{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QVSBK2LC5C3W22SBHTJY7UZPRS","short_pith_number":"pith:QVSBK2LC","canonical_record":{"source":{"id":"1903.03995","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T14:05:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"834a0a01a9940874a24dc5531f408154ca2f7e754a49cef4061e5b2ac1908a37","abstract_canon_sha256":"6a103f9f6aa477c11bfc6dbedf021caeda2f597222be4dcdb4d8a7e3ecf9fa83"},"schema_version":"1.0"},"canonical_sha256":"8564156962e8b76d6a413cd38fd32f8c99a81f9a27eb5be7079ed9d553f4abb2","source":{"kind":"arxiv","id":"1903.03995","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03995","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03995v3","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03995","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"QVSBK2LC5C3W","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"QVSBK2LC5C3W22SB","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"QVSBK2LC","created_at":"2026-07-05T00:14:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QVSBK2LC5C3W22SBHTJY7UZPRS","target":"record","payload":{"canonical_record":{"source":{"id":"1903.03995","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T14:05:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"834a0a01a9940874a24dc5531f408154ca2f7e754a49cef4061e5b2ac1908a37","abstract_canon_sha256":"6a103f9f6aa477c11bfc6dbedf021caeda2f597222be4dcdb4d8a7e3ecf9fa83"},"schema_version":"1.0"},"canonical_sha256":"8564156962e8b76d6a413cd38fd32f8c99a81f9a27eb5be7079ed9d553f4abb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:30.812278Z","signature_b64":"P+EKfg7R1ItzCLucE+sBzGbOS4vAdN77jEtSYNgMyZ3gTrW53yxcb1VHYa/lyyA6dJCXwVNqvK2pQF3mjYdZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8564156962e8b76d6a413cd38fd32f8c99a81f9a27eb5be7079ed9d553f4abb2","last_reissued_at":"2026-07-05T00:14:30.811813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:30.811813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.03995","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:14:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsx+H1UnbTy94mI1Je3oQVQQ+sMmYTqQ/fYwD2NjBD88HO3kd5EKSeinas/wety890JAN4YzharULdVVr4hnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:31:17.168988Z"},"content_sha256":"c2e16463a240e6d28e95f66631ce11dc52de2d1c628e56ccb26aac19e3eea987","schema_version":"1.0","event_id":"sha256:c2e16463a240e6d28e95f66631ce11dc52de2d1c628e56ccb26aac19e3eea987"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QVSBK2LC5C3W22SBHTJY7UZPRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficiently Reusing Natural Language Processing Models for Phenotype-Mention Identification in Free-text Electronic Medical Records: Methodology Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cathie Sudlow, Ehtesham Iqbal, Honghan Wu, Karen Hodgson, Katherine I. Morley, Richard JB Dobson, Robert Stewart, Sue Dyson, Zina M. Ibrahim","submitted_at":"2019-03-10T14:05:08Z","abstract_excerpt":"Background: Many efforts have been put into the use of automated approaches, such as natural language processing (NLP), to mine or extract data from free-text medical records to construct comprehensive patient profiles for delivering better health-care. Reusing NLP models in new settings, however, remains cumbersome - requiring validation and/or retraining on new data iteratively to achieve convergent results.\n  Objective: The aim of this work is to minimize the effort involved in reusing NLP models on free-text medical records.\n  Methods: We formally define and analyse the model adaptation pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03995","kind":"arxiv","version":3},"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/1903.03995/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":"2026-07-05T00:14:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VY38K75FBwLfTIfPtO7fW9dL3aAIOsImjd5xeyOB695SgDuQoVqzUHzI+9NdmmwuC7Ag+0gSTp/7G7l/MujnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:31:17.169620Z"},"content_sha256":"6088fcdff1a09911b8b71abd8910751b1cac4d334ab9d19c0e27e4c8604e89f9","schema_version":"1.0","event_id":"sha256:6088fcdff1a09911b8b71abd8910751b1cac4d334ab9d19c0e27e4c8604e89f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVSBK2LC5C3W22SBHTJY7UZPRS/bundle.json","state_url":"https://pith.science/pith/QVSBK2LC5C3W22SBHTJY7UZPRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVSBK2LC5C3W22SBHTJY7UZPRS/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":"2026-07-05T14:31:17Z","links":{"resolver":"https://pith.science/pith/QVSBK2LC5C3W22SBHTJY7UZPRS","bundle":"https://pith.science/pith/QVSBK2LC5C3W22SBHTJY7UZPRS/bundle.json","state":"https://pith.science/pith/QVSBK2LC5C3W22SBHTJY7UZPRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVSBK2LC5C3W22SBHTJY7UZPRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QVSBK2LC5C3W22SBHTJY7UZPRS","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":"6a103f9f6aa477c11bfc6dbedf021caeda2f597222be4dcdb4d8a7e3ecf9fa83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T14:05:08Z","title_canon_sha256":"834a0a01a9940874a24dc5531f408154ca2f7e754a49cef4061e5b2ac1908a37"},"schema_version":"1.0","source":{"id":"1903.03995","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03995","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03995v3","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03995","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"QVSBK2LC5C3W","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"QVSBK2LC5C3W22SB","created_at":"2026-07-05T00:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"QVSBK2LC","created_at":"2026-07-05T00:14:30Z"}],"graph_snapshots":[{"event_id":"sha256:6088fcdff1a09911b8b71abd8910751b1cac4d334ab9d19c0e27e4c8604e89f9","target":"graph","created_at":"2026-07-05T00:14:30Z","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/1903.03995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background: Many efforts have been put into the use of automated approaches, such as natural language processing (NLP), to mine or extract data from free-text medical records to construct comprehensive patient profiles for delivering better health-care. Reusing NLP models in new settings, however, remains cumbersome - requiring validation and/or retraining on new data iteratively to achieve convergent results.\n  Objective: The aim of this work is to minimize the effort involved in reusing NLP models on free-text medical records.\n  Methods: We formally define and analyse the model adaptation pr","authors_text":"Cathie Sudlow, Ehtesham Iqbal, Honghan Wu, Karen Hodgson, Katherine I. Morley, Richard JB Dobson, Robert Stewart, Sue Dyson, Zina M. Ibrahim","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T14:05:08Z","title":"Efficiently Reusing Natural Language Processing Models for Phenotype-Mention Identification in Free-text Electronic Medical Records: Methodology Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03995","kind":"arxiv","version":3},"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:c2e16463a240e6d28e95f66631ce11dc52de2d1c628e56ccb26aac19e3eea987","target":"record","created_at":"2026-07-05T00:14:30Z","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":"6a103f9f6aa477c11bfc6dbedf021caeda2f597222be4dcdb4d8a7e3ecf9fa83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T14:05:08Z","title_canon_sha256":"834a0a01a9940874a24dc5531f408154ca2f7e754a49cef4061e5b2ac1908a37"},"schema_version":"1.0","source":{"id":"1903.03995","kind":"arxiv","version":3}},"canonical_sha256":"8564156962e8b76d6a413cd38fd32f8c99a81f9a27eb5be7079ed9d553f4abb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8564156962e8b76d6a413cd38fd32f8c99a81f9a27eb5be7079ed9d553f4abb2","first_computed_at":"2026-07-05T00:14:30.811813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:14:30.811813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P+EKfg7R1ItzCLucE+sBzGbOS4vAdN77jEtSYNgMyZ3gTrW53yxcb1VHYa/lyyA6dJCXwVNqvK2pQF3mjYdZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:14:30.812278Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.03995","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2e16463a240e6d28e95f66631ce11dc52de2d1c628e56ccb26aac19e3eea987","sha256:6088fcdff1a09911b8b71abd8910751b1cac4d334ab9d19c0e27e4c8604e89f9"],"state_sha256":"f446479e0d3c05e5f3f9a30f0ed9609996cd9e6db58c58b803bd285efb0762e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mHqdBylhDjmhOYIeLkPi2Pfs1tNifTRKhZGqvuK84YrQwsNqbIXL050rmyeUhSCiMqximeZffBjmdO7LfX/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:31:17.173057Z","bundle_sha256":"bda78707c5d5ad30052930ef93362f7e23d6efaee751242734c532cc60162857"}}