{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XL6J5GZF7MLLXBOI6IY7YFYTER","short_pith_number":"pith:XL6J5GZF","canonical_record":{"source":{"id":"2507.11059","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-15T07:52:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"471a80d8bb4b463849190992ec9102b3ad602f0911dab0da34301385c0c9e11a","abstract_canon_sha256":"e29d2821afe42ca8c716ef3a0295651c41ff59b3f23b92330705cae509bfc591"},"schema_version":"1.0"},"canonical_sha256":"bafc9e9b25fb16bb85c8f231fc17132471cdb6acdd78d0fb2541a18fcde8cd7d","source":{"kind":"arxiv","id":"2507.11059","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11059","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11059v2","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11059","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"XL6J5GZF7MLL","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"pith_short_16","alias_value":"XL6J5GZF7MLLXBOI","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"pith_short_8","alias_value":"XL6J5GZF","created_at":"2026-07-05T11:38:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XL6J5GZF7MLLXBOI6IY7YFYTER","target":"record","payload":{"canonical_record":{"source":{"id":"2507.11059","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-15T07:52:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"471a80d8bb4b463849190992ec9102b3ad602f0911dab0da34301385c0c9e11a","abstract_canon_sha256":"e29d2821afe42ca8c716ef3a0295651c41ff59b3f23b92330705cae509bfc591"},"schema_version":"1.0"},"canonical_sha256":"bafc9e9b25fb16bb85c8f231fc17132471cdb6acdd78d0fb2541a18fcde8cd7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:52.413097Z","signature_b64":"JoQEl3ZyoKMCXYw9eB7TViZcBqacY7f0JfjqpFfaiJVsPP1Ck++HnXYp4uxuyHLLOs+9NReETMc0VohTnm6qDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bafc9e9b25fb16bb85c8f231fc17132471cdb6acdd78d0fb2541a18fcde8cd7d","last_reissued_at":"2026-07-05T11:38:52.412601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:52.412601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.11059","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":"2026-07-05T11:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dvvzovk51iIW8/c0h0/3gP+F2+iy6OX9Az0vzaBFmvQJyH3cPy1CCv1j8R/bFGZNOnoO5x1ffHzP2jnADCj4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:51:34.761738Z"},"content_sha256":"e9cddb480b2c6aac71ac2e35f12f005a80fda1b3e9ed6d6d09a871a0d765d601","schema_version":"1.0","event_id":"sha256:e9cddb480b2c6aac71ac2e35f12f005a80fda1b3e9ed6d6d09a871a0d765d601"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XL6J5GZF7MLLXBOI6IY7YFYTER","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Aidar Valeev, Alena Fenogenova, Dmitry Babayev, Ivan Lopatin, Mikhail Ivanov, Pavel Adamenko, Pavel Zadorozhny, Rodion Levichev, Valentin Malykh","submitted_at":"2025-07-15T07:52:33Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset. Recent studies have uncovered severe data contamination issues, e.g. SWE-bench reports 32.67% of successful patches involve direct solution leakage and 31.08% pass due to inadequate test cases. We introduce SWE-MERA, a dynamic, continuously updated benchmark designed to address these fundamental challenges through an automated collection of real-world GitHub issues and rigorous quality validation. Our approach im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11059","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/2507.11059/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":"2026-07-05T11:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wV9gyQrQb/fCntrjRn3la1DgxZm7sVI/omjVtM3KAobQAoi6m2iXXsO8mO524VfHO0ypCq2x5OExd3Y0GuWVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:51:34.762313Z"},"content_sha256":"478213f1a92d938f0ae82c7d20b9c42591c3c1032e668c2acc09090cd58118e6","schema_version":"1.0","event_id":"sha256:478213f1a92d938f0ae82c7d20b9c42591c3c1032e668c2acc09090cd58118e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XL6J5GZF7MLLXBOI6IY7YFYTER/bundle.json","state_url":"https://pith.science/pith/XL6J5GZF7MLLXBOI6IY7YFYTER/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XL6J5GZF7MLLXBOI6IY7YFYTER/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":"2026-08-22T22:51:34Z","links":{"resolver":"https://pith.science/pith/XL6J5GZF7MLLXBOI6IY7YFYTER","bundle":"https://pith.science/pith/XL6J5GZF7MLLXBOI6IY7YFYTER/bundle.json","state":"https://pith.science/pith/XL6J5GZF7MLLXBOI6IY7YFYTER/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XL6J5GZF7MLLXBOI6IY7YFYTER/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XL6J5GZF7MLLXBOI6IY7YFYTER","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":"e29d2821afe42ca8c716ef3a0295651c41ff59b3f23b92330705cae509bfc591","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-15T07:52:33Z","title_canon_sha256":"471a80d8bb4b463849190992ec9102b3ad602f0911dab0da34301385c0c9e11a"},"schema_version":"1.0","source":{"id":"2507.11059","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11059","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11059v2","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11059","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"XL6J5GZF7MLL","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"pith_short_16","alias_value":"XL6J5GZF7MLLXBOI","created_at":"2026-07-05T11:38:52Z"},{"alias_kind":"pith_short_8","alias_value":"XL6J5GZF","created_at":"2026-07-05T11:38:52Z"}],"graph_snapshots":[{"event_id":"sha256:478213f1a92d938f0ae82c7d20b9c42591c3c1032e668c2acc09090cd58118e6","target":"graph","created_at":"2026-07-05T11:38:52Z","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/2507.11059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset. Recent studies have uncovered severe data contamination issues, e.g. SWE-bench reports 32.67% of successful patches involve direct solution leakage and 31.08% pass due to inadequate test cases. We introduce SWE-MERA, a dynamic, continuously updated benchmark designed to address these fundamental challenges through an automated collection of real-world GitHub issues and rigorous quality validation. Our approach im","authors_text":"Aidar Valeev, Alena Fenogenova, Dmitry Babayev, Ivan Lopatin, Mikhail Ivanov, Pavel Adamenko, Pavel Zadorozhny, Rodion Levichev, Valentin Malykh","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-15T07:52:33Z","title":"SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11059","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:e9cddb480b2c6aac71ac2e35f12f005a80fda1b3e9ed6d6d09a871a0d765d601","target":"record","created_at":"2026-07-05T11:38:52Z","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":"e29d2821afe42ca8c716ef3a0295651c41ff59b3f23b92330705cae509bfc591","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-15T07:52:33Z","title_canon_sha256":"471a80d8bb4b463849190992ec9102b3ad602f0911dab0da34301385c0c9e11a"},"schema_version":"1.0","source":{"id":"2507.11059","kind":"arxiv","version":2}},"canonical_sha256":"bafc9e9b25fb16bb85c8f231fc17132471cdb6acdd78d0fb2541a18fcde8cd7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bafc9e9b25fb16bb85c8f231fc17132471cdb6acdd78d0fb2541a18fcde8cd7d","first_computed_at":"2026-07-05T11:38:52.412601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:52.412601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JoQEl3ZyoKMCXYw9eB7TViZcBqacY7f0JfjqpFfaiJVsPP1Ck++HnXYp4uxuyHLLOs+9NReETMc0VohTnm6qDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:52.413097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11059","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9cddb480b2c6aac71ac2e35f12f005a80fda1b3e9ed6d6d09a871a0d765d601","sha256:478213f1a92d938f0ae82c7d20b9c42591c3c1032e668c2acc09090cd58118e6"],"state_sha256":"ddea3b963a1d691d68f8951f81c835a718c2a612465d82b6139a2ee75ed6009e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXaiZ88bNv008mn3OtqsRsAY8TqcpueAu82rSPjEy+JZvy0BXKiF707JxVptfDWwPjUI1LM/STFeeMVSbzPhBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:51:34.768676Z","bundle_sha256":"b8fdd0f915f2921bee45b34c25e0a5ee59c999999e4c0ff186b00de60fa6e88e"}}