{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:IPOOWZFGUFYALA3IOIDESNGQW5","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":"bb24f9de21dbf1141d93b147c0e8d915a7f59b1f799024f67bbaa45eb7d1a70e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2011-07-28T15:37:56Z","title_canon_sha256":"3474e4cacf0f3ae1dd365599d3428b13aeb4b5a318d0efce1d389d2134e8fe61"},"schema_version":"1.0","source":{"id":"1107.5743","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.5743","created_at":"2026-05-18T04:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"1107.5743v1","created_at":"2026-05-18T04:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.5743","created_at":"2026-05-18T04:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"IPOOWZFGUFYA","created_at":"2026-05-18T12:26:32Z"},{"alias_kind":"pith_short_16","alias_value":"IPOOWZFGUFYALA3I","created_at":"2026-05-18T12:26:32Z"},{"alias_kind":"pith_short_8","alias_value":"IPOOWZFG","created_at":"2026-05-18T12:26:32Z"}],"graph_snapshots":[{"event_id":"sha256:cf3a0b33089ebf688c620db67c6a2274136de7b33aafee8142794f19280ee15e","target":"graph","created_at":"2026-05-18T04:16:41Z","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":"We propose NEMO, a system for extracting organization names in the affiliation and normalizing them to a canonical organization name. Our parsing process involves multi-layered rule matching with multiple dictionaries. The system achieves more than 98% f-score in extracting organization names. Our process of normalization that involves clustering based on local sequence alignment metrics and local learning based on finding connected components. A high precision was also observed in normalization. NEMO is the missing link in associating each biomedical paper and its authors to an organization n","authors_text":"Philip Topham, Siddhartha Jonnalagadda","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2011-07-28T15:37:56Z","title":"NEMO: Extraction and normalization of organization names from PubMed affiliation strings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.5743","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":"sha256:136dd79e68bc79f19d4048fce21cf4d4462dc40cb1d00c22577059108967657c","target":"record","created_at":"2026-05-18T04:16:41Z","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":"bb24f9de21dbf1141d93b147c0e8d915a7f59b1f799024f67bbaa45eb7d1a70e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2011-07-28T15:37:56Z","title_canon_sha256":"3474e4cacf0f3ae1dd365599d3428b13aeb4b5a318d0efce1d389d2134e8fe61"},"schema_version":"1.0","source":{"id":"1107.5743","kind":"arxiv","version":1}},"canonical_sha256":"43dceb64a6a17005836872064934d0b7664fe256ff5ade4aebf174c1a6116d3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43dceb64a6a17005836872064934d0b7664fe256ff5ade4aebf174c1a6116d3b","first_computed_at":"2026-05-18T04:16:41.406774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:16:41.406774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Zi+1p7pTXDr62acNBN3WirqifkkV8naui+A18oAFS1+uk5thRvi5gzICwKpgv6RVIe9DaQbtAHBkNykNZLMBw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:16:41.407381Z","signed_message":"canonical_sha256_bytes"},"source_id":"1107.5743","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:136dd79e68bc79f19d4048fce21cf4d4462dc40cb1d00c22577059108967657c","sha256:cf3a0b33089ebf688c620db67c6a2274136de7b33aafee8142794f19280ee15e"],"state_sha256":"e170c424ca117bcd4ea2af6610f48a3f46406aaf0bb6a75fd0fc20fe3fb8c907"}