{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HBIETVWSXR2ERP3IFOKMVZVGJ6","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":"2d5f4aa262e8840be3e47e47b6399c2a6588727ff327c06fd9f46e609e946550","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-19T14:02:21Z","title_canon_sha256":"81a4e1ce3f7c2a94d4bc541d7cc371f5e33001671298526c5f9299e35cd6605a"},"schema_version":"1.0","source":{"id":"2503.15223","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15223","created_at":"2026-07-05T12:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15223v2","created_at":"2026-07-05T12:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15223","created_at":"2026-07-05T12:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"HBIETVWSXR2E","created_at":"2026-07-05T12:07:04Z"},{"alias_kind":"pith_short_16","alias_value":"HBIETVWSXR2ERP3I","created_at":"2026-07-05T12:07:04Z"},{"alias_kind":"pith_short_8","alias_value":"HBIETVWS","created_at":"2026-07-05T12:07:04Z"}],"graph_snapshots":[{"event_id":"sha256:ea8469975f52c524f95e3da2a06181c4e85f0fb13f4f9ae595828eb5fe2a564e","target":"graph","created_at":"2026-07-05T12:07:04Z","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/2503.15223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated issue solving aims to resolve real-world issues in software repositories. The most popular benchmarks for automated issue solving are SWE-bench and its human-filtered subset SWE-bench Verified. These benchmarks leverage testing to validate generated patches. However, because testing is rarely exhaustive, a patch may pass the tests but nevertheless fail to match the developers' expectations. Unfortunately, it is currently unclear to what extent evaluations performed with SWE-bench suffer from such plausible but incorrect patches. This paper presents an in-depth empirical study of the ","authors_text":"Michael Pradel, You Wang, Zhongxin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-19T14:02:21Z","title":"Are \"Solved Issues\" in SWE-bench Really Solved Correctly? An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15223","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":"sha256:59adb5d23662e92d69a217bb56c37656b922aabfdf9e8163fef2ea5edeaa1c6b","target":"record","created_at":"2026-07-05T12:07:04Z","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":"2d5f4aa262e8840be3e47e47b6399c2a6588727ff327c06fd9f46e609e946550","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-19T14:02:21Z","title_canon_sha256":"81a4e1ce3f7c2a94d4bc541d7cc371f5e33001671298526c5f9299e35cd6605a"},"schema_version":"1.0","source":{"id":"2503.15223","kind":"arxiv","version":2}},"canonical_sha256":"385049d6d2bc7448bf682b94cae6a64fa29c108409ace171d2c1c32da28b38c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"385049d6d2bc7448bf682b94cae6a64fa29c108409ace171d2c1c32da28b38c9","first_computed_at":"2026-07-05T12:07:04.077184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:04.077184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3R1BvEkRwZX4KqDjbXBSWba9xi/g7ssI4aSttJ4r8Yr6mmhlzVUP1i03w1RaU4wyw4+g71Myv2U8Dt7hdeahCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:04.077642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15223","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59adb5d23662e92d69a217bb56c37656b922aabfdf9e8163fef2ea5edeaa1c6b","sha256:ea8469975f52c524f95e3da2a06181c4e85f0fb13f4f9ae595828eb5fe2a564e"],"state_sha256":"c908fd63bf6557dcbc5e98bfeb17b1258b9cc28e3f84867d0bcfe1ca7e2b1fb3"}