6, "responses_adding_source": 3 }, "completed_grep": { "new_physical_lines": 250, "annotated_lines": 77, "responses_adding_source": 3 }, "original_read": { "new_physical_lines": 227, "annotated_lines": 100, "responses_adding_source": 3 }, "completed_read": { "new_physical_lines": 77, "annotated_lines": 59, "responses_adding_source": 2 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "categories": { "original_grep": { "new_physical_lines": 53, "annotated_lines": 18, "responses_adding_source": 4 }, "completed_grep": { "new_physical_lines": 224, "annotated_lines": 85, "responses_adding_source": 4 }, "original_read": { "new_physical_lines": 364, "annotated_lines": 43, "responses_adding_source": 4 }, "completed_read": { "new_physical_lines": 16, "annotated_lines": 0, "responses_adding_source": 2 } } }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "categories": { "original_read": { "new_physical_lines": 954, "annotated_lines": 167, "responses_adding_source": 10 }, "original_grep": { "new_physical_lines": 81, "annotated_lines": 8, "responses_adding_source": 4 }, "completed_grep": { "new_physical_lines": 217, "annotated_lines": 35, "responses_adding_source": 2 }, "completed_read": { "new_physical_lines": 235, "annotated_lines": 4, "responses_adding_source": 5 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "categories": { "original_grep": { "new_physical_lines": 71, "annotated_lines": 6, "responses_adding_source": 8 }, "completed_grep": { "new_physical_lines": 533, "annotated_lines": 92, "responses_adding_source": 7 }, "original_read": { "new_physical_lines": 831, "annotated_lines": 104, "responses_adding_source": 5 }, "completed_read": { "new_physical_lines": 34, "annotated_lines": 0, "responses_adding_source": 2 } } } ] }, "required-hop-control-functions": { "n_tasks": 8, "totals": { "completed_grep": { "new_physical_lines": 1931, "annotated_lines": 335, "responses_adding_source": 29, "annotated_fraction": 0.17348524080787156 }, "completed_read": { "new_physical_lines": 640, "annotated_lines": 102, "responses_adding_source": 19, "annotated_fraction": 0.159375 }, "original_grep": { "new_physical_lines": 542, "annotated_lines": 72, "responses_adding_source": 35, "annotated_fraction": 0.13284132841328414 }, "original_read": { "new_physical_lines": 3952, "annotated_lines": 1058, "responses_adding_source": 37, "annotated_fraction": 0.26771255060728744 } }, "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "categories": { "original_grep": { "new_physical_lines": 15, "annotated_lines": 14, "responses_adding_source": 1 }, "completed_grep": { "new_physical_lines": 64, "annotated_lines": 51, "responses_adding_source": 1 }, "original_read": { "new_physical_lines": 152, "annotated_lines": 43, "responses_adding_source": 3 }, "completed_read": { "new_physical_lines": 110, "annotated_lines": 30, "responses_adding_source": 2 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "categories": { "original_grep": { "new_physical_lines": 68, "annotated_lines": 0, "responses_adding_source": 4 }, "completed_grep": { "new_physical_lines": 217, "annotated_lines": 0, "responses_adding_source": 3 }, "original_read": { "new_physical_lines": 479, "annotated_lines": 0, "responses_adding_source": 6 }, "completed_read": { "new_physical_lines": 96, "annotated_lines": 0, "responses_adding_source": 1 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "categories": { "original_grep": { "new_physical_lines": 97, "annotated_lines": 12, "responses_adding_source": 8 }, "completed_grep": { "new_physical_lines": 336, "annotated_lines": 41, "responses_adding_source": 5 }, "original_read": { "new_physical_lines": 889, "annotated_lines": 377, "responses_adding_source": 6 }, "completed_read": { "new_physical_lines": 93, "annotated_lines": 11, "responses_adding_source": 4 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "categories": { "original_grep": { "new_physical_lines": 50, "annotated_lines": 11, "responses_adding_source": 2 }, "completed_grep": { "new_physical_lines": 35, "annotated_lines": 0, "responses_adding_source": 1 }, "original_read": { "new_physical_lines": 310, "annotated_lines": 196, "responses_adding_source": 1 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "categories": { "original_grep": { "new_physical_lines": 11, "annotated_lines": 6, "responses_adding_source": 4 }, "completed_grep": { "new_physical_lines": 280, "annotated_lines": 76, "responses_adding_source": 4 }, "original_read": { "new_physical_lines": 79, "annotated_lines": 79, "responses_adding_source": 1 }, "completed_read": { "new_physical_lines": 54, "annotated_lines": 54, "responses_adding_source": 1 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "categories": { "original_grep": { "new_physical_lines": 56, "annotated_lines": 11, "responses_adding_source": 7 }, "completed_grep": { "new_physical_lines": 197, "annotated_lines": 37, "responses_adding_source": 7 }, "original_read": { "new_physical_lines": 358, "annotated_lines": 109, "responses_adding_source": 4 }, "completed_read": { "new_physical_lines": 18, "annotated_lines": 2, "responses_adding_source": 3 } } }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "categories": { "original_read": { "new_physical_lines": 928, "annotated_lines": 171, "responses_adding_source": 10 }, "completed_read": { "new_physical_lines": 213, "annotated_lines": 0, "responses_adding_source": 5 }, "original_grep": { "new_physical_lines": 118, "annotated_lines": 8, "responses_adding_source": 3 }, "completed_grep": { "new_physical_lines": 218, "annotated_lines": 35, "responses_adding_source": 2 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "categories": { "original_grep": { "new_physical_lines": 127, "annotated_lines": 10, "responses_adding_source": 6 }, "completed_grep": { "new_physical_lines": 584, "annotated_lines": 95, "responses_adding_source": 6 }, "original_read": { "new_physical_lines": 757, "annotated_lines": 83, "responses_adding_source": 6 }, "completed_read": { "new_physical_lines": 56, "annotated_lines": 5, "responses_adding_source": 3 } } } ] }, "required-hop-candidate": { "n_tasks": 8, "totals": { "completed_grep": { "new_physical_lines": 2123, "annotated_lines": 278, "responses_adding_source": 30, "annotated_fraction": 0.13094677343382008 }, "completed_read": { "new_physical_lines": 382, "annotated_lines": 115, "responses_adding_source": 16, "annotated_fraction": 0.3010471204188482 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0, "annotated_fraction": 0 }, "original_grep": { "new_physical_lines": 642, "annotated_lines": 96, "responses_adding_source": 40, "annotated_fraction": 0.14953271028037382 }, "original_read": { "new_physical_lines": 4495, "annotated_lines": 1130, "responses_adding_source": 39, "annotated_fraction": 0.25139043381535037 } }, "cases": [ { "instance_id": "SWE-Bench-Verified__python__maintenance__bugfix__1409977d", "categories": { "original_grep": { "new_physical_lines": 17, "annotated_lines": 14, "responses_adding_source": 2 }, "completed_grep": { "new_physical_lines": 72, "annotated_lines": 51, "responses_adding_source": 2 }, "original_read": { "new_physical_lines": 48, "annotated_lines": 42, "responses_adding_source": 1 }, "completed_read": { "new_physical_lines": 76, "annotated_lines": 30, "responses_adding_source": 1 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0 } } }, { "instance_id": "Multi-SWE-Bench__typescript__maintenance__bugfix__7c41997b", "categories": { "original_grep": { "new_physical_lines": 132, "annotated_lines": 2, "responses_adding_source": 6 }, "completed_grep": { "new_physical_lines": 339, "annotated_lines": 0, "responses_adding_source": 4 }, "original_read": { "new_physical_lines": 418, "annotated_lines": 59, "responses_adding_source": 7 }, "completed_read": { "new_physical_lines": 103, "annotated_lines": 0, "responses_adding_source": 2 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0 } } }, { "instance_id": "Multi-SWE-Bench__c__maintenance__bugfix__b8c88ac8", "categories": { "original_grep": { "new_physical_lines": 145, "annotated_lines": 22, "responses_adding_source": 9 }, "completed_grep": { "new_physical_lines": 481, "annotated_lines": 0, "responses_adding_source": 6 }, "original_read": { "new_physical_lines": 1110, "annotated_lines": 384, "responses_adding_source": 8 }, "completed_read": { "new_physical_lines": 47, "annotated_lines": 12, "responses_adding_source": 4 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0 } } }, { "instance_id": "Multi-SWE-Bench__cpp__maintenance__bugfix__8ebb764e", "categories": { "original_grep": { "new_physical_lines": 50, "annotated_lines": 11, "responses_adding_source": 2 }, "completed_grep": { "new_physical_lines": 35, "annotated_lines": 0, "responses_adding_source": 1 }, "original_read": { "new_physical_lines": 310, "annotated_lines": 196, "responses_adding_source": 1 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0 } } }, { "instance_id": "SWE-Bench-Pro__go__maintenance__bugfix__720b4d92", "categories": { "original_grep": { "new_physical_lines": 9, "annotated_lines": 6, "responses_adding_source": 3 }, "completed_grep": { "new_physical_lines": 198, "annotated_lines": 76, "responses_adding_source": 3 }, "original_read": { "new_physical_lines": 79, "annotated_lines": 79, "responses_adding_source": 1 }, "completed_read": { "new_physical_lines": 53, "annotated_lines": 53, "responses_adding_source": 1 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0 } } }, { "instance_id": "Multi-SWE-Bench__java__maintenance__bugfix__07d7817b", "categories": { "original_grep": { "new_physical_lines": 60, "annotated_lines": 20, "responses_adding_source": 5 }, "completed_grep": { "new_physical_lines": 229, "annotated_lines": 30, "responses_adding_source": 5 }, "original_read": { "new_physical_lines": 513, "annotated_lines": 100, "responses_adding_source": 5 }, "completed_read": { "new_physical_lines": 24, "annotated_lines": 20, "responses_adding_source": 2 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0 } } }, { "instance_id": "SWE-Bench-Pro__javascript__maintenance__bugfix__4eb0e647", "categories": { "original_grep": { "new_physical_lines": 103, "annotated_lines": 16, "responses_adding_source": 6 }, "completed_grep": { "new_physical_lines": 237, "annotated_lines": 28, "responses_adding_source": 2 }, "original_read": { "new_physical_lines": 983, "annotated_lines": 175, "responses_adding_source": 10 }, "completed_read": { "new_physical_lines": 34, "annotated_lines": 0, "responses_adding_source": 3 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0 } } }, { "instance_id": "Multi-SWE-Bench__rust__maintenance__bugfix__3be02163", "categories": { "original_grep": { "new_physical_lines": 126, "annotated_lines": 5, "responses_adding_source": 7 }, "completed_grep": { "new_physical_lines": 532, "annotated_lines": 93, "responses_adding_source": 7 }, "original_read": { "new_physical_lines": 1034, "annotated_lines": 95, "responses_adding_source": 6 }, "completed_read": { "new_physical_lines": 45, "annotated_lines": 0, "responses_adding_source": 3 }, "graph": { "new_physical_lines": 0, "annotated_lines": 0, "responses_adding_source": 0 } } } ] } }, "all_frozen_inputs_and_runtime_hashes_match": true, "input_receipts_sha256": "d3e430f26aaa0edc3a6ba75b154c6b74ed20b371aeabc0ba5738c1252adbd46e" }