{"id":"W4316589304","doi":"10.7202/1095480ar","title":"(In)Stability of Test Scores","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Pasture and Agricultural Systems","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Test (biology); Statistic; Standardized test; Cohort; Psychological intervention; Achievement test; Psychology; Scale (ratio); Test score; Mathematics education; Statistics; Mathematics; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.01084946,0.0002712658,0.0004473636,0.003328144,0.0008879395,0.002097005,0.001145495,0.0005589304,0.003741714],"category_scores_gemma":[0.05682195,0.0001973024,0.0005040012,0.00386356,0.001513749,0.001239614,0.001612377,0.0007801764,0.001011061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002639468,"about_ca_system_score_gemma":0.002119662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0767436,"about_ca_topic_score_gemma":0.06706671,"domain_scores_codex":[0.9925437,0.001591393,0.001012343,0.001128755,0.003067554,0.0006562167],"domain_scores_gemma":[0.9480108,0.009426303,0.0102442,0.007309186,0.02328079,0.001728787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003678427,0.00006135291,0.8689443,0.0001119356,0.000228333,0.0001059873,0.002077105,0.001036834,0.001121777,0.004154491,0.006548029,0.115242],"study_design_scores_gemma":[0.000008146831,0.0001540943,0.9874015,0.00003020942,0.00004032483,0.0001420123,0.000720184,0.001373651,0.001350417,0.001382362,0.007375433,0.00002178465],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9040768,0.001357085,0.02763736,0.002358489,0.0004426933,0.0002394291,0.008837765,0.0008815487,0.05416876],"genre_scores_gemma":[0.9916775,0.00009509902,0.002766244,0.000171359,0.00006172445,0.00006569838,0.001693267,0.00006639279,0.003402808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0767436,"threshold_uncertainty_score":0.1525938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03150941875166875,"score_gpt":0.2813356173383293,"score_spread":0.2498261985866606,"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."}}