{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001414292,0.000118917,0.0001496186,0.0001181527,0.002185076,0.0001913067,0.0002839575,0.0001305233,0.001998972],"category_scores_gemma":[0.0009539828,0.0001181937,0.0001238631,0.0007532985,0.0003575008,0.000326524,0.000108992,0.0001373879,0.002460206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006148195,"about_ca_system_score_gemma":0.00009038556,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001963739,"about_ca_topic_score_gemma":0.03551695,"domain_scores_codex":[0.9981669,0.0001318657,0.000251749,0.0003214941,0.0004412756,0.0006867125],"domain_scores_gemma":[0.9986321,0.0009342073,0.00007620768,0.000130156,0.00007918072,0.0001480909],"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":[0.00003198908,0.00001562674,0.002083236,0.0000138381,0.00002838303,0.00001104722,0.01092006,0.00213463,0.00096565,0.9494069,0.02819838,0.006190256],"study_design_scores_gemma":[0.00009477935,0.00007751044,0.00008156568,0.00001900879,0.00001907292,8.603956e-7,0.08328953,0.01618307,0.001518202,0.04148949,0.8568891,0.0003377519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0605229,0.00006432899,0.1160771,0.0102388,0.00239816,0.001088892,0.000007691857,0.001707472,0.8078946],"genre_scores_gemma":[0.8639979,0.00004623795,0.0002742359,0.0001506869,0.0004307961,0.00003518655,0.00001035796,0.00002477244,0.1350299],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9079174,"threshold_uncertainty_score":0.9991139,"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."}}