{"id":"W4392781756","doi":"10.48550/arxiv.2403.07124","title":"Stochastic gradient descent-based inference for dynamic network models with attractors","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks Stability and Synchronization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Inference; Stochastic gradient descent; Attractor; Computer science; Gradient descent; Mathematics; Artificial intelligence; Artificial neural network; Mathematical analysis","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":[0.004324041,0.001414527,0.002107594,0.001651045,0.0009492261,0.001530941,0.002427497,0.001681112,0.001841086],"category_scores_gemma":[0.02299457,0.001482368,0.001078857,0.001412111,0.002079447,0.002457282,0.002307512,0.00295545,0.0004638103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00231518,"about_ca_system_score_gemma":0.002223106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01629214,"about_ca_topic_score_gemma":0.01976776,"domain_scores_codex":[0.9986029,0.0007741618,0.00007145286,0.0003116317,0.0001442665,0.00009564057],"domain_scores_gemma":[0.9852776,0.0124266,0.0008082121,0.0004644324,0.0007600361,0.0002631971],"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":[0.00004603445,0.000028323,0.001316379,0.00005189463,0.0000764207,0.00004679334,0.00005734497,0.9593765,0.0002058345,0.02587906,0.0008689432,0.01204649],"study_design_scores_gemma":[0.000003530047,0.000002902276,0.00004305197,0.000003322098,0.000002141407,0.000002371341,0.000002580353,0.9886778,0.00003025669,0.0111486,0.00008080233,0.000002515865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01891615,0.0004095308,0.9787444,0.0005600845,0.00004908583,0.00004274537,0.0001642596,0.0003589705,0.0007547719],"genre_scores_gemma":[0.7552052,0.0006773751,0.2360743,0.0004071235,0.0002087548,0.0004659868,0.001242506,0.000328441,0.005390222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01629214,"threshold_uncertainty_score":0.03239465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06604388694041291,"score_gpt":0.1971509589911997,"score_spread":0.1311070720507868,"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."}}