{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:27LPG7DEG3NQBXPI5VW7CMNOPA","short_pith_number":"pith:27LPG7DE","schema_version":"1.0","canonical_sha256":"d7d6f37c6436db00dde8ed6df131ae781c73215ea24fb2a40940c19f57fdbe70","source":{"kind":"arxiv","id":"2402.05802","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Discovery of Clinical Disease Signatures Using Probabilistic Independence","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bennett A. Landman, Eric V. Strobl, Fabien Maldonado, John M. Still, Marco Barbero Mota, Thomas A. Lasko, Thomas Z. Li, William W. Stead","submitted_at":"2024-02-08T16:41:03Z","abstract_excerpt":"Insufficiently precise diagnosis of clinical disease is likely responsible for many treatment failures, even for common conditions and treatments. With a large enough dataset, it may be possible to use unsupervised machine learning to define clinical disease patterns more precisely. We present an approach to learning these patterns by using probabilistic independence to disentangle the imprint on the medical record of causal latent sources of disease. We inferred a broad set of 2000 clinical signatures of latent sources from 9195 variables in 269,099 Electronic Health Records. The learned sign"},"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":"2402.05802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T16:41:03Z","cross_cats_sorted":["stat.AP","stat.ML"],"title_canon_sha256":"ddb641d771d3e74dbe7ef11dcf1f6f4eac431e53dc53064b7450517b33358bf1","abstract_canon_sha256":"76ab482a9696fb6f8318374e10444df023304c32f0223d27f06b09f39e5cfe78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:03.674436Z","signature_b64":"k+lSJ6XYco86gUOxDmY8ID7DgTjTVDtrO4geHLjCLzrv2j3Dxe9SrLSLe4MqM28w6R9sfsfoeI9JeYBB+XFZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7d6f37c6436db00dde8ed6df131ae781c73215ea24fb2a40940c19f57fdbe70","last_reissued_at":"2026-07-05T07:43:03.673825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:03.673825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Discovery of Clinical Disease Signatures Using Probabilistic Independence","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bennett A. Landman, Eric V. Strobl, Fabien Maldonado, John M. Still, Marco Barbero Mota, Thomas A. Lasko, Thomas Z. Li, William W. Stead","submitted_at":"2024-02-08T16:41:03Z","abstract_excerpt":"Insufficiently precise diagnosis of clinical disease is likely responsible for many treatment failures, even for common conditions and treatments. With a large enough dataset, it may be possible to use unsupervised machine learning to define clinical disease patterns more precisely. We present an approach to learning these patterns by using probabilistic independence to disentangle the imprint on the medical record of causal latent sources of disease. We inferred a broad set of 2000 clinical signatures of latent sources from 9195 variables in 269,099 Electronic Health Records. The learned sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05802","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/2402.05802/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":"2402.05802","created_at":"2026-07-05T07:43:03.673880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05802v1","created_at":"2026-07-05T07:43:03.673880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05802","created_at":"2026-07-05T07:43:03.673880+00:00"},{"alias_kind":"pith_short_12","alias_value":"27LPG7DEG3NQ","created_at":"2026-07-05T07:43:03.673880+00:00"},{"alias_kind":"pith_short_16","alias_value":"27LPG7DEG3NQBXPI","created_at":"2026-07-05T07:43:03.673880+00:00"},{"alias_kind":"pith_short_8","alias_value":"27LPG7DE","created_at":"2026-07-05T07:43:03.673880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA","json":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA.json","graph_json":"https://pith.science/api/pith-number/27LPG7DEG3NQBXPI5VW7CMNOPA/graph.json","events_json":"https://pith.science/api/pith-number/27LPG7DEG3NQBXPI5VW7CMNOPA/events.json","paper":"https://pith.science/paper/27LPG7DE"},"agent_actions":{"view_html":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA","download_json":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA.json","view_paper":"https://pith.science/paper/27LPG7DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05802&json=true","fetch_graph":"https://pith.science/api/pith-number/27LPG7DEG3NQBXPI5VW7CMNOPA/graph.json","fetch_events":"https://pith.science/api/pith-number/27LPG7DEG3NQBXPI5VW7CMNOPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA/action/storage_attestation","attest_author":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA/action/author_attestation","sign_citation":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA/action/citation_signature","submit_replication":"https://pith.science/pith/27LPG7DEG3NQBXPI5VW7CMNOPA/action/replication_record"}},"created_at":"2026-07-05T07:43:03.673880+00:00","updated_at":"2026-07-05T07:43:03.673880+00:00"}