{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:37OA2A22DCLPRKR6RBFCAFXSEE","short_pith_number":"pith:37OA2A22","schema_version":"1.0","canonical_sha256":"dfdc0d035a1896f8aa3e884a2016f2212c3c66f7c18eb1a1ba6072ee325b9103","source":{"kind":"arxiv","id":"2006.03685","version":1},"attestation_state":"computed","paper":{"title":"BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Jingshu Liu, Narges Razavian, Zachariah Zhang","submitted_at":"2020-05-26T21:12:43Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.03685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-05-26T21:12:43Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"799bc2fdeee19d43cfe16fc5cf76b516ff0ae7b1ad8d09cef0de527188cfb5e4","abstract_canon_sha256":"1746e1d7e3c63359a122bf3e54f51d8abab3feb7adcc6f2e6ff9acf42aad51fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:31.988353Z","signature_b64":"k1dtcN0CJ/CQXuLXtmfY9HwJ7Q+9b4vn50Prc4ARZ4a3o4esCey8Fn81Jaa9wPWiq8Yw6gGGA6kone6Gb/byCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfdc0d035a1896f8aa3e884a2016f2212c3c66f7c18eb1a1ba6072ee325b9103","last_reissued_at":"2026-07-05T01:08:31.987910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:31.987910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Jingshu Liu, Narges Razavian, Zachariah Zhang","submitted_at":"2020-05-26T21:12:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03685","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/2006.03685/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.03685","created_at":"2026-07-05T01:08:31.987977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.03685v1","created_at":"2026-07-05T01:08:31.987977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03685","created_at":"2026-07-05T01:08:31.987977+00:00"},{"alias_kind":"pith_short_12","alias_value":"37OA2A22DCLP","created_at":"2026-07-05T01:08:31.987977+00:00"},{"alias_kind":"pith_short_16","alias_value":"37OA2A22DCLPRKR6","created_at":"2026-07-05T01:08:31.987977+00:00"},{"alias_kind":"pith_short_8","alias_value":"37OA2A22","created_at":"2026-07-05T01:08:31.987977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.09699","citing_title":"Structured Information Matters: Explainable ICD Coding with Patient-Level Knowledge Graphs","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE","json":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE.json","graph_json":"https://pith.science/api/pith-number/37OA2A22DCLPRKR6RBFCAFXSEE/graph.json","events_json":"https://pith.science/api/pith-number/37OA2A22DCLPRKR6RBFCAFXSEE/events.json","paper":"https://pith.science/paper/37OA2A22"},"agent_actions":{"view_html":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE","download_json":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE.json","view_paper":"https://pith.science/paper/37OA2A22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.03685&json=true","fetch_graph":"https://pith.science/api/pith-number/37OA2A22DCLPRKR6RBFCAFXSEE/graph.json","fetch_events":"https://pith.science/api/pith-number/37OA2A22DCLPRKR6RBFCAFXSEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE/action/storage_attestation","attest_author":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE/action/author_attestation","sign_citation":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE/action/citation_signature","submit_replication":"https://pith.science/pith/37OA2A22DCLPRKR6RBFCAFXSEE/action/replication_record"}},"created_at":"2026-07-05T01:08:31.987977+00:00","updated_at":"2026-07-05T01:08:31.987977+00:00"}