{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M3BOAGBJXZSXYNVIHT5FMCQQFK","short_pith_number":"pith:M3BOAGBJ","schema_version":"1.0","canonical_sha256":"66c2e01829be657c36a83cfa560a102a8acf0501fbc556820d84c90b6319a6c4","source":{"kind":"arxiv","id":"2211.00381","version":2},"attestation_state":"computed","paper":{"title":"An Empirical Study on Data Leakage and Generalizability of Link Prediction Models for Issues and Commits","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Arie van Deursen, Maliheh Izadi, Pooya Rostami Mazrae, Tom Mens","submitted_at":"2022-11-01T10:54:26Z","abstract_excerpt":"To enhance documentation and maintenance practices, developers conventionally establish links between related software artifacts manually. Empirical research has revealed that developers frequently overlook this practice, resulting in significant information loss. To address this issue, automatic link recovery techniques have been proposed. However, these approaches primarily focused on improving prediction accuracy on randomly-split datasets, with limited attention given to the impact of data leakage and the generalizability of the predictive models. LinkFormer seeks to address these limitati"},"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":"2211.00381","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2022-11-01T10:54:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a7ecca5491f899162972cc12dd85ca348dc7adb96da58bd077582ff1ea7774b","abstract_canon_sha256":"526ac6661fafcb0fddbd907415ba2ce53f75ccf305be1863dda94635d7cad016"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:26.257593Z","signature_b64":"LRzx6jH2Uy1EbXc4fiGNve3ZLA/oDmVg0Kd4eH+HY0joK3bOnkgTOlfszzI4ciAdwutr7Rc542jTy0iuyX+TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66c2e01829be657c36a83cfa560a102a8acf0501fbc556820d84c90b6319a6c4","last_reissued_at":"2026-07-05T06:03:26.257168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:26.257168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study on Data Leakage and Generalizability of Link Prediction Models for Issues and Commits","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Arie van Deursen, Maliheh Izadi, Pooya Rostami Mazrae, Tom Mens","submitted_at":"2022-11-01T10:54:26Z","abstract_excerpt":"To enhance documentation and maintenance practices, developers conventionally establish links between related software artifacts manually. Empirical research has revealed that developers frequently overlook this practice, resulting in significant information loss. To address this issue, automatic link recovery techniques have been proposed. However, these approaches primarily focused on improving prediction accuracy on randomly-split datasets, with limited attention given to the impact of data leakage and the generalizability of the predictive models. LinkFormer seeks to address these limitati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00381","kind":"arxiv","version":2},"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/2211.00381/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":"2211.00381","created_at":"2026-07-05T06:03:26.257224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00381v2","created_at":"2026-07-05T06:03:26.257224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00381","created_at":"2026-07-05T06:03:26.257224+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3BOAGBJXZSX","created_at":"2026-07-05T06:03:26.257224+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3BOAGBJXZSXYNVI","created_at":"2026-07-05T06:03:26.257224+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3BOAGBJ","created_at":"2026-07-05T06:03:26.257224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18319","citing_title":"Gotta catch 'em all! Towards File Localisation from Issues at Large","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK","json":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK.json","graph_json":"https://pith.science/api/pith-number/M3BOAGBJXZSXYNVIHT5FMCQQFK/graph.json","events_json":"https://pith.science/api/pith-number/M3BOAGBJXZSXYNVIHT5FMCQQFK/events.json","paper":"https://pith.science/paper/M3BOAGBJ"},"agent_actions":{"view_html":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK","download_json":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK.json","view_paper":"https://pith.science/paper/M3BOAGBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00381&json=true","fetch_graph":"https://pith.science/api/pith-number/M3BOAGBJXZSXYNVIHT5FMCQQFK/graph.json","fetch_events":"https://pith.science/api/pith-number/M3BOAGBJXZSXYNVIHT5FMCQQFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK/action/storage_attestation","attest_author":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK/action/author_attestation","sign_citation":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK/action/citation_signature","submit_replication":"https://pith.science/pith/M3BOAGBJXZSXYNVIHT5FMCQQFK/action/replication_record"}},"created_at":"2026-07-05T06:03:26.257224+00:00","updated_at":"2026-07-05T06:03:26.257224+00:00"}