{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MG5JSCZ2NLHYV2ZB463LBAGF2B","short_pith_number":"pith:MG5JSCZ2","schema_version":"1.0","canonical_sha256":"61ba990b3a6acf8aeb21e7b6b080c5d0682bd0d04b70d81c4acce5e9fc108633","source":{"kind":"arxiv","id":"2410.01353","version":3},"attestation_state":"computed","paper":{"title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Binhua Li, Fei Huang, Han Liu, Rongyu Cao, Yingwei Ma, Yongbin Li, Yongchang Cao, Zhenyu Pan","submitted_at":"2024-10-02T09:11:10Z","abstract_excerpt":"Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intelligent completion tools evolve, we need a robust evaluation benchmark that enables meaningful comparisons between products and guides future advancements. However, existing benchmarks focus more on coarse-grained tasks without industrial analysis resembling general code generation rather than the real-world scenarios developers encounter. Moreover, these benchmarks often rely on costly and time-consuming human annotat"},"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":"2410.01353","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-02T09:11:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e789c0278d1b9fbec0a46766ea5ba560fc879556905e24f32cc3ccd32cfed18a","abstract_canon_sha256":"d98a53bc0c6b09ecf104f74e3aabda42540372700a602ca3750b924bff50c944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:01.761386Z","signature_b64":"F5DYbbd7iQ2r35kH35o1FmNSxtnW/VbYIlNIVnuNFbSAc8oJ/4/Dq3xkRmB5zkgYwaVxXPDvHX5EUCk2v7S/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61ba990b3a6acf8aeb21e7b6b080c5d0682bd0d04b70d81c4acce5e9fc108633","last_reissued_at":"2026-07-05T09:25:01.760899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:01.760899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Binhua Li, Fei Huang, Han Liu, Rongyu Cao, Yingwei Ma, Yongbin Li, Yongchang Cao, Zhenyu Pan","submitted_at":"2024-10-02T09:11:10Z","abstract_excerpt":"Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intelligent completion tools evolve, we need a robust evaluation benchmark that enables meaningful comparisons between products and guides future advancements. However, existing benchmarks focus more on coarse-grained tasks without industrial analysis resembling general code generation rather than the real-world scenarios developers encounter. Moreover, these benchmarks often rely on costly and time-consuming human annotat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01353","kind":"arxiv","version":3},"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/2410.01353/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":"2410.01353","created_at":"2026-07-05T09:25:01.760957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01353v3","created_at":"2026-07-05T09:25:01.760957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01353","created_at":"2026-07-05T09:25:01.760957+00:00"},{"alias_kind":"pith_short_12","alias_value":"MG5JSCZ2NLHY","created_at":"2026-07-05T09:25:01.760957+00:00"},{"alias_kind":"pith_short_16","alias_value":"MG5JSCZ2NLHYV2ZB","created_at":"2026-07-05T09:25:01.760957+00:00"},{"alias_kind":"pith_short_8","alias_value":"MG5JSCZ2","created_at":"2026-07-05T09:25:01.760957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03814","citing_title":"Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B","json":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B.json","graph_json":"https://pith.science/api/pith-number/MG5JSCZ2NLHYV2ZB463LBAGF2B/graph.json","events_json":"https://pith.science/api/pith-number/MG5JSCZ2NLHYV2ZB463LBAGF2B/events.json","paper":"https://pith.science/paper/MG5JSCZ2"},"agent_actions":{"view_html":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B","download_json":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B.json","view_paper":"https://pith.science/paper/MG5JSCZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01353&json=true","fetch_graph":"https://pith.science/api/pith-number/MG5JSCZ2NLHYV2ZB463LBAGF2B/graph.json","fetch_events":"https://pith.science/api/pith-number/MG5JSCZ2NLHYV2ZB463LBAGF2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B/action/storage_attestation","attest_author":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B/action/author_attestation","sign_citation":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B/action/citation_signature","submit_replication":"https://pith.science/pith/MG5JSCZ2NLHYV2ZB463LBAGF2B/action/replication_record"}},"created_at":"2026-07-05T09:25:01.760957+00:00","updated_at":"2026-07-05T09:25:01.760957+00:00"}