ROSE: RADICAL Orchestrator for Surrogate Exploration
Bibliographic record
Abstract
Scientific computing increasingly relies on surrogate models to accelerate high-fidelity simulations, enable real-time predictions, and facilitate exploration of the design space. However, building effective surrogates at scale presents several challenges: simulations are computationally expensive, data generation must be carefully managed, and surrogate learning requires handling large, heterogeneous, and dynamically evolving workflows. These challenges are amplified in active learning contexts, where surrogate models guide further data acquisition, resulting in a tight coupling between simulation, inference, and model training. This paper introduces the ROSE (RADICAL Orchestrator for Surrogate Exploration) framework, a flexible, portable, and scalable software system designed to support the end-to-end lifecycle of surrogate modeling in high-performance computing environments. ROSE integrates active learning algorithms with scalable orchestration, managing asynchronous execution across diverse computing resources while minimizing user burden. It supports both in-situ and ex-situ workflows, online and offline training, and accommodates the dynamic structure of adaptive sampling and surrogate refinement. ROSE is used for three scientific use cases: electrolyte structure extraction, neutron diffraction structure recovery, and colloid phase classification. Across Polaris, Perlmutter, and Delta, ROSE sustains high throughput with low orchestration overhead, and delivers 4–8 × end-to-end speedups in our three use cases by exploiting parallel, pilot-based execution, where asynchronous orchestration typically yields 1.5–3 × versus synchronous baselines.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.017 | 0.008 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".