{"id":"W4416004471","doi":"10.1145/3731599.3767347","title":"ROSE: RADICAL Orchestrator for Surrogate Exploration","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Orchestration; Scalability; Asynchronous communication; Surrogate model; Throughput; Software; Inference","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004287831,0.0004671364,0.0006169664,0.0002439399,0.0008175522,0.001391052,0.001203159,0.000319261,0.004426226],"category_scores_gemma":[0.002635365,0.0004285252,0.0001716588,0.000786285,0.0007639602,0.001228431,0.0003373515,0.0002316479,0.000741246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001775452,"about_ca_system_score_gemma":0.0007848295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001578052,"about_ca_topic_score_gemma":0.00005148917,"domain_scores_codex":[0.9954159,0.0005791039,0.001109182,0.001291006,0.0005823169,0.00102251],"domain_scores_gemma":[0.9974856,0.0007660856,0.0003384156,0.0008337131,0.0003305373,0.0002456621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003486755,0.0002227051,0.0003832628,0.000603219,0.00001899798,0.000004901095,0.0004131833,0.00284806,0.846549,0.1313936,0.01427072,0.002943674],"study_design_scores_gemma":[0.002453218,0.0005799896,0.001052558,0.0003718608,0.0001338206,0.000007161125,0.0004944672,0.1209503,0.7331963,0.02619,0.1136022,0.0009680521],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2869184,0.0002969146,0.6707223,0.01456844,0.01286838,0.002674454,0.0001302017,0.0005331341,0.01128774],"genre_scores_gemma":[0.8774741,0.00008544989,0.09326024,0.001553502,0.0006073071,0.0004448012,0.00003595353,0.00005070107,0.026488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5905557,"threshold_uncertainty_score":0.9998167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02903142424395828,"score_gpt":0.3319663657140954,"score_spread":0.3029349414701372,"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."}}