{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001201929,0.0005566035,0.0005081035,0.000299728,0.01221616,0.0004192652,0.003367578,0.0004153457,0.00003443291],"category_scores_gemma":[0.0009360695,0.00054283,0.0002868383,0.001167474,0.000349175,0.001107111,0.003077234,0.001528006,0.0001580867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002802915,"about_ca_system_score_gemma":0.003141833,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01404519,"about_ca_topic_score_gemma":0.004858002,"domain_scores_codex":[0.9953768,0.0004474079,0.000755742,0.001297191,0.001386387,0.0007365086],"domain_scores_gemma":[0.9962701,0.0009707635,0.000671456,0.001206384,0.0005028014,0.0003784522],"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":[0.0009562669,0.0002102921,0.02885789,0.0006586001,0.001162045,0.002769409,0.123986,0.2944714,0.003784768,0.4879175,0.002433912,0.05279191],"study_design_scores_gemma":[0.0008897556,0.000249107,0.05910364,0.001722943,0.0006796428,0.0005831624,0.04821419,0.632965,0.0008932233,0.001278447,0.2521266,0.001294309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6397855,0.08079939,0.2082731,0.01081566,0.01525058,0.001639759,0.000668211,0.0007778853,0.04198999],"genre_scores_gemma":[0.9521286,0.0002813176,0.00686233,0.00004430504,0.0006044645,0.00001823848,0.001458789,0.00005331225,0.03854857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4866391,"threshold_uncertainty_score":0.9997023,"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."}}