{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JN4EWNUZNTJPLWV7XOFOTORAZF","short_pith_number":"pith:JN4EWNUZ","schema_version":"1.0","canonical_sha256":"4b784b36996cd2f5dabfbb8ae9ba20c9484f16cc3f1c73a818abe028ebb5c923","source":{"kind":"arxiv","id":"2508.01615","version":1},"attestation_state":"computed","paper":{"title":"TCDiff: Triplex Cascaded Diffusion for High-fidelity Multimodal EHRs Generation with Incomplete Clinical Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenxi Li, Dexuan Xu, Huamin Zhang, Jiaqi Zhu, Yandong Yan, Yu Huang, Zhongyan Chai","submitted_at":"2025-08-03T06:24:20Z","abstract_excerpt":"The scarcity of large-scale and high-quality electronic health records (EHRs) remains a major bottleneck in biomedical research, especially as large foundation models become increasingly data-hungry. Synthesizing substantial volumes of de-identified and high-fidelity data from existing datasets has emerged as a promising solution. However, existing methods suffer from a series of limitations: they struggle to model the intrinsic properties of heterogeneous multimodal EHR data (e.g., continuous, discrete, and textual modalities), capture the complex dependencies among them, and robustly handle "},"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":"2508.01615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-03T06:24:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ae3907a687a34fef1c8cd0fe08bf8d1fd72045d1c56f2163ec271d7419b1322","abstract_canon_sha256":"249ec2801bd1ca08518c4a994934712de88af8ac872ac1c75f020c757e637682"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:42.356524Z","signature_b64":"zv+akLbr8YfE0mikd0+5UNvh/Cv5nodyJLF1mJpqamXmRqJa1/K77pA6uMqCA12c9I139cqXDqWtpsH2aF+jDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b784b36996cd2f5dabfbb8ae9ba20c9484f16cc3f1c73a818abe028ebb5c923","last_reissued_at":"2026-07-05T11:47:42.355995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:42.355995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TCDiff: Triplex Cascaded Diffusion for High-fidelity Multimodal EHRs Generation with Incomplete Clinical Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenxi Li, Dexuan Xu, Huamin Zhang, Jiaqi Zhu, Yandong Yan, Yu Huang, Zhongyan Chai","submitted_at":"2025-08-03T06:24:20Z","abstract_excerpt":"The scarcity of large-scale and high-quality electronic health records (EHRs) remains a major bottleneck in biomedical research, especially as large foundation models become increasingly data-hungry. Synthesizing substantial volumes of de-identified and high-fidelity data from existing datasets has emerged as a promising solution. However, existing methods suffer from a series of limitations: they struggle to model the intrinsic properties of heterogeneous multimodal EHR data (e.g., continuous, discrete, and textual modalities), capture the complex dependencies among them, and robustly handle "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01615","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/2508.01615/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":"2508.01615","created_at":"2026-07-05T11:47:42.356060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01615v1","created_at":"2026-07-05T11:47:42.356060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01615","created_at":"2026-07-05T11:47:42.356060+00:00"},{"alias_kind":"pith_short_12","alias_value":"JN4EWNUZNTJP","created_at":"2026-07-05T11:47:42.356060+00:00"},{"alias_kind":"pith_short_16","alias_value":"JN4EWNUZNTJPLWV7","created_at":"2026-07-05T11:47:42.356060+00:00"},{"alias_kind":"pith_short_8","alias_value":"JN4EWNUZ","created_at":"2026-07-05T11:47:42.356060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20125","citing_title":"Federated Learning with Incomplete Data: When to Use Complete Cases and When to Weight","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF","json":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF.json","graph_json":"https://pith.science/api/pith-number/JN4EWNUZNTJPLWV7XOFOTORAZF/graph.json","events_json":"https://pith.science/api/pith-number/JN4EWNUZNTJPLWV7XOFOTORAZF/events.json","paper":"https://pith.science/paper/JN4EWNUZ"},"agent_actions":{"view_html":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF","download_json":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF.json","view_paper":"https://pith.science/paper/JN4EWNUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01615&json=true","fetch_graph":"https://pith.science/api/pith-number/JN4EWNUZNTJPLWV7XOFOTORAZF/graph.json","fetch_events":"https://pith.science/api/pith-number/JN4EWNUZNTJPLWV7XOFOTORAZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF/action/storage_attestation","attest_author":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF/action/author_attestation","sign_citation":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF/action/citation_signature","submit_replication":"https://pith.science/pith/JN4EWNUZNTJPLWV7XOFOTORAZF/action/replication_record"}},"created_at":"2026-07-05T11:47:42.356060+00:00","updated_at":"2026-07-05T11:47:42.356060+00:00"}