{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00122901,0.0002691238,0.0005072993,0.001126404,0.0002914349,0.0000844717,0.0006612277,0.0001923763,0.0002261948],"category_scores_gemma":[0.0006260491,0.0002811576,0.00003986357,0.002073626,0.00147819,0.0003364297,0.0004855003,0.0002383805,0.000006906091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001500652,"about_ca_system_score_gemma":0.0009059144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0011265,"about_ca_topic_score_gemma":0.002010319,"domain_scores_codex":[0.9974303,0.00009774727,0.0005178631,0.001011135,0.0005492676,0.0003937036],"domain_scores_gemma":[0.9974442,0.0002382672,0.0007942527,0.0009564627,0.0004477684,0.0001190143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007838568,0.0005807477,0.008030336,0.0009563389,0.0002884868,0.000002243141,0.0003690136,0.0001925072,0.6814905,0.003255996,0.2955222,0.009233249],"study_design_scores_gemma":[0.005573665,0.002152434,0.028179,0.003571285,0.002007088,0.0004329522,0.002548567,0.2132296,0.03769506,0.001218132,0.7000879,0.003304339],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03525271,0.008258088,0.6010052,0.009954953,0.008463951,0.01735025,0.01799671,0.003432209,0.2982859],"genre_scores_gemma":[0.5115047,0.0009695534,0.2334785,0.000355655,0.001782618,0.0003080448,0.01193787,0.002790146,0.2368729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6437955,"threshold_uncertainty_score":0.9999641,"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."}}