{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4SOO26UD5LSIZFQWUZL46EPIHM","short_pith_number":"pith:4SOO26UD","schema_version":"1.0","canonical_sha256":"e49ced7a83eae48c9616a657cf11e83b319947a1458cd82aae4dbd719620466b","source":{"kind":"arxiv","id":"2502.09771","version":1},"attestation_state":"computed","paper":{"title":"Knowledge-Enhanced Program Repair for Data Science Code","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Albert Merono Penuela, Jie M. Zhang, Shuyin Ouyang, Zeyu Sun","submitted_at":"2025-02-13T21:00:21Z","abstract_excerpt":"This paper introduces DSrepair, a knowledge-enhanced program repair method designed to repair the buggy code generated by LLMs in the data science domain. DSrepair uses knowledge graph based RAG for API knowledge retrieval as well as bug knowledge enrichment to construct repair prompts for LLMs. Specifically, to enable knowledge graph based API retrieval, we construct DS-KG (Data Science Knowledge Graph) for widely used data science libraries. For bug knowledge enrichment, we employ an abstract syntax tree (AST) to localize errors at the AST node level. DSrepair's effectiveness is evaluated ag"},"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":"2502.09771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-13T21:00:21Z","cross_cats_sorted":[],"title_canon_sha256":"9433f299d7c7d92a255afd90b052149decf6d597931b6fc3d2c00d51b8e7daec","abstract_canon_sha256":"bdb56f4b961d38ab45bb0b8ba961020a4c457173b025c1395c77aaacc452ebc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:54.253226Z","signature_b64":"5L/KBsuGsUwE2DlLqVNxBPRMvm/Y8ZlB29cwqkpK0BneqvZvR2G8MKXbTk20tHBC0BeOHQisRedy+/slqrKUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e49ced7a83eae48c9616a657cf11e83b319947a1458cd82aae4dbd719620466b","last_reissued_at":"2026-07-05T10:17:54.252763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:54.252763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-Enhanced Program Repair for Data Science Code","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Albert Merono Penuela, Jie M. Zhang, Shuyin Ouyang, Zeyu Sun","submitted_at":"2025-02-13T21:00:21Z","abstract_excerpt":"This paper introduces DSrepair, a knowledge-enhanced program repair method designed to repair the buggy code generated by LLMs in the data science domain. DSrepair uses knowledge graph based RAG for API knowledge retrieval as well as bug knowledge enrichment to construct repair prompts for LLMs. Specifically, to enable knowledge graph based API retrieval, we construct DS-KG (Data Science Knowledge Graph) for widely used data science libraries. For bug knowledge enrichment, we employ an abstract syntax tree (AST) to localize errors at the AST node level. DSrepair's effectiveness is evaluated ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09771","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/2502.09771/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":"2502.09771","created_at":"2026-07-05T10:17:54.252813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09771v1","created_at":"2026-07-05T10:17:54.252813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09771","created_at":"2026-07-05T10:17:54.252813+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SOO26UD5LSI","created_at":"2026-07-05T10:17:54.252813+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SOO26UD5LSIZFQW","created_at":"2026-07-05T10:17:54.252813+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SOO26UD","created_at":"2026-07-05T10:17:54.252813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17174","citing_title":"Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM","json":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM.json","graph_json":"https://pith.science/api/pith-number/4SOO26UD5LSIZFQWUZL46EPIHM/graph.json","events_json":"https://pith.science/api/pith-number/4SOO26UD5LSIZFQWUZL46EPIHM/events.json","paper":"https://pith.science/paper/4SOO26UD"},"agent_actions":{"view_html":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM","download_json":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM.json","view_paper":"https://pith.science/paper/4SOO26UD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09771&json=true","fetch_graph":"https://pith.science/api/pith-number/4SOO26UD5LSIZFQWUZL46EPIHM/graph.json","fetch_events":"https://pith.science/api/pith-number/4SOO26UD5LSIZFQWUZL46EPIHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM/action/storage_attestation","attest_author":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM/action/author_attestation","sign_citation":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM/action/citation_signature","submit_replication":"https://pith.science/pith/4SOO26UD5LSIZFQWUZL46EPIHM/action/replication_record"}},"created_at":"2026-07-05T10:17:54.252813+00:00","updated_at":"2026-07-05T10:17:54.252813+00:00"}