{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:PKRBMRBIB4T3AC5BKG5HUUBMDJ","short_pith_number":"pith:PKRBMRBI","schema_version":"1.0","canonical_sha256":"7aa21644280f27b00ba151ba7a502c1a499c86b4677a6084a13d3532228875ce","source":{"kind":"arxiv","id":"1402.0282","version":1},"attestation_state":"computed","paper":{"title":"Principled Graph Matching Algorithms for Integrating Multiple Data Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DB","authors_text":"Benjamin I. P. Rubinstein, Duo Zhang, Jim Gemmell","submitted_at":"2014-02-03T04:56:58Z","abstract_excerpt":"This paper explores combinatorial optimization for problems of max-weight graph matching on multi-partite graphs, which arise in integrating multiple data sources. Entity resolution-the data integration problem of performing noisy joins on structured data-typically proceeds by first hashing each record into zero or more blocks, scoring pairs of records that are co-blocked for similarity, and then matching pairs of sufficient similarity. In the most common case of matching two sources, it is often desirable for the final matching to be one-to-one (a record may be matched with at most one other)"},"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":"1402.0282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-02-03T04:56:58Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fd1bd6dd6289c407dc9a2e0dc5b57da59556d71eb91dd301bd224f8077013550","abstract_canon_sha256":"410ef330433671da7511a8f290c19a40e51c076af4dafb66b10af165c813fe0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:00:24.032556Z","signature_b64":"3ESr9fA/NsXfcaJ+352T3+Z84eFc6nnZ5DlN+jjopY2uYqHQoVw1E3pnBGWb0XthDesAP8enbSsJxo4fqPSdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aa21644280f27b00ba151ba7a502c1a499c86b4677a6084a13d3532228875ce","last_reissued_at":"2026-05-18T03:00:24.031743Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:00:24.031743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principled Graph Matching Algorithms for Integrating Multiple Data Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DB","authors_text":"Benjamin I. P. Rubinstein, Duo Zhang, Jim Gemmell","submitted_at":"2014-02-03T04:56:58Z","abstract_excerpt":"This paper explores combinatorial optimization for problems of max-weight graph matching on multi-partite graphs, which arise in integrating multiple data sources. Entity resolution-the data integration problem of performing noisy joins on structured data-typically proceeds by first hashing each record into zero or more blocks, scoring pairs of records that are co-blocked for similarity, and then matching pairs of sufficient similarity. In the most common case of matching two sources, it is often desirable for the final matching to be one-to-one (a record may be matched with at most one other)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.0282","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":""},"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":"1402.0282","created_at":"2026-05-18T03:00:24.031912+00:00"},{"alias_kind":"arxiv_version","alias_value":"1402.0282v1","created_at":"2026-05-18T03:00:24.031912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.0282","created_at":"2026-05-18T03:00:24.031912+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKRBMRBIB4T3","created_at":"2026-05-18T12:28:43.426989+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKRBMRBIB4T3AC5B","created_at":"2026-05-18T12:28:43.426989+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKRBMRBI","created_at":"2026-05-18T12:28:43.426989+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/PKRBMRBIB4T3AC5BKG5HUUBMDJ","json":"https://pith.science/pith/PKRBMRBIB4T3AC5BKG5HUUBMDJ.json","graph_json":"https://pith.science/api/pith-number/PKRBMRBIB4T3AC5BKG5HUUBMDJ/graph.json","events_json":"https://pith.science/api/pith-number/PKRBMRBIB4T3AC5BKG5HUUBMDJ/events.json","paper":"https://pith.science/paper/PKRBMRBI"},"agent_actions":{"view_html":"https://pith.science/pith/PKRBMRBIB4T3AC5BKG5HUUBMDJ","download_json":"https://pith.science/pith/PKRBMRBIB4T3AC5BKG5HUUBMDJ.json","view_paper":"https://pith.science/paper/PKRBMRBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1402.0282&json=true","fetch_graph":"https://pith.science/api/pith-number/PKRBMRBIB4T3AC5BKG5HUUBMDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PKRBMRBIB4T3AC5BKG5HUUBMDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKRBMRBIB4T3AC5BKG5HUUBMDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKRBMRBIB4T3AC5BKG5HUUBMDJ/action/storage_attestation","attest_author":"https://pith.science/pith/PKRBMRBIB4T3AC5BKG5HUUBMDJ/action/author_attestation","sign_citation":"https://pith.science/pith/PKRBMRBIB4T3AC5BKG5HUUBMDJ/action/citation_signature","submit_replication":"https://pith.science/pith/PKRBMRBIB4T3AC5BKG5HUUBMDJ/action/replication_record"}},"created_at":"2026-05-18T03:00:24.031912+00:00","updated_at":"2026-05-18T03:00:24.031912+00:00"}