{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LUH7D5P6J7SNK2F5FQI46REFJP","short_pith_number":"pith:LUH7D5P6","schema_version":"1.0","canonical_sha256":"5d0ff1f5fe4fe4d568bd2c11cf44854bfd7134684cec4000c5bda22487bb0def","source":{"kind":"arxiv","id":"2311.17560","version":1},"attestation_state":"computed","paper":{"title":"Interpreting Differentiable Latent States for Healthcare Time-series Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nivedita Bijlani, Payam Barnaghi, Samaneh Kouchaki, Yu Chen","submitted_at":"2023-11-29T11:48:16Z","abstract_excerpt":"Machine learning enables extracting clinical insights from large temporal datasets. The applications of such machine learning models include identifying disease patterns and predicting patient outcomes. However, limited interpretability poses challenges for deploying advanced machine learning in digital healthcare. Understanding the meaning of latent states is crucial for interpreting machine learning models, assuming they capture underlying patterns. In this paper, we present a concise algorithm that allows for i) interpreting latent states using highly related input features; ii) interpretin"},"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":"2311.17560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:48:16Z","cross_cats_sorted":[],"title_canon_sha256":"180bc476dc90792baa398b8338c3f79630881d669c74d7f1f5d2a84e866f13e6","abstract_canon_sha256":"62f8e7b7ed47c76129715fa0d03d66459bfcba8bc839878d47db9df145941726"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:15.523860Z","signature_b64":"TcQVkAlX5xKfTDhMxWhNNHqMwVIuXH6XF47P1aGcpmTkxgw6BM8D4H2mZ2Tfkfj3txcEKyHZbc746zSftR+aDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d0ff1f5fe4fe4d568bd2c11cf44854bfd7134684cec4000c5bda22487bb0def","last_reissued_at":"2026-07-05T07:18:15.523364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:15.523364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpreting Differentiable Latent States for Healthcare Time-series Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nivedita Bijlani, Payam Barnaghi, Samaneh Kouchaki, Yu Chen","submitted_at":"2023-11-29T11:48:16Z","abstract_excerpt":"Machine learning enables extracting clinical insights from large temporal datasets. The applications of such machine learning models include identifying disease patterns and predicting patient outcomes. However, limited interpretability poses challenges for deploying advanced machine learning in digital healthcare. Understanding the meaning of latent states is crucial for interpreting machine learning models, assuming they capture underlying patterns. In this paper, we present a concise algorithm that allows for i) interpreting latent states using highly related input features; ii) interpretin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17560","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/2311.17560/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":"2311.17560","created_at":"2026-07-05T07:18:15.523428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17560v1","created_at":"2026-07-05T07:18:15.523428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17560","created_at":"2026-07-05T07:18:15.523428+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUH7D5P6J7SN","created_at":"2026-07-05T07:18:15.523428+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUH7D5P6J7SNK2F5","created_at":"2026-07-05T07:18:15.523428+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUH7D5P6","created_at":"2026-07-05T07:18:15.523428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08873","citing_title":"Towards modeling evolving longitudinal health trajectories with a transformer-based deep learning model","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP","json":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP.json","graph_json":"https://pith.science/api/pith-number/LUH7D5P6J7SNK2F5FQI46REFJP/graph.json","events_json":"https://pith.science/api/pith-number/LUH7D5P6J7SNK2F5FQI46REFJP/events.json","paper":"https://pith.science/paper/LUH7D5P6"},"agent_actions":{"view_html":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP","download_json":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP.json","view_paper":"https://pith.science/paper/LUH7D5P6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17560&json=true","fetch_graph":"https://pith.science/api/pith-number/LUH7D5P6J7SNK2F5FQI46REFJP/graph.json","fetch_events":"https://pith.science/api/pith-number/LUH7D5P6J7SNK2F5FQI46REFJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP/action/storage_attestation","attest_author":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP/action/author_attestation","sign_citation":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP/action/citation_signature","submit_replication":"https://pith.science/pith/LUH7D5P6J7SNK2F5FQI46REFJP/action/replication_record"}},"created_at":"2026-07-05T07:18:15.523428+00:00","updated_at":"2026-07-05T07:18:15.523428+00:00"}