{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5EDET72ROYRNBVNACEEF7PVNXP","short_pith_number":"pith:5EDET72R","schema_version":"1.0","canonical_sha256":"e90649ff517622d0d5a011085fbeadbbecb5107681874a84d9e2425646e5fadf","source":{"kind":"arxiv","id":"2402.01730","version":1},"attestation_state":"computed","paper":{"title":"Evaluating LLM -- Generated Multimodal Diagnosis from Medical Images and Symptom Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Dimitrios P. Panagoulias, George A. Tsihrintzis, Maria Virvou","submitted_at":"2024-01-28T09:25:12Z","abstract_excerpt":"Large language models (LLMs) constitute a breakthrough state-of-the-art Artificial Intelligence technology which is rapidly evolving and promises to aid in medical diagnosis. However, the correctness and the accuracy of their returns has not yet been properly evaluated. In this work, we propose an LLM evaluation paradigm that incorporates two independent steps of a novel methodology, namely (1) multimodal LLM evaluation via structured interactions and (2) follow-up, domain-specific analysis based on data extracted via the previous interactions. Using this paradigm, (1) we evaluate the correctn"},"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":"2402.01730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-28T09:25:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"03d4ed6be6a8f56e31866ad8c510f0ed05450db728162d95f26ac5b173eafca7","abstract_canon_sha256":"f8394291b3db88fa87eda490a59ba4e612f47bb4c6193302bd9ac62cdb8c4fe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:47.969223Z","signature_b64":"ZbXc+o5y0Gv2VUl7InP0zZqY9hUPjRpAse14fFbLPgtLjewXoFQwHh5KOVTKCFTf8KFfgi/6gsV02uorybj+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e90649ff517622d0d5a011085fbeadbbecb5107681874a84d9e2425646e5fadf","last_reissued_at":"2026-07-05T07:41:47.968674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:47.968674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating LLM -- Generated Multimodal Diagnosis from Medical Images and Symptom Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Dimitrios P. Panagoulias, George A. Tsihrintzis, Maria Virvou","submitted_at":"2024-01-28T09:25:12Z","abstract_excerpt":"Large language models (LLMs) constitute a breakthrough state-of-the-art Artificial Intelligence technology which is rapidly evolving and promises to aid in medical diagnosis. However, the correctness and the accuracy of their returns has not yet been properly evaluated. In this work, we propose an LLM evaluation paradigm that incorporates two independent steps of a novel methodology, namely (1) multimodal LLM evaluation via structured interactions and (2) follow-up, domain-specific analysis based on data extracted via the previous interactions. Using this paradigm, (1) we evaluate the correctn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01730","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/2402.01730/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":"2402.01730","created_at":"2026-07-05T07:41:47.968807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01730v1","created_at":"2026-07-05T07:41:47.968807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01730","created_at":"2026-07-05T07:41:47.968807+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EDET72ROYRN","created_at":"2026-07-05T07:41:47.968807+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EDET72ROYRNBVNA","created_at":"2026-07-05T07:41:47.968807+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EDET72R","created_at":"2026-07-05T07:41:47.968807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01901","citing_title":"SABER: A Semantic-Aligned Brain Network Analysis Framework via Multi-scale Hypergraphs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28556","citing_title":"IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP","json":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP.json","graph_json":"https://pith.science/api/pith-number/5EDET72ROYRNBVNACEEF7PVNXP/graph.json","events_json":"https://pith.science/api/pith-number/5EDET72ROYRNBVNACEEF7PVNXP/events.json","paper":"https://pith.science/paper/5EDET72R"},"agent_actions":{"view_html":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP","download_json":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP.json","view_paper":"https://pith.science/paper/5EDET72R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01730&json=true","fetch_graph":"https://pith.science/api/pith-number/5EDET72ROYRNBVNACEEF7PVNXP/graph.json","fetch_events":"https://pith.science/api/pith-number/5EDET72ROYRNBVNACEEF7PVNXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP/action/storage_attestation","attest_author":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP/action/author_attestation","sign_citation":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP/action/citation_signature","submit_replication":"https://pith.science/pith/5EDET72ROYRNBVNACEEF7PVNXP/action/replication_record"}},"created_at":"2026-07-05T07:41:47.968807+00:00","updated_at":"2026-07-05T07:41:47.968807+00:00"}