A Statistically-Bounded Machine Learning Framework for Robust Full-Wave Electromagnetic Inversion
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper proposes a novel framework for solving electromagnetic inverse scattering (EMIS) problems under heterogeneous and high-contrast conditions. Traditional deterministic methods are fundamentally limited in such scenarios, as they struggle to express complex prior knowledge in tractable mathematical forms. Although recent machine learning (ML) approaches bypass this limitation by directly mapping observations to physical properties, their statistical nature often results in instability when encountering out-of-distribution (OOD) samples. To address this, we introduce a statistically bounded framework that integrates a ML model capable of producing heuristic estimates of the physical parameter distribution, along with corresponding upper and lower bounds. These bounds are calibrated to satisfy formal statistical guarantees and are incorporated into a bounded optimization algorithm for full-wave inversion (FWI). This design combines the speed of ML with the stability and interpretability of deterministic methods. The proposed framework is validated on OOD datasets and systematically evaluated through comprehensive ablation studies to assess the contribution of each component.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 it