{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002401089,0.0005671035,0.0006042064,0.0004054794,0.0001861471,0.0006977069,0.0008621263,0.001308057,0.008020215],"category_scores_gemma":[0.02811918,0.000174662,0.000435556,0.0001651083,0.0004526571,0.002060866,0.0009787611,0.000940631,0.002189871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001870082,"about_ca_system_score_gemma":0.0005658694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004422132,"about_ca_topic_score_gemma":0.0007840444,"domain_scores_codex":[0.9982096,0.0006811889,0.0002435576,0.0002913413,0.0004823618,0.00009187013],"domain_scores_gemma":[0.9834841,0.01062712,0.002189927,0.00167597,0.0009113426,0.001111563],"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":[0.006176629,0.01027074,0.07633064,0.005650274,0.0005515259,0.00464765,0.01143986,0.002713701,0.1346696,0.007913835,0.04516715,0.6944684],"study_design_scores_gemma":[0.007572101,0.03549835,0.3820194,0.00555545,0.002555157,0.02238227,0.04211403,0.02900611,0.1825272,0.04139667,0.2487844,0.0005887553],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9684198,0.0004814636,0.004958658,0.001350767,0.0002134071,0.0001664433,0.0005384525,0.00100233,0.02286864],"genre_scores_gemma":[0.97751,0.0003926473,0.01403432,0.0008122744,0.00004428223,0.0002495611,0.0007041286,0.0001581627,0.006094577],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008020215,"threshold_uncertainty_score":0.02683032,"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."}}