{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CNNIKPCSBKTR45EGOBF4A5WVYX","short_pith_number":"pith:CNNIKPCS","schema_version":"1.0","canonical_sha256":"135a853c520aa71e7486704bc076d5c5e465547bbef3d58fabcc9bed2e95144f","source":{"kind":"arxiv","id":"2608.10316","version":1},"attestation_state":"computed","paper":{"title":"UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Shuang Zhou, Song Wang, Weikai Lin, Zihan Chen, Zijian Gu","submitted_at":"2026-08-10T23:39:49Z","abstract_excerpt":"Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning: models exploit the easier modality (e.g., diagnostic cues in text) while neglecting harder-to-learn features (e.g., subtle visual patterns). We propose UniMod, a framework that mitigates shortcut learning by requiring each modality to predict the diagnosis on its own. It supervises image-only, text-only, and multi-modal classification simultaneously, so each modality must extract diagnostic features. We add cross-modality alignme"},"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":"2608.10316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T23:39:49Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"85258205fab27d42685f380702e94d487f91c244cd07cfe29262b2832bde206b","abstract_canon_sha256":"467c956f0ecb0576cea97724ef6a92a572d7c5e2f258bb6ebd8da6e174281fca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T00:23:51.859260Z","signature_b64":"h1SfwwRyzHHkLYPq4Vuu8k9mtR9EqHhwpr/6CPSleRCv/gqBLqBnmdt3t+WHNlp0+3Tnx4Nw5xZKVeIGbtB4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"135a853c520aa71e7486704bc076d5c5e465547bbef3d58fabcc9bed2e95144f","last_reissued_at":"2026-08-12T00:23:51.857334Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T00:23:51.857334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Shuang Zhou, Song Wang, Weikai Lin, Zihan Chen, Zijian Gu","submitted_at":"2026-08-10T23:39:49Z","abstract_excerpt":"Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning: models exploit the easier modality (e.g., diagnostic cues in text) while neglecting harder-to-learn features (e.g., subtle visual patterns). We propose UniMod, a framework that mitigates shortcut learning by requiring each modality to predict the diagnosis on its own. It supervises image-only, text-only, and multi-modal classification simultaneously, so each modality must extract diagnostic features. We add cross-modality alignme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10316","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/2608.10316/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":"2608.10316","created_at":"2026-08-12T00:23:51.860168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10316v1","created_at":"2026-08-12T00:23:51.860168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10316","created_at":"2026-08-12T00:23:51.860168+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNNIKPCSBKTR","created_at":"2026-08-12T00:23:51.860168+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNNIKPCSBKTR45EG","created_at":"2026-08-12T00:23:51.860168+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNNIKPCS","created_at":"2026-08-12T00:23:51.860168+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/CNNIKPCSBKTR45EGOBF4A5WVYX","json":"https://pith.science/pith/CNNIKPCSBKTR45EGOBF4A5WVYX.json","graph_json":"https://pith.science/api/pith-number/CNNIKPCSBKTR45EGOBF4A5WVYX/graph.json","events_json":"https://pith.science/api/pith-number/CNNIKPCSBKTR45EGOBF4A5WVYX/events.json","paper":"https://pith.science/paper/CNNIKPCS"},"agent_actions":{"view_html":"https://pith.science/pith/CNNIKPCSBKTR45EGOBF4A5WVYX","download_json":"https://pith.science/pith/CNNIKPCSBKTR45EGOBF4A5WVYX.json","view_paper":"https://pith.science/paper/CNNIKPCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10316&json=true","fetch_graph":"https://pith.science/api/pith-number/CNNIKPCSBKTR45EGOBF4A5WVYX/graph.json","fetch_events":"https://pith.science/api/pith-number/CNNIKPCSBKTR45EGOBF4A5WVYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNNIKPCSBKTR45EGOBF4A5WVYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNNIKPCSBKTR45EGOBF4A5WVYX/action/storage_attestation","attest_author":"https://pith.science/pith/CNNIKPCSBKTR45EGOBF4A5WVYX/action/author_attestation","sign_citation":"https://pith.science/pith/CNNIKPCSBKTR45EGOBF4A5WVYX/action/citation_signature","submit_replication":"https://pith.science/pith/CNNIKPCSBKTR45EGOBF4A5WVYX/action/replication_record"}},"created_at":"2026-08-12T00:23:51.860168+00:00","updated_at":"2026-08-12T00:23:51.860168+00:00"}