{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N4TNQZGDGE27MJIVRPXGWGMU7J","short_pith_number":"pith:N4TNQZGD","schema_version":"1.0","canonical_sha256":"6f26d864c33135f625158bee6b1994fa4fb34f03217ee371292bbb2561566105","source":{"kind":"arxiv","id":"2310.12558","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Chen Zhao, Hal Daum\\'e III, Jordan Boyd-Graber, Navita Goyal, Sherry Tongshuang Wu, Shi Feng","submitted_at":"2023-10-19T08:09:58Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get, LLMs should not only provide information but also help users fact-check it. Our experiments with 80 crowdworkers compare language models with search engines (information retrieval systems) at facilitating fact-checking. We prompt LLMs to validate a given claim and provide corresponding explanations. Users reading LLM explanations are significantly more efficient than those us"},"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":"2310.12558","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T08:09:58Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"838e6e8b1d69969d9e2f0770fa376f4454062f01514a77ce3b1bff1ea41a531a","abstract_canon_sha256":"c33cdee0d1bc326c61287dbf636a0fc9602a5d4ff81d74389a8cf590b1f9bb0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:07.705200Z","signature_b64":"GhyjXJqRt9KFc48rDnhBUq5YB2xxWFWtjWqnaz6f8ksaf/ktpbCGWgUscBrnYnyNWtXCzf38VsRIs7DbPrQNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f26d864c33135f625158bee6b1994fa4fb34f03217ee371292bbb2561566105","last_reissued_at":"2026-07-05T08:03:07.704704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:07.704704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Chen Zhao, Hal Daum\\'e III, Jordan Boyd-Graber, Navita Goyal, Sherry Tongshuang Wu, Shi Feng","submitted_at":"2023-10-19T08:09:58Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get, LLMs should not only provide information but also help users fact-check it. Our experiments with 80 crowdworkers compare language models with search engines (information retrieval systems) at facilitating fact-checking. We prompt LLMs to validate a given claim and provide corresponding explanations. Users reading LLM explanations are significantly more efficient than those us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12558","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/2310.12558/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":"2310.12558","created_at":"2026-07-05T08:03:07.704762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12558v2","created_at":"2026-07-05T08:03:07.704762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12558","created_at":"2026-07-05T08:03:07.704762+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4TNQZGDGE27","created_at":"2026-07-05T08:03:07.704762+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4TNQZGDGE27MJIV","created_at":"2026-07-05T08:03:07.704762+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4TNQZGD","created_at":"2026-07-05T08:03:07.704762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.08010","citing_title":"Measuring and mitigating overreliance to build human-compatible AI","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11954","citing_title":"VizCopilot: Fostering Appropriate Reliance on Enterprise Chatbots with Context Visualization","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06608","citing_title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20131","citing_title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","ref_index":149,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J","json":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J.json","graph_json":"https://pith.science/api/pith-number/N4TNQZGDGE27MJIVRPXGWGMU7J/graph.json","events_json":"https://pith.science/api/pith-number/N4TNQZGDGE27MJIVRPXGWGMU7J/events.json","paper":"https://pith.science/paper/N4TNQZGD"},"agent_actions":{"view_html":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J","download_json":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J.json","view_paper":"https://pith.science/paper/N4TNQZGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12558&json=true","fetch_graph":"https://pith.science/api/pith-number/N4TNQZGDGE27MJIVRPXGWGMU7J/graph.json","fetch_events":"https://pith.science/api/pith-number/N4TNQZGDGE27MJIVRPXGWGMU7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J/action/storage_attestation","attest_author":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J/action/author_attestation","sign_citation":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J/action/citation_signature","submit_replication":"https://pith.science/pith/N4TNQZGDGE27MJIVRPXGWGMU7J/action/replication_record"}},"created_at":"2026-07-05T08:03:07.704762+00:00","updated_at":"2026-07-05T08:03:07.704762+00:00"}