{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:GYZW4CX2B73GW7GIUI4DQA5KHD","short_pith_number":"pith:GYZW4CX2","schema_version":"1.0","canonical_sha256":"36336e0afa0ff66b7cc8a2383803aa38f5faae12e235de826ac9e71698d6f52d","source":{"kind":"arxiv","id":"1207.4180","version":1},"attestation_state":"computed","paper":{"title":"A Hierarchical Graphical Model for Record Linkage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Pradeep Ravikumar, William Cohen","submitted_at":"2012-07-12T19:48:03Z","abstract_excerpt":"The task of matching co-referent records is known among other names as rocord linkage. For large record-linkage problems, often there is little or no labeled data available, but unlabeled data shows a reasonable clear structure. For such problems, unsupervised or semi-supervised methods are preferable to supervised methods. In this paper, we describe a hierarchical graphical model framework for the linakge-problem in an unsupervised setting. In addition to proposing new methods, we also cast existing unsupervised probabilistic record-linkage methods in this framework. Some of the techniques we"},"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":"1207.4180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-12T19:48:03Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"1eec63a8894e257f5fd97dc6989f3de7d18c282e7aad9b2b104ec615eefc058e","abstract_canon_sha256":"d6716054a7c1d3a2d627a69158ef0f2ae0a8351a7814706d8b7c4766170738af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:47.375567Z","signature_b64":"GR7pPsanPQFua9g1AwO9ht4Wq6VDEw6V1mA/SbvGKmRdjTykO/H2OMJD5u9Rf6X4y9Zv3wKzndpfKFItqdHACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36336e0afa0ff66b7cc8a2383803aa38f5faae12e235de826ac9e71698d6f52d","last_reissued_at":"2026-05-18T03:50:47.374865Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:47.374865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hierarchical Graphical Model for Record Linkage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Pradeep Ravikumar, William Cohen","submitted_at":"2012-07-12T19:48:03Z","abstract_excerpt":"The task of matching co-referent records is known among other names as rocord linkage. For large record-linkage problems, often there is little or no labeled data available, but unlabeled data shows a reasonable clear structure. For such problems, unsupervised or semi-supervised methods are preferable to supervised methods. In this paper, we describe a hierarchical graphical model framework for the linakge-problem in an unsupervised setting. In addition to proposing new methods, we also cast existing unsupervised probabilistic record-linkage methods in this framework. Some of the techniques we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4180","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":"1207.4180","created_at":"2026-05-18T03:50:47.374996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.4180v1","created_at":"2026-05-18T03:50:47.374996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4180","created_at":"2026-05-18T03:50:47.374996+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYZW4CX2B73G","created_at":"2026-05-18T12:27:06.952714+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYZW4CX2B73GW7GI","created_at":"2026-05-18T12:27:06.952714+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYZW4CX2","created_at":"2026-05-18T12:27:06.952714+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/GYZW4CX2B73GW7GIUI4DQA5KHD","json":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD.json","graph_json":"https://pith.science/api/pith-number/GYZW4CX2B73GW7GIUI4DQA5KHD/graph.json","events_json":"https://pith.science/api/pith-number/GYZW4CX2B73GW7GIUI4DQA5KHD/events.json","paper":"https://pith.science/paper/GYZW4CX2"},"agent_actions":{"view_html":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD","download_json":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD.json","view_paper":"https://pith.science/paper/GYZW4CX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.4180&json=true","fetch_graph":"https://pith.science/api/pith-number/GYZW4CX2B73GW7GIUI4DQA5KHD/graph.json","fetch_events":"https://pith.science/api/pith-number/GYZW4CX2B73GW7GIUI4DQA5KHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/action/storage_attestation","attest_author":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/action/author_attestation","sign_citation":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/action/citation_signature","submit_replication":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/action/replication_record"}},"created_at":"2026-05-18T03:50:47.374996+00:00","updated_at":"2026-05-18T03:50:47.374996+00:00"}