{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZRQNUQ3IYWH5IVP4JUSW4MXMY7","short_pith_number":"pith:ZRQNUQ3I","canonical_record":{"source":{"id":"2505.23419","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-29T13:09:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c0abb368441d1aa01251a2bf65275f53603e481df7010658006b24529f8cb33e","abstract_canon_sha256":"62dd631ef9f12712e18c62033217fbed302047ed09abf58893e4cf48cddcd02f"},"schema_version":"1.0"},"canonical_sha256":"cc60da4368c58fd455fc4d256e32ecc7fe30c3e0af860554d16b9212ea2b3b63","source":{"kind":"arxiv","id":"2505.23419","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23419","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23419v2","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23419","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZRQNUQ3IYWH5","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"ZRQNUQ3IYWH5IVP4","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"ZRQNUQ3I","created_at":"2026-07-05T11:13:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZRQNUQ3IYWH5IVP4JUSW4MXMY7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23419","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-29T13:09:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c0abb368441d1aa01251a2bf65275f53603e481df7010658006b24529f8cb33e","abstract_canon_sha256":"62dd631ef9f12712e18c62033217fbed302047ed09abf58893e4cf48cddcd02f"},"schema_version":"1.0"},"canonical_sha256":"cc60da4368c58fd455fc4d256e32ecc7fe30c3e0af860554d16b9212ea2b3b63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:27.773296Z","signature_b64":"hl7SwDOnopfTrlAF+3wczzoXlYB6HDXhO9O+ALyzwYVc8zkuBgGc1kYm1XDPMXEo5iIeFtTBqNXxLIH5MiblBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc60da4368c58fd455fc4d256e32ecc7fe30c3e0af860554d16b9212ea2b3b63","last_reissued_at":"2026-07-05T11:13:27.772807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:27.772807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23419","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogKPTQeeYcvH8fT/ezxe5puL/RJKB6Q7RNdz48KsmwVt7pI3Vk3Efix/1j1uyx1raFDEYGcb4NbgwXdtq/bVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:39:45.711855Z"},"content_sha256":"43c7a4d42b4661d7537f4a066715a81afe68cdcab1c72ce5e5d58b7480ffe0ea","schema_version":"1.0","event_id":"sha256:43c7a4d42b4661d7537f4a066715a81afe68cdcab1c72ce5e5d58b7480ffe0ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZRQNUQ3IYWH5IVP4JUSW4MXMY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SWE-bench Goes Live!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Bowen Li, Chaoyun Zhang, Chengxing Xie, Dongmei Zhang, Elsie Nallipogu, Junhao Wang, Linghao Zhang, Maoquan Wang, Qingwei Lin, Saravan Rajmohan, Shengyu Fu, Shilin He, Yingnong Dang, Yufan Huang, Yu Kang","submitted_at":"2025-05-29T13:09:44Z","abstract_excerpt":"The issue-resolving task, where a model generates patches to fix real-world bugs, has emerged as a critical benchmark for evaluating the capabilities of large language models (LLMs). While SWE-bench and its variants have become standard in this domain, they suffer from key limitations: they have not been updated since their initial releases, cover a narrow set of repositories, and depend heavily on manual effort for instance construction and environment setup. These factors hinder scalability and introduce risks of overfitting and data contamination. In this work, we present SWE-bench-Live, a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23419","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/2505.23419/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6VrasLh+HykHsmOvZ73rtDXwKAvbgj/k75feB4onBQ9CpjkwtbGZzCosCiLyUoM81yw7m0leVbh/A8UzA6o2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:39:45.712369Z"},"content_sha256":"15eef8cb7628c1dbf3f7dfbfed8cc49d279779f1e96b3f1e87b071a58bf11675","schema_version":"1.0","event_id":"sha256:15eef8cb7628c1dbf3f7dfbfed8cc49d279779f1e96b3f1e87b071a58bf11675"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZRQNUQ3IYWH5IVP4JUSW4MXMY7/bundle.json","state_url":"https://pith.science/pith/ZRQNUQ3IYWH5IVP4JUSW4MXMY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZRQNUQ3IYWH5IVP4JUSW4MXMY7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T20:39:45Z","links":{"resolver":"https://pith.science/pith/ZRQNUQ3IYWH5IVP4JUSW4MXMY7","bundle":"https://pith.science/pith/ZRQNUQ3IYWH5IVP4JUSW4MXMY7/bundle.json","state":"https://pith.science/pith/ZRQNUQ3IYWH5IVP4JUSW4MXMY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZRQNUQ3IYWH5IVP4JUSW4MXMY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZRQNUQ3IYWH5IVP4JUSW4MXMY7","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":"62dd631ef9f12712e18c62033217fbed302047ed09abf58893e4cf48cddcd02f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-29T13:09:44Z","title_canon_sha256":"c0abb368441d1aa01251a2bf65275f53603e481df7010658006b24529f8cb33e"},"schema_version":"1.0","source":{"id":"2505.23419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23419","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23419v2","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23419","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZRQNUQ3IYWH5","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"ZRQNUQ3IYWH5IVP4","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"ZRQNUQ3I","created_at":"2026-07-05T11:13:27Z"}],"graph_snapshots":[{"event_id":"sha256:15eef8cb7628c1dbf3f7dfbfed8cc49d279779f1e96b3f1e87b071a58bf11675","target":"graph","created_at":"2026-07-05T11:13:27Z","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/2505.23419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The issue-resolving task, where a model generates patches to fix real-world bugs, has emerged as a critical benchmark for evaluating the capabilities of large language models (LLMs). While SWE-bench and its variants have become standard in this domain, they suffer from key limitations: they have not been updated since their initial releases, cover a narrow set of repositories, and depend heavily on manual effort for instance construction and environment setup. These factors hinder scalability and introduce risks of overfitting and data contamination. In this work, we present SWE-bench-Live, a ","authors_text":"Bowen Li, Chaoyun Zhang, Chengxing Xie, Dongmei Zhang, Elsie Nallipogu, Junhao Wang, Linghao Zhang, Maoquan Wang, Qingwei Lin, Saravan Rajmohan, Shengyu Fu, Shilin He, Yingnong Dang, Yufan Huang, Yu Kang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-29T13:09:44Z","title":"SWE-bench Goes Live!"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23419","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":"sha256:43c7a4d42b4661d7537f4a066715a81afe68cdcab1c72ce5e5d58b7480ffe0ea","target":"record","created_at":"2026-07-05T11:13:27Z","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":"62dd631ef9f12712e18c62033217fbed302047ed09abf58893e4cf48cddcd02f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-29T13:09:44Z","title_canon_sha256":"c0abb368441d1aa01251a2bf65275f53603e481df7010658006b24529f8cb33e"},"schema_version":"1.0","source":{"id":"2505.23419","kind":"arxiv","version":2}},"canonical_sha256":"cc60da4368c58fd455fc4d256e32ecc7fe30c3e0af860554d16b9212ea2b3b63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc60da4368c58fd455fc4d256e32ecc7fe30c3e0af860554d16b9212ea2b3b63","first_computed_at":"2026-07-05T11:13:27.772807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:27.772807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hl7SwDOnopfTrlAF+3wczzoXlYB6HDXhO9O+ALyzwYVc8zkuBgGc1kYm1XDPMXEo5iIeFtTBqNXxLIH5MiblBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:27.773296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43c7a4d42b4661d7537f4a066715a81afe68cdcab1c72ce5e5d58b7480ffe0ea","sha256:15eef8cb7628c1dbf3f7dfbfed8cc49d279779f1e96b3f1e87b071a58bf11675"],"state_sha256":"04c94fa3691c6f81bfec32c0f8e652f34c590a3b39c6f4e8c038e88f22898ac7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0RmxYUciRVB/SvtjXn1DUxZhku9hX1fvz/VxTt3ZiBfxu5bvUHJReL8JXzdoVuARrh204LwTH+aNfG1YBzuCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:39:45.715956Z","bundle_sha256":"c39092b2163b49a79f1f86d647ba3125779f4119c6d7bdccd2f26721342167dc"}}