{"id":"W4320302550","doi":"10.53841/bpsadm.2018.10.2.22","title":"Assessment in the digital age: Some challenges for Test Developers and Users","year":2018,"lang":"en","type":"article","venue":"Assessment and Development Matters","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"ASTER","funders":"","keywords":"Key (lock); Test (biology); Psychometrics; Computer science; Data science; Psychometric testing; Engineering ethics; Psychology; Applied psychology; Engineering; Clinical psychology; Computer security","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1308294,0.0006193836,0.001073321,0.001995906,0.005209227,0.01494619,0.003705686,0.01082972,0.009276546],"category_scores_gemma":[0.2400442,0.0006669873,0.0007704265,0.001829928,0.01443,0.024095,0.01437023,0.01573755,0.005310631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003084805,"about_ca_system_score_gemma":0.01219746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003088191,"about_ca_topic_score_gemma":0.005646418,"domain_scores_codex":[0.925756,0.05003898,0.00504027,0.002328443,0.01468149,0.002154808],"domain_scores_gemma":[0.6471632,0.2676624,0.007438462,0.01492539,0.03850804,0.02430251],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001336555,0.0003458302,0.01140664,0.001938649,0.0000466942,0.001413297,0.05372254,0.0007658447,0.00128566,0.1327989,0.1754751,0.6206672],"study_design_scores_gemma":[0.00007214522,0.0002742854,0.007203687,0.007354747,0.00004849027,0.005519757,0.1230028,0.002273579,0.0009636533,0.353502,0.4995387,0.000246079],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.004903088,0.009414121,0.02221185,0.9545563,0.001524342,0.00005684807,0.00003896424,0.0002003607,0.007094106],"genre_scores_gemma":[0.3205566,0.04053213,0.1992927,0.4122722,0.009824168,0.0009288472,0.0002461679,0.0005908697,0.01575639],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.8691705,"threshold_uncertainty_score":0.6919004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4041266623758634,"score_gpt":0.4711374105617989,"score_spread":0.06701074818593555,"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."}}