arXiv:2606. 26228v1 Announce Type: cross Abstract: We review the concepts of interpretability and explainability as they apply to machine learning in physics.
arXiv:2606. 12289v1 Announce Type: cross Abstract: As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations.
The paper argues that explainable AI for computer vision has focused too much on developing interpretability methods rather than assessing how interpretable the models themselves are. It proposes a shift toward model-centric evaluation, using existing tools to compare what different models represent and compute, and emphasizes the need to measure whether humans can truly understand these models. The authors review the current toolbox, survey limited model comparison work, draw parallels to systems neuroscience, and outline a future agenda for model-focused XAI.
arXiv:2506. 15199v4 Announce Type: replace Abstract: While there are many applications of ML to scientific problems that look promising, visuals can be deceiving.
arXiv:2605. 27618v2 Announce Type: replace Abstract: Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable.
arXiv:2606. 29346v1 Announce Type: new Abstract: Post-hoc explanation methods are routinely used to interpret scientific machine learning models, with the deliverable understood to be insight into the phenomenon the model has been trained on.
arXiv:2607. 02203v1 Announce Type: new Abstract: Operator learning has emerged as a powerful tool for modeling complex physical systems in functional spaces.
arXiv:2601. 12913v4 Announce Type: replace Abstract: This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpretability can be formally tested or designed for.
arXiv:2608. 05702v1 Announce Type: new Abstract: Scientific machine learning commonly validates models at the level of a subdomain, a benchmark split, or an explanation for one prediction.
The paper introduces a framework that separates physical modeling from execution in physics reasoning tasks. It uses a two‑stage post‑training approach: supervised fine‑tuning to build structured models and reinforcement learning with rubric‑based feedback to refine them. Experiments on PhysReason, PhyX, and SeePhys show that this explicit modeling improves reasoning performance by about 3% on average for small LLMs.
arXiv:2606. 06533v1 Announce Type: new Abstract: What would it mean to have a scientific understanding of AI?
arXiv:2607. 14315v1 Announce Type: cross Abstract: In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score.
The paper proposes Domain-aware Fourier Features (DaFFs) for Physics-Informed Neural Networks (PINNs), embedding domain-specific geometry and boundary conditions into the positional encoding. DaFFs eliminate the need for explicit boundary loss terms, simplify optimization, and reduce training cost, leading to orders-of-magnitude lower errors and faster convergence compared to vanilla PINNs and RFF-based PINNs. An LRP-based explainability framework further shows that DaFFs produce more physically consistent relevance attributions, improving interpretability.