{"id":"W4416037236","doi":"10.18653/v1/2025.emnlp-main.5","title":"JUDGEBERT: Assessing Legal Meaning Preservation Between Sentences","year":2025,"lang":"","type":"article","venue":"","topic":"Legal Language and Interpretation","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Université Laval","keywords":"Meaning (existential); Sentence; Interpretation (philosophy); Term (time); Semantics (computer science)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001051568,0.0002092115,0.0002962202,0.0001936816,0.001055146,0.001721379,0.0004647697,0.0002318858,0.001175899],"category_scores_gemma":[0.0007280085,0.0001945731,0.0001512135,0.001070452,0.0002276021,0.005516207,0.000136369,0.0003046597,0.00008338311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001993166,"about_ca_system_score_gemma":0.0005942673,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02387353,"about_ca_topic_score_gemma":0.003743463,"domain_scores_codex":[0.9974315,0.0004532732,0.0005816653,0.0004604537,0.0005973449,0.0004757687],"domain_scores_gemma":[0.9987231,0.0004480523,0.0002127324,0.0002133199,0.0003040144,0.00009874497],"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":[0.00002554359,0.0001237099,0.0860631,0.0001840378,0.0003593429,0.00001235514,0.1156033,0.00004601813,0.001496932,0.5721186,0.008380232,0.2155868],"study_design_scores_gemma":[0.001481937,0.000295811,0.05093871,0.002792024,0.001084728,0.000001300134,0.1481373,0.02617887,0.01830662,0.0289711,0.7199824,0.0018291],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.06442233,0.0004792793,0.01972906,0.008351588,0.001354301,0.0002983343,0.00000351336,0.0001146537,0.9052469],"genre_scores_gemma":[0.9357234,0.00004911678,0.0007500413,0.001170032,0.0006040623,0.000008544371,0.00001737202,0.000008847362,0.06166855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8713011,"threshold_uncertainty_score":0.9997371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02408618950152515,"score_gpt":0.360512529111511,"score_spread":0.3364263396099859,"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."}}