{"id":"W2979218902","doi":"","title":"Turning Standards into Rules Part 1: Using Machine Learning to Predict Tax Outcomes","year":2018,"lang":"en","type":"article","venue":"TSpace","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Rule of thumb; Field (mathematics); Order (exchange); Computer science; Compliance (psychology); Outcome (game theory); Artificial intelligence; Business; Psychology; Economics","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001898651,0.0001502714,0.0002211291,0.00008865553,0.001455364,0.0001756255,0.0003207435,0.00009926465,0.001792239],"category_scores_gemma":[0.003471196,0.0001412032,0.00006683472,0.0003324083,0.0005401651,0.0002182991,0.0001408247,0.0002200456,0.0003338629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003560907,"about_ca_system_score_gemma":0.0002523524,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02722394,"about_ca_topic_score_gemma":0.0229082,"domain_scores_codex":[0.9978588,0.0002849383,0.00025084,0.0002955451,0.0008069763,0.0005029219],"domain_scores_gemma":[0.9988958,0.0002344469,0.0001171669,0.0001982179,0.0003196204,0.0002347853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001350862,0.00008523053,0.2683594,0.00002642707,0.0001035366,0.00002448763,0.659072,0.002160823,0.008950042,0.0248583,0.007494616,0.02873005],"study_design_scores_gemma":[0.00007363378,0.0001846722,0.000672679,0.0001036963,0.00002806609,9.977742e-7,0.04017508,0.004433176,0.00683274,0.001945719,0.945168,0.0003816058],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9586936,0.0000761633,0.01045434,0.00359686,0.0009490607,0.0002533015,0.00001020482,0.0002758403,0.02569069],"genre_scores_gemma":[0.9816652,0.00001560888,0.008819461,0.0003608507,0.001044382,0.000007350085,0.00000220331,0.00002847019,0.008056464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9376733,"threshold_uncertainty_score":0.9998446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06745830783268637,"score_gpt":0.4373483669076771,"score_spread":0.3698900590749908,"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."}}