{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CNNIKPCSBKTR45EGOBF4A5WVYX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"467c956f0ecb0576cea97724ef6a92a572d7c5e2f258bb6ebd8da6e174281fca","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T23:39:49Z","title_canon_sha256":"85258205fab27d42685f380702e94d487f91c244cd07cfe29262b2832bde206b"},"schema_version":"1.0","source":{"id":"2608.10316","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10316","created_at":"2026-08-12T00:23:51Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10316v1","created_at":"2026-08-12T00:23:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10316","created_at":"2026-08-12T00:23:51Z"},{"alias_kind":"pith_short_12","alias_value":"CNNIKPCSBKTR","created_at":"2026-08-12T00:23:51Z"},{"alias_kind":"pith_short_16","alias_value":"CNNIKPCSBKTR45EG","created_at":"2026-08-12T00:23:51Z"},{"alias_kind":"pith_short_8","alias_value":"CNNIKPCS","created_at":"2026-08-12T00:23:51Z"}],"graph_snapshots":[{"event_id":"sha256:f888099bb0567c4db265fc86ce8e06e9b7d3122075916fc1e76d55202486059f","target":"graph","created_at":"2026-08-12T00:23:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.10316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Shuang Zhou, Song Wang, Weikai Lin, Zihan Chen, Zijian Gu","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T23:39:49Z","title":"UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10316","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b64c5b604116920d4ed01a3b039fc46a80328ddf165f53575022c148abec3ba1","target":"record","created_at":"2026-08-12T00:23:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"467c956f0ecb0576cea97724ef6a92a572d7c5e2f258bb6ebd8da6e174281fca","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T23:39:49Z","title_canon_sha256":"85258205fab27d42685f380702e94d487f91c244cd07cfe29262b2832bde206b"},"schema_version":"1.0","source":{"id":"2608.10316","kind":"arxiv","version":1}},"canonical_sha256":"135a853c520aa71e7486704bc076d5c5e465547bbef3d58fabcc9bed2e95144f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"135a853c520aa71e7486704bc076d5c5e465547bbef3d58fabcc9bed2e95144f","first_computed_at":"2026-08-12T00:23:51.857334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T00:23:51.857334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h1SfwwRyzHHkLYPq4Vuu8k9mtR9EqHhwpr/6CPSleRCv/gqBLqBnmdt3t+WHNlp0+3Tnx4Nw5xZKVeIGbtB4Cg==","signature_status":"signed_v1","signed_at":"2026-08-12T00:23:51.859260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10316","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b64c5b604116920d4ed01a3b039fc46a80328ddf165f53575022c148abec3ba1","sha256:f888099bb0567c4db265fc86ce8e06e9b7d3122075916fc1e76d55202486059f"],"state_sha256":"3480b583e9f4374d48cd12a06667c929e79a2d06d51d124f8d2bd818f742f2e1"}