{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z45HVTJXRJA7G3TTM6VVTJOSRV","short_pith_number":"pith:Z45HVTJX","schema_version":"1.0","canonical_sha256":"cf3a7acd378a41f36e7367ab59a5d28d75bd25c116ce50acbb1b64ddc8aaa259","source":{"kind":"arxiv","id":"2503.23674","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models Pass the Turing Test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Benjamin K. Bergen, Cameron R. Jones","submitted_at":"2025-03-31T02:37:45Z","abstract_excerpt":"We evaluated 4 systems (ELIZA, GPT-4o, LLaMa-3.1-405B, and GPT-4.5) in two randomised, controlled, and pre-registered Turing tests on independent populations. Participants had 5 minute conversations simultaneously with another human participant and one of these systems before judging which conversational partner they thought was human. When prompted to adopt a humanlike persona, GPT-4.5 was judged to be the human 73% of the time: significantly more often than interrogators selected the real human participant. LLaMa-3.1, with the same prompt, was judged to be the human 56% of the time -- not si"},"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":"2503.23674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T02:37:45Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"b6aee95500eb6a959b42feddf5cc0d73b7cde17f3eb795f147c79292375042f6","abstract_canon_sha256":"29c5752dffc75e4e69d190b25ddff67fb42e27c2ea12caa12740717dcd862fa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:57.410513Z","signature_b64":"GLfjW4xVPgnPO54dbiu4oTQNN9WrPLlF73gy4n93uOxdIleaNjzySFs1y2ONDFpNkYte3gsjSpOHA2wkRv/JDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3a7acd378a41f36e7367ab59a5d28d75bd25c116ce50acbb1b64ddc8aaa259","last_reissued_at":"2026-07-05T10:41:57.410040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:57.410040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Pass the Turing Test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Benjamin K. Bergen, Cameron R. Jones","submitted_at":"2025-03-31T02:37:45Z","abstract_excerpt":"We evaluated 4 systems (ELIZA, GPT-4o, LLaMa-3.1-405B, and GPT-4.5) in two randomised, controlled, and pre-registered Turing tests on independent populations. Participants had 5 minute conversations simultaneously with another human participant and one of these systems before judging which conversational partner they thought was human. When prompted to adopt a humanlike persona, GPT-4.5 was judged to be the human 73% of the time: significantly more often than interrogators selected the real human participant. LLaMa-3.1, with the same prompt, was judged to be the human 56% of the time -- not si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23674","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/2503.23674/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":"2503.23674","created_at":"2026-07-05T10:41:57.410099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23674v1","created_at":"2026-07-05T10:41:57.410099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23674","created_at":"2026-07-05T10:41:57.410099+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z45HVTJXRJA7","created_at":"2026-07-05T10:41:57.410099+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z45HVTJXRJA7G3TT","created_at":"2026-07-05T10:41:57.410099+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z45HVTJX","created_at":"2026-07-05T10:41:57.410099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18591","citing_title":"Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00168","citing_title":"RealityTest: How People Probe AI Identity and Whether Models Disclose It","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29278","citing_title":"Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02121","citing_title":"What biology can, and cannot, tell us about conscious AI","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17773","citing_title":"How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03676","citing_title":"Different types of syntactic agreement recruit the same units within large language models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16280","citing_title":"Love, Lies, and Language Models: Investigating AI's Role in Romance-Baiting Scams","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11206","citing_title":"Instructions Shape Production of Language, not Processing","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11206","citing_title":"Instructions Shape Production of Language, not Processing","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10851","citing_title":"The Generalized Turing Test: A Foundation for Comparing Intelligence","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV","json":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV.json","graph_json":"https://pith.science/api/pith-number/Z45HVTJXRJA7G3TTM6VVTJOSRV/graph.json","events_json":"https://pith.science/api/pith-number/Z45HVTJXRJA7G3TTM6VVTJOSRV/events.json","paper":"https://pith.science/paper/Z45HVTJX"},"agent_actions":{"view_html":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV","download_json":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV.json","view_paper":"https://pith.science/paper/Z45HVTJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23674&json=true","fetch_graph":"https://pith.science/api/pith-number/Z45HVTJXRJA7G3TTM6VVTJOSRV/graph.json","fetch_events":"https://pith.science/api/pith-number/Z45HVTJXRJA7G3TTM6VVTJOSRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV/action/storage_attestation","attest_author":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV/action/author_attestation","sign_citation":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV/action/citation_signature","submit_replication":"https://pith.science/pith/Z45HVTJXRJA7G3TTM6VVTJOSRV/action/replication_record"}},"created_at":"2026-07-05T10:41:57.410099+00:00","updated_at":"2026-07-05T10:41:57.410099+00:00"}