{"id":"W4393988025","doi":"10.20944/preprints202404.0359.v1","title":"A 'Turing Test' for Self-Awareness","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Cognitive Science and Education Research","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Test (biology); Turing; Turing test; Computer science; Psychology; Artificial intelligence; Programming language; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001099374,0.0003193806,0.0002965615,0.0003733402,0.0003069369,0.0001958983,0.001268514,0.0002135085,0.000708674],"category_scores_gemma":[0.005088096,0.0003102197,0.0002549514,0.0004846137,0.00016504,0.0001139246,0.004136702,0.001059318,0.005333706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002111026,"about_ca_system_score_gemma":0.00126331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006815248,"about_ca_topic_score_gemma":0.00000778617,"domain_scores_codex":[0.9962775,0.000114408,0.0003875126,0.001925141,0.0006265141,0.0006689493],"domain_scores_gemma":[0.9972849,0.001077245,0.0001292081,0.001011959,0.0002610772,0.0002355667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008309559,0.001358975,0.3187055,0.004567157,0.00007633938,0.00008269414,0.009442193,0.0002738836,0.6526458,0.003231481,0.001674096,0.007858722],"study_design_scores_gemma":[0.000212079,0.00002931386,0.04166713,0.0003706625,0.00006056204,0.00001624316,0.0002307279,0.002356261,0.9091429,0.03195656,0.01339953,0.0005580399],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760494,0.00006112592,0.0001171192,0.002390339,0.002209636,0.001484132,0.0001113957,0.0005209541,0.01705596],"genre_scores_gemma":[0.9899942,0.0001240993,0.0001485694,0.0003710809,0.0004705657,0.001380318,0.0000103379,0.00005245233,0.00744834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2770384,"threshold_uncertainty_score":0.999935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3558458261368965,"score_gpt":0.4744927798536631,"score_spread":0.1186469537167666,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}