{"id":"W3172982719","doi":"10.1109/lra.2021.3083465","title":"Expectations Vs. Reality: Unreliability and Transparency in a Treasure Hunt Game With Icub","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"European Commission","keywords":"iCub; Transparency (behavior); Affect (linguistics); Robot; Treasure; Humanoid robot; Computer science; Human–computer interaction; Psychology; Quality (philosophy); Simulation; Artificial intelligence; Computer security; Communication; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.0001452601,0.0001101333,0.0001525201,0.00007300936,0.00007206161,0.0001686684,0.0001138302,0.00004154092,0.000002882748],"category_scores_gemma":[0.00003589801,0.0001007832,0.00002078968,0.0003313256,0.00009354203,0.0003558925,0.00001889002,0.00009868304,0.00000273878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000035101,"about_ca_system_score_gemma":0.00004851866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008344138,"about_ca_topic_score_gemma":0.0003652719,"domain_scores_codex":[0.9989541,0.00009164974,0.0002681405,0.0003384197,0.0001836775,0.0001640527],"domain_scores_gemma":[0.9994242,0.0001220586,0.0000653793,0.0002579176,0.00006816911,0.00006224539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004934375,0.0007359775,0.08451235,0.0003947455,0.0001133659,0.0003777768,0.06574573,0.6506008,0.03031926,0.06578865,0.001029499,0.1003325],"study_design_scores_gemma":[0.0004013489,0.0001114903,0.1552327,0.0001883476,0.00002742215,0.0000593656,0.0007534396,0.8280767,0.008941802,0.005561378,0.0001726668,0.0004733408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4145401,0.00006139259,0.5639381,0.02115151,0.00009032093,0.0001009164,0.000002221524,0.00007190164,0.00004345286],"genre_scores_gemma":[0.974653,0.00002555289,0.02465078,0.0006169137,0.0000201559,0.00001327288,0.000003670844,0.000005663588,0.00001098565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5601128,"threshold_uncertainty_score":0.410982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02469985435777006,"score_gpt":0.261043406057689,"score_spread":0.2363435516999189,"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."}}