{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EK6A6VQCQQRRAIXFGSYUJ4EHK5","short_pith_number":"pith:EK6A6VQC","schema_version":"1.0","canonical_sha256":"22bc0f560284231022e534b144f0875752dfe9f1f7c2aef2fdc8213902834a3a","source":{"kind":"arxiv","id":"2405.08007","version":1},"attestation_state":"computed","paper":{"title":"People cannot distinguish GPT-4 from a human in a Turing test","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Benjamin K. Bergen, Cameron R. Jones","submitted_at":"2024-05-09T04:14:09Z","abstract_excerpt":"We evaluated 3 systems (ELIZA, GPT-3.5 and GPT-4) in a randomized, controlled, and preregistered Turing test. Human participants had a 5 minute conversation with either a human or an AI, and judged whether or not they thought their interlocutor was human. GPT-4 was judged to be a human 54% of the time, outperforming ELIZA (22%) but lagging behind actual humans (67%). The results provide the first robust empirical demonstration that any artificial system passes an interactive 2-player Turing test. The results have implications for debates around machine intelligence and, more urgently, suggest "},"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":"2405.08007","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-09T04:14:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23b2e4eac5e4c349a6511ff4ebebd6bf43b0e747ed468de348c4cb589d736519","abstract_canon_sha256":"cde15a32e4436c929934e8bf1e20a032f2a2f4e53b0585333c5f9d7c5dc7bdb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:53.916535Z","signature_b64":"APfe9OuuDECNAjKVvFvOOM+gKtJIY2hgUD4VxTypr0ZKULRDdD/8SirjgwQXlGiR/4XtHxD0Ty4gDNRPbbtGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22bc0f560284231022e534b144f0875752dfe9f1f7c2aef2fdc8213902834a3a","last_reissued_at":"2026-07-05T08:18:53.916061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:53.916061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"People cannot distinguish GPT-4 from a human in a Turing test","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Benjamin K. Bergen, Cameron R. Jones","submitted_at":"2024-05-09T04:14:09Z","abstract_excerpt":"We evaluated 3 systems (ELIZA, GPT-3.5 and GPT-4) in a randomized, controlled, and preregistered Turing test. Human participants had a 5 minute conversation with either a human or an AI, and judged whether or not they thought their interlocutor was human. GPT-4 was judged to be a human 54% of the time, outperforming ELIZA (22%) but lagging behind actual humans (67%). The results provide the first robust empirical demonstration that any artificial system passes an interactive 2-player Turing test. The results have implications for debates around machine intelligence and, more urgently, suggest "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08007","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/2405.08007/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":"2405.08007","created_at":"2026-07-05T08:18:53.916131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08007v1","created_at":"2026-07-05T08:18:53.916131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08007","created_at":"2026-07-05T08:18:53.916131+00:00"},{"alias_kind":"pith_short_12","alias_value":"EK6A6VQCQQRR","created_at":"2026-07-05T08:18:53.916131+00:00"},{"alias_kind":"pith_short_16","alias_value":"EK6A6VQCQQRRAIXF","created_at":"2026-07-05T08:18:53.916131+00:00"},{"alias_kind":"pith_short_8","alias_value":"EK6A6VQC","created_at":"2026-07-05T08:18:53.916131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.16280","citing_title":"Love, Lies, and Language Models: Investigating AI's Role in Romance-Baiting Scams","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5","json":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5.json","graph_json":"https://pith.science/api/pith-number/EK6A6VQCQQRRAIXFGSYUJ4EHK5/graph.json","events_json":"https://pith.science/api/pith-number/EK6A6VQCQQRRAIXFGSYUJ4EHK5/events.json","paper":"https://pith.science/paper/EK6A6VQC"},"agent_actions":{"view_html":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5","download_json":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5.json","view_paper":"https://pith.science/paper/EK6A6VQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08007&json=true","fetch_graph":"https://pith.science/api/pith-number/EK6A6VQCQQRRAIXFGSYUJ4EHK5/graph.json","fetch_events":"https://pith.science/api/pith-number/EK6A6VQCQQRRAIXFGSYUJ4EHK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5/action/storage_attestation","attest_author":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5/action/author_attestation","sign_citation":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5/action/citation_signature","submit_replication":"https://pith.science/pith/EK6A6VQCQQRRAIXFGSYUJ4EHK5/action/replication_record"}},"created_at":"2026-07-05T08:18:53.916131+00:00","updated_at":"2026-07-05T08:18:53.916131+00:00"}