{"id":"W4391878587","doi":"10.3389/feduc.2024.1342424","title":"Teacher RePlay and Children ReAct: pilot testing a formative toolkit to support playful learning in the classroom","year":2024,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Child Development and Digital Technology","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Formative assessment; Computer science; Mathematics education; Multimedia; Human–computer interaction; Pedagogy; Psychology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0008130762,0.00006841181,0.00008164191,0.0002662422,0.0001283567,0.0001610565,0.0001461054,0.00005794544,0.00001114256],"category_scores_gemma":[0.0009680709,0.00005796034,0.00001020647,0.0006892335,0.00006042459,0.0003731552,0.00003195486,0.0002554503,0.00001291932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001932785,"about_ca_system_score_gemma":0.0003756224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005675791,"about_ca_topic_score_gemma":0.0004463283,"domain_scores_codex":[0.9992614,0.00007087934,0.0001589351,0.0001849973,0.0001341241,0.0001897122],"domain_scores_gemma":[0.9997387,0.0001069847,0.00003178048,0.00007438407,0.00001756294,0.00003057411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006734218,0.00005527735,0.5855412,0.000004625915,0.000004269661,0.000001028701,0.06271474,0.00000189284,0.00000326142,0.002245698,0.04773718,0.3016841],"study_design_scores_gemma":[0.0001716271,0.0001935605,0.7288843,0.0001486767,0.000008115311,0.00001149486,0.09426302,0.00009426167,0.00001222912,0.01778901,0.1581801,0.0002436197],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9174808,0.0002645079,0.0002038088,0.003969077,0.0005531052,0.0003596614,8.47875e-7,0.0000900642,0.07707813],"genre_scores_gemma":[0.9954739,0.00002645246,0.002175027,0.0002816173,0.0001125956,0.00004983394,0.00001613021,0.000006297974,0.001858211],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3014404,"threshold_uncertainty_score":0.2363554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01856382701695465,"score_gpt":0.2965556136560942,"score_spread":0.2779917866391396,"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."}}