{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VEOQCOVPAC4MIFM5LUIUR6DX54","short_pith_number":"pith:VEOQCOVP","schema_version":"1.0","canonical_sha256":"a91d013aaf00b8c4159d5d1148f877ef342585d423d33b3cb88911d22f170fbf","source":{"kind":"arxiv","id":"2304.08979","version":2},"attestation_state":"computed","paper":{"title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Xinyue Shen, Yang Zhang, Zeyuan Chen","submitted_at":"2023-04-18T13:20:45Z","abstract_excerpt":"The way users acquire information is undergoing a paradigm shift with the advent of ChatGPT. Unlike conventional search engines, ChatGPT retrieves knowledge from the model itself and generates answers for users. ChatGPT's impressive question-answering (QA) capability has attracted more than 100 million users within a short period of time but has also raised concerns regarding its reliability. In this paper, we perform the first large-scale measurement of ChatGPT's reliability in the generic QA scenario with a carefully curated set of 5,695 questions across ten datasets and eight domains. We fi"},"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":"2304.08979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-04-18T13:20:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0df6749cae93714b601f1467d80dc2d497d47bafd8d388428bf18d7297f83d4b","abstract_canon_sha256":"62945c7ee749b222e41866addafcc3075043bc716137458cdf27eed8a415b123"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:22.675710Z","signature_b64":"5IZygqGaiulEZ7TxPACptmbYEnZ6/eBOYHgA7aqb2F5ABrq+vmkhH6W+iLNgVldknFCIiJfjAqCmouFkrlS9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a91d013aaf00b8c4159d5d1148f877ef342585d423d33b3cb88911d22f170fbf","last_reissued_at":"2026-07-05T06:57:22.675251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:22.675251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Xinyue Shen, Yang Zhang, Zeyuan Chen","submitted_at":"2023-04-18T13:20:45Z","abstract_excerpt":"The way users acquire information is undergoing a paradigm shift with the advent of ChatGPT. Unlike conventional search engines, ChatGPT retrieves knowledge from the model itself and generates answers for users. ChatGPT's impressive question-answering (QA) capability has attracted more than 100 million users within a short period of time but has also raised concerns regarding its reliability. In this paper, we perform the first large-scale measurement of ChatGPT's reliability in the generic QA scenario with a carefully curated set of 5,695 questions across ten datasets and eight domains. We fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08979","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/2304.08979/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":"2304.08979","created_at":"2026-07-05T06:57:22.675305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08979v2","created_at":"2026-07-05T06:57:22.675305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08979","created_at":"2026-07-05T06:57:22.675305+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEOQCOVPAC4M","created_at":"2026-07-05T06:57:22.675305+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEOQCOVPAC4MIFM5","created_at":"2026-07-05T06:57:22.675305+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEOQCOVP","created_at":"2026-07-05T06:57:22.675305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.01055","citing_title":"Towards Agentic Runtime Healing","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2508.20325","citing_title":"GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2308.03825","citing_title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13064","citing_title":"Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06423","citing_title":"Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19429","citing_title":"Discerning Authorship in Online Health Communities: Experience, Trust, and Transparency Implications for Moderating AI","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54","json":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54.json","graph_json":"https://pith.science/api/pith-number/VEOQCOVPAC4MIFM5LUIUR6DX54/graph.json","events_json":"https://pith.science/api/pith-number/VEOQCOVPAC4MIFM5LUIUR6DX54/events.json","paper":"https://pith.science/paper/VEOQCOVP"},"agent_actions":{"view_html":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54","download_json":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54.json","view_paper":"https://pith.science/paper/VEOQCOVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08979&json=true","fetch_graph":"https://pith.science/api/pith-number/VEOQCOVPAC4MIFM5LUIUR6DX54/graph.json","fetch_events":"https://pith.science/api/pith-number/VEOQCOVPAC4MIFM5LUIUR6DX54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54/action/storage_attestation","attest_author":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54/action/author_attestation","sign_citation":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54/action/citation_signature","submit_replication":"https://pith.science/pith/VEOQCOVPAC4MIFM5LUIUR6DX54/action/replication_record"}},"created_at":"2026-07-05T06:57:22.675305+00:00","updated_at":"2026-07-05T06:57:22.675305+00:00"}