{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002136004,0.0002178961,0.0003365179,0.0003035602,0.0001328663,0.0006349299,0.002442128,0.00006325183,0.000005891239],"category_scores_gemma":[0.0001825802,0.0001381242,0.0001895037,0.0005586843,0.00007665035,0.003467344,0.0009668872,0.0004779746,0.000004377076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002982645,"about_ca_system_score_gemma":0.00004259783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002390854,"about_ca_topic_score_gemma":0.00000554745,"domain_scores_codex":[0.9977428,0.0001085204,0.0007667209,0.0004478691,0.0006897271,0.000244402],"domain_scores_gemma":[0.9977987,0.0008414248,0.0005387489,0.0005635907,0.0002305417,0.00002701217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001872849,0.000305041,0.0009719468,0.002342351,0.0003581931,0.000002976333,0.03721262,0.1755832,0.4544742,0.1520501,0.001445333,0.1750668],"study_design_scores_gemma":[0.0001133987,0.0005712928,0.0001231984,0.003023973,0.00001752874,0.0000100982,0.0008912722,0.7833471,0.2049991,0.006770514,0.00003003887,0.0001023784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819643,0.0002206772,0.0119069,0.00202249,0.002354128,0.0009985348,0.000001152876,0.00007227122,0.000459519],"genre_scores_gemma":[0.9979181,0.00001714286,0.001735664,0.00009987785,0.0001212465,0.0000629186,5.788561e-7,0.00001937804,0.00002505946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6077639,"threshold_uncertainty_score":0.6122644,"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."}}