{"id":"W4367052271","doi":"10.1111/mafi.12389","title":"Designing universal causal deep learning models: The geometric (Hyper)transformer","year":2023,"lang":"en","type":"article","venue":"Mathematical Finance","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"H2020 European Research Council; McMaster University; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; Eidgenössische Technische Hochschule Zürich; ETH Zürich Foundation","keywords":"Mathematics; Euclidean geometry; Markov chain; Metric space; Series (stratigraphy); Euclidean space; Algorithm; Computer science; Theoretical computer science; Discrete mathematics; Pure mathematics; Geometry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004053812,0.0007373962,0.000935004,0.001053872,0.0003807915,0.001357647,0.0018694,0.001256068,0.002365264],"category_scores_gemma":[0.01285794,0.000760667,0.0009189537,0.0007632566,0.002863332,0.005148833,0.004154476,0.001929091,0.0003538698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001618362,"about_ca_system_score_gemma":0.000963825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001269121,"about_ca_topic_score_gemma":0.001235178,"domain_scores_codex":[0.9988556,0.0005193459,0.00006008535,0.0002224296,0.0002360615,0.0001064873],"domain_scores_gemma":[0.9965149,0.00202769,0.0004336682,0.0006042983,0.0002298931,0.0001894844],"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":[0.00009652486,0.00005039215,0.001258587,0.00009323285,0.00004547041,0.00007861393,0.00009969,0.4993777,0.002165897,0.4636722,0.0009753083,0.0320864],"study_design_scores_gemma":[0.000008938933,0.00002453067,0.00005989375,0.000008151777,0.00000618889,0.00001802837,0.00001107962,0.8602727,0.000713193,0.1384626,0.0004092646,0.000005235224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02180129,0.00009750733,0.9766315,0.0003285266,0.00001253765,0.00002038471,0.00005713354,0.0002500069,0.0008011343],"genre_scores_gemma":[0.8134124,0.0003819373,0.1839085,0.0003232035,0.00005148393,0.0001030222,0.0001787836,0.0001404767,0.001500275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004053812,"threshold_uncertainty_score":0.0214389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04423998331498467,"score_gpt":0.2421600431032657,"score_spread":0.197920059788281,"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."}}