{"id":"W4385573352","doi":"10.18653/v1/2022.nllp-1.24","title":"Detecting Relevant Differences Between Similar Legal Texts","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Metadata; Computer science; Task (project management); Terminology; Natural language processing; Sentence; Artificial intelligence; Information retrieval; Focus (optics); Variation (astronomy); Resource (disambiguation); Legal case; Data science; World Wide Web; Linguistics; Political science; Law","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":[],"consensus_categories":[],"category_scores_codex":[0.0003155394,0.00008424541,0.0001174276,0.00006600918,0.0003743783,0.0001152446,0.0009163754,0.00001736826,0.0001137811],"category_scores_gemma":[0.00003371708,0.00007491556,0.00004209924,0.0002036772,0.00001018938,0.0002287534,0.0009098362,0.0002212267,0.00001450196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004418171,"about_ca_system_score_gemma":0.00004420755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001109426,"about_ca_topic_score_gemma":0.00001240201,"domain_scores_codex":[0.9988155,0.00007982393,0.0001814498,0.0003366462,0.0003469572,0.0002396385],"domain_scores_gemma":[0.9993549,0.0001321812,0.00004943095,0.00039146,0.00001596503,0.00005608967],"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":[0.000004272775,0.00006938073,0.06700817,0.00002312088,0.00005315469,0.00009996477,0.002658768,0.003833469,0.001643953,0.1214431,0.0007904643,0.8023722],"study_design_scores_gemma":[0.0004948747,0.0003038593,0.02418172,0.00001317096,0.00001420919,0.0000550918,0.000503152,0.9181499,0.003432247,0.02704146,0.02510447,0.0007057982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3398375,0.00004265588,0.6537247,0.0015305,0.0002797984,0.00006863484,9.973365e-7,0.0002503756,0.004264898],"genre_scores_gemma":[0.9605147,8.091671e-7,0.03820537,0.0002563048,0.00009023207,0.00001210487,3.646516e-7,0.000004769109,0.0009153162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9143165,"threshold_uncertainty_score":0.3054968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03539416592959268,"score_gpt":0.2492053513097113,"score_spread":0.2138111853801186,"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."}}