{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007155085,0.0001545028,0.0002540557,0.0003497296,0.0003494805,0.0001476846,0.001139138,0.00007477938,0.00008021],"category_scores_gemma":[0.0004212398,0.0000948294,0.0001258253,0.006632677,0.0001089198,0.000471405,0.0002334479,0.00029271,0.001135684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002847367,"about_ca_system_score_gemma":0.00001946015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001512496,"about_ca_topic_score_gemma":0.000001413553,"domain_scores_codex":[0.9983724,0.00008142385,0.000257794,0.000375409,0.0004256836,0.0004872436],"domain_scores_gemma":[0.9984565,0.0009170405,0.00006431423,0.0004417411,0.00005108296,0.00006926256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004476456,0.00008125454,0.0001115898,0.0000330244,0.00004484711,0.00007223577,0.0008907329,0.03066002,0.0000784071,0.8367801,0.0008829158,0.1303604],"study_design_scores_gemma":[0.0001699688,0.0000822029,0.0006550126,0.0000192899,0.00002698048,0.00001677768,0.0002127412,0.8266817,0.0002069872,0.1652812,0.006410428,0.0002367176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01116786,0.00019571,0.9823483,0.001339847,0.00005628885,0.00009773037,0.000001946969,0.000307834,0.004484524],"genre_scores_gemma":[0.9610788,0.0002670015,0.03527795,0.0001467051,0.00004074797,0.00002289538,0.000005645246,0.000011357,0.003148907],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9499109,"threshold_uncertainty_score":0.9996421,"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."}}