{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q2RUWMI3YIXWXZOQXJTAA2HIG7","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":"74819da44339cb94e4ae5190ae90460c0e81bfb402636e06817ce31e54f91a77","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T08:31:22Z","title_canon_sha256":"4d1cb504932cf2927bc4edfaa01d491610b835621fd1ab5507c0d53bed315552"},"schema_version":"1.0","source":{"id":"2505.19031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19031","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19031v1","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19031","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"Q2RUWMI3YIXW","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_16","alias_value":"Q2RUWMI3YIXWXZOQ","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_8","alias_value":"Q2RUWMI3","created_at":"2026-07-05T11:09:23Z"}],"graph_snapshots":[{"event_id":"sha256:0e6b1688e7dc4056e82a227888312fdf86fb1e84abf8d0b31de75f4ebf0cc8ea","target":"graph","created_at":"2026-07-05T11:09:23Z","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/2505.19031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiaze Wang, Jinpeng Li, Juzheng Miao, Pheng-Ann Heng, Qi Dou, Xikai Yang, Yuchen Yuan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T08:31:22Z","title":"Medical Large Vision Language Models with Multi-Image Visual Ability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19031","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":"sha256:8255574ee4671b9322751085983b4c87e2855f9d846d066e682596945aff281e","target":"record","created_at":"2026-07-05T11:09:23Z","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":"74819da44339cb94e4ae5190ae90460c0e81bfb402636e06817ce31e54f91a77","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T08:31:22Z","title_canon_sha256":"4d1cb504932cf2927bc4edfaa01d491610b835621fd1ab5507c0d53bed315552"},"schema_version":"1.0","source":{"id":"2505.19031","kind":"arxiv","version":1}},"canonical_sha256":"86a34b311bc22f6be5d0ba660068e837c65d2a2afa5b30933baec554271d62c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86a34b311bc22f6be5d0ba660068e837c65d2a2afa5b30933baec554271d62c8","first_computed_at":"2026-07-05T11:09:23.824053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:23.824053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DGZBv16FhOEIPIQk/BN7eJGO6ojivYbTQem9THSyLH8ig6s/+Y72bkaHAT9rTsXwV0HxzeAWzHScQlDWyvqEDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:23.824578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8255574ee4671b9322751085983b4c87e2855f9d846d066e682596945aff281e","sha256:0e6b1688e7dc4056e82a227888312fdf86fb1e84abf8d0b31de75f4ebf0cc8ea"],"state_sha256":"2df9af2182a087ef37f4ed08bcd2e64f2f4ec4315053893453737c526b12452f"}