{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OHCLE5D42SWLUD6XGXF5453DYR","short_pith_number":"pith:OHCLE5D4","canonical_record":{"source":{"id":"2410.00752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-10-01T14:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"002b46388d5fd01a589d6445a24805b5459df67974c73a84e3ac0257f5bb316c","abstract_canon_sha256":"9dac4776f976470769ce5a0f5b970d17cf2b40d8c8a9708e52c236a54cf72366"},"schema_version":"1.0"},"canonical_sha256":"71c4b2747cd4acba0fd735cbde7763c44829009c54af420e4a8a335737e59d1d","source":{"kind":"arxiv","id":"2410.00752","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00752","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00752v2","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00752","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"OHCLE5D42SWL","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"pith_short_16","alias_value":"OHCLE5D42SWLUD6X","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"pith_short_8","alias_value":"OHCLE5D4","created_at":"2026-07-05T10:34:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OHCLE5D42SWLUD6XGXF5453DYR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.00752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-10-01T14:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"002b46388d5fd01a589d6445a24805b5459df67974c73a84e3ac0257f5bb316c","abstract_canon_sha256":"9dac4776f976470769ce5a0f5b970d17cf2b40d8c8a9708e52c236a54cf72366"},"schema_version":"1.0"},"canonical_sha256":"71c4b2747cd4acba0fd735cbde7763c44829009c54af420e4a8a335737e59d1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:10.607936Z","signature_b64":"YWMRJrWFTJqbrwNpUAqzwQ749wOeGP/bvHedKmxWwLaAnjThsV76gZSWC1bxVcWqBBbHgavyqVBeen5K8TJcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71c4b2747cd4acba0fd735cbde7763c44829009c54af420e4a8a335737e59d1d","last_reissued_at":"2026-07-05T10:34:10.607124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:10.607124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.00752","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":"2026-07-05T10:34:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3OYeamo/m7NOc0EcWcz3e5hWw9jxK+8OGVykgTAooANgfl8I7uY3xmukMNZoTabifIxl2gUbi/ogL6vrRpy6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:37:29.860067Z"},"content_sha256":"1040cd80e33df6534cf0baf71ca471a96b3095bf64dd0bff148648ef4bd899a6","schema_version":"1.0","event_id":"sha256:1040cd80e33df6534cf0baf71ca471a96b3095bf64dd0bff148648ef4bd899a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OHCLE5D42SWLUD6XGXF5453DYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Baptiste Rozi\\`ere, Gabriel Synnaeve, Kush Jain","submitted_at":"2024-10-01T14:47:05Z","abstract_excerpt":"Code generation models can help improve many common software tasks ranging from code completion to defect prediction. Most of the existing benchmarks for code generation LLMs focus on code authoring or code completion. Surprisingly, there has been far less effort dedicated to benchmarking software testing, despite the strong correlation between well-tested software and effective bug detection. To address this gap, we create and release TestGenEval, a large-scale benchmark to measure test generation performance. Based on SWEBench, TestGenEval comprises 68,647 tests from 1,210 code and test file"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00752","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/2410.00752/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":"2026-07-05T10:34:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Im+x7wVbPrmiq63UfiHtdN1hefnuXNezpF3piRlK7YPQzb+YMxeRxwjHOsiB6oXtc5V6N0gaiVJQpLvBH9PDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:37:29.860460Z"},"content_sha256":"bc468c5474ba51cb415bce62b977d3385d146a89510e6e4e01d3fc5de5731d64","schema_version":"1.0","event_id":"sha256:bc468c5474ba51cb415bce62b977d3385d146a89510e6e4e01d3fc5de5731d64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/bundle.json","state_url":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHCLE5D42SWLUD6XGXF5453DYR/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":"2026-07-06T20:37:29Z","links":{"resolver":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR","bundle":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/bundle.json","state":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHCLE5D42SWLUD6XGXF5453DYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OHCLE5D42SWLUD6XGXF5453DYR","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":"9dac4776f976470769ce5a0f5b970d17cf2b40d8c8a9708e52c236a54cf72366","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-10-01T14:47:05Z","title_canon_sha256":"002b46388d5fd01a589d6445a24805b5459df67974c73a84e3ac0257f5bb316c"},"schema_version":"1.0","source":{"id":"2410.00752","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00752","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00752v2","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00752","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"OHCLE5D42SWL","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"pith_short_16","alias_value":"OHCLE5D42SWLUD6X","created_at":"2026-07-05T10:34:10Z"},{"alias_kind":"pith_short_8","alias_value":"OHCLE5D4","created_at":"2026-07-05T10:34:10Z"}],"graph_snapshots":[{"event_id":"sha256:bc468c5474ba51cb415bce62b977d3385d146a89510e6e4e01d3fc5de5731d64","target":"graph","created_at":"2026-07-05T10:34:10Z","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/2410.00752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code generation models can help improve many common software tasks ranging from code completion to defect prediction. Most of the existing benchmarks for code generation LLMs focus on code authoring or code completion. Surprisingly, there has been far less effort dedicated to benchmarking software testing, despite the strong correlation between well-tested software and effective bug detection. To address this gap, we create and release TestGenEval, a large-scale benchmark to measure test generation performance. Based on SWEBench, TestGenEval comprises 68,647 tests from 1,210 code and test file","authors_text":"Baptiste Rozi\\`ere, Gabriel Synnaeve, Kush Jain","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-10-01T14:47:05Z","title":"TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00752","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":"sha256:1040cd80e33df6534cf0baf71ca471a96b3095bf64dd0bff148648ef4bd899a6","target":"record","created_at":"2026-07-05T10:34:10Z","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":"9dac4776f976470769ce5a0f5b970d17cf2b40d8c8a9708e52c236a54cf72366","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-10-01T14:47:05Z","title_canon_sha256":"002b46388d5fd01a589d6445a24805b5459df67974c73a84e3ac0257f5bb316c"},"schema_version":"1.0","source":{"id":"2410.00752","kind":"arxiv","version":2}},"canonical_sha256":"71c4b2747cd4acba0fd735cbde7763c44829009c54af420e4a8a335737e59d1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71c4b2747cd4acba0fd735cbde7763c44829009c54af420e4a8a335737e59d1d","first_computed_at":"2026-07-05T10:34:10.607124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:10.607124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YWMRJrWFTJqbrwNpUAqzwQ749wOeGP/bvHedKmxWwLaAnjThsV76gZSWC1bxVcWqBBbHgavyqVBeen5K8TJcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:10.607936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00752","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1040cd80e33df6534cf0baf71ca471a96b3095bf64dd0bff148648ef4bd899a6","sha256:bc468c5474ba51cb415bce62b977d3385d146a89510e6e4e01d3fc5de5731d64"],"state_sha256":"761e41e7fad61ef78fb5359926c4d8971652c2a17995057ff5ec889b32cc8114"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQy3YAiHHwVHep94tf2S3ZFtp4Ocr/LUDCf/2bTj7hLV6DInNO3FyubMxHU5ExwERAinwK4p50foXScGxgFOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:37:29.862647Z","bundle_sha256":"64ba92d4a37bed18d1dad1e4494a6c21e912970380aafe4221f3d7a73bf786a2"}}