{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C3UM23LLGZENG45A7S24JPD3ZI","short_pith_number":"pith:C3UM23LL","schema_version":"1.0","canonical_sha256":"16e8cd6d6b3648d373a0fcb5c4bc7bca1209d5bd61eb3dc9aceb8d97cc265623","source":{"kind":"arxiv","id":"2508.08224","version":2},"attestation_state":"computed","paper":{"title":"Capabilities of GPT-5 on Multimodal Medical Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mingzhe Hu, Mojtaba Safari, Qiang Li, Shansong Wang, Xiaofeng Yang","submitted_at":"2025-08-11T17:43:45Z","abstract_excerpt":"Recent advances in large language models (LLMs) have enabled general-purpose systems to perform increasingly complex domain-specific reasoning without extensive fine-tuning. In the medical domain, decision-making often requires integrating heterogeneous information sources, including patient narratives, structured data, and medical images. This study positions GPT-5 as a generalist multimodal reasoner for medical decision support and systematically evaluates its zero-shot chain-of-thought reasoning performance on both text-based question answering and visual question answering tasks under a un"},"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":"2508.08224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T17:43:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"27c84e2eb138c73fbd34d54372a66ff88101051ebf9f8ebc42665e3b6dcf1074","abstract_canon_sha256":"d7dded6173bb472880481438050431b34da43a710cb55f69bf963d5dadbdb8b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:07.922032Z","signature_b64":"lEKHMFv+8Pte4qQJ2ZZc2q7Z+AJE8fI1tDBOW7cMt03CU5BFvMWSR0qITUAACGQhiFHAF9QaEGqpr+sKqZVGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16e8cd6d6b3648d373a0fcb5c4bc7bca1209d5bd61eb3dc9aceb8d97cc265623","last_reissued_at":"2026-07-05T11:53:07.921564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:07.921564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capabilities of GPT-5 on Multimodal Medical Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mingzhe Hu, Mojtaba Safari, Qiang Li, Shansong Wang, Xiaofeng Yang","submitted_at":"2025-08-11T17:43:45Z","abstract_excerpt":"Recent advances in large language models (LLMs) have enabled general-purpose systems to perform increasingly complex domain-specific reasoning without extensive fine-tuning. In the medical domain, decision-making often requires integrating heterogeneous information sources, including patient narratives, structured data, and medical images. This study positions GPT-5 as a generalist multimodal reasoner for medical decision support and systematically evaluates its zero-shot chain-of-thought reasoning performance on both text-based question answering and visual question answering tasks under a un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08224","kind":"arxiv","version":2},"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/2508.08224/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":"2508.08224","created_at":"2026-07-05T11:53:07.921622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08224v2","created_at":"2026-07-05T11:53:07.921622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08224","created_at":"2026-07-05T11:53:07.921622+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3UM23LLGZEN","created_at":"2026-07-05T11:53:07.921622+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3UM23LLGZENG45A","created_at":"2026-07-05T11:53:07.921622+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3UM23LL","created_at":"2026-07-05T11:53:07.921622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20277","citing_title":"Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24649","citing_title":"MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09675","citing_title":"CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11365","citing_title":"Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08014","citing_title":"Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17725","citing_title":"RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI","json":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI.json","graph_json":"https://pith.science/api/pith-number/C3UM23LLGZENG45A7S24JPD3ZI/graph.json","events_json":"https://pith.science/api/pith-number/C3UM23LLGZENG45A7S24JPD3ZI/events.json","paper":"https://pith.science/paper/C3UM23LL"},"agent_actions":{"view_html":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI","download_json":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI.json","view_paper":"https://pith.science/paper/C3UM23LL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08224&json=true","fetch_graph":"https://pith.science/api/pith-number/C3UM23LLGZENG45A7S24JPD3ZI/graph.json","fetch_events":"https://pith.science/api/pith-number/C3UM23LLGZENG45A7S24JPD3ZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI/action/storage_attestation","attest_author":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI/action/author_attestation","sign_citation":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI/action/citation_signature","submit_replication":"https://pith.science/pith/C3UM23LLGZENG45A7S24JPD3ZI/action/replication_record"}},"created_at":"2026-07-05T11:53:07.921622+00:00","updated_at":"2026-07-05T11:53:07.921622+00:00"}