{"id":"W4311991579","doi":"10.48550/arxiv.2212.08132","title":"WEKA-Based: Key Features and Classifier for French of Five Countries","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Python (programming language); Sketch; Classifier (UML); Key (lock); Artificial intelligence; Computer science; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008434774,0.001656711,0.0006815244,0.003859743,0.001058035,0.001483707,0.001220421,0.001059303,0.01019721],"category_scores_gemma":[0.005293256,0.0004324853,0.0017917,0.00231014,0.0003639889,0.001527081,0.000939626,0.001262207,0.008681414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001263842,"about_ca_system_score_gemma":0.001707458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03838758,"about_ca_topic_score_gemma":0.03771161,"domain_scores_codex":[0.9990356,0.0001393566,0.0001134777,0.0003050283,0.0002304091,0.0001760921],"domain_scores_gemma":[0.9990232,0.0003899965,0.0000594948,0.0001566421,0.0003337475,0.00003693795],"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":[0.0005738657,0.0001749112,0.01024293,0.0007427372,0.0002926369,0.0006559945,0.0004325102,0.01818625,0.02695546,0.004057179,0.102043,0.8356425],"study_design_scores_gemma":[0.000243145,0.000373799,0.03709594,0.0003491451,0.0005750619,0.001782372,0.001346793,0.4991271,0.1069155,0.01528529,0.3365659,0.0003400073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09809788,0.002664338,0.6881666,0.000869892,0.0005675409,0.001633019,0.05877355,0.136187,0.01304015],"genre_scores_gemma":[0.3022096,0.0008736078,0.5730897,0.0003143618,0.00009541028,0.002513205,0.1025851,0.002928284,0.01539076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03838758,"threshold_uncertainty_score":0.07632834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03592874856793279,"score_gpt":0.2081681734616282,"score_spread":0.1722394248936954,"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."}}