{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01325334,0.001697352,0.00341048,0.002387615,0.001248433,0.007295046,0.002274371,0.002920352,0.01207427],"category_scores_gemma":[0.04188846,0.0005594221,0.002033883,0.002252037,0.001592463,0.01226089,0.003821415,0.003400972,0.003736883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078668,"about_ca_system_score_gemma":0.001060818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001663753,"about_ca_topic_score_gemma":0.001552469,"domain_scores_codex":[0.9903041,0.003681215,0.00054586,0.003529975,0.001461482,0.0004773811],"domain_scores_gemma":[0.9575369,0.02737059,0.0017406,0.006077929,0.004784938,0.00248905],"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":[0.003103332,0.001127492,0.03762385,0.002308764,0.002471586,0.0003090572,0.002107404,0.03738532,0.02284802,0.02707462,0.05050829,0.8131323],"study_design_scores_gemma":[0.0003319797,0.0009617326,0.03469806,0.0005544019,0.001905717,0.001072663,0.002429681,0.5338607,0.01549685,0.351754,0.05672288,0.0002113996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.219745,0.01533387,0.7114848,0.02104133,0.0009698923,0.0005807486,0.00485489,0.003796612,0.02219281],"genre_scores_gemma":[0.8022636,0.004156959,0.169576,0.003604189,0.004289974,0.0003120202,0.009494769,0.0007953618,0.005507199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01325334,"threshold_uncertainty_score":0.07009113,"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."}}