{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RIALZA7BTQ3LYDLBCL7NXF7CG5","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":"f1a7bb60f7ffebb0c9d034b6d76cced4a27d22302e88952228799dd7fc970232","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T08:10:50Z","title_canon_sha256":"6d5977402e7eda954ee9b1daed50753bb6e9d165027a41f37385fedc9f1f0bef"},"schema_version":"1.0","source":{"id":"2404.00599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00599","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00599v1","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00599","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"pith_short_12","alias_value":"RIALZA7BTQ3L","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"pith_short_16","alias_value":"RIALZA7BTQ3LYDLB","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"pith_short_8","alias_value":"RIALZA7B","created_at":"2026-07-05T08:02:54Z"}],"graph_snapshots":[{"event_id":"sha256:496863d6032a9e5e10823f70eeb29c1768f77f5233f1c71283986e92794d50ef","target":"graph","created_at":"2026-07-05T08:02:54Z","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/2404.00599/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 is an open question. Existing benchmarks demonstrate poor alignment with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. This paper proposes a new benchmark - EvoCodeBench to address the preceding problems, which has three primary advances. (1) EvoCodeBench aligns with real-world repositories in multiple dimensions, e.g., code distributions and dependency distributions. (2) EvoCodeBench offers comprehensive annotations (e.g., requirements, reference code, and reference dependencies), and","authors_text":"Ge Li, Jia Li, Xuanming Zhang, Yihong Dong, Zhi Jin","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T08:10:50Z","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00599","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":"sha256:556b37f9a3768b7139c62a99d7930b8704240ca34dc7ca913909e7ab69dc2b09","target":"record","created_at":"2026-07-05T08:02:54Z","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":"f1a7bb60f7ffebb0c9d034b6d76cced4a27d22302e88952228799dd7fc970232","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T08:10:50Z","title_canon_sha256":"6d5977402e7eda954ee9b1daed50753bb6e9d165027a41f37385fedc9f1f0bef"},"schema_version":"1.0","source":{"id":"2404.00599","kind":"arxiv","version":1}},"canonical_sha256":"8a00bc83e19c36bc0d6112fedb97e23742b988910b04e94cc7d9f1ae1e69ba17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a00bc83e19c36bc0d6112fedb97e23742b988910b04e94cc7d9f1ae1e69ba17","first_computed_at":"2026-07-05T08:02:54.181474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:54.181474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SfN1dcgPH4UiazPlLL9ZHH9mjJgcmAazQZddd0P/VnJNIUPnGxJcLv2B0iS9F/JgoTzxDHoEm37qVTIgvw8CBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:54.181958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:556b37f9a3768b7139c62a99d7930b8704240ca34dc7ca913909e7ab69dc2b09","sha256:496863d6032a9e5e10823f70eeb29c1768f77f5233f1c71283986e92794d50ef"],"state_sha256":"ee403aee4b21a079216ff91523f1766d5397c2679762e0fd73865fa246f3ecff"}