{"id":"W4385570734","doi":"10.18653/v1/2023.semeval-1.79","title":"uOttawa at SemEval-2023 Task 6: Deep Learning for Legal Text Understanding","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Task (project management); SemEval; Judgement; Artificial intelligence; Natural language processing; Rhetorical question; Deep learning; Process (computing); Domain (mathematical analysis); Linguistics; Programming language; Political science; Law; Management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005419364,0.002052541,0.001122429,0.001900294,0.002333087,0.003431976,0.002510276,0.004604069,0.03043899],"category_scores_gemma":[0.01303356,0.0006722132,0.001677869,0.00140191,0.0009015129,0.004375792,0.003490378,0.005145086,0.02023641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00293844,"about_ca_system_score_gemma":0.004417386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04205535,"about_ca_topic_score_gemma":0.08410478,"domain_scores_codex":[0.9967543,0.001099218,0.0001592386,0.0009192479,0.0006983283,0.0003696486],"domain_scores_gemma":[0.9953459,0.001462293,0.0001295872,0.001178679,0.001288758,0.000594815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005958969,0.0005986055,0.001526674,0.0004707428,0.0001583871,0.0004754199,0.0003559504,0.0103806,0.005448965,0.006025834,0.7675166,0.2064464],"study_design_scores_gemma":[0.0008370666,0.000610233,0.006312515,0.0003584888,0.0001206634,0.000808176,0.0009652291,0.3541555,0.04071615,0.03757703,0.5573066,0.0002323553],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1417198,0.006081812,0.2806152,0.0197258,0.009101604,0.003869237,0.2495073,0.137114,0.1522651],"genre_scores_gemma":[0.2190498,0.000722961,0.3310717,0.003601987,0.0005193964,0.001668416,0.3587233,0.005127676,0.07951474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04205535,"threshold_uncertainty_score":0.1018286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1387156012462086,"score_gpt":0.3870068507842291,"score_spread":0.2482912495380205,"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."}}