{"id":"W2898858791","doi":"10.1016/j.learninstruc.2018.10.002","title":"Response sentences, examples, and authenticity do not help children solve real wor(l)d problems","year":2018,"lang":"en","type":"article","venue":"Learning and Instruction","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Variety (cybernetics); Replicate; Word (group theory); Sentence; Computer science; Intervention (counseling); Psychological intervention; Sample (material); Psychology; Cognitive psychology; Mathematics education; Artificial intelligence; Linguistics; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005738837,0.0001447895,0.0001855323,0.00007295956,0.0003523625,0.00009909301,0.00004408036,0.00007976648,0.00009990476],"category_scores_gemma":[0.0006144439,0.0001209426,0.0000268459,0.0001096781,0.0002432262,0.0001443938,0.00009469043,0.0001920781,0.00002445345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002592642,"about_ca_system_score_gemma":0.0000159666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007133014,"about_ca_topic_score_gemma":0.00001644182,"domain_scores_codex":[0.9989824,0.0001033139,0.0002275097,0.0002888197,0.0001933612,0.0002045425],"domain_scores_gemma":[0.9993964,0.0002430244,0.0001141407,0.00008072562,0.000076249,0.00008949098],"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":[0.002052979,0.000439227,0.1646045,0.0004907119,0.0003549843,0.0000138211,0.02249907,0.000001140232,0.0171149,0.05166955,0.0009756795,0.7397835],"study_design_scores_gemma":[0.004276273,0.001857724,0.6165089,0.001557968,0.0001719942,0.0009503774,0.006205073,0.0007660509,0.01485825,0.3460859,0.005430021,0.001331494],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962346,0.00003479898,0.001267876,0.0001400981,0.00007887346,0.0001889311,0.000002884805,0.000111067,0.001940869],"genre_scores_gemma":[0.988811,0.0001128817,0.01013352,0.00003387819,0.0001297714,0.000008215314,0.000005284388,0.00001629158,0.0007491975],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.738452,"threshold_uncertainty_score":0.4931896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0245611300618863,"score_gpt":0.2768522740337336,"score_spread":0.2522911439718473,"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."}}