{"id":"W4292772413","doi":"10.3102/1443120","title":"Large-Scale Assessment in Mathematics: The Relationship Between Teachers' Views and Classroom Practice","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Mathematics education; Computer science; Mathematics; Geography","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":[0.005514716,0.0001279526,0.0002363553,0.00005534241,0.0004288817,0.0001495424,0.0005233316,0.0001079599,0.00001968008],"category_scores_gemma":[0.001599268,0.00008222744,0.00006783188,0.0003696234,0.0001506376,0.0007435285,0.0002667186,0.0004582177,0.00002356988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009209698,"about_ca_system_score_gemma":0.00006696091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002289784,"about_ca_topic_score_gemma":0.0001112678,"domain_scores_codex":[0.9983355,0.00009896897,0.0003942552,0.0002221949,0.0006211855,0.0003279392],"domain_scores_gemma":[0.9976606,0.001505328,0.0004813918,0.0001096493,0.0001971059,0.00004594566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003743269,0.00005052325,0.8608474,0.00002955544,0.00001344983,3.02536e-8,0.1216748,6.665319e-7,0.0001249554,0.0160676,0.00109961,0.00008766546],"study_design_scores_gemma":[0.0003874661,0.00003298416,0.6345562,0.000248541,0.00006052099,5.445266e-7,0.3479769,0.00003728933,0.00003130217,0.004187621,0.01234097,0.000139647],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8710303,0.000130553,0.000004478986,0.008308626,0.0001390458,0.0006997657,0.000005506071,0.00002265003,0.1196591],"genre_scores_gemma":[0.9928727,0.00003370388,0.002869702,0.0001050751,0.0001841653,0.00001681581,8.305278e-7,0.00001392691,0.003903106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2263021,"threshold_uncertainty_score":0.3353138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03136347923416086,"score_gpt":0.354898228618803,"score_spread":0.3235347493846421,"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."}}