{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RIALZA7BTQ3LYDLBCL7NXF7CG5","short_pith_number":"pith:RIALZA7B","schema_version":"1.0","canonical_sha256":"8a00bc83e19c36bc0d6112fedb97e23742b988910b04e94cc7d9f1ae1e69ba17","source":{"kind":"arxiv","id":"2404.00599","version":1},"attestation_state":"computed","paper":{"title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Ge Li, Jia Li, Xuanming Zhang, Yihong Dong, Zhi Jin","submitted_at":"2024-03-31T08:10:50Z","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"},"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":"2404.00599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T08:10:50Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"6d5977402e7eda954ee9b1daed50753bb6e9d165027a41f37385fedc9f1f0bef","abstract_canon_sha256":"f1a7bb60f7ffebb0c9d034b6d76cced4a27d22302e88952228799dd7fc970232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:54.181958Z","signature_b64":"SfN1dcgPH4UiazPlLL9ZHH9mjJgcmAazQZddd0P/VnJNIUPnGxJcLv2B0iS9F/JgoTzxDHoEm37qVTIgvw8CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a00bc83e19c36bc0d6112fedb97e23742b988910b04e94cc7d9f1ae1e69ba17","last_reissued_at":"2026-07-05T08:02:54.181474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:54.181474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Ge Li, Jia Li, Xuanming Zhang, Yihong Dong, Zhi Jin","submitted_at":"2024-03-31T08:10:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00599","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/2404.00599/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":"2404.00599","created_at":"2026-07-05T08:02:54.181539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00599v1","created_at":"2026-07-05T08:02:54.181539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00599","created_at":"2026-07-05T08:02:54.181539+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIALZA7BTQ3L","created_at":"2026-07-05T08:02:54.181539+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIALZA7BTQ3LYDLB","created_at":"2026-07-05T08:02:54.181539+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIALZA7B","created_at":"2026-07-05T08:02:54.181539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08009","citing_title":"From Execution to Education: A Bloom-Aligned Framework for Measuring Educational Control in LLMs","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19741","citing_title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20517","citing_title":"Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29277","citing_title":"Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17526","citing_title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00376","citing_title":"In Line with Context: Repository-Level Code Generation via Context Inlining","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02709","citing_title":"Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22659","citing_title":"RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19742","citing_title":"PlayCoder: Making LLM-Generated GUI Code Playable","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5","json":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5.json","graph_json":"https://pith.science/api/pith-number/RIALZA7BTQ3LYDLBCL7NXF7CG5/graph.json","events_json":"https://pith.science/api/pith-number/RIALZA7BTQ3LYDLBCL7NXF7CG5/events.json","paper":"https://pith.science/paper/RIALZA7B"},"agent_actions":{"view_html":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5","download_json":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5.json","view_paper":"https://pith.science/paper/RIALZA7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00599&json=true","fetch_graph":"https://pith.science/api/pith-number/RIALZA7BTQ3LYDLBCL7NXF7CG5/graph.json","fetch_events":"https://pith.science/api/pith-number/RIALZA7BTQ3LYDLBCL7NXF7CG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5/action/storage_attestation","attest_author":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5/action/author_attestation","sign_citation":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5/action/citation_signature","submit_replication":"https://pith.science/pith/RIALZA7BTQ3LYDLBCL7NXF7CG5/action/replication_record"}},"created_at":"2026-07-05T08:02:54.181539+00:00","updated_at":"2026-07-05T08:02:54.181539+00:00"}