{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HIRTRTXLAM5PT7YZYIT3FYF3CQ","short_pith_number":"pith:HIRTRTXL","schema_version":"1.0","canonical_sha256":"3a2338ceeb033af9ff19c227b2e0bb142331ce3d43eebad3dcca1e683b499812","source":{"kind":"arxiv","id":"2603.24631","version":2},"attestation_state":"computed","paper":{"title":"Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Baishakhi Ray, Dingmin Wang, Farima Farmahinifarahani, Myeongsoo Kim, Rajdeep Mukherjee, Shweta Garg, Siwei Cui, Terry Yue Zhuo, Varun Kumar","submitted_at":"2026-03-25T05:27:03Z","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,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.24631","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-25T05:27:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22bffe01d677d8052b5720991b4069e5843c856a3a3454fa4e79690960f2520a","abstract_canon_sha256":"4602cce8b26363bdc02025b62cf250c166eddf1bb7d446286e0a300670406eeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:08.279097Z","signature_b64":"b3Z+fI0IhneIqNDDTJz14dlqzlsU289wpw5uIaUfTCSMN3tkOc4kTNKDJUgAP5hIH1fqQZBVx5Ri1NCtANj9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a2338ceeb033af9ff19c227b2e0bb142331ce3d43eebad3dcca1e683b499812","last_reissued_at":"2026-05-28T01:04:08.278553Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:08.278553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Baishakhi Ray, Dingmin Wang, Farima Farmahinifarahani, Myeongsoo Kim, Rajdeep Mukherjee, Shweta Garg, Siwei Cui, Terry Yue Zhuo, Varun Kumar","submitted_at":"2026-03-25T05:27:03Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.24631","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.24631/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.24631","created_at":"2026-05-28T01:04:08.278616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.24631v2","created_at":"2026-05-28T01:04:08.278616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24631","created_at":"2026-05-28T01:04:08.278616+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIRTRTXLAM5P","created_at":"2026-05-28T01:04:08.278616+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIRTRTXLAM5PT7YZ","created_at":"2026-05-28T01:04:08.278616+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIRTRTXL","created_at":"2026-05-28T01:04:08.278616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ","json":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ.json","graph_json":"https://pith.science/api/pith-number/HIRTRTXLAM5PT7YZYIT3FYF3CQ/graph.json","events_json":"https://pith.science/api/pith-number/HIRTRTXLAM5PT7YZYIT3FYF3CQ/events.json","paper":"https://pith.science/paper/HIRTRTXL"},"agent_actions":{"view_html":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ","download_json":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ.json","view_paper":"https://pith.science/paper/HIRTRTXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.24631&json=true","fetch_graph":"https://pith.science/api/pith-number/HIRTRTXLAM5PT7YZYIT3FYF3CQ/graph.json","fetch_events":"https://pith.science/api/pith-number/HIRTRTXLAM5PT7YZYIT3FYF3CQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ/action/storage_attestation","attest_author":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ/action/author_attestation","sign_citation":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ/action/citation_signature","submit_replication":"https://pith.science/pith/HIRTRTXLAM5PT7YZYIT3FYF3CQ/action/replication_record"}},"created_at":"2026-05-28T01:04:08.278616+00:00","updated_at":"2026-05-28T01:04:08.278616+00:00"}