{"id":"W7039767753","doi":"","title":"Natural Language Reasoning with Transformer Language Models","year":2023,"lang":"fr","type":"other","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Environmental Monitoring and Data Management","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Transformer; Natural language understanding; Natural language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.002786995,0.0008924813,0.000584984,0.001705892,0.0005257392,0.003932335,0.001586636,0.001066585,0.009020254],"category_scores_gemma":[0.01297304,0.0007315525,0.003021547,0.001299432,0.001876607,0.007105129,0.002235378,0.002138176,0.002130117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002100561,"about_ca_system_score_gemma":0.002035566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009661699,"about_ca_topic_score_gemma":0.01331137,"domain_scores_codex":[0.9970965,0.001177593,0.0002523726,0.0004621012,0.0008119338,0.0001995297],"domain_scores_gemma":[0.9905917,0.006641273,0.0003994769,0.001380492,0.000835087,0.0001519706],"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":[0.0006182066,0.0002003978,0.003472945,0.0008306092,0.0002179735,0.001022244,0.001597273,0.2169708,0.007206517,0.6271051,0.00989592,0.1308619],"study_design_scores_gemma":[0.00007724737,0.00006587863,0.0002436711,0.00009331026,0.0001182654,0.0003356571,0.0002744816,0.6042333,0.007387661,0.3686732,0.01845762,0.00003973863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01709374,0.0003521924,0.9681785,0.001053295,0.00008974284,0.0001504012,0.001030445,0.004353052,0.007698729],"genre_scores_gemma":[0.5397245,0.0008034247,0.4449828,0.0005787656,0.0001461035,0.0002284579,0.00267353,0.0007603096,0.0101021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009661699,"threshold_uncertainty_score":0.03017569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007871666646805255,"score_gpt":0.2010996627027025,"score_spread":0.1932279960558972,"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."}}