{"id":"W2805660998","doi":"10.63317/44bfrjvhx2no","title":"Lexical Profiling of Environmental Corpora","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Profiling (computer programming); Computer science; Natural language processing; Artificial intelligence; 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":[0.0008003105,0.0004403693,0.0004379999,0.007207382,0.00132553,0.002406253,0.0005599524,0.0004360105,0.006569961],"category_scores_gemma":[0.005972167,0.0003261707,0.0004571069,0.006239629,0.0004279267,0.002075477,0.001395159,0.0005906161,0.00311861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004129056,"about_ca_system_score_gemma":0.001112114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002937279,"about_ca_topic_score_gemma":0.009301638,"domain_scores_codex":[0.9984208,0.0004275053,0.000206627,0.0003623349,0.000440339,0.0001423121],"domain_scores_gemma":[0.9963936,0.001694783,0.0002774533,0.0004266776,0.001090403,0.0001170794],"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":[0.0007788531,0.0004562318,0.05614619,0.002440276,0.0002458699,0.003124719,0.004441515,0.0101417,0.149218,0.02812577,0.03732418,0.7075567],"study_design_scores_gemma":[0.0001175354,0.0003651822,0.2000969,0.001082109,0.00061882,0.004721944,0.01285542,0.1570807,0.1486973,0.03571625,0.4383932,0.0002545168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6373526,0.003322671,0.2264219,0.001019272,0.0005253026,0.0005186626,0.04270506,0.007439442,0.08069505],"genre_scores_gemma":[0.8168513,0.001372697,0.1077755,0.0001665647,0.0001720362,0.0003066174,0.06191058,0.001406785,0.0100379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007207382,"threshold_uncertainty_score":0.02197868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01254305679712006,"score_gpt":0.2557455875849487,"score_spread":0.2432025307878286,"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."}}