{"id":"W4387184490","doi":"10.31234/osf.io/mjx2v","title":"Illusions of Confidence in Artificial Systems","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Leverhulme Trust; UK Research and Innovation; Wellcome Trust; Canadian Institute for Advanced Research","keywords":"Metacognition; Illusion; Psychology; Perception; Low Confidence; Attribution; Cognitive psychology; Cognition; Self-confidence; Social psychology; Artificial intelligence; Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00439448,0.0003625818,0.0002746654,0.0009934419,0.0006557492,0.002991866,0.0006231163,0.001228307,0.001654233],"category_scores_gemma":[0.05162062,0.0003843468,0.0002945311,0.0004304182,0.006519169,0.004506245,0.004415652,0.002055126,0.000127537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000897433,"about_ca_system_score_gemma":0.0003135181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008105661,"about_ca_topic_score_gemma":0.0003736114,"domain_scores_codex":[0.9950495,0.002239246,0.0003414497,0.000617715,0.001463355,0.0002885323],"domain_scores_gemma":[0.9578391,0.0255881,0.007027207,0.006287639,0.002034582,0.001223393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002108718,0.0003350262,0.1925869,0.001322624,0.0004267157,0.001830485,0.1359515,0.02313117,0.1495264,0.2976801,0.002137839,0.1929624],"study_design_scores_gemma":[0.0001408748,0.0009772469,0.2872497,0.0004804958,0.0001742682,0.003250699,0.01696918,0.07003091,0.03774978,0.5639291,0.01848308,0.0005647048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.952009,0.0005723389,0.03091859,0.001104745,0.00002722631,0.00002659645,0.00005103064,0.0001655758,0.0151249],"genre_scores_gemma":[0.9979665,0.00004560138,0.001738394,0.00006708111,0.000005571217,0.000007754086,0.00001155834,0.0000106943,0.0001467545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00439448,"threshold_uncertainty_score":0.02324057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1289611583689716,"score_gpt":0.3816784506817267,"score_spread":0.2527172923127551,"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."}}