{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5G2DZRAS3VAIH3YEH5CAN2UZ3F","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":"e9f2973322ad0dbb1a29885fc412ad85969f7be40e32b86ed995d150cf3e1ef7","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T08:57:59Z","title_canon_sha256":"8c68b422f17a01d3ae9f307cb1ccb37cf501278aaac097caeb84c072882ccac3"},"schema_version":"1.0","source":{"id":"2410.22821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22821","created_at":"2026-07-05T09:28:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22821v1","created_at":"2026-07-05T09:28:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22821","created_at":"2026-07-05T09:28:36Z"},{"alias_kind":"pith_short_12","alias_value":"5G2DZRAS3VAI","created_at":"2026-07-05T09:28:36Z"},{"alias_kind":"pith_short_16","alias_value":"5G2DZRAS3VAIH3YE","created_at":"2026-07-05T09:28:36Z"},{"alias_kind":"pith_short_8","alias_value":"5G2DZRAS","created_at":"2026-07-05T09:28:36Z"}],"graph_snapshots":[{"event_id":"sha256:e168d388081356720409e08b49272278140a229a54fe2b166a72751bb3ee67b3","target":"graph","created_at":"2026-07-05T09:28:36Z","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/2410.22821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Binhua Li, Fei Huang, Ge Li, Jia Li, Xuanming Zhang, Yihong Dong, Yongbin Li, Yunfei Zhao, Zhi Jin","cross_cats":["cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T08:57:59Z","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22821","kind":"arxiv","version":1},"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":"sha256:35b7f2931ce133ce05375e6ac0e7e1ee2a18d9f9b2911d40dba281f58ff39488","target":"record","created_at":"2026-07-05T09:28:36Z","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":"e9f2973322ad0dbb1a29885fc412ad85969f7be40e32b86ed995d150cf3e1ef7","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T08:57:59Z","title_canon_sha256":"8c68b422f17a01d3ae9f307cb1ccb37cf501278aaac097caeb84c072882ccac3"},"schema_version":"1.0","source":{"id":"2410.22821","kind":"arxiv","version":1}},"canonical_sha256":"e9b43cc412dd4083ef043f4406ea99d96ee9babb1a12069298ebe2b751b8642a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9b43cc412dd4083ef043f4406ea99d96ee9babb1a12069298ebe2b751b8642a","first_computed_at":"2026-07-05T09:28:36.633252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:36.633252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o4J8+70zI/WpAG685Vfn7RTTfho59nhG2SBdrZcisz2c6JmJcGgwC1VvH94xiLk6xykELC6FLRX00+VDjH40DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:36.633808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35b7f2931ce133ce05375e6ac0e7e1ee2a18d9f9b2911d40dba281f58ff39488","sha256:e168d388081356720409e08b49272278140a229a54fe2b166a72751bb3ee67b3"],"state_sha256":"1851be10127a21838d705d8c1184eb00cd4a007972428d9d673db50e5c42bdb5"}