{"id":"W2954402113","doi":"","title":"Detecting Low-Complexity Confounders from Data","year":2018,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"","keywords":"Confounding; Python (programming language); Latent variable; Computer science; Causal structure; Variable (mathematics); Data mining; Statistics; Econometrics; Mathematics; Machine learning","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","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005706577,0.0004247557,0.0004394129,0.0001456782,0.0005419061,0.001593636,0.008694705,0.0003669143,0.0001169061],"category_scores_gemma":[0.00159954,0.0004693026,0.0001378313,0.0003545097,0.000453458,0.000485733,0.01047787,0.0009886257,0.0001491634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001164218,"about_ca_system_score_gemma":0.0005939498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005740815,"about_ca_topic_score_gemma":0.003002161,"domain_scores_codex":[0.992735,0.003732203,0.000634732,0.001811947,0.0005859818,0.0005001611],"domain_scores_gemma":[0.9873717,0.001444865,0.0006129311,0.008439776,0.001864921,0.0002658081],"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":[0.00003125186,0.001392245,0.002475248,0.0005240824,0.0004804557,0.00003836562,0.03136818,0.0002629471,0.004827124,0.4750684,0.007990829,0.4755409],"study_design_scores_gemma":[0.0003380313,3.795839e-7,0.001048794,0.001734554,0.00003509194,0.000006824327,0.00005826947,0.8511749,0.01334178,0.1297199,0.001810166,0.0007313314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03081149,0.0003995178,0.9444991,0.005167041,0.0006327062,0.0002483502,0.0001424981,0.0006207076,0.01747853],"genre_scores_gemma":[0.6534162,0.0001078225,0.3449257,0.0002154283,0.00006871271,0.00001709114,0.00063269,0.00003129499,0.0005851028],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.850912,"threshold_uncertainty_score":0.9997759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07567582855254602,"score_gpt":0.2782861065801628,"score_spread":0.2026102780276168,"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."}}