{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002071075,0.0003793046,0.00034481,0.0001836622,0.0002100759,0.0002394168,0.001156623,0.000244633,0.000003615908],"category_scores_gemma":[0.00001563415,0.0003753915,0.0001860139,0.0008544358,0.0001423507,0.0002663918,0.0008662675,0.0006011798,0.000009999877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004829176,"about_ca_system_score_gemma":0.0004764507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003923778,"about_ca_topic_score_gemma":0.0003402599,"domain_scores_codex":[0.9977643,0.00009243596,0.0002263807,0.001307491,0.0001063691,0.0005029942],"domain_scores_gemma":[0.9982117,0.0002929215,0.0001799158,0.0009669077,0.0002048133,0.0001436792],"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":[0.00005084701,0.00005376373,0.0001558758,0.0001850433,0.00004915415,0.00002559009,0.00005140597,0.8144134,0.000001291478,0.1845139,0.00004642195,0.0004533613],"study_design_scores_gemma":[0.0002714034,0.00009103718,0.000102945,0.0003504586,0.00008901882,7.942664e-7,0.000007238347,0.7595244,0.000003234555,0.239241,0.00001309919,0.0003054058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09695851,0.0001442688,0.9006764,0.0001509877,0.0008584739,0.0008084944,0.00001708411,0.0003204903,0.00006526538],"genre_scores_gemma":[0.9947043,0.00001946121,0.004911431,0.00008079239,0.0000515992,0.000008168303,0.00004532862,0.00002915987,0.0001497831],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8977458,"threshold_uncertainty_score":0.9998698,"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."}}