{"id":"W4385775400","doi":"","title":"Complex question answering: homogeneous or heterogeneous, which ensemble is better?","year":2014,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Homogeneous; Computer science; Question answering; Artificial intelligence; Natural language processing; Statistical physics; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.002818161,0.0002420156,0.000255091,0.0001348413,0.0004009985,0.0004818598,0.001694572,0.0001216256,0.00009568284],"category_scores_gemma":[0.000586212,0.0002385098,0.00009555982,0.0005180917,0.0000706348,0.0002942087,0.0006297845,0.0002044712,0.00009975662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007520024,"about_ca_system_score_gemma":0.0001001004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004341555,"about_ca_topic_score_gemma":0.001418877,"domain_scores_codex":[0.9956349,0.002334095,0.0004242942,0.0007583601,0.0004210825,0.0004273056],"domain_scores_gemma":[0.995523,0.0006367168,0.0002181031,0.002313684,0.001108009,0.0002005225],"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":[0.0000167113,0.0005186714,0.003088329,0.0001115916,0.00007146144,0.00001853603,0.01134125,0.001123733,0.03673685,0.2112899,0.001723069,0.7339599],"study_design_scores_gemma":[0.0005160641,0.000002009928,0.001435661,0.000285432,0.00001388646,0.000114837,0.00001701832,0.8373752,0.1074399,0.005071402,0.04724287,0.0004857476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.107541,0.0001053043,0.8710008,0.01118293,0.0001522136,0.0001719356,0.000004243499,0.0003930527,0.009448523],"genre_scores_gemma":[0.7560954,0.00004526796,0.2412204,0.000640082,0.00002991468,0.00001842454,0.00002317792,0.00002250242,0.001904759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8362514,"threshold_uncertainty_score":0.9726145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0212606667660785,"score_gpt":0.2377485816345423,"score_spread":0.2164879148684638,"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."}}