{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J4ZTQI4EH5WYVBBA7I3XW6KOMI","short_pith_number":"pith:J4ZTQI4E","schema_version":"1.0","canonical_sha256":"4f333823843f6d8a8420fa377b794e6226c7e45714b98c1d1c6d59246dff005c","source":{"kind":"arxiv","id":"2309.09362","version":1},"attestation_state":"computed","paper":{"title":"Language models are susceptible to incorrect patient self-diagnosis in medical applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rojin Ziaei, Samuel Schmidgall","submitted_at":"2023-09-17T19:56:39Z","abstract_excerpt":"Large language models (LLMs) are becoming increasingly relevant as a potential tool for healthcare, aiding communication between clinicians, researchers, and patients. However, traditional evaluations of LLMs on medical exam questions do not reflect the complexity of real patient-doctor interactions. An example of this complexity is the introduction of patient self-diagnosis, where a patient attempts to diagnose their own medical conditions from various sources. While the patient sometimes arrives at an accurate conclusion, they more often are led toward misdiagnosis due to the patient's over-"},"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":"2309.09362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-17T19:56:39Z","cross_cats_sorted":[],"title_canon_sha256":"6ab02064eb7bf2c85e4446a67625bff73872756a092db92dd32d13f787b02b20","abstract_canon_sha256":"7664149b8c388e9a564dcf596ee0725f0eb93ca280e138723c32823cc55de98d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:37.811176Z","signature_b64":"0b0OFk16PJ7ycuNC/GFywVSdg0Buzvw4MBxlbfgMWCVd5ZJvGycUSbxnobgpTTAMJF371QaTtXRVknsyTIJMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f333823843f6d8a8420fa377b794e6226c7e45714b98c1d1c6d59246dff005c","last_reissued_at":"2026-07-05T06:51:37.810666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:37.810666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language models are susceptible to incorrect patient self-diagnosis in medical applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rojin Ziaei, Samuel Schmidgall","submitted_at":"2023-09-17T19:56:39Z","abstract_excerpt":"Large language models (LLMs) are becoming increasingly relevant as a potential tool for healthcare, aiding communication between clinicians, researchers, and patients. However, traditional evaluations of LLMs on medical exam questions do not reflect the complexity of real patient-doctor interactions. An example of this complexity is the introduction of patient self-diagnosis, where a patient attempts to diagnose their own medical conditions from various sources. While the patient sometimes arrives at an accurate conclusion, they more often are led toward misdiagnosis due to the patient's over-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09362","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/2309.09362/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":"2309.09362","created_at":"2026-07-05T06:51:37.810727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09362v1","created_at":"2026-07-05T06:51:37.810727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09362","created_at":"2026-07-05T06:51:37.810727+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4ZTQI4EH5WY","created_at":"2026-07-05T06:51:37.810727+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4ZTQI4EH5WYVBBA","created_at":"2026-07-05T06:51:37.810727+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4ZTQI4E","created_at":"2026-07-05T06:51:37.810727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07186","citing_title":"Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI","json":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI.json","graph_json":"https://pith.science/api/pith-number/J4ZTQI4EH5WYVBBA7I3XW6KOMI/graph.json","events_json":"https://pith.science/api/pith-number/J4ZTQI4EH5WYVBBA7I3XW6KOMI/events.json","paper":"https://pith.science/paper/J4ZTQI4E"},"agent_actions":{"view_html":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI","download_json":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI.json","view_paper":"https://pith.science/paper/J4ZTQI4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09362&json=true","fetch_graph":"https://pith.science/api/pith-number/J4ZTQI4EH5WYVBBA7I3XW6KOMI/graph.json","fetch_events":"https://pith.science/api/pith-number/J4ZTQI4EH5WYVBBA7I3XW6KOMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI/action/storage_attestation","attest_author":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI/action/author_attestation","sign_citation":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI/action/citation_signature","submit_replication":"https://pith.science/pith/J4ZTQI4EH5WYVBBA7I3XW6KOMI/action/replication_record"}},"created_at":"2026-07-05T06:51:37.810727+00:00","updated_at":"2026-07-05T06:51:37.810727+00:00"}