{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004503929,0.001327072,0.0007063427,0.009014066,0.001735386,0.002717142,0.001150906,0.001749816,0.00423381],"category_scores_gemma":[0.03705345,0.0001923289,0.0007745627,0.00322533,0.001390843,0.00406505,0.00309763,0.001198712,0.002393232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001417997,"about_ca_system_score_gemma":0.00199438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008027684,"about_ca_topic_score_gemma":0.01675755,"domain_scores_codex":[0.9927933,0.002036101,0.001038503,0.001127956,0.002749177,0.0002550036],"domain_scores_gemma":[0.9780259,0.01136318,0.00244512,0.003202722,0.004364901,0.0005982547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001448665,0.0007335465,0.09417819,0.006428016,0.0008091089,0.001544975,0.006589351,0.01469005,0.03920474,0.0152937,0.2372353,0.5818444],"study_design_scores_gemma":[0.0004606614,0.001470843,0.2289884,0.001438675,0.0006769935,0.00402854,0.007859979,0.1490455,0.07409216,0.02755369,0.5038611,0.000523407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6337146,0.008859635,0.1388456,0.0016274,0.00116619,0.002471424,0.1320632,0.02462839,0.0566234],"genre_scores_gemma":[0.5506628,0.001184066,0.1546283,0.0005944293,0.0002973877,0.001736784,0.279824,0.001466986,0.009605313],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.009014066,"threshold_uncertainty_score":0.02381939,"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."}}