Papers where the original authors have engaged with our plain-language explanation.
For every paper on this page, at least one of the original authors has seen our plain-language explanation and engaged with it — either confirming it reads accurately or requesting corrections that we then applied. An endorsement does not mean the authors formally approve every sentence, but it does mean the explanation has passed the eyes of the people who wrote the paper.
1364 papers reviewed by authors · 1131–1140 / 1364
This paper proves that the misspecification penalty in kernelized bandit optimization — both offline (simple regret) and online (cumulative regret) — can be reduced from a square-root-of-complexity factor to a logarithmic or polylogarithmic one, by exploiting spectral localization in the offline setting and spatial domain-splitting in the online setting.
This paper demonstrates that while unsupervised Transformer-VAE latent spaces trained on SELFIES can support meaningful chemical property steering, such control is only valid when rigorously validated through decoded molecules and confound-aware evaluation to distinguish genuine chemical signals from sequence-level artifacts.
This paper provides a fine-grained analysis of the "suspicious alignment" phenomenon in SGD under ill-conditioned optimization, revealing how specific step size conditions cause gradient updates to align with a dominant subspace that paradoxically fails to reduce loss, while updates to the bulk subspace remain effective.
This computer-aided study demonstrates that single-walled carbon nanotubes effectively adsorb ionized glyphosate species through various interaction mechanisms, thereby underscoring their potential for environmental monitoring and the remediation of agricultural contamination.
This contribution introduces Semantic Pullbacks, a theoretically grounded method that interprets deep networks as input-conditioned affine operators to generate perceptually appropriate, stable, and reliable post-hoc explanations by reconstructing coherent local structures from target neurons.
This paper proposes the Adaptive Dynamic UX Statistical Framework (ADUX-Stat), a novel evaluation model that replaces static usability metrics with probabilistic constructs—specifically the Interaction Entropy Index, Temporal Drift Coefficient, and Bayesian Usability Confidence Score—to effectively assess the stochastic and context-sensitive nature of AI-mediated systems.
This paper presents a comprehensive Monte Carlo study demonstrating that the Temporal Spectral Noise-Floor Adaptation (TSNFA) method, which uniquely combines spectral band selection, temporal persistence filtering, and adaptive noise-floor tracking, achieves perfect detection with zero false positives in a 200-node IoT mesh network, outperforming six alternative algorithms that fail due to the absence of at least one of these critical defenses.
This paper establishes a connection between coarse-grained quantum dynamics and the quantum conditional states formalism from a Bayesian perspective, addressing the existence of emergent dynamics through analytical solutions and semidefinite programming while introducing a new robustness measure to quantify noise tolerance in these effective descriptions.
This paper challenges the notion that temporal reasoning is the primary bottleneck for large language models, proposing instead that failures stem from unstructured text-to-event representation and introducing a neuro-symbolic framework with a Probabilistic Inconsistency Signal that achieves perfect accuracy on benchmarks by decoupling semantic extraction from symbolic reasoning.
This paper introduces a transferable graph neural network framework that predicts optimized molecular orbital coefficients directly from geometry, enabling scalable, retraining-free acceleration of variational quantum eigensolver workflows by significantly reducing classical pre-processing overhead and improving convergence for larger hydrogen systems.