{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JJWRCZGTPTFEPRBFVJRJVEUWCP","short_pith_number":"pith:JJWRCZGT","schema_version":"1.0","canonical_sha256":"4a6d1164d37cca47c425aa629a929613fa554a171c0aaf9b006840dd5fbd1472","source":{"kind":"arxiv","id":"2405.00623","version":2},"attestation_state":"computed","paper":{"title":"\"I'm Not Sure, But...\": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Jennifer Wortman Vaughan, Mihaela Vorvoreanu, Q. Vera Liao, Stephanie Ballard, Sunnie S. Y. Kim","submitted_at":"2024-05-01T16:43:55Z","abstract_excerpt":"Widely deployed large language models (LLMs) can produce convincing yet incorrect outputs, potentially misleading users who may rely on them as if they were correct. To reduce such overreliance, there have been calls for LLMs to communicate their uncertainty to end users. However, there has been little empirical work examining how users perceive and act upon LLMs' expressions of uncertainty. We explore this question through a large-scale, pre-registered, human-subject experiment (N=404) in which participants answer medical questions with or without access to responses from a fictional LLM-infu"},"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":"2405.00623","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-01T16:43:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"234d39b40cf82024719d8ff08962f3bebf502b1727eb970c23a346e4d9b9fb03","abstract_canon_sha256":"0c8aaf680e42e87b40d6a4aa5b2c48719ec28db55848cb3b2017d89df34e2cad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:24.554402Z","signature_b64":"J5e7wAujk8X4+ji4iNm+rqhZCMhHFYtHJWv8pzPhkpQZkMckmWuUwpnsWB8TkqdP5DIzQrNw0WI0MO2Q2QQSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a6d1164d37cca47c425aa629a929613fa554a171c0aaf9b006840dd5fbd1472","last_reissued_at":"2026-07-05T08:19:24.553868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:24.553868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"I'm Not Sure, But...\": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Jennifer Wortman Vaughan, Mihaela Vorvoreanu, Q. Vera Liao, Stephanie Ballard, Sunnie S. Y. Kim","submitted_at":"2024-05-01T16:43:55Z","abstract_excerpt":"Widely deployed large language models (LLMs) can produce convincing yet incorrect outputs, potentially misleading users who may rely on them as if they were correct. To reduce such overreliance, there have been calls for LLMs to communicate their uncertainty to end users. However, there has been little empirical work examining how users perceive and act upon LLMs' expressions of uncertainty. We explore this question through a large-scale, pre-registered, human-subject experiment (N=404) in which participants answer medical questions with or without access to responses from a fictional LLM-infu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00623","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/2405.00623/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":"2405.00623","created_at":"2026-07-05T08:19:24.553929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00623v2","created_at":"2026-07-05T08:19:24.553929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00623","created_at":"2026-07-05T08:19:24.553929+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJWRCZGTPTFE","created_at":"2026-07-05T08:19:24.553929+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJWRCZGTPTFEPRBF","created_at":"2026-07-05T08:19:24.553929+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJWRCZGT","created_at":"2026-07-05T08:19:24.553929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.00883","citing_title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17843","citing_title":"Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP","json":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP.json","graph_json":"https://pith.science/api/pith-number/JJWRCZGTPTFEPRBFVJRJVEUWCP/graph.json","events_json":"https://pith.science/api/pith-number/JJWRCZGTPTFEPRBFVJRJVEUWCP/events.json","paper":"https://pith.science/paper/JJWRCZGT"},"agent_actions":{"view_html":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP","download_json":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP.json","view_paper":"https://pith.science/paper/JJWRCZGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00623&json=true","fetch_graph":"https://pith.science/api/pith-number/JJWRCZGTPTFEPRBFVJRJVEUWCP/graph.json","fetch_events":"https://pith.science/api/pith-number/JJWRCZGTPTFEPRBFVJRJVEUWCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP/action/storage_attestation","attest_author":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP/action/author_attestation","sign_citation":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP/action/citation_signature","submit_replication":"https://pith.science/pith/JJWRCZGTPTFEPRBFVJRJVEUWCP/action/replication_record"}},"created_at":"2026-07-05T08:19:24.553929+00:00","updated_at":"2026-07-05T08:19:24.553929+00:00"}