{"id":"W4410713958","doi":"10.31234/osf.io/mjx2v_v2","title":"Illusions of Confidence in Artificial Systems","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; UK Research and Innovation; HORIZON EUROPE Framework Programme; Government of the United Kingdom; Canadian Institute for Advanced Research","keywords":"Illusion; Artificial intelligence; Computer science; Cognitive psychology; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009260107,0.0002619851,0.0006482494,0.0004176278,0.00004315638,0.0001612387,0.002639069,0.0002928466,0.00002795306],"category_scores_gemma":[0.0002220518,0.0002460251,0.0001527564,0.0006444866,0.0001109357,0.0001027622,0.006704261,0.000551321,0.00001686777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001513701,"about_ca_system_score_gemma":0.0007460687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003537202,"about_ca_topic_score_gemma":0.0004473668,"domain_scores_codex":[0.9970987,0.0002538457,0.0009276662,0.0009473906,0.000464473,0.0003079315],"domain_scores_gemma":[0.9970477,0.0005214886,0.0002470087,0.001806826,0.0003013191,0.0000757068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000542575,0.0003529135,0.0007953228,0.000652465,0.0000295861,0.00003186534,0.001208746,0.08078693,0.0001577571,0.8939481,0.000447571,0.02158332],"study_design_scores_gemma":[0.00009399171,0.00003343444,0.002023146,0.0004254123,0.000006993883,0.000004848357,0.00007983105,0.9016772,0.00044803,0.09456988,0.0003206222,0.0003166187],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006692736,0.0003319783,0.9745108,0.0007777094,0.004286872,0.0008189079,0.0000239771,0.0002258608,0.01233109],"genre_scores_gemma":[0.9425098,0.00002958861,0.05600837,0.00008895591,0.0001230679,0.0000849251,0.000005784293,0.000006788473,0.001142674],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9358171,"threshold_uncertainty_score":0.9999992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04108516131200808,"score_gpt":0.2953251531698814,"score_spread":0.2542399918578734,"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."}}