{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JT2SE2TYJRXDM3RGLXNDQHLZXV","short_pith_number":"pith:JT2SE2TY","schema_version":"1.0","canonical_sha256":"4cf5226a784c6e366e265dda381d79bd66adb269cbdfc22f8472b08b472dac82","source":{"kind":"arxiv","id":"2303.04738","version":4},"attestation_state":"computed","paper":{"title":"Defectors: A Large, Diverse Python Dataset for Defect Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mohammad Masudur Rahman, Ohiduzzaman Shuvo, Parvez Mahbub","submitted_at":"2023-03-08T17:23:24Z","abstract_excerpt":"Defect prediction has been a popular research topic where machine learning (ML) and deep learning (DL) have found numerous applications. However, these ML/DL-based defect prediction models are often limited by the quality and size of their datasets. In this paper, we present Defectors, a large dataset for just-in-time and line-level defect prediction. Defectors consists of $\\approx$ 213K source code files ($\\approx$ 93K defective and $\\approx$ 120K defect-free) that span across 24 popular Python projects. These projects come from 18 different domains, including machine learning, automation, an"},"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":"2303.04738","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-08T17:23:24Z","cross_cats_sorted":[],"title_canon_sha256":"6c0e9aa7183db2b3b46d114911477470ba668390b897ffd32c4580581faa2e1e","abstract_canon_sha256":"bab67785e46f134c99806764676d08c8e0e8c681ac81391e7eb4915cd4ba75c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:04.507275Z","signature_b64":"/exoMA0W2QOAUjb8slOZa1/IUXaUoNiTT2/6AukZGPDcDQGIZsohlj8bYvu8fGag/k0/oDO3npvX40kqcEhTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cf5226a784c6e366e265dda381d79bd66adb269cbdfc22f8472b08b472dac82","last_reissued_at":"2026-07-05T06:34:04.506785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:04.506785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defectors: A Large, Diverse Python Dataset for Defect Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mohammad Masudur Rahman, Ohiduzzaman Shuvo, Parvez Mahbub","submitted_at":"2023-03-08T17:23:24Z","abstract_excerpt":"Defect prediction has been a popular research topic where machine learning (ML) and deep learning (DL) have found numerous applications. However, these ML/DL-based defect prediction models are often limited by the quality and size of their datasets. In this paper, we present Defectors, a large dataset for just-in-time and line-level defect prediction. Defectors consists of $\\approx$ 213K source code files ($\\approx$ 93K defective and $\\approx$ 120K defect-free) that span across 24 popular Python projects. These projects come from 18 different domains, including machine learning, automation, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04738","kind":"arxiv","version":4},"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/2303.04738/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":"2303.04738","created_at":"2026-07-05T06:34:04.506849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04738v4","created_at":"2026-07-05T06:34:04.506849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04738","created_at":"2026-07-05T06:34:04.506849+00:00"},{"alias_kind":"pith_short_12","alias_value":"JT2SE2TYJRXD","created_at":"2026-07-05T06:34:04.506849+00:00"},{"alias_kind":"pith_short_16","alias_value":"JT2SE2TYJRXDM3RG","created_at":"2026-07-05T06:34:04.506849+00:00"},{"alias_kind":"pith_short_8","alias_value":"JT2SE2TY","created_at":"2026-07-05T06:34:04.506849+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/JT2SE2TYJRXDM3RGLXNDQHLZXV","json":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV.json","graph_json":"https://pith.science/api/pith-number/JT2SE2TYJRXDM3RGLXNDQHLZXV/graph.json","events_json":"https://pith.science/api/pith-number/JT2SE2TYJRXDM3RGLXNDQHLZXV/events.json","paper":"https://pith.science/paper/JT2SE2TY"},"agent_actions":{"view_html":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV","download_json":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV.json","view_paper":"https://pith.science/paper/JT2SE2TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04738&json=true","fetch_graph":"https://pith.science/api/pith-number/JT2SE2TYJRXDM3RGLXNDQHLZXV/graph.json","fetch_events":"https://pith.science/api/pith-number/JT2SE2TYJRXDM3RGLXNDQHLZXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/action/storage_attestation","attest_author":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/action/author_attestation","sign_citation":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/action/citation_signature","submit_replication":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/action/replication_record"}},"created_at":"2026-07-05T06:34:04.506849+00:00","updated_at":"2026-07-05T06:34:04.506849+00:00"}