Observable-Specific Validity Tests for Scientific AI: Controlled Approximations and Intervention Response
cs.LG, cs.AI, cs.DL
Submitted: 2026-10-30
Updated: 2026-10-30
License: http://creativecommons.org/licenses/by/4.0/
The gist: An approximation can reproduce an energy while missing its response, or satisfy an error tolerance without being certified by a given bound.
Terminology
Abstract
An approximation can reproduce an energy while missing its response, or satisfy an error tolerance without being certified by a given bound. We formulate observable-specific validity records for scientific artificial intelligence (AI) that link a reduction to its reference model, error measure, tolerance, parameter domain, and transformations or interventions. Explicit displacement and velocity certificates for a singularly perturbed oscillator recover distinct convergence orders and provide sufficient validity guarantees. Exact Hubbard dimer relations resolve the different coupling domains accepted by energy and response criteria. Across 16 repeated neural fits, imposing dimensional homogeneity reduces energy scale transfer error from 52.3% to 0.0768% and raises the median fraction jointly satisfying gap and response tolerances from zero to 100%. Paired transformations verify the protected scaling relation, while a coupling crossover identifies the additional information needed for response transfer. A causal model recovers a positive intervention response beneath a strong negative observational association. For two mechanisms observed with Gaussian noise whose responses first differ at order x k, we derive an exact fixed control query requirement scaling as x-2k and verify its full success curve numerically. Together with a 256-task evaluation interface, these results provide independently checkable tests of controlled approximation, physical transfer, and mechanism discrimination in scientific AI.
Sources
- PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
- CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics
- Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark
- PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language Models
- PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
- LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
- DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking
- Think like a Scientist: Physics-guided LLM Agent for Equation Discovery
- Lagrangian Neural Networks
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis