{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JT2SE2TYJRXDM3RGLXNDQHLZXV","short_pith_number":"pith:JT2SE2TY","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"},"canonical_sha256":"4cf5226a784c6e366e265dda381d79bd66adb269cbdfc22f8472b08b472dac82","source":{"kind":"arxiv","id":"2303.04738","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04738","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04738v4","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04738","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"pith_short_12","alias_value":"JT2SE2TYJRXD","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"pith_short_16","alias_value":"JT2SE2TYJRXDM3RG","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"pith_short_8","alias_value":"JT2SE2TY","created_at":"2026-07-05T06:34:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JT2SE2TYJRXDM3RGLXNDQHLZXV","target":"record","payload":{"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"},"canonical_sha256":"4cf5226a784c6e366e265dda381d79bd66adb269cbdfc22f8472b08b472dac82","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"},"source_kind":"arxiv","source_id":"2303.04738","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:34:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cpLyWV5xRfVoyexSM0KKfPogn5lKRzmK5HoDz9GUyG5Dbo8Wp4T7M6AvymWLbgJZ0bU7+M/X/kb7GKIjiBohAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:26:09.547606Z"},"content_sha256":"740ccd252befab04bce16a6b7df871abb335162d87c22abe7da6cd0b0cef5ca9","schema_version":"1.0","event_id":"sha256:740ccd252befab04bce16a6b7df871abb335162d87c22abe7da6cd0b0cef5ca9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JT2SE2TYJRXDM3RGLXNDQHLZXV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:34:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bA8oPLQ0QiOSB3W5SAXpSNVaPJ9gElYvDF59KpMicSlq5Yb3TXD8arXgb1VTHOTaiCKB1X9MO4LKapqwXkEeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:26:09.548494Z"},"content_sha256":"7a95b32da7b6990511f6331b855b90402435cb0b84d52a052ea47f500de800b9","schema_version":"1.0","event_id":"sha256:7a95b32da7b6990511f6331b855b90402435cb0b84d52a052ea47f500de800b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/bundle.json","state_url":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T00:26:09Z","links":{"resolver":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV","bundle":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/bundle.json","state":"https://pith.science/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JT2SE2TYJRXDM3RGLXNDQHLZXV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JT2SE2TYJRXDM3RGLXNDQHLZXV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bab67785e46f134c99806764676d08c8e0e8c681ac81391e7eb4915cd4ba75c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-08T17:23:24Z","title_canon_sha256":"6c0e9aa7183db2b3b46d114911477470ba668390b897ffd32c4580581faa2e1e"},"schema_version":"1.0","source":{"id":"2303.04738","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04738","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04738v4","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04738","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"pith_short_12","alias_value":"JT2SE2TYJRXD","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"pith_short_16","alias_value":"JT2SE2TYJRXDM3RG","created_at":"2026-07-05T06:34:04Z"},{"alias_kind":"pith_short_8","alias_value":"JT2SE2TY","created_at":"2026-07-05T06:34:04Z"}],"graph_snapshots":[{"event_id":"sha256:7a95b32da7b6990511f6331b855b90402435cb0b84d52a052ea47f500de800b9","target":"graph","created_at":"2026-07-05T06:34:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.04738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mohammad Masudur Rahman, Ohiduzzaman Shuvo, Parvez Mahbub","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-08T17:23:24Z","title":"Defectors: A Large, Diverse Python Dataset for Defect Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04738","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:740ccd252befab04bce16a6b7df871abb335162d87c22abe7da6cd0b0cef5ca9","target":"record","created_at":"2026-07-05T06:34:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bab67785e46f134c99806764676d08c8e0e8c681ac81391e7eb4915cd4ba75c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-03-08T17:23:24Z","title_canon_sha256":"6c0e9aa7183db2b3b46d114911477470ba668390b897ffd32c4580581faa2e1e"},"schema_version":"1.0","source":{"id":"2303.04738","kind":"arxiv","version":4}},"canonical_sha256":"4cf5226a784c6e366e265dda381d79bd66adb269cbdfc22f8472b08b472dac82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cf5226a784c6e366e265dda381d79bd66adb269cbdfc22f8472b08b472dac82","first_computed_at":"2026-07-05T06:34:04.506785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:04.506785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/exoMA0W2QOAUjb8slOZa1/IUXaUoNiTT2/6AukZGPDcDQGIZsohlj8bYvu8fGag/k0/oDO3npvX40kqcEhTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:04.507275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.04738","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:740ccd252befab04bce16a6b7df871abb335162d87c22abe7da6cd0b0cef5ca9","sha256:7a95b32da7b6990511f6331b855b90402435cb0b84d52a052ea47f500de800b9"],"state_sha256":"0ef892ce642401ae0dbd447a1fd1aa9f3910851e9f08b32413a2607ae69fc924"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JpTXL1Zf/28DYQ4jUUw9ciAxmB5XWRLmWt18oZj31RlHindPUGes+jIdpcYczLYvtsFeW78upu0zEUsKF26yAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:26:09.552602Z","bundle_sha256":"3eb95c26778991cd48a390ed4bbd557b767503273fd65f3de3954649eb565238"}}