{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:GYZW4CX2B73GW7GIUI4DQA5KHD","short_pith_number":"pith:GYZW4CX2","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"},"canonical_sha256":"36336e0afa0ff66b7cc8a2383803aa38f5faae12e235de826ac9e71698d6f52d","source":{"kind":"arxiv","id":"1207.4180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.4180","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"1207.4180v1","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4180","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"GYZW4CX2B73G","created_at":"2026-05-18T12:27:06Z"},{"alias_kind":"pith_short_16","alias_value":"GYZW4CX2B73GW7GI","created_at":"2026-05-18T12:27:06Z"},{"alias_kind":"pith_short_8","alias_value":"GYZW4CX2","created_at":"2026-05-18T12:27:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:GYZW4CX2B73GW7GIUI4DQA5KHD","target":"record","payload":{"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"},"canonical_sha256":"36336e0afa0ff66b7cc8a2383803aa38f5faae12e235de826ac9e71698d6f52d","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"},"source_kind":"arxiv","source_id":"1207.4180","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TDq1DNd33R+gtl0ym35iPxaIDttJOxTzrPjCaHbiRbxKe2bWXGp4jZ5eg56Z+NPirwJrYHT6Jw/qT5ovfTNuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:00:47.543812Z"},"content_sha256":"d4937f3305a83fc52ed8d4371876e8997cb4d65da5b762537780e225d1040ee5","schema_version":"1.0","event_id":"sha256:d4937f3305a83fc52ed8d4371876e8997cb4d65da5b762537780e225d1040ee5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:GYZW4CX2B73GW7GIUI4DQA5KHD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1tvAFneB8cInsKGoR4hMO8HnvxHUsRpTdH7ldKiRTMOztLICO+dcZfGY7/WW5NYRy8XYVhF1xw/Gfx5vWGIPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:00:47.544196Z"},"content_sha256":"074aba43be88eb77dff57abe5978e50514fdb81909299c0b16cfefb88097e57a","schema_version":"1.0","event_id":"sha256:074aba43be88eb77dff57abe5978e50514fdb81909299c0b16cfefb88097e57a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/bundle.json","state_url":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/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":"2026-05-30T07:00:47Z","links":{"resolver":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD","bundle":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/bundle.json","state":"https://pith.science/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYZW4CX2B73GW7GIUI4DQA5KHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:GYZW4CX2B73GW7GIUI4DQA5KHD","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":"d6716054a7c1d3a2d627a69158ef0f2ae0a8351a7814706d8b7c4766170738af","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-12T19:48:03Z","title_canon_sha256":"1eec63a8894e257f5fd97dc6989f3de7d18c282e7aad9b2b104ec615eefc058e"},"schema_version":"1.0","source":{"id":"1207.4180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.4180","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"1207.4180v1","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4180","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"GYZW4CX2B73G","created_at":"2026-05-18T12:27:06Z"},{"alias_kind":"pith_short_16","alias_value":"GYZW4CX2B73GW7GI","created_at":"2026-05-18T12:27:06Z"},{"alias_kind":"pith_short_8","alias_value":"GYZW4CX2","created_at":"2026-05-18T12:27:06Z"}],"graph_snapshots":[{"event_id":"sha256:074aba43be88eb77dff57abe5978e50514fdb81909299c0b16cfefb88097e57a","target":"graph","created_at":"2026-05-18T03:50:47Z","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"},"paper":{"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","authors_text":"Pradeep Ravikumar, William Cohen","cross_cats":["cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-12T19:48:03Z","title":"A Hierarchical Graphical Model for Record Linkage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4180","kind":"arxiv","version":1},"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:d4937f3305a83fc52ed8d4371876e8997cb4d65da5b762537780e225d1040ee5","target":"record","created_at":"2026-05-18T03:50:47Z","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":"d6716054a7c1d3a2d627a69158ef0f2ae0a8351a7814706d8b7c4766170738af","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-12T19:48:03Z","title_canon_sha256":"1eec63a8894e257f5fd97dc6989f3de7d18c282e7aad9b2b104ec615eefc058e"},"schema_version":"1.0","source":{"id":"1207.4180","kind":"arxiv","version":1}},"canonical_sha256":"36336e0afa0ff66b7cc8a2383803aa38f5faae12e235de826ac9e71698d6f52d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36336e0afa0ff66b7cc8a2383803aa38f5faae12e235de826ac9e71698d6f52d","first_computed_at":"2026-05-18T03:50:47.374865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:50:47.374865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GR7pPsanPQFua9g1AwO9ht4Wq6VDEw6V1mA/SbvGKmRdjTykO/H2OMJD5u9Rf6X4y9Zv3wKzndpfKFItqdHACg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:50:47.375567Z","signed_message":"canonical_sha256_bytes"},"source_id":"1207.4180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4937f3305a83fc52ed8d4371876e8997cb4d65da5b762537780e225d1040ee5","sha256:074aba43be88eb77dff57abe5978e50514fdb81909299c0b16cfefb88097e57a"],"state_sha256":"583ce17418de9984767f24adde46a1b2b4da69b2fb5faf598b16926c5f7bb238"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zjbdynQpSWZXtSpnDzfo/ePNjC5BMuUjE+6Iv9tmI7sGTDcgTvTY0RGHInDAWLml5AMJ3XqdhtX+tIyH8sVIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:00:47.546229Z","bundle_sha256":"38f3fb90a40b17964d018a9b3a8d48ca8ca0f63c8ec10c9fc2a648c2ad8fcf5e"}}