aiqbench analysis
SHRAV introduces a state-continuation framework that bridges physical modeling and inverse design, enabling reusable computational states across architecture-independent workflows. The approach demonstrates significant gains in computational lithography metrics by integrating learned evolution with explicit numerical quantities for forward and inverse configurations. This work advances the intersection of machine learning and physics-informed computation, offering a structured method for handling complex iterative design problems.
SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design
arXiv:2609.27621v2 Announce Type: replace Abstract: Physical modeling and inverse design require computation that can continue from reusable state. We introduce SHRAV, an architecture-independent computational framework organized around State, Hypothesis, Reason, Action, and Verify. Its central mechanism is a state-continuation core with declared reuse boundaries and explicit roles for learned evolution and numerical quantities. Forward configurations evolve predictive state and read out physical responses; inverse-design configurations additionally generate target-directed modifications and consume evaluator feedback. Electromagnetic world-model studies are mapped to forward configurations, with selected readout and reuse diagnostics reported here. Computational lithography demonstrates an inverse-design configuration: four fixed-weight design updates improve thresholded aerial-image intersection-over-union from 0.5313 to 0.8153 under independent scalar-pupil replay, with a maximum absolute IoU difference of approximately 0.000824 between predictor estimates and independent replay.
Abstract:Physical modeling and inverse design require computation that can continue from reusable state. We introduce SHRAV, an architecture-independent computational framework organized around State, Hypothesis, Reason, Action, and Verify. Its central mechanism is a state-continuation core with declared reuse boundaries and explicit roles for learned evolution and numerical quantities. Forward configurations evolve predictive state and read out physical responses; inverse-design configurations additionally generate target-directed modifications and consume evaluator feedback. Electromagnetic world-model studies are mapped to forward configurations, with selected readout and reuse diagnostics reported here. Computational lithography demonstrates an inverse-design configuration: four fixed-weight design updates improve thresholded aerial-image intersection-over-union from 0.5313 to 0.8153 under independent scalar-pupil replay, with a maximum absolute IoU difference of approximately 0.000824 between predictor estimates and independent replay.
Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computational Physics (physics.comp-ph); Optics (physics.optics)
arXiv:2609.27621 [cs.AI]
(or arXiv:2609.27621v2 [cs.AI] for this version)
Full text under the publisher's open licence · 143 words
