{"id":"W4415317390","doi":"10.48550/arxiv.2509.13032","title":"Introducing the A2AJ's Canadian Legal Data: An open-source alternative to CanLII for the era of computational law","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Statute; Legal research; Context (archaeology); Economic Justice; Big data; Legal practice; Legal profession; Legal aspects of computing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.002541555,0.0001868482,0.0002742761,0.00005394723,0.001719399,0.0004430613,0.005382739,0.0001356158,0.0001147301],"category_scores_gemma":[0.001107359,0.0001376565,0.00006061822,0.0002637793,0.0007611241,0.0003736244,0.00187868,0.0006005471,0.00002127827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003566257,"about_ca_system_score_gemma":0.002935434,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9686165,"about_ca_topic_score_gemma":0.9812931,"domain_scores_codex":[0.9977059,0.0003633895,0.0004145579,0.0007005346,0.000392876,0.0004227063],"domain_scores_gemma":[0.9965078,0.001359747,0.0002262677,0.001194957,0.0005192693,0.0001920049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005362323,0.00006823237,0.005440818,0.00002536375,0.0002548204,0.00000314784,0.04994581,0.3072815,0.00001185324,0.6075981,0.01197689,0.01733988],"study_design_scores_gemma":[0.00009790873,0.00007825149,0.003546782,0.0002089952,0.0001307087,6.952064e-7,0.0177726,0.02014002,0.0004779006,0.02406845,0.9330072,0.0004704796],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5686955,0.0003648016,0.07120207,0.2782346,0.01198986,0.0111955,0.005302709,0.0001560096,0.05285891],"genre_scores_gemma":[0.9910071,0.00001403361,0.001569969,0.004144855,0.00154776,0.000139617,0.0001724407,0.00001902586,0.001385165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9210303,"threshold_uncertainty_score":0.9999986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1701021814015538,"score_gpt":0.423525482485024,"score_spread":0.2534233010834703,"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."}}