{"id":"W3214288572","doi":"10.1080/13546783.2021.1999327","title":"Investigating lay evaluations of models","year":2021,"lang":"en","type":"article","venue":"Thinking & Reasoning","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Overfitting; Distrust; Computer science; Cognitive psychology; Mean squared prediction error; Mean squared error; Machine learning; Psychology; Function (biology); Econometrics; Artificial intelligence; Statistics; Mathematics; Artificial neural network","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":[0.0005838064,0.00006899513,0.0001180623,0.00005757823,0.00016234,0.000161031,0.0004076397,0.00003103754,0.00001759588],"category_scores_gemma":[0.0004834864,0.00007195575,0.00004038222,0.0005848592,0.00002699481,0.0005317879,0.0002639987,0.00008764171,0.000008141436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001889261,"about_ca_system_score_gemma":0.000178659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001791462,"about_ca_topic_score_gemma":0.000004749338,"domain_scores_codex":[0.998968,0.00009257466,0.0002179029,0.0002047571,0.0003812473,0.0001355375],"domain_scores_gemma":[0.9990898,0.0000958396,0.0001315798,0.0003914775,0.0002380896,0.00005320944],"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":[8.992281e-8,0.0000183356,0.0007969069,0.00001339532,0.000013451,0.000003178543,0.003330876,0.01600434,0.001140509,0.9729455,0.0001870296,0.005546441],"study_design_scores_gemma":[0.0001050839,0.000006490397,0.000307276,0.0002127919,0.00001085027,0.000008649389,0.0001226831,0.9072813,0.004245518,0.08744026,0.0001731363,0.00008600525],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01488647,0.0001671275,0.9766073,0.0003148612,0.000101363,0.00003014799,0.000002452597,0.000125037,0.0077652],"genre_scores_gemma":[0.6171392,0.00001296242,0.3819917,0.0005237221,0.00003092568,0.000001647101,0.00002525151,0.000007608964,0.0002669837],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8912769,"threshold_uncertainty_score":0.2934271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05356244137974382,"score_gpt":0.3362210250929328,"score_spread":0.282658583713189,"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."}}