{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:65SERJAJ6LAVVIJTP7GQVEOEDQ","short_pith_number":"pith:65SERJAJ","schema_version":"1.0","canonical_sha256":"f76448a409f2c15aa1337fcd0a91c41c191e2fdd93662bcf47f7a33104701b00","source":{"kind":"arxiv","id":"2608.10522","version":1},"attestation_state":"computed","paper":{"title":"Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiming Li, H. Peter Soyer, Jiajun Sun, Jingmin Zhu, Monika Janda, Victoria Mar, Yingsheng Liu, Zhen Yu, Zongyuan Ge","submitted_at":"2026-08-11T05:57:09Z","abstract_excerpt":"While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as flat vectors and employ unstable continuous regression objectives. To overcome this, we propose a novel semantic-aware framework explicitly modeling the intrinsic two-dimensional structure of tabular data. First, addressing the inter-feature hierarchy of varying diagnostic impor"},"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":"2608.10522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T05:57:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3fd5dc7ecc7bac0edb0ba972c374fafb455caf3f01d782e682e01c43b12c9481","abstract_canon_sha256":"928546ef362f5ed37daf00d9b50c72b36b7897249bad1a5dc976562f2cbbcd94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:22:40.208613Z","signature_b64":"5AXnt0jniNy/+FHJbD3TQgry2zBHbLt9GS+UxuOkLZApoDIjljbuT4HJh1tWuWPCi1wlRHaMRb/zX57f9MfBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f76448a409f2c15aa1337fcd0a91c41c191e2fdd93662bcf47f7a33104701b00","last_reissued_at":"2026-08-12T01:22:40.206897Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:22:40.206897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiming Li, H. Peter Soyer, Jiajun Sun, Jingmin Zhu, Monika Janda, Victoria Mar, Yingsheng Liu, Zhen Yu, Zongyuan Ge","submitted_at":"2026-08-11T05:57:09Z","abstract_excerpt":"While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as flat vectors and employ unstable continuous regression objectives. To overcome this, we propose a novel semantic-aware framework explicitly modeling the intrinsic two-dimensional structure of tabular data. First, addressing the inter-feature hierarchy of varying diagnostic impor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10522","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/2608.10522/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":"2608.10522","created_at":"2026-08-12T01:22:40.210771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10522v1","created_at":"2026-08-12T01:22:40.210771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10522","created_at":"2026-08-12T01:22:40.210771+00:00"},{"alias_kind":"pith_short_12","alias_value":"65SERJAJ6LAV","created_at":"2026-08-12T01:22:40.210771+00:00"},{"alias_kind":"pith_short_16","alias_value":"65SERJAJ6LAVVIJT","created_at":"2026-08-12T01:22:40.210771+00:00"},{"alias_kind":"pith_short_8","alias_value":"65SERJAJ","created_at":"2026-08-12T01:22:40.210771+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/65SERJAJ6LAVVIJTP7GQVEOEDQ","json":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ.json","graph_json":"https://pith.science/api/pith-number/65SERJAJ6LAVVIJTP7GQVEOEDQ/graph.json","events_json":"https://pith.science/api/pith-number/65SERJAJ6LAVVIJTP7GQVEOEDQ/events.json","paper":"https://pith.science/paper/65SERJAJ"},"agent_actions":{"view_html":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ","download_json":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ.json","view_paper":"https://pith.science/paper/65SERJAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10522&json=true","fetch_graph":"https://pith.science/api/pith-number/65SERJAJ6LAVVIJTP7GQVEOEDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/65SERJAJ6LAVVIJTP7GQVEOEDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/action/storage_attestation","attest_author":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/action/author_attestation","sign_citation":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/action/citation_signature","submit_replication":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/action/replication_record"}},"created_at":"2026-08-12T01:22:40.210771+00:00","updated_at":"2026-08-12T01:22:40.210771+00:00"}