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.
1362 papers reviewed by authors · 1051–1060 / 1362
Based on 17 years of Fermi-LAT observations, this study identifies multiple GeV sources around the microquasar SS 433, including distinct East and West excesses, and provides the first observational evidence suggesting the acceleration of cosmic-ray protons in the large-scale outflows of Galactic microquasars.
This paper evaluates the resilience of various AI-generated text detection methods against paraphrasing attacks, revealing a critical trade-off where ensemble models like Binoculars offer superior accuracy but suffer the most significant performance degradation when faced with adversarial manipulation.
This paper proposes a kernelized convex clustering framework that projects data into a Reproducing Kernel Hilbert Space to effectively handle non-linear and non-convex structures, while providing theoretical guarantees on convergence and finite sample bounds alongside empirical evidence of superior performance over state-of-the-art methods.
This paper proposes a finite sheaf-theoretic framework that detects scientific theory shifts in AI agents by quantifying representational transport failures and obstruction costs to distinguish between valid deformations within an existing language and necessary extensions into new regimes.
Using 17 simulated low-mass galaxies from the Auriga Project, this study reveals that while stellar metallicity gradients are independent of intrinsic galaxy properties, the dispersion in halo metallicity is driven by satellite accretion timing and the characteristic U-shaped radial age profiles arise from a combination of ceased outer star formation and merger-driven stellar redistribution.
This paper introduces "Epistematics," a meta-evaluative methodology for auditing AI benchmarks to expose how unexamined theoretical assumptions create self-reinforcing evaluation traps that obscure structural limits, demonstrating its application by critiquing a recent proposal that inadvertently entrenches the very paradigm it seeks to revise.
This paper reveals that while KV cache compression improves throughput, it can severely degrade performance in multi-instruction scenarios by causing specific instructions to be ignored and system prompts to leak, but proposes simple eviction policy adjustments to mitigate these issues.
The paper presents SuperADD, a training-free, class-agnostic anomaly segmentation pipeline that leverages a DINOv3 backbone and robust preprocessing techniques to achieve state-of-the-art performance on the MVTec AD 2 dataset under challenging distribution shifts without requiring per-class hyperparameter tuning.
This paper argues that securing LLM-based AI agents requires applying operating system security principles, demonstrating through a unified architecture analysis and case study that while some risks are inherent, many vulnerabilities can be mitigated using established OS techniques like resource isolation and privilege separation.
This paper demonstrates that in the weak coupling regime of the IKKT model, quantum fluctuations are negligible compared to noncommutativity scales, thereby validating the emergence of semi-classical 3+1-dimensional geometry and gravity from specific matrix vacua.