{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HZNIDVW4UBX3FVWD3HSBVO3EXH","short_pith_number":"pith:HZNIDVW4","canonical_record":{"source":{"id":"2502.15040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T20:55:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cefb929788c3fbf695e8640dacf590572369ca55d65c9343b3a0827d71a83ca5","abstract_canon_sha256":"0fc629b472bbde3bdb8ce2b177013586c4a3a855283f4ac1169930f9cfeb5792"},"schema_version":"1.0"},"canonical_sha256":"3e5a81d6dca06fb2d6c3d9e41abb64b9fd0f1d211b319d8c82e5b406316a2386","source":{"kind":"arxiv","id":"2502.15040","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HZNIDVW4UBX3FVWD3HSBVO3EXH","target":"record","payload":{"canonical_record":{"source":{"id":"2502.15040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T20:55:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cefb929788c3fbf695e8640dacf590572369ca55d65c9343b3a0827d71a83ca5","abstract_canon_sha256":"0fc629b472bbde3bdb8ce2b177013586c4a3a855283f4ac1169930f9cfeb5792"},"schema_version":"1.0"},"canonical_sha256":"3e5a81d6dca06fb2d6c3d9e41abb64b9fd0f1d211b319d8c82e5b406316a2386","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:38.523984Z","signature_b64":"2IgEd/pTgiazD1DswSNBsvKZ2rsIATctZZIw67N32c0TOSGEUt5ab9tPauz1UuLQ5QeG5lBbCH5mWjtuqKVdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e5a81d6dca06fb2d6c3d9e41abb64b9fd0f1d211b319d8c82e5b406316a2386","last_reissued_at":"2026-07-05T10:17:38.523460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:38.523460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.15040","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ag96y+FWy8E2cjkXMjjENLaGd29xAqzG5NOPfY73OZsbMgFs/NyKrIRfT0J6kmNZL2exyBR5zANf56TO86NCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:40:27.103429Z"},"content_sha256":"e0ca05e8882348535188a61c949f4d5a44b3f38438de7c7f09cb879a9a014be0","schema_version":"1.0","event_id":"sha256:e0ca05e8882348535188a61c949f4d5a44b3f38438de7c7f09cb879a9a014be0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HZNIDVW4UBX3FVWD3HSBVO3EXH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christopher Malon, Kai Zhang, Martin Renqiang Min, Yun-Wei Chu","submitted_at":"2025-02-20T20:55:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15040","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/2502.15040/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+rUip3f2HbjYSEsBhk4ket371YpICZ6wGLT5CLKTBrmfTRNT7SRgU43XJYA6TPIWMeYymwlfW9SJ1CPS5eSBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:40:27.104492Z"},"content_sha256":"c867f04ee69e552311fac24147705148835e237f609d0beaf1f4a3239ebd1e46","schema_version":"1.0","event_id":"sha256:c867f04ee69e552311fac24147705148835e237f609d0beaf1f4a3239ebd1e46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZNIDVW4UBX3FVWD3HSBVO3EXH/bundle.json","state_url":"https://pith.science/pith/HZNIDVW4UBX3FVWD3HSBVO3EXH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZNIDVW4UBX3FVWD3HSBVO3EXH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T10:40:27Z","links":{"resolver":"https://pith.science/pith/HZNIDVW4UBX3FVWD3HSBVO3EXH","bundle":"https://pith.science/pith/HZNIDVW4UBX3FVWD3HSBVO3EXH/bundle.json","state":"https://pith.science/pith/HZNIDVW4UBX3FVWD3HSBVO3EXH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZNIDVW4UBX3FVWD3HSBVO3EXH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++KZUXkrdB6Eaf/H2C1ThXbPt2aizMbmfDOhXoEGVn5gYYaWYLFqhoVIkXkBjPx/jlOC6tWPfiblwiFMNE4bDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:40:27.109182Z","bundle_sha256":"71a679a146047e775de211d2f44a5af2385d86fb8662c885d62f7cf7fe305cb8"}}