{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IKIL3VFS7D2MD64VXGFKRBYADK","short_pith_number":"pith:IKIL3VFS","schema_version":"1.0","canonical_sha256":"4290bdd4b2f8f4c1fb95b98aa887001aae0db1e7be179e1e32f972c91bcb01c0","source":{"kind":"arxiv","id":"2411.12137","version":3},"attestation_state":"computed","paper":{"title":"Towards Understanding the Impact of Data Bugs on Deep Learning Models in Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Foutse Khomh, Mehil B Shah, Mohammad Masudur Rahman","submitted_at":"2024-11-19T00:28:20Z","abstract_excerpt":"Deep learning (DL) techniques have achieved significant success in various software engineering tasks (e.g., code completion by Copilot). However, DL systems are prone to bugs from many sources, including training data. Existing literature suggests that bugs in training data are highly prevalent, but little research has focused on understanding their impacts on the models used in software engineering tasks. In this paper, we address this research gap through a comprehensive empirical investigation focused on three types of data prevalent in software engineering tasks: code-based, text-based, a"},"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":"2411.12137","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-19T00:28:20Z","cross_cats_sorted":[],"title_canon_sha256":"1d83b4ceb440799e0f820aa718ffb354ccb035bb34751808cd5d910ced18f0ef","abstract_canon_sha256":"a4433b995fcaf1f9398b5e4549eecfeab10429691f048912b2dbe3b79874e4d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:00.837797Z","signature_b64":"0OujPgM9CUcDVEILVvA5oHOCYdDuUlTllW3pXb/UknNfAv1ZdsNPVp2AifAGN4E2y9o3aVTr/wr30oJaghvrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4290bdd4b2f8f4c1fb95b98aa887001aae0db1e7be179e1e32f972c91bcb01c0","last_reissued_at":"2026-07-05T11:52:00.837324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:00.837324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding the Impact of Data Bugs on Deep Learning Models in Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Foutse Khomh, Mehil B Shah, Mohammad Masudur Rahman","submitted_at":"2024-11-19T00:28:20Z","abstract_excerpt":"Deep learning (DL) techniques have achieved significant success in various software engineering tasks (e.g., code completion by Copilot). However, DL systems are prone to bugs from many sources, including training data. Existing literature suggests that bugs in training data are highly prevalent, but little research has focused on understanding their impacts on the models used in software engineering tasks. In this paper, we address this research gap through a comprehensive empirical investigation focused on three types of data prevalent in software engineering tasks: code-based, text-based, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12137","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/2411.12137/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":"2411.12137","created_at":"2026-07-05T11:52:00.837382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12137v3","created_at":"2026-07-05T11:52:00.837382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12137","created_at":"2026-07-05T11:52:00.837382+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKIL3VFS7D2M","created_at":"2026-07-05T11:52:00.837382+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKIL3VFS7D2MD64V","created_at":"2026-07-05T11:52:00.837382+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKIL3VFS","created_at":"2026-07-05T11:52:00.837382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK","json":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK.json","graph_json":"https://pith.science/api/pith-number/IKIL3VFS7D2MD64VXGFKRBYADK/graph.json","events_json":"https://pith.science/api/pith-number/IKIL3VFS7D2MD64VXGFKRBYADK/events.json","paper":"https://pith.science/paper/IKIL3VFS"},"agent_actions":{"view_html":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK","download_json":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK.json","view_paper":"https://pith.science/paper/IKIL3VFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12137&json=true","fetch_graph":"https://pith.science/api/pith-number/IKIL3VFS7D2MD64VXGFKRBYADK/graph.json","fetch_events":"https://pith.science/api/pith-number/IKIL3VFS7D2MD64VXGFKRBYADK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK/action/storage_attestation","attest_author":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK/action/author_attestation","sign_citation":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK/action/citation_signature","submit_replication":"https://pith.science/pith/IKIL3VFS7D2MD64VXGFKRBYADK/action/replication_record"}},"created_at":"2026-07-05T11:52:00.837382+00:00","updated_at":"2026-07-05T11:52:00.837382+00:00"}