{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:72JITNEMFJYAOSIYWA2MXPRW5C","short_pith_number":"pith:72JITNEM","schema_version":"1.0","canonical_sha256":"fe9289b48c2a70074918b034cbbe36e88e1c025a5bd7f14bcea72b8a35506f5c","source":{"kind":"arxiv","id":"2505.04653","version":1},"attestation_state":"computed","paper":{"title":"Advancing Conversational Diagnostic AI with Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdullah Ahmed, Adam Rodman, Alan Karthikesalingam, Anil Palepu, Avinatan Hassidim, Chunjong Park, Cian Hughes, Dale R. Webster, David G.T. Barrett, David Stutz, Elahe Vedadi, Geoff Brown, James Manyika, Jan Freyberg, Jo\\\"elle Barral, Katherine Chou, Khaled Saab, Kimberly Kanada, Mike Schaekermann, Nenad Tomasev, Pushmeet Kohli, Roma Ruparel, Ryutaro Tanno, Sean Li, S.M. Ali Eslami, S. Sara Mahdavi, Tao Tu, Tim Strother, Valentin Li\\'evin, Vivek Natarajan, Wei-Hung Weng, Yang Gao, Yash Sharma, Yong Cheng, Yossi Matias, Yun Liu","submitted_at":"2025-05-06T20:52:01Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated great potential for conducting diagnostic conversations but evaluation has been largely limited to language-only interactions, deviating from the real-world requirements of remote care delivery. Instant messaging platforms permit clinicians and patients to upload and discuss multimodal medical artifacts seamlessly in medical consultation, but the ability of LLMs to reason over such data while preserving other attributes of competent diagnostic conversation remains unknown. Here we advance the conversational diagnosis and management performance of "},"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":"2505.04653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T20:52:01Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"657fafb891f39abad04b40d2fc73be217c913313baf0be5d1db73f1a67d5b9cb","abstract_canon_sha256":"d6808b088f10cd34b57c637a0de0de1e67d950523fe2d16336f507d372a429aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:11.135224Z","signature_b64":"9TJpppIamyoii58VFNMnWvGwGvXY/4VaXJd8jpM9Dc++qQv0kehyLRKCE7br8KnTOp/0NkMpoEL52jyQlm4PCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9289b48c2a70074918b034cbbe36e88e1c025a5bd7f14bcea72b8a35506f5c","last_reissued_at":"2026-07-05T11:00:11.134688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:11.134688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Conversational Diagnostic AI with Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdullah Ahmed, Adam Rodman, Alan Karthikesalingam, Anil Palepu, Avinatan Hassidim, Chunjong Park, Cian Hughes, Dale R. Webster, David G.T. Barrett, David Stutz, Elahe Vedadi, Geoff Brown, James Manyika, Jan Freyberg, Jo\\\"elle Barral, Katherine Chou, Khaled Saab, Kimberly Kanada, Mike Schaekermann, Nenad Tomasev, Pushmeet Kohli, Roma Ruparel, Ryutaro Tanno, Sean Li, S.M. Ali Eslami, S. Sara Mahdavi, Tao Tu, Tim Strother, Valentin Li\\'evin, Vivek Natarajan, Wei-Hung Weng, Yang Gao, Yash Sharma, Yong Cheng, Yossi Matias, Yun Liu","submitted_at":"2025-05-06T20:52:01Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated great potential for conducting diagnostic conversations but evaluation has been largely limited to language-only interactions, deviating from the real-world requirements of remote care delivery. Instant messaging platforms permit clinicians and patients to upload and discuss multimodal medical artifacts seamlessly in medical consultation, but the ability of LLMs to reason over such data while preserving other attributes of competent diagnostic conversation remains unknown. Here we advance the conversational diagnosis and management performance of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04653","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/2505.04653/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":"2505.04653","created_at":"2026-07-05T11:00:11.134758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04653v1","created_at":"2026-07-05T11:00:11.134758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04653","created_at":"2026-07-05T11:00:11.134758+00:00"},{"alias_kind":"pith_short_12","alias_value":"72JITNEMFJYA","created_at":"2026-07-05T11:00:11.134758+00:00"},{"alias_kind":"pith_short_16","alias_value":"72JITNEMFJYAOSIY","created_at":"2026-07-05T11:00:11.134758+00:00"},{"alias_kind":"pith_short_8","alias_value":"72JITNEM","created_at":"2026-07-05T11:00:11.134758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07853","citing_title":"Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04012","citing_title":"SymptomAI: Toward a Conversational AI Agent for Everyday Symptom Assessment","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09272","citing_title":"Towards Conversational Medical AI with Eyes, Ears and a Voice","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04012","citing_title":"SymptomAI: Toward a Conversational AI Agent for Everyday Symptom Assessment","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C","json":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C.json","graph_json":"https://pith.science/api/pith-number/72JITNEMFJYAOSIYWA2MXPRW5C/graph.json","events_json":"https://pith.science/api/pith-number/72JITNEMFJYAOSIYWA2MXPRW5C/events.json","paper":"https://pith.science/paper/72JITNEM"},"agent_actions":{"view_html":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C","download_json":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C.json","view_paper":"https://pith.science/paper/72JITNEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04653&json=true","fetch_graph":"https://pith.science/api/pith-number/72JITNEMFJYAOSIYWA2MXPRW5C/graph.json","fetch_events":"https://pith.science/api/pith-number/72JITNEMFJYAOSIYWA2MXPRW5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C/action/storage_attestation","attest_author":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C/action/author_attestation","sign_citation":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C/action/citation_signature","submit_replication":"https://pith.science/pith/72JITNEMFJYAOSIYWA2MXPRW5C/action/replication_record"}},"created_at":"2026-07-05T11:00:11.134758+00:00","updated_at":"2026-07-05T11:00:11.134758+00:00"}