{"id":"W4311843543","doi":"","title":"Vers une étude comparative de différentes approches de classification automatique de textes provenant des secteurs métiers","year":2021,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Berger (Canada)","funders":"","keywords":"Computer science","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007066452,0.0007802186,0.0007880657,0.0003838038,0.001048508,0.002202503,0.003681295,0.0007453073,0.00006639162],"category_scores_gemma":[0.003306204,0.0008539788,0.0004142224,0.001612761,0.001856735,0.0008965463,0.001834558,0.001340722,0.00004445306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00163052,"about_ca_system_score_gemma":0.00246634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002887921,"about_ca_topic_score_gemma":0.003817728,"domain_scores_codex":[0.9866704,0.008760672,0.001050606,0.001646781,0.0006677714,0.001203785],"domain_scores_gemma":[0.9897508,0.002865572,0.001261813,0.003040651,0.002619433,0.000461752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002183772,0.001703893,0.01829892,0.000532451,0.0002883712,0.00001760946,0.1215434,0.0006760698,0.05653434,0.6885946,0.0008767455,0.1109117],"study_design_scores_gemma":[0.0008713235,0.000004841446,0.189814,0.003789296,0.0001545023,0.00009234291,0.00995497,0.4629516,0.2862308,0.03694212,0.007896988,0.001297228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2624196,0.002184896,0.7034541,0.02114308,0.000194686,0.000711409,0.00002887731,0.001019038,0.008844295],"genre_scores_gemma":[0.7202588,0.001792731,0.2727754,0.0001366451,0.00002300423,0.0004154445,0.0002386395,0.0000491102,0.004310234],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6516525,"threshold_uncertainty_score":0.9993911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03285696509734804,"score_gpt":0.2624052596048865,"score_spread":0.2295482945075384,"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."}}