{"id":"W4404172818","doi":"10.1145/3686912","title":"Evaluating What Others Say: The Effect of Accuracy Assessment in Shaping Mental Models of AI Systems","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Psychology; Mental model; Artificial intelligence; Cognitive psychology; Computer science; Machine learning; Cognitive science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01756616,0.001103348,0.000494599,0.0008086768,0.001295036,0.004630762,0.0009148027,0.001647426,0.001988185],"category_scores_gemma":[0.2063785,0.0007258768,0.0009432853,0.0002962222,0.002823209,0.004701519,0.00305296,0.001990468,0.0004707862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001317699,"about_ca_system_score_gemma":0.0009480891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002644656,"about_ca_topic_score_gemma":0.002344144,"domain_scores_codex":[0.9808608,0.01304876,0.0009060735,0.001612583,0.002918886,0.0006529079],"domain_scores_gemma":[0.7259451,0.2287199,0.01746197,0.01571779,0.009148405,0.003006752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.007297334,0.002584119,0.3721719,0.001534187,0.0007617344,0.0009490385,0.2669924,0.01321392,0.08917058,0.005580267,0.002006239,0.2377384],"study_design_scores_gemma":[0.000596504,0.009886196,0.742,0.001098439,0.001528093,0.001001813,0.08819176,0.06975145,0.04912408,0.02283279,0.01282063,0.001168362],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893582,0.00007504276,0.006401095,0.0003061019,0.00002812939,0.0001091916,0.00002266617,0.0001248991,0.003574667],"genre_scores_gemma":[0.9936852,0.0000414537,0.00567841,0.0000978242,0.000009013806,0.00007374615,0.00003639457,0.0000405248,0.0003374758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01756616,"threshold_uncertainty_score":0.09289986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1326140698810932,"score_gpt":0.4322873931486458,"score_spread":0.2996733232675526,"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."}}