{"id":"W4327990163","doi":"10.48550/arxiv.2303.09669","title":"Predicting discrete-time bifurcations with deep learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Ecosystem dynamics and resilience","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; University of Waterloo; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Bifurcation; Artificial intelligence; Deep learning; Period-doubling bifurcation; Computer science; Discrete time and continuous time; Bifurcation theory; Classifier (UML); Statistical physics; Machine learning; Mathematics; Nonlinear system; Physics; Statistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002037448,0.0002262144,0.0002065276,0.00008690512,0.0003639881,0.00005688845,0.0006002358,0.0001681032,0.0003302254],"category_scores_gemma":[0.00003337548,0.0002151506,0.00009145198,0.0005080082,0.0001877766,0.0001538364,0.001258814,0.0005346483,0.001351133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002909426,"about_ca_system_score_gemma":0.00002735723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009545677,"about_ca_topic_score_gemma":0.001505096,"domain_scores_codex":[0.9984782,0.00008835306,0.0001475529,0.0008375782,0.0001185251,0.0003297767],"domain_scores_gemma":[0.9990469,0.00008874758,0.0002150637,0.000486464,0.00001689223,0.0001459168],"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":[0.000006972966,0.00001452318,0.26699,0.00002041815,0.00002362186,0.00006175172,0.0001473052,0.7322873,0.00004324913,0.0003430822,0.00001388078,0.0000478856],"study_design_scores_gemma":[0.0001472419,0.00004740959,0.04724783,0.0001195542,0.00006589136,0.000003919061,0.0003396148,0.9504477,0.000007288612,0.00113545,0.0001261701,0.0003119289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9577349,0.000008665565,0.02766627,0.00005318294,0.000132561,0.0002938238,0.00001509996,0.0002920216,0.01380351],"genre_scores_gemma":[0.9831581,0.00006275418,0.000211154,0.000008331511,0.00003054312,0.000002023668,0.0000390665,0.00003462863,0.01645336],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2197421,"threshold_uncertainty_score":0.9994264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02213678607427279,"score_gpt":0.1588919283225028,"score_spread":0.13675514224823,"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."}}