{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FFYGGET53F6CLMG66B6E2NTE4T","short_pith_number":"pith:FFYGGET5","schema_version":"1.0","canonical_sha256":"297063127dd97c25b0def07c4d3664e4c785537d1476358f29a6523f6552b3a1","source":{"kind":"arxiv","id":"1904.05342","version":3},"attestation_state":"computed","paper":{"title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ClinicalBERT applies bidirectional transformers to clinical notes to outperform baselines in predicting 30-day hospital readmission.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jaan Altosaar, Kexin Huang, Rajesh Ranganath","submitted_at":"2019-04-10T17:53:13Z","abstract_excerpt":"Clinical notes contain information about patients that goes beyond structured data like lab values and medications. However, clinical notes have been underused relative to structured data, because notes are high-dimensional and sparse. This work develops and evaluates representations of clinical notes using bidirectional transformers (ClinicalBERT). ClinicalBERT uncovers high-quality relationships between medical concepts as judged by humans. ClinicalBert outperforms baselines on 30-day hospital readmission prediction using both discharge summaries and the first few days of notes in the intens"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"1904.05342","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-10T17:53:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"07bf6b6c5f4b624787e2712f002aaf6eaa8bdf6905533f64324edb2eb275a6e1","abstract_canon_sha256":"54acfa256804dbd11c7ad213322265ab4c5e5d67bf7aa349334a99b6a3f876fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.903954Z","signature_b64":"Al20IZiHMh51BlmDCe1w6TwZ64WTZLCiaky9uT3/JLotDMfIaHLV1YZ+g+hPMh6gBC+qCqmZf4WIFxubituICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"297063127dd97c25b0def07c4d3664e4c785537d1476358f29a6523f6552b3a1","last_reissued_at":"2026-05-17T23:38:52.903248Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.903248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ClinicalBERT applies bidirectional transformers to clinical notes to outperform baselines in predicting 30-day hospital readmission.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jaan Altosaar, Kexin Huang, Rajesh Ranganath","submitted_at":"2019-04-10T17:53:13Z","abstract_excerpt":"Clinical notes contain information about patients that goes beyond structured data like lab values and medications. However, clinical notes have been underused relative to structured data, because notes are high-dimensional and sparse. This work develops and evaluates representations of clinical notes using bidirectional transformers (ClinicalBERT). ClinicalBERT uncovers high-quality relationships between medical concepts as judged by humans. ClinicalBert outperforms baselines on 30-day hospital readmission prediction using both discharge summaries and the first few days of notes in the intens"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ClinicalBERT outperforms baselines on 30-day hospital readmission prediction using both discharge summaries and the first few days of notes in the intensive care unit.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the human evaluation of medical concept relationships and the readmission labels drawn from administrative data are sufficiently reliable proxies for clinical utility and that the model generalizes beyond the training hospital's note style.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ClinicalBERT applies BERT-style transformers to clinical notes and outperforms baselines on 30-day readmission prediction while revealing human-judged medical concept links.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ClinicalBERT applies bidirectional transformers to clinical notes to outperform baselines in predicting 30-day hospital readmission.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d74c47d192ad3c5f92103cb02fcd37d595f910b3719f7e69a5a32ebd4ca064aa"},"source":{"id":"1904.05342","kind":"arxiv","version":3},"verdict":{"id":"2b9c0cb2-350e-43a7-83d0-821dd702f2eb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T09:22:31.827636Z","strongest_claim":"ClinicalBERT outperforms baselines on 30-day hospital readmission prediction using both discharge summaries and the first few days of notes in the intensive care unit.","one_line_summary":"ClinicalBERT applies BERT-style transformers to clinical notes and outperforms baselines on 30-day readmission prediction while revealing human-judged medical concept links.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the human evaluation of medical concept relationships and the readmission labels drawn from administrative data are sufficiently reliable proxies for clinical utility and that the model generalizes beyond the training hospital's note style.","pith_extraction_headline":"ClinicalBERT applies bidirectional transformers to clinical notes to outperform baselines in predicting 30-day hospital readmission."},"references":{"count":40,"sample":[{"doi":"","year":1904,"title":"Publicly Available Clinical BERT Embeddings","work_id":"f6ed1c91-cfb8-4068-b29c-322cd51c4028","ref_index":1,"cited_arxiv_id":"1904.03323","is_internal_anchor":true},{"doi":"","year":1984,"title":"Hospital readmissions in the Medicare population","work_id":"c3d09b9e-1843-4684-b829-abc87b868cc4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Aninformatics-based approach to reducing heart failure all-cause readmissions: the Stanfordheartfailuredashboard","work_id":"4bf32126-049b-4014-b678-468ae4704f76","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Dynamic Hierarchical Clas- sification for Patient Risk-of-Readmission","work_id":"ddfd1845-2429-4019-9ed8-58a74a958fa0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"What’s in a Note? Unpacking Predictive Value in Clinical Note Repre- sentations","work_id":"56347644-b909-4b41-84e5-9cf438cc7cd6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":40,"snapshot_sha256":"c9fcc9026d47095c6b061cfb0d6737ffc7e893310a9a3608459a8020074c5844","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9d91def4bd1fd7f4bedc4368e8ac1f14e077ca3c68dc0e0c8e9c12ffe33b6574"},"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":"1904.05342","created_at":"2026-05-17T23:38:52.903375+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.05342v3","created_at":"2026-05-17T23:38:52.903375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05342","created_at":"2026-05-17T23:38:52.903375+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFYGGET53F6C","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFYGGET53F6CLMG6","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFYGGET5","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2306.00890","citing_title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2501.02407","citing_title":"Towards the Anonymization of the Language Modeling","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2601.09722","citing_title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17775","citing_title":"Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03259","citing_title":"From Pre-trained Models to Large Language Models: A Comprehensive Survey of AI-Driven Psychological Computing","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16364","citing_title":"Clinical Note Bloat Reduction for Efficient LLM Use","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16378","citing_title":"Reciprocal Co-Training (RCT): Coupling Gradient-Based and Non-Differentiable Models via Reinforcement Learning","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12817","citing_title":"Training Large Language Models to Predict Clinical Events","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2303.17564","citing_title":"BloombergGPT: A Large Language Model for Finance","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27319","citing_title":"REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version)","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10813","citing_title":"NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10286","citing_title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06191","citing_title":"Systematic Evaluation of Large Language Models for Post-Discharge Clinical Action Extraction","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06173","citing_title":"Retina-RAG: Retrieval-Augmented Vision-Language Modeling for Joint Retinal Diagnosis and Clinical Report Generation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01664","citing_title":"A Hybrid Retrieval and Reranking Framework for Evidence-Grounded Retrieval-Augmented Generation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00708","citing_title":"Deep Kernel Learning for Stratifying Glaucoma Trajectories","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10783","citing_title":"Learning Preference-Based Objectives from Clinical Narratives for Dynamic Sepsis Treatment","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11137","citing_title":"From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09975","citing_title":"EncFormer: Secure and Efficient Transformer Inference over Encrypted Data","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07274","citing_title":"A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06173","citing_title":"Retina-RAG: Retrieval-Augmented Vision-Language Modeling for Joint Retinal Diagnosis and Clinical Report Generation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08045","citing_title":"Uncertainty-Aware Structured Data Extraction from Full CMR Reports via Distilled LLMs","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14651","citing_title":"CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18753","citing_title":"Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":284,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T","json":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T.json","graph_json":"https://pith.science/api/pith-number/FFYGGET53F6CLMG66B6E2NTE4T/graph.json","events_json":"https://pith.science/api/pith-number/FFYGGET53F6CLMG66B6E2NTE4T/events.json","paper":"https://pith.science/paper/FFYGGET5"},"agent_actions":{"view_html":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T","download_json":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T.json","view_paper":"https://pith.science/paper/FFYGGET5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.05342&json=true","fetch_graph":"https://pith.science/api/pith-number/FFYGGET53F6CLMG66B6E2NTE4T/graph.json","fetch_events":"https://pith.science/api/pith-number/FFYGGET53F6CLMG66B6E2NTE4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T/action/storage_attestation","attest_author":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T/action/author_attestation","sign_citation":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T/action/citation_signature","submit_replication":"https://pith.science/pith/FFYGGET53F6CLMG66B6E2NTE4T/action/replication_record"}},"created_at":"2026-05-17T23:38:52.903375+00:00","updated_at":"2026-05-17T23:38:52.903375+00:00"}