{"id":"W3166104071","doi":"10.21203/rs.3.rs-3027011/v1","title":"Multi-Resolution Continuous Normalizing Flows","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Samsung; Institut de Valorisation des Données; McGill University; Canadian Institute for Advanced Research","keywords":"Transformation (genetics); Invertible matrix; Image (mathematics); Computer science; Generative grammar; Distribution (mathematics); Ode; Conditional probability distribution; Ordinary differential equation; Algorithm; Applied mathematics; Generative model; Mathematics; Perspective (graphical); Artificial intelligence; Pattern recognition (psychology); Statistics; Differential equation; Mathematical analysis","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003124624,0.0003029219,0.0004114051,0.0005459673,0.0005697434,0.0009611254,0.002054419,0.0003465541,0.0000333561],"category_scores_gemma":[0.0008249964,0.0002874122,0.0002488613,0.0008344391,0.0001125626,0.0003472517,0.00567969,0.001553585,0.0007666629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002457128,"about_ca_system_score_gemma":0.0003797633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001469387,"about_ca_topic_score_gemma":0.0004076438,"domain_scores_codex":[0.9950008,0.001141986,0.0003948164,0.001127206,0.001254487,0.001080738],"domain_scores_gemma":[0.9967672,0.000488195,0.0001164693,0.00147675,0.0009087475,0.0002426901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000813163,0.0007445929,0.002582859,0.001716001,0.0005395306,0.001069746,0.006049912,0.728817,0.008989687,0.006679194,0.1320323,0.1106979],"study_design_scores_gemma":[0.0002475501,0.00007362603,0.003266505,0.0004567218,0.000005676325,0.000002472587,0.000127658,0.9845357,0.0006329006,0.00119878,0.009119013,0.0003334041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001152694,0.001179701,0.9922017,0.001704966,0.001616897,0.000952299,0.00004095907,0.0004932012,0.0006575265],"genre_scores_gemma":[0.6326513,0.000999429,0.3591566,0.00007622703,0.001792309,0.0005139794,0.0001199492,0.0001073696,0.004582731],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6330451,"threshold_uncertainty_score":0.9999578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1356743159674273,"score_gpt":0.3837862226472649,"score_spread":0.2481119066798376,"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."}}