{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RHBTXJNPT5WKCZBD6HY7X7LSTM","short_pith_number":"pith:RHBTXJNP","canonical_record":{"source":{"id":"2504.15261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:41:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f00feee545227e48e73987878af4b97882a6cbf0598eb12b28e4673c8c798066","abstract_canon_sha256":"fe421c25dd4913e934d41a136e14df1e03f9eb8ee634c804beff542116f7cbbe"},"schema_version":"1.0"},"canonical_sha256":"89c33ba5af9f6ca16423f1f1fbfd729b0f0db8e21f69ef50cd3735d90f5a6212","source":{"kind":"arxiv","id":"2504.15261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15261","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15261v1","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15261","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"pith_short_12","alias_value":"RHBTXJNPT5WK","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"pith_short_16","alias_value":"RHBTXJNPT5WKCZBD","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"pith_short_8","alias_value":"RHBTXJNP","created_at":"2026-07-05T10:51:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RHBTXJNPT5WKCZBD6HY7X7LSTM","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:41:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f00feee545227e48e73987878af4b97882a6cbf0598eb12b28e4673c8c798066","abstract_canon_sha256":"fe421c25dd4913e934d41a136e14df1e03f9eb8ee634c804beff542116f7cbbe"},"schema_version":"1.0"},"canonical_sha256":"89c33ba5af9f6ca16423f1f1fbfd729b0f0db8e21f69ef50cd3735d90f5a6212","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:58.940625Z","signature_b64":"LkFJtcV2h+8X+eoLT1PAlJ7i+Ry20LrliWHENFzcy7ZWO4F/x3H/wm9ESsXD2cGc07VPORSGyhWnf16JXbK+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c33ba5af9f6ca16423f1f1fbfd729b0f0db8e21f69ef50cd3735d90f5a6212","last_reissued_at":"2026-07-05T10:51:58.939823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:58.939823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15261","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":"2026-07-05T10:51:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohoC2Qx1wIT/Oee3OPBhJfxxS0Ocue1xotocqNSTLxPqwhihrCyadlaoEHR3KcSCXIODqgNLgewMS2iavVM1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:18:15.973442Z"},"content_sha256":"3dc7fa967e847ffdae1c4383795f62ca05f3bce6e488fa9bac9acdb8af1ca11d","schema_version":"1.0","event_id":"sha256:3dc7fa967e847ffdae1c4383795f62ca05f3bce6e488fa9bac9acdb8af1ca11d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RHBTXJNPT5WKCZBD6HY7X7LSTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Language Models for Automated Patient Record Linkage","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Iris Zachary, Lovedeep Gondara, Mohammad Beheshti","submitted_at":"2025-04-21T17:41:15Z","abstract_excerpt":"Objective: Healthcare data fragmentation presents a major challenge for linking patient data, necessitating robust record linkage to integrate patient records from diverse sources. This study investigates the feasibility of leveraging language models for automated patient record linkage, focusing on two key tasks: blocking and matching. Materials and Methods: We utilized real-world healthcare data from the Missouri Cancer Registry and Research Center, linking patient records from two independent sources using probabilistic linkage as a baseline. A transformer-based model, RoBERTa, was fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15261","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.15261/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T10:51:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x8q2JGrwv5WmCSkR0lZDC0tuA9q1AecNr5Qi88JckEkLnDxqt4wouThYak/j5jb05Gk6pibuo6P9sneoKOGZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:18:15.973980Z"},"content_sha256":"9e7625b2229b127d1074a39f292c529aacd9a83b262a2f917d4b238b064c12fc","schema_version":"1.0","event_id":"sha256:9e7625b2229b127d1074a39f292c529aacd9a83b262a2f917d4b238b064c12fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHBTXJNPT5WKCZBD6HY7X7LSTM/bundle.json","state_url":"https://pith.science/pith/RHBTXJNPT5WKCZBD6HY7X7LSTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHBTXJNPT5WKCZBD6HY7X7LSTM/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":"2026-08-18T08:18:15Z","links":{"resolver":"https://pith.science/pith/RHBTXJNPT5WKCZBD6HY7X7LSTM","bundle":"https://pith.science/pith/RHBTXJNPT5WKCZBD6HY7X7LSTM/bundle.json","state":"https://pith.science/pith/RHBTXJNPT5WKCZBD6HY7X7LSTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHBTXJNPT5WKCZBD6HY7X7LSTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RHBTXJNPT5WKCZBD6HY7X7LSTM","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":"fe421c25dd4913e934d41a136e14df1e03f9eb8ee634c804beff542116f7cbbe","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:41:15Z","title_canon_sha256":"f00feee545227e48e73987878af4b97882a6cbf0598eb12b28e4673c8c798066"},"schema_version":"1.0","source":{"id":"2504.15261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15261","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15261v1","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15261","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"pith_short_12","alias_value":"RHBTXJNPT5WK","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"pith_short_16","alias_value":"RHBTXJNPT5WKCZBD","created_at":"2026-07-05T10:51:58Z"},{"alias_kind":"pith_short_8","alias_value":"RHBTXJNP","created_at":"2026-07-05T10:51:58Z"}],"graph_snapshots":[{"event_id":"sha256:9e7625b2229b127d1074a39f292c529aacd9a83b262a2f917d4b238b064c12fc","target":"graph","created_at":"2026-07-05T10:51:58Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.15261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Objective: Healthcare data fragmentation presents a major challenge for linking patient data, necessitating robust record linkage to integrate patient records from diverse sources. This study investigates the feasibility of leveraging language models for automated patient record linkage, focusing on two key tasks: blocking and matching. Materials and Methods: We utilized real-world healthcare data from the Missouri Cancer Registry and Research Center, linking patient records from two independent sources using probabilistic linkage as a baseline. A transformer-based model, RoBERTa, was fine-tun","authors_text":"Iris Zachary, Lovedeep Gondara, Mohammad Beheshti","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:41:15Z","title":"Leveraging Language Models for Automated Patient Record Linkage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15261","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":"sha256:3dc7fa967e847ffdae1c4383795f62ca05f3bce6e488fa9bac9acdb8af1ca11d","target":"record","created_at":"2026-07-05T10:51:58Z","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":"fe421c25dd4913e934d41a136e14df1e03f9eb8ee634c804beff542116f7cbbe","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:41:15Z","title_canon_sha256":"f00feee545227e48e73987878af4b97882a6cbf0598eb12b28e4673c8c798066"},"schema_version":"1.0","source":{"id":"2504.15261","kind":"arxiv","version":1}},"canonical_sha256":"89c33ba5af9f6ca16423f1f1fbfd729b0f0db8e21f69ef50cd3735d90f5a6212","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89c33ba5af9f6ca16423f1f1fbfd729b0f0db8e21f69ef50cd3735d90f5a6212","first_computed_at":"2026-07-05T10:51:58.939823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:58.939823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LkFJtcV2h+8X+eoLT1PAlJ7i+Ry20LrliWHENFzcy7ZWO4F/x3H/wm9ESsXD2cGc07VPORSGyhWnf16JXbK+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:58.940625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dc7fa967e847ffdae1c4383795f62ca05f3bce6e488fa9bac9acdb8af1ca11d","sha256:9e7625b2229b127d1074a39f292c529aacd9a83b262a2f917d4b238b064c12fc"],"state_sha256":"be1462c5cc3e2832c6f3d506364a4685b7c7ff221593342fb23ace8727c01087"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jf181pICnvmeSajK9XFRc33vUb+u02t5Jdm/qEBFPjDWRiJAN4Xgfb1nQBSDDklPaNtAV8f7u/2mQrA1skm3BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:18:15.978767Z","bundle_sha256":"5b80b283b81d78771223babeddc89422672552ee68044560e0b2e0afc1d889ed"}}