{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P2LAEWPFD6CFYNJ2J2ZQJEBW7C","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":"a8bd8ef70a419cd94787c015d4681aa2571619f4415d81f5bc85be3f17fff791","cross_cats_sorted":["cs.AI","cs.CV","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-10T19:08:28Z","title_canon_sha256":"38834c17c7a62d64093573eb9653292e9441d4e2830768c2838aa3a6eb5edd21"},"schema_version":"1.0","source":{"id":"2402.07023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07023","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07023v1","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07023","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"P2LAEWPFD6CF","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_16","alias_value":"P2LAEWPFD6CFYNJ2","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_8","alias_value":"P2LAEWPF","created_at":"2026-07-05T07:43:42Z"}],"graph_snapshots":[{"event_id":"sha256:346a959032c5723c14b114e2caa1d4844b23fb8a6549e3cef688759f8bac6661","target":"graph","created_at":"2026-07-05T07:43:42Z","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/2402.07023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have the potential to be valuable in the healthcare industry, but it's crucial to verify their safety and effectiveness through rigorous evaluation. For this purpose, we comprehensively evaluated both open-source LLMs and Google's new multimodal LLM called Gemini across Medical reasoning, hallucination detection, and Medical Visual Question Answering tasks. While Gemini showed competence, it lagged behind state-of-the-art models like MedPaLM 2 and GPT-4 in diagnostic accuracy. Additionally, Gemini achieved an accuracy of 61.45\\% on the medical VQA dataset, significantly l","authors_text":"Ankit Pal, Malaikannan Sankarasubbu","cross_cats":["cs.AI","cs.CV","cs.HC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-10T19:08:28Z","title":"Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07023","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":"sha256:8a1c93f99b41ef81cf612196aa09f55dcb9a0553147285ef69f315bfae0e98f2","target":"record","created_at":"2026-07-05T07:43:42Z","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":"a8bd8ef70a419cd94787c015d4681aa2571619f4415d81f5bc85be3f17fff791","cross_cats_sorted":["cs.AI","cs.CV","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-10T19:08:28Z","title_canon_sha256":"38834c17c7a62d64093573eb9653292e9441d4e2830768c2838aa3a6eb5edd21"},"schema_version":"1.0","source":{"id":"2402.07023","kind":"arxiv","version":1}},"canonical_sha256":"7e960259e51f845c353a4eb3049036f88bd15243a5200e73e12e3a062507be2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e960259e51f845c353a4eb3049036f88bd15243a5200e73e12e3a062507be2d","first_computed_at":"2026-07-05T07:43:42.710623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:42.710623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rUgMHhSLI3AfOCaSEjiQkSDbP5NcSfMfbTmcYGAC+rzuAHrbYiRyr7/Pr54U87dsQhBGXGxpBDOORrmkRTo3AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:42.711095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a1c93f99b41ef81cf612196aa09f55dcb9a0553147285ef69f315bfae0e98f2","sha256:346a959032c5723c14b114e2caa1d4844b23fb8a6549e3cef688759f8bac6661"],"state_sha256":"aed7d40221a529ddfff16b10913dc14f2d25f3d9ce25e40a5949a121e1107b27"}