RobGenX: Uncertainty-Aware Inference in eXtreme Computing Power Networks
Bibliographic record
Abstract
Computing Power Networks (CPNs) emerged as a promising architectural paradigm that unifies the edge and user-owned eXtreme Edge Devices (XEDs) into an orchestrated compute fabric. By leveraging opportunistic idle resources at the eXtreme Edge (XE), CPNs offer a pathway to democratize generative AI and reduce reliance on cloud monopolies. However, inference delegation within CPNs is hindered by the volatile and user-dependent nature of compute availability of XEDs. In this work, we propose RobGenX, a robust task allocation framework tailored for inference in XE-enabled CPNs under stochastic compute capacity constraints. To the best of our knowledge, RobGenX is the first work to explicitly model the uncertainty of XEDs' compute capacity. RobGenX integrates Recourse Programming (RP) to penalize overassignment and Chance-Constrained Programming (CCP) to enforce probabilistic workload guarantees, respectively. We model the task allocation problem as a two-stage chance-constrained program and obtain an equivalent deterministic reformulation using a scenario-based approach. To overcome the computational burden of the resulting Integer Linear Program (ILP), we develop a decomposition-based solution using the Alternating Direction Method of Multipliers (ADMM), which decouples the relaxed problem into parallelizable subproblems across uncertainty scenarios. Simulation results demonstrate that RobGenX and its lower complexity ADMM-based solution consistently outperform the state-of-the-art task allocation baselines, achieving up to 58% improvement in inference completion rates and 55% in assignment stability.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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".