{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EA5GSJCOL6JPY4DQCLMLXAX7BX","short_pith_number":"pith:EA5GSJCO","schema_version":"1.0","canonical_sha256":"203a69244e5f92fc707012d8bb82ff0dc2d7fae1911e1002a1606f208822b43e","source":{"kind":"arxiv","id":"2606.21844","version":1},"attestation_state":"computed","paper":{"title":"Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Cameron Jones, Ishika Rathi, Masum Hasan, William Hager","submitted_at":"2026-06-20T02:47:56Z","abstract_excerpt":"As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing Bench, a benchmark that evaluates LLMs and other models on their ability to differentiate humans and AI in multi-turn text. The benchmark provides a collection of paired dialogue transcripts, wherein one dialogue is between two humans and the other is between a human and an AI. The task is to correctly identify which dialogue is human-only vs. human-AI. We evaluated a preliminary set of models against this benchmark, and found that GPTZero, Claude O"},"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":"2606.21844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T02:47:56Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"4db815f5fe295e25e7c0b74ad67417d75a8a6e457b423ac76a9931758c01a503","abstract_canon_sha256":"a0b6d6418e5bd49677ede45f36c83630d59b8af5db308011170357bccf52bb14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:00.622622Z","signature_b64":"jMnUlgJ4sguPnI8iPxC7S93Kh6n3W1hoT1PiAAu88zBH14Q2gXRhSdGeCmjh/6H52tSKgokrCN4RpIpxpFbsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"203a69244e5f92fc707012d8bb82ff0dc2d7fae1911e1002a1606f208822b43e","last_reissued_at":"2026-06-23T02:13:00.622201Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:00.622201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Cameron Jones, Ishika Rathi, Masum Hasan, William Hager","submitted_at":"2026-06-20T02:47:56Z","abstract_excerpt":"As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing Bench, a benchmark that evaluates LLMs and other models on their ability to differentiate humans and AI in multi-turn text. The benchmark provides a collection of paired dialogue transcripts, wherein one dialogue is between two humans and the other is between a human and an AI. The task is to correctly identify which dialogue is human-only vs. human-AI. We evaluated a preliminary set of models against this benchmark, and found that GPTZero, Claude O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21844","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/2606.21844/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":"2606.21844","created_at":"2026-06-23T02:13:00.622256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21844v1","created_at":"2026-06-23T02:13:00.622256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21844","created_at":"2026-06-23T02:13:00.622256+00:00"},{"alias_kind":"pith_short_12","alias_value":"EA5GSJCOL6JP","created_at":"2026-06-23T02:13:00.622256+00:00"},{"alias_kind":"pith_short_16","alias_value":"EA5GSJCOL6JPY4DQ","created_at":"2026-06-23T02:13:00.622256+00:00"},{"alias_kind":"pith_short_8","alias_value":"EA5GSJCO","created_at":"2026-06-23T02:13:00.622256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX","json":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX.json","graph_json":"https://pith.science/api/pith-number/EA5GSJCOL6JPY4DQCLMLXAX7BX/graph.json","events_json":"https://pith.science/api/pith-number/EA5GSJCOL6JPY4DQCLMLXAX7BX/events.json","paper":"https://pith.science/paper/EA5GSJCO"},"agent_actions":{"view_html":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX","download_json":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX.json","view_paper":"https://pith.science/paper/EA5GSJCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21844&json=true","fetch_graph":"https://pith.science/api/pith-number/EA5GSJCOL6JPY4DQCLMLXAX7BX/graph.json","fetch_events":"https://pith.science/api/pith-number/EA5GSJCOL6JPY4DQCLMLXAX7BX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX/action/storage_attestation","attest_author":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX/action/author_attestation","sign_citation":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX/action/citation_signature","submit_replication":"https://pith.science/pith/EA5GSJCOL6JPY4DQCLMLXAX7BX/action/replication_record"}},"created_at":"2026-06-23T02:13:00.622256+00:00","updated_at":"2026-06-23T02:13:00.622256+00:00"}