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.
438 papers reviewed by authors · 71–80 / 438
This paper demonstrates that while linear probes suggest a Transformer trained on base-digit extraction computes staged arithmetic intermediates, causal tests reveal that the actual computational route relies on separate input streams that combine late, highlighting a significant divergence between representational evidence and causal mechanism.
This paper proposes a comprehensive framework for cardless AI banking that leverages machine learning algorithms, AI-driven data cryptography, and auto-generated virtual cards to enhance cybersecurity, authenticate transactions, and proactively mitigate fraud risks.
This study demonstrates that sunlight, when converted into a partially coherent source, can effectively detect rotational Doppler shifts by leveraging the superposition of signals across different wavelengths to enhance the signal-to-noise ratio, thereby enabling accurate passive remote sensing of rotational speeds.
This census-based study of Nepal's marginalized Raute community reveals that while over half of married women utilize family planning, primarily through injectables, there is a critical lack of awareness regarding safe abortion policies and negligible access to these services, highlighting an urgent need for culturally tailored, mobile outreach and legal literacy programs to improve reproductive health equity.
By comparing the spectral and mineralogical properties of LL chondrites and near-Earth objects with their potential sources, this study concludes that the Nysa and Flora asteroid families are the distinct parent bodies responsible for the petrologic diversity of LL chondrites, favoring a multiple-parent-body model over a single thermally stratified one.
This review synthesizes recent advances in evolutionary game dynamics that utilize reinforcement learning as a superior alternative to imitation learning, demonstrating its effectiveness in explaining the emergence of cooperation, fairness, trust, and resource coordination in human and natural systems.
This paper introduces a rigorous and computationally efficient measure of model complexity based on input gradient similarities that unifies various existing metrics and provides new insights into the double descent phenomenon across diverse model architectures.
This paper presents a tiered KV cache architecture that enables runtime-certified bounded-error quantized attention by computing online error bounds to trigger adaptive precision selection and deterministic FP16 fallback, thereby guaranteeing recovery to exact dense attention outputs while maintaining high compression for long-context LLM inference.
This study identifies the subgiant star TOI-5882 as a strong candidate for planetary engulfment, evidenced by its significant lithium enrichment which modeling suggests could result from the ingestion of a super-Earth to Neptune-mass planet.
The paper introduces BALLAST, a Bayesian active learning framework that optimizes the placement of Lagrangian sea drifters for inferring time-dependent ocean vector fields by incorporating look-ahead trajectory predictions and a novel efficient Gaussian Process inference method called VaSE.