{"id":"W4410967522","doi":"10.21083/ajote.v14i1.8038","title":"Teachers’ conceptualization of validity and reliability in classroom assessment in Ghana","year":2025,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Conceptualization; Psychology; Reliability (semiconductor); Validity; Test validity; Mathematics education; Construct validity; Psychometrics; Computer science; Developmental psychology; Artificial intelligence; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04895346,0.0002911396,0.000548645,0.003544271,0.001736791,0.00420913,0.0009297388,0.001024964,0.0007446599],"category_scores_gemma":[0.08597456,0.0006409663,0.0004247042,0.002291263,0.01218168,0.003940901,0.002989811,0.001697262,0.000118793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00615342,"about_ca_system_score_gemma":0.007480078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01267599,"about_ca_topic_score_gemma":0.008978497,"domain_scores_codex":[0.957463,0.02802186,0.003188429,0.00171868,0.008163619,0.001444425],"domain_scores_gemma":[0.9003653,0.06714836,0.01152959,0.003636531,0.01559987,0.001720392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001753645,0.0002562744,0.3257219,0.001549655,0.0001215956,0.001833749,0.3984338,0.002300725,0.004287696,0.08679127,0.003819565,0.1747083],"study_design_scores_gemma":[0.00009894087,0.0006787198,0.4867685,0.007090484,0.0001431728,0.003146181,0.3316994,0.008939307,0.003182045,0.08503645,0.07293285,0.0002840084],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8777624,0.01112812,0.04319061,0.01790605,0.0002692097,0.0006341925,0.00007999292,0.000113515,0.04891581],"genre_scores_gemma":[0.9926742,0.0009166579,0.005697567,0.0002395053,0.00002019919,0.0001034978,0.00001325062,0.00001086972,0.0003242262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04895346,"threshold_uncertainty_score":0.2588937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03049116894654656,"score_gpt":0.389104163268703,"score_spread":0.3586129943221564,"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."}}