{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DAT75XKWVXZ7FJAQCRXUVTUJEZ","short_pith_number":"pith:DAT75XKW","canonical_record":{"source":{"id":"1903.03985","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T13:16:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bfcb02b13433a64641c821df279cd180e70746332f7852ce17d9c38584d6a6cd","abstract_canon_sha256":"8a9f92cb93b65a156c0439229b1d63361ebc4098382ba39ff3aa4067014abac3"},"schema_version":"1.0"},"canonical_sha256":"1827fedd56adf3f2a410146f4ace89266c99712b3377f6e26919cdc7d869419a","source":{"kind":"arxiv","id":"1903.03985","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03985","created_at":"2026-05-17T23:44:07Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03985v2","created_at":"2026-05-17T23:44:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03985","created_at":"2026-05-17T23:44:07Z"},{"alias_kind":"pith_short_12","alias_value":"DAT75XKWVXZ7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DAT75XKWVXZ7FJAQ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DAT75XKW","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DAT75XKWVXZ7FJAQCRXUVTUJEZ","target":"record","payload":{"canonical_record":{"source":{"id":"1903.03985","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T13:16:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bfcb02b13433a64641c821df279cd180e70746332f7852ce17d9c38584d6a6cd","abstract_canon_sha256":"8a9f92cb93b65a156c0439229b1d63361ebc4098382ba39ff3aa4067014abac3"},"schema_version":"1.0"},"canonical_sha256":"1827fedd56adf3f2a410146f4ace89266c99712b3377f6e26919cdc7d869419a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:07.064262Z","signature_b64":"xTenAo8+zL1fkwkx1VDvVPyTuu3eKcEgnWgn2dlSD7OpKJFOb2g+9Cbtaqlx8H0ZqtEIn5XUaX78lfWWsc12DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1827fedd56adf3f2a410146f4ace89266c99712b3377f6e26919cdc7d869419a","last_reissued_at":"2026-05-17T23:44:07.063435Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:07.063435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.03985","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knIZsR+ZldYSnruqa62o+wga1zPOk81erErIBhkFkwsevTTLUKG/fHMgyoJ97ji3q3Co3F3jH3xeQET6UdjbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T16:09:40.118553Z"},"content_sha256":"3edc84106e0cc6dacc7b18fc2eeddffb7cd276e3861d3cb80232d5e2e318448e","schema_version":"1.0","event_id":"sha256:3edc84106e0cc6dacc7b18fc2eeddffb7cd276e3861d3cb80232d5e2e318448e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DAT75XKWVXZ7FJAQCRXUVTUJEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Named Entity Recognition for Electronic Health Records: A Comparison of Rule-based and Machine Learning Approaches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Beatrice Alex, Cathie Sudlow, Claire Grover, Conn Talbot, Heather Whalley, Honghan Wu, Philip John Gorinski, Richard Tobin, William Whiteley","submitted_at":"2019-03-10T13:16:37Z","abstract_excerpt":"This work investigates multiple approaches to Named Entity Recognition (NER) for text in Electronic Health Record (EHR) data. In particular, we look into the application of (i) rule-based, (ii) deep learning and (iii) transfer learning systems for the task of NER on brain imaging reports with a focus on records from patients with stroke. We explore the strengths and weaknesses of each approach, develop rules and train on a common dataset, and evaluate each system's performance on common test sets of Scottish radiology reports from two sources (brain imaging reports in ESS -- Edinburgh Stroke S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03985","kind":"arxiv","version":2},"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":"2026-05-17T23:44:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h3bWcgXNII4P3HDJDgUFjEC4BAToM+Edef8FmS+lqT98oBklGpljI5ef8Si8gfbwRbm0pDPSfETR+KqZtHF3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T16:09:40.118900Z"},"content_sha256":"8d1462fdabe1c97fa91b22e5e66b12d92fe06bdcd36086fc76ba5c6cd671d2bd","schema_version":"1.0","event_id":"sha256:8d1462fdabe1c97fa91b22e5e66b12d92fe06bdcd36086fc76ba5c6cd671d2bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAT75XKWVXZ7FJAQCRXUVTUJEZ/bundle.json","state_url":"https://pith.science/pith/DAT75XKWVXZ7FJAQCRXUVTUJEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAT75XKWVXZ7FJAQCRXUVTUJEZ/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":"2026-06-28T16:09:40Z","links":{"resolver":"https://pith.science/pith/DAT75XKWVXZ7FJAQCRXUVTUJEZ","bundle":"https://pith.science/pith/DAT75XKWVXZ7FJAQCRXUVTUJEZ/bundle.json","state":"https://pith.science/pith/DAT75XKWVXZ7FJAQCRXUVTUJEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAT75XKWVXZ7FJAQCRXUVTUJEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DAT75XKWVXZ7FJAQCRXUVTUJEZ","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":"8a9f92cb93b65a156c0439229b1d63361ebc4098382ba39ff3aa4067014abac3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T13:16:37Z","title_canon_sha256":"bfcb02b13433a64641c821df279cd180e70746332f7852ce17d9c38584d6a6cd"},"schema_version":"1.0","source":{"id":"1903.03985","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03985","created_at":"2026-05-17T23:44:07Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03985v2","created_at":"2026-05-17T23:44:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03985","created_at":"2026-05-17T23:44:07Z"},{"alias_kind":"pith_short_12","alias_value":"DAT75XKWVXZ7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DAT75XKWVXZ7FJAQ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DAT75XKW","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:8d1462fdabe1c97fa91b22e5e66b12d92fe06bdcd36086fc76ba5c6cd671d2bd","target":"graph","created_at":"2026-05-17T23:44:07Z","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":"This work investigates multiple approaches to Named Entity Recognition (NER) for text in Electronic Health Record (EHR) data. In particular, we look into the application of (i) rule-based, (ii) deep learning and (iii) transfer learning systems for the task of NER on brain imaging reports with a focus on records from patients with stroke. We explore the strengths and weaknesses of each approach, develop rules and train on a common dataset, and evaluate each system's performance on common test sets of Scottish radiology reports from two sources (brain imaging reports in ESS -- Edinburgh Stroke S","authors_text":"Beatrice Alex, Cathie Sudlow, Claire Grover, Conn Talbot, Heather Whalley, Honghan Wu, Philip John Gorinski, Richard Tobin, William Whiteley","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T13:16:37Z","title":"Named Entity Recognition for Electronic Health Records: A Comparison of Rule-based and Machine Learning Approaches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03985","kind":"arxiv","version":2},"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":"sha256:3edc84106e0cc6dacc7b18fc2eeddffb7cd276e3861d3cb80232d5e2e318448e","target":"record","created_at":"2026-05-17T23:44:07Z","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":"8a9f92cb93b65a156c0439229b1d63361ebc4098382ba39ff3aa4067014abac3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-10T13:16:37Z","title_canon_sha256":"bfcb02b13433a64641c821df279cd180e70746332f7852ce17d9c38584d6a6cd"},"schema_version":"1.0","source":{"id":"1903.03985","kind":"arxiv","version":2}},"canonical_sha256":"1827fedd56adf3f2a410146f4ace89266c99712b3377f6e26919cdc7d869419a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1827fedd56adf3f2a410146f4ace89266c99712b3377f6e26919cdc7d869419a","first_computed_at":"2026-05-17T23:44:07.063435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:07.063435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xTenAo8+zL1fkwkx1VDvVPyTuu3eKcEgnWgn2dlSD7OpKJFOb2g+9Cbtaqlx8H0ZqtEIn5XUaX78lfWWsc12DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:07.064262Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.03985","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3edc84106e0cc6dacc7b18fc2eeddffb7cd276e3861d3cb80232d5e2e318448e","sha256:8d1462fdabe1c97fa91b22e5e66b12d92fe06bdcd36086fc76ba5c6cd671d2bd"],"state_sha256":"fb18f557461171243bb963e0a4d4c3d4870af48d14d129751f4672324e8aec93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f13tinaJ43h38NX3k0QYu2XkZcL6inPzWz26S0tc1vHpiNxjiIOQz77OFyVUY78Hl+YSufidN0rZiKSV9nN8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T16:09:40.120940Z","bundle_sha256":"7ac52fb69c17a7dba68450b5666b1be5d74bc3201e05616d0b7b4de3ccb9ccf0"}}