{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.21844", "kind": "paper", "url": "https://arxiv.org/abs/2606.21844"}], "authors": ["William Hager", "Ishika Rathi", "Masum Hasan", "Cameron Jones"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.21844", "source_url": "https://arxiv.org/abs/2606.21844"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "The benchmark evaluates language models on distinguishing human-only vs. human-AI multi-turn dialogues, using paired transcripts and accuracy as the metric."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.21844", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.21844", "title": "Inverse Turing Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.21844", "modality": null, "name": "Inverse Turing Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_inverse-turing-bench_7691d060", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a5b52661d4b24b77ed78ee5365da1d3db1535a3232fe46bf16fe5034ff67a3a8", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.21844"}, "publisher": null, "released": "2026-06-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.21844", "source_url": "https://arxiv.org/abs/2606.21844"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-21844", "source": "claire_radar", "source_benchmark_id": "2606.21844", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.21844", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "9b22c4ab48773d9c9bf76944e2a21876b67978012142db356ca68d7dc5fb4507", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "The benchmark evaluates language models on distinguishing human-only vs. human-AI multi-turn dialogues, using paired transcripts and accuracy as the metric.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "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."}, "familyId": "bmf_3c53c6fe0c9e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_inverse-turing-bench_7691d060", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.21844", "paper": "https://arxiv.org/abs/2606.21844", "pdf": "https://arxiv.org/pdf/2606.21844", "project": null, "report": "https://arxiv.org/abs/2606.21844"}, "metrics": [], "motivation": "As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important.", "name": "Inverse Turing Bench", "oneLine": "The benchmark evaluates language models on distinguishing human-only vs. human-AI multi-turn dialogues, using paired transcripts and accuracy as the metric.", "paperTitle": "Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.21844", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-20", "source": {"authors": ["William Hager", "Ishika Rathi", "Masum Hasan", "Cameron Jones"], "categories": ["cs.CL", "cs.CY"], "id": "2606.21844", "title": "Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue", "type": "arxiv", "url": "https://arxiv.org/abs/2606.21844"}, "sourceUpdatedAt": "2026-06-20T02:47:56Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It addresses the practical need for reliable human-AI differentiation in online spaces, with implications for trust and safety. The benchmark may help compare detection approaches, though its current form primarily supports the paper's findings."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
