{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WL3H4D5ELZAPITRVMTSUAHAK4P","short_pith_number":"pith:WL3H4D5E","schema_version":"1.0","canonical_sha256":"b2f67e0fa45e40f44e3564e5401c0ae3d985434e1abe14c3785681e19c53c96b","source":{"kind":"arxiv","id":"2408.05006","version":3},"attestation_state":"computed","paper":{"title":"COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ge Yu, Hanbin Wang, Minghe Yu, Shuo Wang, Weiqing Yang, Xinze Li, Yu Gu, Yukun Yan, Zhenghao Liu, Zhiyuan Liu","submitted_at":"2024-08-09T11:35:44Z","abstract_excerpt":"Code debugging is a vital stage of software development, essential for ensuring the reliability and performance of Large Language Models (LLMs) in the code generation task. Human debugging typically follows a multi-stage process, which includes Bug Localization, Bug Identification, Code Repair, and Code Recognition. However, existing code debugging benchmarks predominantly focus on the Code Repair stage, which offers only a limited perspective on evaluating the debugging capabilities of LLMs. In this paper, we introduce DEBUGEVAL, a comprehensive benchmark for evaluating the debugging abilitie"},"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":"2408.05006","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-09T11:35:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41b06fe76bb939b910bb0afd73b8a4bab9cf17d2e237d8efffccfeb2f8e5d53c","abstract_canon_sha256":"c57165cc8aa85a205859d68620491d5bb596889847746e32cd920d965728acfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:02.417640Z","signature_b64":"GNCy+V+le5IJxgp4cWHKUX8fbuDA4Z/hOFTtQmt6aQyUjcoOPwYvHH6ZfLfqpD/xNK07QhbtqgM1rd+lI5p8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f67e0fa45e40f44e3564e5401c0ae3d985434e1abe14c3785681e19c53c96b","last_reissued_at":"2026-07-05T10:13:02.416939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:02.416939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ge Yu, Hanbin Wang, Minghe Yu, Shuo Wang, Weiqing Yang, Xinze Li, Yu Gu, Yukun Yan, Zhenghao Liu, Zhiyuan Liu","submitted_at":"2024-08-09T11:35:44Z","abstract_excerpt":"Code debugging is a vital stage of software development, essential for ensuring the reliability and performance of Large Language Models (LLMs) in the code generation task. Human debugging typically follows a multi-stage process, which includes Bug Localization, Bug Identification, Code Repair, and Code Recognition. However, existing code debugging benchmarks predominantly focus on the Code Repair stage, which offers only a limited perspective on evaluating the debugging capabilities of LLMs. In this paper, we introduce DEBUGEVAL, a comprehensive benchmark for evaluating the debugging abilitie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05006","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/2408.05006/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":"2408.05006","created_at":"2026-07-05T10:13:02.417018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05006v3","created_at":"2026-07-05T10:13:02.417018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05006","created_at":"2026-07-05T10:13:02.417018+00:00"},{"alias_kind":"pith_short_12","alias_value":"WL3H4D5ELZAP","created_at":"2026-07-05T10:13:02.417018+00:00"},{"alias_kind":"pith_short_16","alias_value":"WL3H4D5ELZAPITRV","created_at":"2026-07-05T10:13:02.417018+00:00"},{"alias_kind":"pith_short_8","alias_value":"WL3H4D5E","created_at":"2026-07-05T10:13:02.417018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.08561","citing_title":"Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P","json":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P.json","graph_json":"https://pith.science/api/pith-number/WL3H4D5ELZAPITRVMTSUAHAK4P/graph.json","events_json":"https://pith.science/api/pith-number/WL3H4D5ELZAPITRVMTSUAHAK4P/events.json","paper":"https://pith.science/paper/WL3H4D5E"},"agent_actions":{"view_html":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P","download_json":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P.json","view_paper":"https://pith.science/paper/WL3H4D5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05006&json=true","fetch_graph":"https://pith.science/api/pith-number/WL3H4D5ELZAPITRVMTSUAHAK4P/graph.json","fetch_events":"https://pith.science/api/pith-number/WL3H4D5ELZAPITRVMTSUAHAK4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P/action/storage_attestation","attest_author":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P/action/author_attestation","sign_citation":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P/action/citation_signature","submit_replication":"https://pith.science/pith/WL3H4D5ELZAPITRVMTSUAHAK4P/action/replication_record"}},"created_at":"2026-07-05T10:13:02.417018+00:00","updated_at":"2026-07-05T10:13:02.417018+00:00"}