{"id":"W2923174012","doi":"","title":"Assessing teachers’ interpretation of Canadian large scale assessment results: An innovative approach to piloting a questionnaire","year":2019,"lang":"en","type":"article","venue":"2019 Conference of the Canadian Society for the Study of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue; University of Ottawa","funders":"","keywords":"Cognitive dissonance; Psychology; Perception; Interpretation (philosophy); Scale (ratio); Cognition; Social psychology; Presentation (obstetrics); Applied psychology; Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.0541229,0.000648864,0.0004805374,0.00321578,0.004266664,0.003087973,0.001520771,0.0006794665,0.003606318],"category_scores_gemma":[0.1022883,0.0006390532,0.0005092926,0.002182559,0.002924768,0.001415671,0.002635781,0.002117113,0.000840398],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01981468,"about_ca_system_score_gemma":0.05351921,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5130775,"about_ca_topic_score_gemma":0.6800222,"domain_scores_codex":[0.9697212,0.01397236,0.00414237,0.001272861,0.009181397,0.001709807],"domain_scores_gemma":[0.8742912,0.03862932,0.003959888,0.007634241,0.0702594,0.00522595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000616315,0.001812755,0.1363893,0.00163533,0.00008155979,0.001315732,0.3824914,0.002605865,0.03402123,0.004866931,0.02663883,0.4075247],"study_design_scores_gemma":[0.0004970353,0.002940199,0.4255939,0.001026094,0.0001361686,0.0006122881,0.2584639,0.0139541,0.02710957,0.003400606,0.2652802,0.0009860407],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8694645,0.0002689282,0.06616499,0.004261517,0.0004189959,0.01711232,0.001283959,0.000951573,0.04007323],"genre_scores_gemma":[0.8834001,0.0004111509,0.09864073,0.0007254162,0.00005692427,0.007034922,0.0004431164,0.0001659452,0.009121634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9801853,"threshold_uncertainty_score":0.9795802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1451326791833945,"score_gpt":0.4531347117191755,"score_spread":0.308002032535781,"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."}}