{"id":"W6996356034","doi":"","title":"The shifting landscape of data : learning to tame distributional shifts","year":2024,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Science; Samsung; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Université de Montréal; Canadian Institute for Advanced Research; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Fonds de recherche du Québec – Nature et technologies; Deutscher Akademischer Austauschdienst; Institute for Catastrophic Loss Reduction; Microsoft Research; Canada Excellence Research Chairs, Government of Canada; U.S. Department of Energy","keywords":"Distribution (mathematics); ESPACE; Context (archaeology); Convergence (economics)","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":[0.008497842,0.001086392,0.001560222,0.001611572,0.0008488104,0.002743571,0.002297836,0.002063897,0.002259977],"category_scores_gemma":[0.04557926,0.0007620375,0.001250734,0.001492985,0.002289653,0.008723107,0.004550092,0.003971064,0.00135982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001409527,"about_ca_system_score_gemma":0.001185059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002518725,"about_ca_topic_score_gemma":0.002614589,"domain_scores_codex":[0.9948756,0.002291493,0.000228458,0.001764258,0.0005843673,0.0002559067],"domain_scores_gemma":[0.971512,0.01927727,0.001699283,0.005249697,0.001604389,0.0006573189],"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":[0.0009316755,0.0003245129,0.0323535,0.0002949881,0.0004423528,0.0002912554,0.001756565,0.2601997,0.008059931,0.02425409,0.004056394,0.667035],"study_design_scores_gemma":[0.00004082796,0.0003184803,0.005596437,0.00005820664,0.00006465452,0.0001803877,0.0003300445,0.9189701,0.0031841,0.06746047,0.003741059,0.00005531703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.186008,0.002157754,0.8034968,0.002532287,0.0001687339,0.0001297131,0.0004282435,0.002070009,0.003008385],"genre_scores_gemma":[0.8321114,0.0009955013,0.1613605,0.0009311306,0.0002232446,0.000186435,0.0009255808,0.0003965138,0.002869698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008497842,"threshold_uncertainty_score":0.04494148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01252487336566389,"score_gpt":0.2223561101873848,"score_spread":0.2098312368217209,"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."}}