{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HIRTRTXLAM5PT7YZYIT3FYF3CQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4602cce8b26363bdc02025b62cf250c166eddf1bb7d446286e0a300670406eeb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-25T05:27:03Z","title_canon_sha256":"22bffe01d677d8052b5720991b4069e5843c856a3a3454fa4e79690960f2520a"},"schema_version":"1.0","source":{"id":"2603.24631","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.24631","created_at":"2026-05-28T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2603.24631v2","created_at":"2026-05-28T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24631","created_at":"2026-05-28T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"HIRTRTXLAM5P","created_at":"2026-05-28T01:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"HIRTRTXLAM5PT7YZ","created_at":"2026-05-28T01:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"HIRTRTXL","created_at":"2026-05-28T01:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:de31a8f304b9b44dc34bd541b0249d9681118f230f4e8e3edb6b160b07c19f87","target":"graph","created_at":"2026-05-28T01:04:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.24631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code agents resolve 65-70% of SWE-bench Verified issues, but Pass@1 cannot tell us why the rest fail, and, as we show, capable-model failures are systematically misdiagnosed without trajectory data. We introduce TRAJEVAL, a training-free decomposition of agent trajectories into reference-patch-aligned search, read, and edit stages, and apply it across 16,758 trajectories spanning three architectures and seven models. The dominant failure of capable models is not localization: 60-69% of failures on SWE-Agent and OpenHands reach and edit the correct functions yet still produce incorrect patches,","authors_text":"Baishakhi Ray, Dingmin Wang, Farima Farmahinifarahani, Myeongsoo Kim, Rajdeep Mukherjee, Shweta Garg, Siwei Cui, Terry Yue Zhuo, Varun Kumar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-25T05:27:03Z","title":"Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.24631","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e55b95b56214da524a1602977fd688891369fd4e11b1adf5d8747499792ec04b","target":"record","created_at":"2026-05-28T01:04:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4602cce8b26363bdc02025b62cf250c166eddf1bb7d446286e0a300670406eeb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-25T05:27:03Z","title_canon_sha256":"22bffe01d677d8052b5720991b4069e5843c856a3a3454fa4e79690960f2520a"},"schema_version":"1.0","source":{"id":"2603.24631","kind":"arxiv","version":2}},"canonical_sha256":"3a2338ceeb033af9ff19c227b2e0bb142331ce3d43eebad3dcca1e683b499812","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a2338ceeb033af9ff19c227b2e0bb142331ce3d43eebad3dcca1e683b499812","first_computed_at":"2026-05-28T01:04:08.278553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:08.278553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b3Z+fI0IhneIqNDDTJz14dlqzlsU289wpw5uIaUfTCSMN3tkOc4kTNKDJUgAP5hIH1fqQZBVx5Ri1NCtANj9Dg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:08.279097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.24631","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e55b95b56214da524a1602977fd688891369fd4e11b1adf5d8747499792ec04b","sha256:de31a8f304b9b44dc34bd541b0249d9681118f230f4e8e3edb6b160b07c19f87"],"state_sha256":"5778f6126d572cca92dcc317c2698d16a11cc7bc15f07848a65a8dfaac84eae4"}