{"id":"W4402860189","doi":"10.1073/pnas.2409913121","title":"Message-Passing Monte Carlo: Generating low-discrepancy point sets via graph neural networks","year":2024,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Mathematical Approximation and Integration","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Air Force Research Laboratory; Schmidt Futures","keywords":"Computer science; Monte Carlo method; Leverage (statistics); Artificial neural network; Theoretical computer science; Point (geometry); Message passing; Margin (machine learning); Algorithm; Graphics; Computer graphics; Artificial intelligence; Machine learning; Mathematics; Computer graphics (images); Geometry; Parallel computing","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":[],"consensus_categories":[],"category_scores_codex":[0.001728796,0.000143946,0.0002131017,0.0001615032,0.0002461955,0.0001382196,0.0004591323,0.00009756644,0.00005089339],"category_scores_gemma":[0.000795024,0.0000872037,0.0001577963,0.0007699502,0.0003786253,0.0006202859,0.0001026361,0.000267553,0.000001219575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003952039,"about_ca_system_score_gemma":0.00001955458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000045083,"about_ca_topic_score_gemma":1.994886e-7,"domain_scores_codex":[0.9978784,0.00001485286,0.0006074577,0.0002393351,0.001075176,0.0001847468],"domain_scores_gemma":[0.9990386,0.0002988979,0.0003553104,0.00001326805,0.0002510319,0.00004292073],"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":[0.000006107613,0.00006698634,0.00008230133,0.0006168162,0.0000314469,2.432233e-8,0.0008789727,0.000641441,0.03490813,0.9573601,0.002827837,0.002579876],"study_design_scores_gemma":[0.00004675609,0.00001493566,0.0001029207,0.0003363139,0.00001553072,0.00000974368,0.000188887,0.566021,0.01647952,0.4167025,0.0000113053,0.00007060086],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9779207,0.0004360435,0.002088865,0.005430858,0.0001121314,0.0005223297,0.00001172937,0.0001324147,0.01334496],"genre_scores_gemma":[0.9727433,0.000009851655,0.0267143,0.0001774525,0.0001088114,0.00002070054,1.698058e-7,0.000009904132,0.0002155558],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5653796,"threshold_uncertainty_score":0.3556064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05572350366383775,"score_gpt":0.3377305370142211,"score_spread":0.2820070333503834,"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."}}