{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002182036,0.0001291553,0.000383692,0.0002092626,0.0004440154,0.00002585522,0.001035518,0.0001313148,0.000008419779],"category_scores_gemma":[0.0003767881,0.0001078304,0.00009878541,0.001429188,0.0006624866,0.000271551,0.0002156821,0.0002788189,4.908751e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003072015,"about_ca_system_score_gemma":0.0005103564,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0252908,"about_ca_topic_score_gemma":0.8224928,"domain_scores_codex":[0.9973727,0.0005960143,0.0001843659,0.0003245536,0.001322927,0.0001994482],"domain_scores_gemma":[0.9987929,0.00015162,0.0004422096,0.0003748554,0.0001919089,0.00004646271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001031442,0.0004436897,0.9752337,0.00003422903,0.000006973583,0.000001299898,0.02345803,0.00001721175,0.0003754963,0.00006317834,0.0000539744,0.0002090198],"study_design_scores_gemma":[0.0009284423,0.00009362648,0.7294658,0.0001376403,0.00003274459,1.850038e-8,0.2689978,0.0000101224,0.00007324173,0.0001486432,0.00003974334,0.00007214502],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961154,0.00001828156,0.000001219236,0.0003122702,0.0001937912,0.001071865,0.000007018987,0.000007034692,0.002273159],"genre_scores_gemma":[0.9994767,0.00004155082,0.00002914192,0.000002275912,0.000008266131,4.74642e-7,0.00000161194,0.000003843201,0.000436094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7972019,"threshold_uncertainty_score":0.9811999,"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."}}