{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EYL3MVMAXHVTHAVPV5CABD7HUO","short_pith_number":"pith:EYL3MVMA","schema_version":"1.0","canonical_sha256":"2617b65580b9eb3382afaf44008fe7a39135a1b956f3c27cb985d23cb9264948","source":{"kind":"arxiv","id":"2411.06767","version":1},"attestation_state":"computed","paper":{"title":"PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Wenbo Liu, Xiaoming Zhao, Yichang Wu, Yiwen Duan, Yonghong Yu","submitted_at":"2024-11-11T07:47:20Z","abstract_excerpt":"Code Large Language Models (Code LLMs), such as Code llama and DeepSeek-Coder, have demonstrated exceptional performance in the code generation tasks. However, most existing models focus on the abilities of generating correct code, but often struggle with bug repair. We introduce a suit of methods to enhance LLM's SQL bug-fixing abilities. The methods are mainly consisted of two parts: A Progressive Dataset Construction (PDC) from scratch and Dynamic Mask Supervised Fine-tuning (DM-SFT). PDC proposes two data expansion methods from the perspectives of breadth first and depth first respectively"},"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":"2411.06767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T07:47:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"40becb41ae89d254b008435f5efd5453afefb2a7321f4b262e513ef665637765","abstract_canon_sha256":"32b3ca3c0c33b5b6615a8b462eb4237244e26a98cbbbe125cae0b2d340f4476d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:51.228225Z","signature_b64":"vbBJRIrjiDs14EIoYsqPZfZrQGz00x0FalVoz4w2cQ8of9PHTiIyTxBBma0J8q6nH3B18Wd377FHqWrGqeGECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2617b65580b9eb3382afaf44008fe7a39135a1b956f3c27cb985d23cb9264948","last_reissued_at":"2026-07-05T09:33:51.227785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:51.227785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Wenbo Liu, Xiaoming Zhao, Yichang Wu, Yiwen Duan, Yonghong Yu","submitted_at":"2024-11-11T07:47:20Z","abstract_excerpt":"Code Large Language Models (Code LLMs), such as Code llama and DeepSeek-Coder, have demonstrated exceptional performance in the code generation tasks. However, most existing models focus on the abilities of generating correct code, but often struggle with bug repair. We introduce a suit of methods to enhance LLM's SQL bug-fixing abilities. The methods are mainly consisted of two parts: A Progressive Dataset Construction (PDC) from scratch and Dynamic Mask Supervised Fine-tuning (DM-SFT). PDC proposes two data expansion methods from the perspectives of breadth first and depth first respectively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06767","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/2411.06767/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":"2411.06767","created_at":"2026-07-05T09:33:51.227841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06767v1","created_at":"2026-07-05T09:33:51.227841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06767","created_at":"2026-07-05T09:33:51.227841+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYL3MVMAXHVT","created_at":"2026-07-05T09:33:51.227841+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYL3MVMAXHVTHAVP","created_at":"2026-07-05T09:33:51.227841+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYL3MVMA","created_at":"2026-07-05T09:33:51.227841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03487","citing_title":"BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO","json":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO.json","graph_json":"https://pith.science/api/pith-number/EYL3MVMAXHVTHAVPV5CABD7HUO/graph.json","events_json":"https://pith.science/api/pith-number/EYL3MVMAXHVTHAVPV5CABD7HUO/events.json","paper":"https://pith.science/paper/EYL3MVMA"},"agent_actions":{"view_html":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO","download_json":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO.json","view_paper":"https://pith.science/paper/EYL3MVMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06767&json=true","fetch_graph":"https://pith.science/api/pith-number/EYL3MVMAXHVTHAVPV5CABD7HUO/graph.json","fetch_events":"https://pith.science/api/pith-number/EYL3MVMAXHVTHAVPV5CABD7HUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO/action/storage_attestation","attest_author":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO/action/author_attestation","sign_citation":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO/action/citation_signature","submit_replication":"https://pith.science/pith/EYL3MVMAXHVTHAVPV5CABD7HUO/action/replication_record"}},"created_at":"2026-07-05T09:33:51.227841+00:00","updated_at":"2026-07-05T09:33:51.227841+00:00"}