{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HZNIDVW4UBX3FVWD3HSBVO3EXH","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":"0fc629b472bbde3bdb8ce2b177013586c4a3a855283f4ac1169930f9cfeb5792","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T20:55:34Z","title_canon_sha256":"cefb929788c3fbf695e8640dacf590572369ca55d65c9343b3a0827d71a83ca5"},"schema_version":"1.0","source":{"id":"2502.15040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15040","created_at":"2026-07-05T10:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15040v1","created_at":"2026-07-05T10:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15040","created_at":"2026-07-05T10:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"HZNIDVW4UBX3","created_at":"2026-07-05T10:17:38Z"},{"alias_kind":"pith_short_16","alias_value":"HZNIDVW4UBX3FVWD","created_at":"2026-07-05T10:17:38Z"},{"alias_kind":"pith_short_8","alias_value":"HZNIDVW4","created_at":"2026-07-05T10:17:38Z"}],"graph_snapshots":[{"event_id":"sha256:c867f04ee69e552311fac24147705148835e237f609d0beaf1f4a3239ebd1e46","target":"graph","created_at":"2026-07-05T10:17:38Z","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/2502.15040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown impressive performance in vision and text tasks. However, hallucination remains a major challenge, especially in fields like healthcare where details are critical. In this work, we show how MLLMs may be enhanced to support Visual RAG (V-RAG), a retrieval-augmented generation framework that incorporates both text and visual data from retrieved images. On the MIMIC-CXR chest X-ray report generation and Multicare medical image caption generation datasets, we show that Visual RAG improves the accuracy of entity probing, which asks whether a medic","authors_text":"Christopher Malon, Kai Zhang, Martin Renqiang Min, Yun-Wei Chu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T20:55:34Z","title":"Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15040","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:e0ca05e8882348535188a61c949f4d5a44b3f38438de7c7f09cb879a9a014be0","target":"record","created_at":"2026-07-05T10:17:38Z","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":"0fc629b472bbde3bdb8ce2b177013586c4a3a855283f4ac1169930f9cfeb5792","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T20:55:34Z","title_canon_sha256":"cefb929788c3fbf695e8640dacf590572369ca55d65c9343b3a0827d71a83ca5"},"schema_version":"1.0","source":{"id":"2502.15040","kind":"arxiv","version":1}},"canonical_sha256":"3e5a81d6dca06fb2d6c3d9e41abb64b9fd0f1d211b319d8c82e5b406316a2386","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e5a81d6dca06fb2d6c3d9e41abb64b9fd0f1d211b319d8c82e5b406316a2386","first_computed_at":"2026-07-05T10:17:38.523460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:38.523460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2IgEd/pTgiazD1DswSNBsvKZ2rsIATctZZIw67N32c0TOSGEUt5ab9tPauz1UuLQ5QeG5lBbCH5mWjtuqKVdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:38.523984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0ca05e8882348535188a61c949f4d5a44b3f38438de7c7f09cb879a9a014be0","sha256:c867f04ee69e552311fac24147705148835e237f609d0beaf1f4a3239ebd1e46"],"state_sha256":"2745944f49ea8be3f0e9f84057cbb24640db6ea09406b0af8298777827ed75a1"}