{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5G2DZRAS3VAIH3YEH5CAN2UZ3F","short_pith_number":"pith:5G2DZRAS","schema_version":"1.0","canonical_sha256":"e9b43cc412dd4083ef043f4406ea99d96ee9babb1a12069298ebe2b751b8642a","source":{"kind":"arxiv","id":"2410.22821","version":1},"attestation_state":"computed","paper":{"title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Binhua Li, Fei Huang, Ge Li, Jia Li, Xuanming Zhang, Yihong Dong, Yongbin Li, Yunfei Zhao, Zhi Jin","submitted_at":"2024-10-30T08:57:59Z","abstract_excerpt":"How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evaluation. The former hurts the fairness of benchmarks, and the latter hinders practitioners from selecting superior LLMs for specific programming domains. To address these two limitations, we propose a new benchmark - EvoCodeBench, which has the following advances: (1) Evolving data. EvoCodeBench will be dynamically updated every period (e.g., 6 months) to avoid data leakage. This paper releases the first version - EvoCo"},"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":"2410.22821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T08:57:59Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"8c68b422f17a01d3ae9f307cb1ccb37cf501278aaac097caeb84c072882ccac3","abstract_canon_sha256":"e9f2973322ad0dbb1a29885fc412ad85969f7be40e32b86ed995d150cf3e1ef7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:36.633808Z","signature_b64":"o4J8+70zI/WpAG685Vfn7RTTfho59nhG2SBdrZcisz2c6JmJcGgwC1VvH94xiLk6xykELC6FLRX00+VDjH40DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9b43cc412dd4083ef043f4406ea99d96ee9babb1a12069298ebe2b751b8642a","last_reissued_at":"2026-07-05T09:28:36.633252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:36.633252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Binhua Li, Fei Huang, Ge Li, Jia Li, Xuanming Zhang, Yihong Dong, Yongbin Li, Yunfei Zhao, Zhi Jin","submitted_at":"2024-10-30T08:57:59Z","abstract_excerpt":"How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evaluation. The former hurts the fairness of benchmarks, and the latter hinders practitioners from selecting superior LLMs for specific programming domains. To address these two limitations, we propose a new benchmark - EvoCodeBench, which has the following advances: (1) Evolving data. EvoCodeBench will be dynamically updated every period (e.g., 6 months) to avoid data leakage. This paper releases the first version - EvoCo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22821","kind":"arxiv","version":1},"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/2410.22821/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":"2410.22821","created_at":"2026-07-05T09:28:36.633321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22821v1","created_at":"2026-07-05T09:28:36.633321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22821","created_at":"2026-07-05T09:28:36.633321+00:00"},{"alias_kind":"pith_short_12","alias_value":"5G2DZRAS3VAI","created_at":"2026-07-05T09:28:36.633321+00:00"},{"alias_kind":"pith_short_16","alias_value":"5G2DZRAS3VAIH3YE","created_at":"2026-07-05T09:28:36.633321+00:00"},{"alias_kind":"pith_short_8","alias_value":"5G2DZRAS","created_at":"2026-07-05T09:28:36.633321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F","json":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F.json","graph_json":"https://pith.science/api/pith-number/5G2DZRAS3VAIH3YEH5CAN2UZ3F/graph.json","events_json":"https://pith.science/api/pith-number/5G2DZRAS3VAIH3YEH5CAN2UZ3F/events.json","paper":"https://pith.science/paper/5G2DZRAS"},"agent_actions":{"view_html":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F","download_json":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F.json","view_paper":"https://pith.science/paper/5G2DZRAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22821&json=true","fetch_graph":"https://pith.science/api/pith-number/5G2DZRAS3VAIH3YEH5CAN2UZ3F/graph.json","fetch_events":"https://pith.science/api/pith-number/5G2DZRAS3VAIH3YEH5CAN2UZ3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F/action/storage_attestation","attest_author":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F/action/author_attestation","sign_citation":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F/action/citation_signature","submit_replication":"https://pith.science/pith/5G2DZRAS3VAIH3YEH5CAN2UZ3F/action/replication_record"}},"created_at":"2026-07-05T09:28:36.633321+00:00","updated_at":"2026-07-05T09:28:36.633321+00:00"}