{"id":"W2921727697","doi":"10.1038/s41539-019-0040-6","title":"DIY productive failure: boosting performance in a large undergraduate biology course","year":2019,"lang":"en","type":"article","venue":"npj Science of Learning","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"University of British Columbia","keywords":"Mathematics education; Context (archaeology); Boosting (machine learning); Computer science; Process (computing); Psychology; Artificial intelligence; Programming language","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":[0.01413742,0.000100912,0.0002087661,0.00028696,0.0006662838,0.00005887679,0.0005647386,0.00006317333,0.00004066283],"category_scores_gemma":[0.004187968,0.0000959063,0.00002603922,0.002416871,0.001136337,0.001177193,0.0001474053,0.0005838015,0.00003176094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001864118,"about_ca_system_score_gemma":0.0006885168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002336914,"about_ca_topic_score_gemma":0.0001287124,"domain_scores_codex":[0.9975055,0.0006729636,0.0002481921,0.0004405757,0.0004701489,0.0006626122],"domain_scores_gemma":[0.998944,0.0002576983,0.000270869,0.000183631,0.0002927282,0.00005102429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007356286,0.00003827252,0.8228386,0.00001350333,0.000002848802,5.675749e-7,0.01785063,0.0006353307,0.0467982,0.106567,0.000003489086,0.005244205],"study_design_scores_gemma":[0.001709518,0.0008386735,0.8320094,0.0005926533,0.00001744456,0.00000499731,0.09555434,0.01221978,0.02513488,0.007462187,0.02334119,0.001114902],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9618518,0.00002184821,0.0007557411,0.001266741,0.0003054628,0.0002330653,4.638873e-7,0.00004948682,0.03551541],"genre_scores_gemma":[0.9902681,0.000007896242,0.008278992,0.00002366465,0.00006536223,0.000004969982,7.481807e-7,0.000007850824,0.001342375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09910481,"threshold_uncertainty_score":0.5124584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0244775429764466,"score_gpt":0.3747604088736635,"score_spread":0.3502828658972169,"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."}}