{"id":"W2555293682","doi":"10.5539/hes.v6n4p181","title":"Students’ and Teacher’s Experiences of the Validity and Reliability of Assessment in a Bioscience Course","year":2016,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Reliability (semiconductor); Recall; Validity; Perception; Mathematics education; Alternative assessment; Quality (philosophy); Medical education; Test validity; Psychometrics; Developmental psychology; Medicine; Cognitive psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009358856,0.00006219101,0.0001451328,0.00002976365,0.0001634376,0.0000162729,0.000192956,0.00002535485,0.00004555521],"category_scores_gemma":[0.00008348546,0.00003359353,0.00001904366,0.0002195996,0.001331917,0.0001567796,0.0001416773,0.00003472262,2.577932e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006337015,"about_ca_system_score_gemma":0.0001949983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002037175,"about_ca_topic_score_gemma":0.00008947105,"domain_scores_codex":[0.9989148,0.0002068336,0.0001934992,0.0001717811,0.0004061407,0.0001069312],"domain_scores_gemma":[0.9993169,0.0002371423,0.0001414909,0.0001252184,0.0001513913,0.00002780938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002153966,0.0002559887,0.9468699,0.000009593054,0.000005035339,1.459e-8,0.04994541,1.830086e-8,0.0001026032,0.002274303,0.0003099818,0.0002249935],"study_design_scores_gemma":[0.0001117735,0.00001961967,0.8180026,0.00004582891,0.000008663002,2.714805e-8,0.1801967,6.273946e-8,0.00004996267,0.0005865112,0.0009401964,0.00003800492],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994041,0.0005388311,0.00000121975,0.003197066,0.00070034,0.0001925025,8.114403e-7,0.000005190528,0.001323095],"genre_scores_gemma":[0.997144,0.0007401257,0.000112224,0.00002887092,0.00003880851,0.00006000092,4.163026e-8,0.000001638943,0.001874219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1302513,"threshold_uncertainty_score":0.4907502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09076394953386803,"score_gpt":0.4697572589009536,"score_spread":0.3789933093670856,"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."}}