{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q2RUWMI3YIXWXZOQXJTAA2HIG7","short_pith_number":"pith:Q2RUWMI3","schema_version":"1.0","canonical_sha256":"86a34b311bc22f6be5d0ba660068e837c65d2a2afa5b30933baec554271d62c8","source":{"kind":"arxiv","id":"2505.19031","version":1},"attestation_state":"computed","paper":{"title":"Medical Large Vision Language Models with Multi-Image Visual Ability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiaze Wang, Jinpeng Li, Juzheng Miao, Pheng-Ann Heng, Qi Dou, Xikai Yang, Yuchen Yuan","submitted_at":"2025-05-25T08:31:22Z","abstract_excerpt":"Medical large vision-language models (LVLMs) have demonstrated promising performance across various single-image question answering (QA) benchmarks, yet their capability in processing multi-image clinical scenarios remains underexplored. Unlike single image based tasks, medical tasks involving multiple images often demand sophisticated visual understanding capabilities, such as temporal reasoning and cross-modal analysis, which are poorly supported by current medical LVLMs. To bridge this critical gap, we present the Med-MIM instruction dataset, comprising 83.2K medical multi-image QA pairs th"},"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":"2505.19031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T08:31:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d1cb504932cf2927bc4edfaa01d491610b835621fd1ab5507c0d53bed315552","abstract_canon_sha256":"74819da44339cb94e4ae5190ae90460c0e81bfb402636e06817ce31e54f91a77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:23.824578Z","signature_b64":"DGZBv16FhOEIPIQk/BN7eJGO6ojivYbTQem9THSyLH8ig6s/+Y72bkaHAT9rTsXwV0HxzeAWzHScQlDWyvqEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86a34b311bc22f6be5d0ba660068e837c65d2a2afa5b30933baec554271d62c8","last_reissued_at":"2026-07-05T11:09:23.824053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:23.824053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Medical Large Vision Language Models with Multi-Image Visual Ability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiaze Wang, Jinpeng Li, Juzheng Miao, Pheng-Ann Heng, Qi Dou, Xikai Yang, Yuchen Yuan","submitted_at":"2025-05-25T08:31:22Z","abstract_excerpt":"Medical large vision-language models (LVLMs) have demonstrated promising performance across various single-image question answering (QA) benchmarks, yet their capability in processing multi-image clinical scenarios remains underexplored. Unlike single image based tasks, medical tasks involving multiple images often demand sophisticated visual understanding capabilities, such as temporal reasoning and cross-modal analysis, which are poorly supported by current medical LVLMs. To bridge this critical gap, we present the Med-MIM instruction dataset, comprising 83.2K medical multi-image QA pairs th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19031","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/2505.19031/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":"2505.19031","created_at":"2026-07-05T11:09:23.824118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19031v1","created_at":"2026-07-05T11:09:23.824118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19031","created_at":"2026-07-05T11:09:23.824118+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2RUWMI3YIXW","created_at":"2026-07-05T11:09:23.824118+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2RUWMI3YIXWXZOQ","created_at":"2026-07-05T11:09:23.824118+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2RUWMI3","created_at":"2026-07-05T11:09:23.824118+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/Q2RUWMI3YIXWXZOQXJTAA2HIG7","json":"https://pith.science/pith/Q2RUWMI3YIXWXZOQXJTAA2HIG7.json","graph_json":"https://pith.science/api/pith-number/Q2RUWMI3YIXWXZOQXJTAA2HIG7/graph.json","events_json":"https://pith.science/api/pith-number/Q2RUWMI3YIXWXZOQXJTAA2HIG7/events.json","paper":"https://pith.science/paper/Q2RUWMI3"},"agent_actions":{"view_html":"https://pith.science/pith/Q2RUWMI3YIXWXZOQXJTAA2HIG7","download_json":"https://pith.science/pith/Q2RUWMI3YIXWXZOQXJTAA2HIG7.json","view_paper":"https://pith.science/paper/Q2RUWMI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19031&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2RUWMI3YIXWXZOQXJTAA2HIG7/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2RUWMI3YIXWXZOQXJTAA2HIG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2RUWMI3YIXWXZOQXJTAA2HIG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2RUWMI3YIXWXZOQXJTAA2HIG7/action/storage_attestation","attest_author":"https://pith.science/pith/Q2RUWMI3YIXWXZOQXJTAA2HIG7/action/author_attestation","sign_citation":"https://pith.science/pith/Q2RUWMI3YIXWXZOQXJTAA2HIG7/action/citation_signature","submit_replication":"https://pith.science/pith/Q2RUWMI3YIXWXZOQXJTAA2HIG7/action/replication_record"}},"created_at":"2026-07-05T11:09:23.824118+00:00","updated_at":"2026-07-05T11:09:23.824118+00:00"}