{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:77XQVLJITYR7AV4P7G5QZUPENF","short_pith_number":"pith:77XQVLJI","canonical_record":{"source":{"id":"1207.4157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-11T15:00:28Z","cross_cats_sorted":["cs.DL","cs.IR","stat.ML"],"title_canon_sha256":"786894c2be46fc6d578e637911cf3ba0d268db691433a981dca86226a3fbe2f0","abstract_canon_sha256":"111347dc7728a3ca520794a3ea0986a454749a6642f685b428115f088878d03f"},"schema_version":"1.0"},"canonical_sha256":"ffef0aad289e23f0578ff9bb0cd1e4697fecd9945fd5b7db95ad0e6eb438341c","source":{"kind":"arxiv","id":"1207.4157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.4157","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"1207.4157v1","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4157","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"77XQVLJITYR7","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"77XQVLJITYR7AV4P","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"77XQVLJI","created_at":"2026-05-18T12:26:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:77XQVLJITYR7AV4P7G5QZUPENF","target":"record","payload":{"canonical_record":{"source":{"id":"1207.4157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-11T15:00:28Z","cross_cats_sorted":["cs.DL","cs.IR","stat.ML"],"title_canon_sha256":"786894c2be46fc6d578e637911cf3ba0d268db691433a981dca86226a3fbe2f0","abstract_canon_sha256":"111347dc7728a3ca520794a3ea0986a454749a6642f685b428115f088878d03f"},"schema_version":"1.0"},"canonical_sha256":"ffef0aad289e23f0578ff9bb0cd1e4697fecd9945fd5b7db95ad0e6eb438341c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:47.569631Z","signature_b64":"3A07Xtg4//ygOXhRaS7tqKwJFdGqT1hJVyoYsyTqYj5iejbwrvNwgAX4Pm2/lvBDe1SIDQdHLOu3mvUFrSeGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffef0aad289e23f0578ff9bb0cd1e4697fecd9945fd5b7db95ad0e6eb438341c","last_reissued_at":"2026-05-18T03:50:47.568860Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:47.568860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1207.4157","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":"SNyraNnsI2E2uDsIkoiL+u3YtXCW2zZKYcPyzgGaxRtKuSCGHcqy9NT231GrA58wtwgS3p3BsS6y+58/dnKQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T17:15:33.808974Z"},"content_sha256":"54f9c66285b0629cca50f1ec31a0ffdf84ea59971bd5dbfbb024909ea61b454c","schema_version":"1.0","event_id":"sha256:54f9c66285b0629cca50f1ec31a0ffdf84ea59971bd5dbfbb024909ea61b454c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:77XQVLJITYR7AV4P7G5QZUPENF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Integrated, Conditional Model of Information Extraction and Coreference with Applications to Citation Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew McCallum, Ben Wellner, Fuchun Peng, Michael Hay","submitted_at":"2012-07-11T15:00:28Z","abstract_excerpt":"Although information extraction and coreference resolution appear together in many applications, most current systems perform them as ndependent steps. This paper describes an approach to integrated inference for extraction and coreference based on conditionally-trained undirected graphical models. We discuss the advantages of conditional probability training, and of a coreference model structure based on graph partitioning. On a data set of research paper citations, we show significant reduction in error by using extraction uncertainty to improve coreference citation matching accuracy, and us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4157","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":"X5/CxQpp0FCEzzFA3d0VvsBKzSYVIiaGBSx4xAxJQiS/o1Pq3yFIOFTTEO0gHgyRqrHWjZwCf+9mT9w2Q1o1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T17:15:33.809623Z"},"content_sha256":"25117a1e989b15bdd6ea0122ba8a7801b9f713b9d8a9ce0d1f75f838d29181f9","schema_version":"1.0","event_id":"sha256:25117a1e989b15bdd6ea0122ba8a7801b9f713b9d8a9ce0d1f75f838d29181f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77XQVLJITYR7AV4P7G5QZUPENF/bundle.json","state_url":"https://pith.science/pith/77XQVLJITYR7AV4P7G5QZUPENF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77XQVLJITYR7AV4P7G5QZUPENF/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":"2026-05-24T17:15:33Z","links":{"resolver":"https://pith.science/pith/77XQVLJITYR7AV4P7G5QZUPENF","bundle":"https://pith.science/pith/77XQVLJITYR7AV4P7G5QZUPENF/bundle.json","state":"https://pith.science/pith/77XQVLJITYR7AV4P7G5QZUPENF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77XQVLJITYR7AV4P7G5QZUPENF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:77XQVLJITYR7AV4P7G5QZUPENF","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":"111347dc7728a3ca520794a3ea0986a454749a6642f685b428115f088878d03f","cross_cats_sorted":["cs.DL","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-11T15:00:28Z","title_canon_sha256":"786894c2be46fc6d578e637911cf3ba0d268db691433a981dca86226a3fbe2f0"},"schema_version":"1.0","source":{"id":"1207.4157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.4157","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"1207.4157v1","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4157","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"77XQVLJITYR7","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"77XQVLJITYR7AV4P","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"77XQVLJI","created_at":"2026-05-18T12:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:25117a1e989b15bdd6ea0122ba8a7801b9f713b9d8a9ce0d1f75f838d29181f9","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":"Although information extraction and coreference resolution appear together in many applications, most current systems perform them as ndependent steps. This paper describes an approach to integrated inference for extraction and coreference based on conditionally-trained undirected graphical models. We discuss the advantages of conditional probability training, and of a coreference model structure based on graph partitioning. On a data set of research paper citations, we show significant reduction in error by using extraction uncertainty to improve coreference citation matching accuracy, and us","authors_text":"Andrew McCallum, Ben Wellner, Fuchun Peng, Michael Hay","cross_cats":["cs.DL","cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-11T15:00:28Z","title":"An Integrated, Conditional Model of Information Extraction and Coreference with Applications to Citation Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4157","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":"sha256:54f9c66285b0629cca50f1ec31a0ffdf84ea59971bd5dbfbb024909ea61b454c","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":"111347dc7728a3ca520794a3ea0986a454749a6642f685b428115f088878d03f","cross_cats_sorted":["cs.DL","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-11T15:00:28Z","title_canon_sha256":"786894c2be46fc6d578e637911cf3ba0d268db691433a981dca86226a3fbe2f0"},"schema_version":"1.0","source":{"id":"1207.4157","kind":"arxiv","version":1}},"canonical_sha256":"ffef0aad289e23f0578ff9bb0cd1e4697fecd9945fd5b7db95ad0e6eb438341c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffef0aad289e23f0578ff9bb0cd1e4697fecd9945fd5b7db95ad0e6eb438341c","first_computed_at":"2026-05-18T03:50:47.568860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:50:47.568860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3A07Xtg4//ygOXhRaS7tqKwJFdGqT1hJVyoYsyTqYj5iejbwrvNwgAX4Pm2/lvBDe1SIDQdHLOu3mvUFrSeGCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:50:47.569631Z","signed_message":"canonical_sha256_bytes"},"source_id":"1207.4157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54f9c66285b0629cca50f1ec31a0ffdf84ea59971bd5dbfbb024909ea61b454c","sha256:25117a1e989b15bdd6ea0122ba8a7801b9f713b9d8a9ce0d1f75f838d29181f9"],"state_sha256":"83d80c5e96b955bf9b9dfe88ac33be0b92eb111be9fd89fe0783121874cf4d6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BVo0lI3E3Zm7uVdGQPZpK6nWAffEFI0qiLce5AFavt13Zf6/lbEFFg3NYb4LIWjNxERaEtLP1DsJ6E8oL3pICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T17:15:33.813085Z","bundle_sha256":"25261ccf55512002f9561857922ab9a62136dc2387cb80d59583770b82e2d070"}}