{"id":"W4385571088","doi":"10.18653/v1/2023.acl-short.89","title":"Decomposed scoring of CCG dependencies","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Predicate (mathematical logic); Parsing; Artificial intelligence; Ranking (information retrieval); Judgement; Grammar; Argument (complex analysis); Task (project management); Linguistics; Programming language","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":[0.02628436,0.002265146,0.001894487,0.005580978,0.001768869,0.005108506,0.002607584,0.002198275,0.006970886],"category_scores_gemma":[0.09954578,0.000756115,0.0008594405,0.004420462,0.001889489,0.003462242,0.004218185,0.002914927,0.003076556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002047362,"about_ca_system_score_gemma":0.003622109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005489251,"about_ca_topic_score_gemma":0.01219305,"domain_scores_codex":[0.967537,0.01718023,0.001982076,0.004930679,0.0070569,0.001312972],"domain_scores_gemma":[0.9072157,0.04526623,0.003959793,0.01440063,0.02715943,0.001998243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001296753,0.000327298,0.04925729,0.0007514508,0.0004292894,0.0005957592,0.00538027,0.04830024,0.04795028,0.03396802,0.03387659,0.7778667],"study_design_scores_gemma":[0.0001900185,0.0006451592,0.04723668,0.0002901927,0.0002451369,0.0008910034,0.002334752,0.7826204,0.05432665,0.07691321,0.03382458,0.0004821338],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2084371,0.0007060706,0.7574592,0.0008467471,0.000532953,0.0008761397,0.001856533,0.01041103,0.01887414],"genre_scores_gemma":[0.686196,0.0001526253,0.3018852,0.0003296396,0.0001003669,0.0004592445,0.002757365,0.002497379,0.005622059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02628436,"threshold_uncertainty_score":0.1390067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04587723139958526,"score_gpt":0.270129075844673,"score_spread":0.2242518444450877,"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."}}