{"id":"W2026485182","doi":"10.1109/tciaig.2013.2275162","title":"Passing a Hide-and-Seek Third-Person Turing Test","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Intelligence and AI in Games","topic":"Social Robot Interaction and HRI","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Turing test; Computer science; Turing; Test (biology); Artificial intelligence; Human–computer interaction","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007548487,0.0001390972,0.0001472669,0.000210118,0.0001661928,0.0001175507,0.00006405794,0.00008734019,0.0009666357],"category_scores_gemma":[0.0000115923,0.0001382533,0.0000521437,0.0001692093,0.0001181179,0.0002388506,0.000001051589,0.0003348993,0.0003285355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000381875,"about_ca_system_score_gemma":0.00002102167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005320713,"about_ca_topic_score_gemma":0.00006591504,"domain_scores_codex":[0.9991121,0.00005075928,0.0002391996,0.0002802762,0.0001291824,0.0001884783],"domain_scores_gemma":[0.9989502,0.0007805347,0.00005030941,0.00007223524,0.00007042698,0.00007623107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008289253,0.000807601,0.002723151,0.00003829686,0.0001254974,0.00002275791,0.01838852,0.07536145,0.0004730253,0.006115946,0.002034734,0.8938261],"study_design_scores_gemma":[0.002509283,0.001792456,0.3700609,0.001266376,0.0001710901,0.0006599858,0.08113655,0.4329397,0.009995207,0.09142762,0.005259823,0.002781029],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1976552,0.00024362,0.7900381,0.005838705,0.001239827,0.0003478374,0.00001006157,0.0001230998,0.004503528],"genre_scores_gemma":[0.9959446,0.00004528743,0.001058687,0.001589223,0.00005518412,0.00007511862,0.000001797278,0.00001351523,0.001216621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8910451,"threshold_uncertainty_score":0.9999466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05074143744200125,"score_gpt":0.3411247877602143,"score_spread":0.2903833503182131,"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."}}