{"id":"W6996941080","doi":"","title":"A study of the reliability and validity of the standardized exams used in grade 10 science in a Winnipeg school division","year":2009,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Test (biology); Affect (linguistics); Statistical analysis; Quality (philosophy); Standardized test; Validity","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01052402,0.0004325851,0.0003799092,0.00234096,0.001413424,0.001165506,0.00117873,0.0002460294,0.0007420537],"category_scores_gemma":[0.04117876,0.0004574127,0.0002157214,0.002253826,0.001083779,0.0003890833,0.001052539,0.0004450094,0.0002640422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003993742,"about_ca_system_score_gemma":0.005555665,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4236651,"about_ca_topic_score_gemma":0.6517606,"domain_scores_codex":[0.9941905,0.0023889,0.0004717762,0.0006647974,0.001842682,0.0004413313],"domain_scores_gemma":[0.9693171,0.007421387,0.005751103,0.001724324,0.01427203,0.001514049],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008551899,0.00009283796,0.9740794,0.00004545363,0.000070152,0.00006382448,0.00533174,0.00007706717,0.0009238722,0.0001066938,0.0003069983,0.0188164],"study_design_scores_gemma":[0.00001218875,0.0001048172,0.9958807,0.00002655437,0.00001441441,0.00003010224,0.002283714,0.0001743387,0.0003466804,0.0000160728,0.001105435,0.000005052509],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9980855,0.000144629,0.0002975918,0.00005430021,0.00002047855,0.00009602943,0.0001057418,0.000008430653,0.001187323],"genre_scores_gemma":[0.9971442,0.0001488,0.001359446,0.00004164245,0.00000990423,0.0000818827,0.0003018397,0.000007228607,0.0009051196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.989476,"threshold_uncertainty_score":0.8423982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03187281653173227,"score_gpt":0.3007936059981488,"score_spread":0.2689207894664165,"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."}}