{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4IYB7I4PPBQTU55F3MIY43XWRJ","short_pith_number":"pith:4IYB7I4P","schema_version":"1.0","canonical_sha256":"e2301fa38f78613a77a5db118e6ef68a6db9ce9ad7150054a3715069bbd2b6ff","source":{"kind":"arxiv","id":"2306.15887","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Elizabeth Tong, Mohammad R. K. Mofrad, Salmonn Talebi","submitted_at":"2023-06-28T03:03:51Z","abstract_excerpt":"The use of large language models (LLMs) in healthcare is gaining popularity, but their practicality and safety in clinical settings have not been thoroughly assessed. In high-stakes environments like medical settings, trust and safety are critical issues for LLMs. To address these concerns, we present an approach to evaluate the performance and trustworthiness of a GPT3.5 model for medical image protocol assignment. We compare it with a fine-tuned BERT model and a radiologist. In addition, we have a radiologist review the GPT3.5 output to evaluate its decision-making process. Our evaluation da"},"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":"2306.15887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-28T03:03:51Z","cross_cats_sorted":[],"title_canon_sha256":"d336cd26d3595e5bbbf32923a3d00a20f14f5dfd8d40a55529dfc04489556d20","abstract_canon_sha256":"576ad311f8e9660588bf3109ffab31a8959547e2ea0d824208e8e0a02529fc1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:45.930990Z","signature_b64":"hrZYkVHH2ED9ofvFJYsq79hwTMdhVYzck1hcLgoxA7qwVoYWtKui+ADfgVRAin5/N7HaVFVqV9tJBk8KX5kKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2301fa38f78613a77a5db118e6ef68a6db9ce9ad7150054a3715069bbd2b6ff","last_reissued_at":"2026-07-05T06:25:45.930518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:45.930518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Elizabeth Tong, Mohammad R. K. Mofrad, Salmonn Talebi","submitted_at":"2023-06-28T03:03:51Z","abstract_excerpt":"The use of large language models (LLMs) in healthcare is gaining popularity, but their practicality and safety in clinical settings have not been thoroughly assessed. In high-stakes environments like medical settings, trust and safety are critical issues for LLMs. To address these concerns, we present an approach to evaluate the performance and trustworthiness of a GPT3.5 model for medical image protocol assignment. We compare it with a fine-tuned BERT model and a radiologist. In addition, we have a radiologist review the GPT3.5 output to evaluate its decision-making process. Our evaluation da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15887","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/2306.15887/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":"2306.15887","created_at":"2026-07-05T06:25:45.930577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15887v1","created_at":"2026-07-05T06:25:45.930577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15887","created_at":"2026-07-05T06:25:45.930577+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IYB7I4PPBQT","created_at":"2026-07-05T06:25:45.930577+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IYB7I4PPBQTU55F","created_at":"2026-07-05T06:25:45.930577+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IYB7I4P","created_at":"2026-07-05T06:25:45.930577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.24176","citing_title":"Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions","ref_index":195,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ","json":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ.json","graph_json":"https://pith.science/api/pith-number/4IYB7I4PPBQTU55F3MIY43XWRJ/graph.json","events_json":"https://pith.science/api/pith-number/4IYB7I4PPBQTU55F3MIY43XWRJ/events.json","paper":"https://pith.science/paper/4IYB7I4P"},"agent_actions":{"view_html":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ","download_json":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ.json","view_paper":"https://pith.science/paper/4IYB7I4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15887&json=true","fetch_graph":"https://pith.science/api/pith-number/4IYB7I4PPBQTU55F3MIY43XWRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4IYB7I4PPBQTU55F3MIY43XWRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ/action/storage_attestation","attest_author":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ/action/author_attestation","sign_citation":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ/action/citation_signature","submit_replication":"https://pith.science/pith/4IYB7I4PPBQTU55F3MIY43XWRJ/action/replication_record"}},"created_at":"2026-07-05T06:25:45.930577+00:00","updated_at":"2026-07-05T06:25:45.930577+00:00"}