{"id":"W1729977867","doi":"","title":"Beyond the Scores: Using Candidate Responses on High Stakes Performance Assessment to Inform Teacher Preparation for English Learners.","year":2009,"lang":"en","type":"article","venue":"University of Washington Tacoma Digital Commons (University of Washington Tacoma)","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pedagogy; Psychology; Mathematics education; Variety (cybernetics); Teacher education; Sociology; Teacher preparation; Quarter (Canadian coin); History; Archaeology; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.008462111,0.0003202824,0.0002454748,0.00155186,0.000510563,0.001352075,0.0005269311,0.0006342352,0.001857667],"category_scores_gemma":[0.04434007,0.0001891537,0.0001778603,0.0009671578,0.0003972601,0.001889805,0.001074139,0.0009130895,0.001526343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004317241,"about_ca_system_score_gemma":0.001169328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004730863,"about_ca_topic_score_gemma":0.01509138,"domain_scores_codex":[0.9952611,0.003304896,0.0002842891,0.0002578211,0.0006899565,0.0002020279],"domain_scores_gemma":[0.9807615,0.01012763,0.003590928,0.0008796151,0.003269003,0.001371368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0006203281,0.0009186303,0.7651339,0.0001361965,0.00005925941,0.0002168144,0.01138622,0.0002913312,0.002055494,0.0009002562,0.008104728,0.2101769],"study_design_scores_gemma":[0.00008133081,0.001408494,0.9533917,0.0002557108,0.00006722869,0.0001678925,0.02407883,0.003484095,0.003785248,0.002640235,0.01055979,0.00007953238],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9773558,0.0001658593,0.004441706,0.001086316,0.00008314502,0.000250527,0.0006792188,0.00009305488,0.01584424],"genre_scores_gemma":[0.9898308,0.0001607414,0.00549345,0.0001848372,0.00001732527,0.0004997603,0.0004465102,0.00001566501,0.0033509],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008462111,"threshold_uncertainty_score":0.04475248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03961253567595996,"score_gpt":0.3355352411582134,"score_spread":0.2959227054822534,"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."}}