{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OHCLE5D42SWLUD6XGXF5453DYR","short_pith_number":"pith:OHCLE5D4","schema_version":"1.0","canonical_sha256":"71c4b2747cd4acba0fd735cbde7763c44829009c54af420e4a8a335737e59d1d","source":{"kind":"arxiv","id":"2410.00752","version":2},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.00752","created_at":"2026-07-05T10:34:10.607246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00752v2","created_at":"2026-07-05T10:34:10.607246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00752","created_at":"2026-07-05T10:34:10.607246+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHCLE5D42SWL","created_at":"2026-07-05T10:34:10.607246+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHCLE5D42SWLUD6X","created_at":"2026-07-05T10:34:10.607246+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHCLE5D4","created_at":"2026-07-05T10:34:10.607246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.06556","citing_title":"MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18470","citing_title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18449","citing_title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13657","citing_title":"Why Do Multi-Agent LLM Systems Fail?","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05159","citing_title":"Planning to Explore: Curiosity-Driven Planning for LLM Test Generation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR","json":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR.json","graph_json":"https://pith.science/api/pith-number/OHCLE5D42SWLUD6XGXF5453DYR/graph.json","events_json":"https://pith.science/api/pith-number/OHCLE5D42SWLUD6XGXF5453DYR/events.json","paper":"https://pith.science/paper/OHCLE5D4"},"agent_actions":{"view_html":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR","download_json":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR.json","view_paper":"https://pith.science/paper/OHCLE5D4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00752&json=true","fetch_graph":"https://pith.science/api/pith-number/OHCLE5D42SWLUD6XGXF5453DYR/graph.json","fetch_events":"https://pith.science/api/pith-number/OHCLE5D42SWLUD6XGXF5453DYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/action/storage_attestation","attest_author":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/action/author_attestation","sign_citation":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/action/citation_signature","submit_replication":"https://pith.science/pith/OHCLE5D42SWLUD6XGXF5453DYR/action/replication_record"}},"created_at":"2026-07-05T10:34:10.607246+00:00","updated_at":"2026-07-05T10:34:10.607246+00:00"}