{"id":"W4315850919","doi":"10.53841/bpsadm.2017.9.1.25","title":"Can combining assessments improve test fairness and enhance user experience?","year":2017,"lang":"en","type":"article","venue":"Assessment and Development Matters","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Association of Physicists","funders":"","keywords":"Test (biology); Computer science; Reliability engineering; Psychology; Process management; Business; Engineering; Geology","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":[0.05142531,0.001129715,0.001693778,0.002140025,0.001181532,0.005690786,0.00186294,0.002172316,0.005764836],"category_scores_gemma":[0.2709203,0.0008950265,0.001085217,0.0012472,0.001134209,0.008581338,0.005166599,0.00170986,0.001679517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007963185,"about_ca_system_score_gemma":0.002107784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001104753,"about_ca_topic_score_gemma":0.002030297,"domain_scores_codex":[0.952604,0.02977157,0.003241767,0.003553668,0.009462602,0.001366414],"domain_scores_gemma":[0.7240046,0.1894349,0.01584145,0.0341816,0.03055488,0.005982714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003929975,0.002601953,0.1715867,0.0005742702,0.0005970793,0.00009092854,0.003662697,0.002200129,0.01724415,0.003733651,0.002826059,0.7909523],"study_design_scores_gemma":[0.001577746,0.01581623,0.7222164,0.001369333,0.002378806,0.001871393,0.007907448,0.07739194,0.05689342,0.08747916,0.02409057,0.0010075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6823099,0.002096482,0.2787859,0.005051838,0.001015544,0.0007518349,0.0002331276,0.002676661,0.02707873],"genre_scores_gemma":[0.9106774,0.000268992,0.08544931,0.0008974366,0.0002660098,0.0002661905,0.0000997458,0.0001961046,0.001878871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05142531,"threshold_uncertainty_score":0.2719663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03281881503818991,"score_gpt":0.4140897758775974,"score_spread":0.3812709608394075,"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."}}