{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DHNMXULJCUVRPMRIDOOFCYHSZ4","short_pith_number":"pith:DHNMXULJ","schema_version":"1.0","canonical_sha256":"19dacbd169152b17b2281b9c5160f2cf024d9965102b874186a88bcc164e9072","source":{"kind":"arxiv","id":"2412.11990","version":1},"attestation_state":"computed","paper":{"title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Jiajun Zhang, Jian Yang, Jiaxi Yang, Junyang Lin, Ke Jin, Ken Deng, Lei Zhang, Qiyao Peng, Tianyu Liu, Yibo Miao, Zeyu Cui","submitted_at":"2024-12-16T17:14:35Z","abstract_excerpt":"Code completion has become an essential tool for daily software development. Existing evaluation benchmarks often employ static methods that do not fully capture the dynamic nature of real-world coding environments and face significant challenges, including limited context length, reliance on superficial evaluation metrics, and potential overfitting to training datasets. In this work, we introduce a novel framework for enhancing code completion in software development through the creation of a repository-level benchmark ExecRepoBench and the instruction corpora Repo-Instruct, aim at improving "},"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":"2412.11990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T17:14:35Z","cross_cats_sorted":[],"title_canon_sha256":"a93f7ca12de23803b56176a2d483c9ce49c95d194afd2143596d7744c223c5d8","abstract_canon_sha256":"ada2e8986ddeb98813fa736b9a51bf459d746a0ac1ec6673541b3dd1ef685a25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:55.014601Z","signature_b64":"5o/+MZh+MD7Dp10yjiilYabW6tkU3xR62VpXh3ewphoqy26Y6Zw2PcdGBncRHw5XQS+EGfddKFVW4Wds8EXgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19dacbd169152b17b2281b9c5160f2cf024d9965102b874186a88bcc164e9072","last_reissued_at":"2026-07-05T09:49:55.014053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:55.014053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Jiajun Zhang, Jian Yang, Jiaxi Yang, Junyang Lin, Ke Jin, Ken Deng, Lei Zhang, Qiyao Peng, Tianyu Liu, Yibo Miao, Zeyu Cui","submitted_at":"2024-12-16T17:14:35Z","abstract_excerpt":"Code completion has become an essential tool for daily software development. Existing evaluation benchmarks often employ static methods that do not fully capture the dynamic nature of real-world coding environments and face significant challenges, including limited context length, reliance on superficial evaluation metrics, and potential overfitting to training datasets. In this work, we introduce a novel framework for enhancing code completion in software development through the creation of a repository-level benchmark ExecRepoBench and the instruction corpora Repo-Instruct, aim at improving "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11990","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/2412.11990/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":"2412.11990","created_at":"2026-07-05T09:49:55.014114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11990v1","created_at":"2026-07-05T09:49:55.014114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11990","created_at":"2026-07-05T09:49:55.014114+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHNMXULJCUVR","created_at":"2026-07-05T09:49:55.014114+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHNMXULJCUVRPMRI","created_at":"2026-07-05T09:49:55.014114+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHNMXULJ","created_at":"2026-07-05T09:49:55.014114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03622","citing_title":"Toward Executable Repository-Level Code Generation via Environment Alignment","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4","json":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4.json","graph_json":"https://pith.science/api/pith-number/DHNMXULJCUVRPMRIDOOFCYHSZ4/graph.json","events_json":"https://pith.science/api/pith-number/DHNMXULJCUVRPMRIDOOFCYHSZ4/events.json","paper":"https://pith.science/paper/DHNMXULJ"},"agent_actions":{"view_html":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4","download_json":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4.json","view_paper":"https://pith.science/paper/DHNMXULJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11990&json=true","fetch_graph":"https://pith.science/api/pith-number/DHNMXULJCUVRPMRIDOOFCYHSZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/DHNMXULJCUVRPMRIDOOFCYHSZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4/action/storage_attestation","attest_author":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4/action/author_attestation","sign_citation":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4/action/citation_signature","submit_replication":"https://pith.science/pith/DHNMXULJCUVRPMRIDOOFCYHSZ4/action/replication_record"}},"created_at":"2026-07-05T09:49:55.014114+00:00","updated_at":"2026-07-05T09:49:55.014114+00:00"}