{"id":"W4248834399","doi":"10.31234/osf.io/9w6a3","title":"Tutorial: Applying Machine Learning in Behavioral Research","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut universitaire en santé mentale de Montréal; Institut Universitaire en Santé Mentale de Québec; Université de Montréal","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Random forest; Stochastic gradient descent; Scarcity; Support vector machine; Online machine learning; Data science; Active learning (machine learning); Artificial neural network","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":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003459126,0.0003671241,0.0005681469,0.0006957552,0.0002754394,0.0006320377,0.003257595,0.0004936788,0.0001067345],"category_scores_gemma":[0.0007522847,0.0003779934,0.0001280927,0.001119075,0.00006570615,0.0001927702,0.009477894,0.01062137,0.0002072848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004377838,"about_ca_system_score_gemma":0.0007438144,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02184021,"about_ca_topic_score_gemma":0.0008492172,"domain_scores_codex":[0.9935478,0.001870582,0.0006844379,0.001612251,0.001381709,0.0009032389],"domain_scores_gemma":[0.9975162,0.0004868773,0.0001884059,0.001244568,0.0002588092,0.0003052062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009366498,0.0004835031,0.3349565,0.00256094,0.00004877755,0.001693552,0.01968866,0.05234782,0.0006905252,0.177729,0.003163715,0.4065434],"study_design_scores_gemma":[0.0004967145,0.0003062129,0.007505696,0.0003610384,0.000005163287,0.00001454571,0.0001036815,0.9058168,0.00007925024,0.01401211,0.07049657,0.000802225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1662025,0.005739273,0.549448,0.1255286,0.03005395,0.01603117,0.00004557138,0.0155807,0.09137029],"genre_scores_gemma":[0.9291915,0.00006151976,0.06771386,0.0002197721,0.0008777323,0.000484642,0.00005770391,0.00006983758,0.00132348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.853469,"threshold_uncertainty_score":0.9998672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2423910610884165,"score_gpt":0.4624341681527402,"score_spread":0.2200431070643238,"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."}}