{"id":"W4390745240","doi":"10.1007/s12626-023-00153-z","title":"Legal Information Retrieval and Entailment Using Transformer-based Approaches","year":2024,"lang":"en","type":"article","venue":"The Review of Socionetwork Strategies","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Alberta; Alberta Machine Intelligence Institute","keywords":"Computer science; Transformer; Textual entailment; Information retrieval; Logical consequence; Natural language processing; Artificial intelligence; Physics; Voltage; Quantum mechanics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.001870205,0.0000973022,0.0001803016,0.00002684884,0.0003976907,0.0002263405,0.0001595468,0.00006039155,0.00008610063],"category_scores_gemma":[0.00003595758,0.00006632576,0.000098675,0.0003540759,0.0007567604,0.0009800509,0.00001034333,0.000145191,0.00001164398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007404986,"about_ca_system_score_gemma":0.0004254417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004145047,"about_ca_topic_score_gemma":0.00005210588,"domain_scores_codex":[0.9987949,0.0002022019,0.0003696781,0.0000913727,0.0003499451,0.0001918623],"domain_scores_gemma":[0.9995134,0.0002033598,0.00009178427,0.000100532,0.00005448874,0.00003643178],"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":[0.00001752801,0.00001283752,0.00001288536,0.003702048,0.00004089266,6.835574e-7,0.01084006,0.0007436082,0.00002045255,0.9328545,0.0004462884,0.05130822],"study_design_scores_gemma":[0.0001500849,0.0002074277,0.00007995601,0.028053,0.000709578,0.000008400235,0.1463258,0.02795565,0.0009972313,0.06740158,0.7272928,0.0008184399],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.07516387,0.7024443,0.05882622,0.03740961,0.001980482,0.004268948,0.00003664485,0.0004671719,0.1194027],"genre_scores_gemma":[0.9437541,0.05545094,0.0003481323,0.0001914026,0.0002132386,0.000008969947,0.00000654109,0.000006069549,0.00002061179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8685902,"threshold_uncertainty_score":0.3058755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09925702547852286,"score_gpt":0.3673346060913517,"score_spread":0.2680775806128288,"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."}}