{"id":"W6928684355","doi":"10.48448/2qrt-7279","title":"Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Generative grammar; Constructive; Process (computing); Field (mathematics); Data collection; Causal model","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1563716,0.001375877,0.001701757,0.006250813,0.0022783,0.007402148,0.003945457,0.00234711,0.00867264],"category_scores_gemma":[0.4230786,0.001123233,0.004108066,0.008452258,0.01328205,0.01379344,0.005561933,0.006062166,0.0007723126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004033867,"about_ca_system_score_gemma":0.007532583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006415722,"about_ca_topic_score_gemma":0.005357261,"domain_scores_codex":[0.8125517,0.1547465,0.008670875,0.01293334,0.01022602,0.0008715448],"domain_scores_gemma":[0.2727343,0.6791305,0.0188157,0.02269478,0.005861017,0.0007636414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001184012,0.0002411501,0.06969018,0.02702074,0.0140819,0.0006967044,0.006141318,0.008449956,0.000653199,0.5202925,0.00835414,0.3431942],"study_design_scores_gemma":[0.0003743613,0.000188171,0.01360351,0.009330323,0.004993369,0.0004407084,0.001499768,0.008797394,0.001093357,0.9366963,0.02287682,0.0001059943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05634294,0.1855359,0.5951893,0.1090025,0.001622001,0.00179018,0.004165644,0.0008894164,0.04546205],"genre_scores_gemma":[0.7985095,0.03339382,0.1465885,0.01307018,0.001503321,0.002617641,0.002130808,0.000422787,0.001763347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1563716,"threshold_uncertainty_score":0.8269821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07523359618592784,"score_gpt":0.3683468979730641,"score_spread":0.2931133017871363,"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."}}