{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5VVJPIZEACEOLKC3XZWLZTH2LH","short_pith_number":"pith:5VVJPIZE","schema_version":"1.0","canonical_sha256":"ed6a97a3240088e5a85bbe6cbcccfa59e30baefa1e1b0748842c2084f93173a5","source":{"kind":"arxiv","id":"2501.12793","version":1},"attestation_state":"computed","paper":{"title":"Revisit Self-Debugging with Self-Generated Tests for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Changzhi Zhou, Haiyan Zhao, Kechi Zhang, Mengdi Zhang, Wanli Gu, Xiancai Chen, Xunliang Cai, Yuanpeng He, Zhengwei Tao, Zhi Jin","submitted_at":"2025-01-22T10:54:19Z","abstract_excerpt":"Large language models (LLMs) have shown significant advancements in code generation, but still face challenges on tasks beyond their basic capabilities. Recently, the notion of self-debugging has been proposed to boost the performance of code generation by leveraging execution feedback from tests. Despite its promise, the availability of high-quality tests in real-world scenarios is limited. In this context, self-debugging with self-generated tests is a promising solution but lacks a full exploration of its limitations and practical potential. Therefore, we investigate its efficacy on diverse "},"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":"2501.12793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-22T10:54:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c4db3ad66bb919a1eafc4dab4c313bca605f6d9d2e679c8e0ad3a87cc34d8e0","abstract_canon_sha256":"0ec999ed5365822c3660440f3256084d6a3f6397b9db88542200fe2b00f76549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:58.781818Z","signature_b64":"rlcNjjQ7r9v7Xm844v1F+paR2jWNo+zY8Q3bLa4zT7kTfGWug/sKHYtUAmAiJC8/IGXlmEStdRATMUb8+dBIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed6a97a3240088e5a85bbe6cbcccfa59e30baefa1e1b0748842c2084f93173a5","last_reissued_at":"2026-07-05T10:03:58.781340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:58.781340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisit Self-Debugging with Self-Generated Tests for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Changzhi Zhou, Haiyan Zhao, Kechi Zhang, Mengdi Zhang, Wanli Gu, Xiancai Chen, Xunliang Cai, Yuanpeng He, Zhengwei Tao, Zhi Jin","submitted_at":"2025-01-22T10:54:19Z","abstract_excerpt":"Large language models (LLMs) have shown significant advancements in code generation, but still face challenges on tasks beyond their basic capabilities. Recently, the notion of self-debugging has been proposed to boost the performance of code generation by leveraging execution feedback from tests. Despite its promise, the availability of high-quality tests in real-world scenarios is limited. In this context, self-debugging with self-generated tests is a promising solution but lacks a full exploration of its limitations and practical potential. Therefore, we investigate its efficacy on diverse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12793","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/2501.12793/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":"2501.12793","created_at":"2026-07-05T10:03:58.781400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12793v1","created_at":"2026-07-05T10:03:58.781400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12793","created_at":"2026-07-05T10:03:58.781400+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VVJPIZEACEO","created_at":"2026-07-05T10:03:58.781400+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VVJPIZEACEOLKC3","created_at":"2026-07-05T10:03:58.781400+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VVJPIZE","created_at":"2026-07-05T10:03:58.781400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04580","citing_title":"Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH","json":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH.json","graph_json":"https://pith.science/api/pith-number/5VVJPIZEACEOLKC3XZWLZTH2LH/graph.json","events_json":"https://pith.science/api/pith-number/5VVJPIZEACEOLKC3XZWLZTH2LH/events.json","paper":"https://pith.science/paper/5VVJPIZE"},"agent_actions":{"view_html":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH","download_json":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH.json","view_paper":"https://pith.science/paper/5VVJPIZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12793&json=true","fetch_graph":"https://pith.science/api/pith-number/5VVJPIZEACEOLKC3XZWLZTH2LH/graph.json","fetch_events":"https://pith.science/api/pith-number/5VVJPIZEACEOLKC3XZWLZTH2LH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH/action/storage_attestation","attest_author":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH/action/author_attestation","sign_citation":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH/action/citation_signature","submit_replication":"https://pith.science/pith/5VVJPIZEACEOLKC3XZWLZTH2LH/action/replication_record"}},"created_at":"2026-07-05T10:03:58.781400+00:00","updated_at":"2026-07-05T10:03:58.781400+00:00"}