{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:37OA2A22DCLPRKR6RBFCAFXSEE","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":"1746e1d7e3c63359a122bf3e54f51d8abab3feb7adcc6f2e6ff9acf42aad51fe","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-05-26T21:12:43Z","title_canon_sha256":"799bc2fdeee19d43cfe16fc5cf76b516ff0ae7b1ad8d09cef0de527188cfb5e4"},"schema_version":"1.0","source":{"id":"2006.03685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.03685","created_at":"2026-07-05T01:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2006.03685v1","created_at":"2026-07-05T01:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03685","created_at":"2026-07-05T01:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"37OA2A22DCLP","created_at":"2026-07-05T01:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"37OA2A22DCLPRKR6","created_at":"2026-07-05T01:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"37OA2A22","created_at":"2026-07-05T01:08:31Z"}],"graph_snapshots":[{"event_id":"sha256:f7c262cc2ada11f2d3c50f35b2b0cafb1d3381ee71b21695f360771303cc38c0","target":"graph","created_at":"2026-07-05T01:08:31Z","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/2006.03685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical interactions are initially recorded and documented in free text medical notes. ICD coding is the task of classifying and coding all diagnoses, symptoms and procedures associated with a patient's visit. The process is often manual and extremely time-consuming and expensive for hospitals. In this paper, we propose a machine learning model, BERT-XML, for large scale automated ICD coding from EHR notes, utilizing recently developed unsupervised pretraining that have achieved state of the art performance on a variety of NLP tasks. We train a BERT model from scratch on EHR notes, learning w","authors_text":"Jingshu Liu, Narges Razavian, Zachariah Zhang","cross_cats":["cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-05-26T21:12:43Z","title":"BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03685","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":"sha256:5da7f4c122df7f4b72c7d851791ff593baea789308384ef6fa9eea59c7301ac1","target":"record","created_at":"2026-07-05T01:08:31Z","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":"1746e1d7e3c63359a122bf3e54f51d8abab3feb7adcc6f2e6ff9acf42aad51fe","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-05-26T21:12:43Z","title_canon_sha256":"799bc2fdeee19d43cfe16fc5cf76b516ff0ae7b1ad8d09cef0de527188cfb5e4"},"schema_version":"1.0","source":{"id":"2006.03685","kind":"arxiv","version":1}},"canonical_sha256":"dfdc0d035a1896f8aa3e884a2016f2212c3c66f7c18eb1a1ba6072ee325b9103","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfdc0d035a1896f8aa3e884a2016f2212c3c66f7c18eb1a1ba6072ee325b9103","first_computed_at":"2026-07-05T01:08:31.987910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:08:31.987910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k1dtcN0CJ/CQXuLXtmfY9HwJ7Q+9b4vn50Prc4ARZ4a3o4esCey8Fn81Jaa9wPWiq8Yw6gGGA6kone6Gb/byCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:08:31.988353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.03685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5da7f4c122df7f4b72c7d851791ff593baea789308384ef6fa9eea59c7301ac1","sha256:f7c262cc2ada11f2d3c50f35b2b0cafb1d3381ee71b21695f360771303cc38c0"],"state_sha256":"882e6e4be423dd18b1fe5ccdf7071d55466ecd3ff0bb5c577ee4e22065a6d2c8"}