{"id":"W2129068307","doi":"10.48550/arxiv.1412.4864","title":"Learning with Pseudo-Ensembles","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":361,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Ensemble learning; Benchmark (surveying); Machine learning; Artificial neural network; Dropout (neural networks); Perturbation (astronomy); Pattern recognition (psychology); Algorithm","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":[0.00008344729,0.00008881825,0.0001054605,0.00005550701,0.0001735112,0.00001853551,0.0001345181,0.00003893668,0.000102852],"category_scores_gemma":[0.00002691825,0.00008457383,0.00004109289,0.0002285056,0.00005159728,0.00008419004,0.0000277419,0.0001175342,0.0001744044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002286998,"about_ca_system_score_gemma":0.000009580657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007945066,"about_ca_topic_score_gemma":0.00001495044,"domain_scores_codex":[0.9994862,0.00005398913,0.00006663259,0.0002203922,0.00003527142,0.0001374779],"domain_scores_gemma":[0.9994015,0.0001623392,0.00006606441,0.0002374139,0.00005793585,0.00007474646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002037237,0.00006204598,0.003769926,0.00001197342,0.00002001672,0.000009940987,0.0000909045,0.003139101,0.0004826366,0.9915556,0.0005792181,0.0002582041],"study_design_scores_gemma":[0.003613111,0.00062052,0.008296711,0.0001294376,0.0003450164,0.00007661017,0.001915746,0.2122107,0.00262775,0.7280676,0.04089757,0.001199254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8193685,9.00252e-7,0.1592748,0.00009582216,0.00001163494,0.00007147824,9.081593e-7,0.0001986696,0.02097719],"genre_scores_gemma":[0.9914671,0.00000472968,0.002664822,0.00006221112,0.00002720093,5.035972e-7,0.000002921125,0.00001416755,0.005756347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2634881,"threshold_uncertainty_score":0.344882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06577836543410738,"score_gpt":0.2018170692429524,"score_spread":0.136038703808845,"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."}}