{"id":"W4328129498","doi":"10.1027/1015-5759/a000748","title":"Process and Product in Computer-Based Assessments","year":2023,"lang":"en","type":"article","venue":"European Journal of Psychological Assessment","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Conflation; Conceptualization; Process (computing); Psychology; Product (mathematics); Scope (computer science); Data science; Computer science; Cognitive psychology; Epistemology; Artificial intelligence; Mathematics","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":[0.002493761,0.0002536218,0.0004499689,0.0002540062,0.00008965701,0.00005317765,0.0004243711,0.0000522447,0.0004846081],"category_scores_gemma":[0.00002438945,0.0001673321,0.0001176494,0.0007030923,0.0001733748,0.0000864861,0.00008641122,0.0006891027,0.0001620871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003408386,"about_ca_system_score_gemma":0.00001258112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001905027,"about_ca_topic_score_gemma":7.173438e-7,"domain_scores_codex":[0.9966903,0.001114436,0.0008495377,0.0005033569,0.0003874048,0.0004550061],"domain_scores_gemma":[0.9989223,0.0001373575,0.0003957947,0.0002462742,0.0001123692,0.0001858854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005460025,0.004108313,0.4447727,0.00003875588,0.0001057619,0.006577187,0.00060643,0.0002420705,0.0005662044,0.0005601385,0.015095,0.5267814],"study_design_scores_gemma":[0.002219427,0.002932169,0.9908885,0.00007047443,0.00001954934,0.0001127898,0.0002118518,0.00004199292,0.000005248519,0.0004245933,0.002865714,0.0002076642],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9795528,0.0001878456,0.001943787,0.002091983,0.001422543,0.0002374549,0.000005496279,0.00008197589,0.01447614],"genre_scores_gemma":[0.9955682,0.00004823336,0.003164551,0.0006843848,0.0003379335,0.00001276585,0.000004310164,0.0000232521,0.0001563606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5461158,"threshold_uncertainty_score":0.6823604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2567079310676423,"score_gpt":0.462275192417802,"score_spread":0.2055672613501597,"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."}}