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.
984 papers reviewed by authors · 661–670 / 984
This empirical study compares LLM-based and search-based merge conflict resolution tools, revealing that while LLMs excel with imbalanced content, search-based methods offer superior robustness and generalization, ultimately suggesting that hybrid systems combining both paradigms are necessary for optimal performance.
The ALPS II experiment at DESY conducted its first science campaign from February to May 2024, achieving a 20-fold improvement in sensitivity limits for axion-like particles without finding evidence of their existence, while demonstrating stable operation and preparing for future upgrades to further enhance detection capabilities.
This paper investigates the dynamical critical behavior of black hole phase transitions in anti-de Sitter spacetime by extending the stochastic free energy landscape framework to Kerr-AdS black holes, demonstrating pronounced critical slowing down and a universal dynamic scaling relation () across diverse black hole systems including RN-AdS and Bardeen black holes.
This paper reports the first observation on the EXL-50U spherical torus that small-scale magnetic reconnection, mediated by multiple magnetic islands, can stably re-accelerate neutral beam-injected energetic ions to energies up to 2.5 times their injection level without degrading core confinement, offering a novel mechanism for auxiliary heating in future fusion reactors.
This study demonstrates that few-shot prompted large language models, particularly Claude Haiku 4.5, can outperform supervised baselines like BioBERT in routing online patient inquiries to appropriate clinical follow-up levels under low-resource conditions, though their performance variability suggests they are best suited for supporting selective human review rather than autonomous deployment.
This paper presents measurements from the Princess Sirindhorn Neutron Monitor using new electronics to analyze cross-counter time delay distributions, revealing that approximately 4.5% of detected counts arise from multiple secondary particles within the same cosmic-ray shower rather than single particles, a finding that validates Monte Carlo simulations and refines the understanding of neutron monitor spectral variations.
This study proposes and validates a simulated annealing optimization method, utilizing the seasonal sliced Wasserstein distance, to select highly representative subsets of climate years from large ensembles, significantly outperforming current practices and alternative algorithms to provide robust, unbiased inputs for energy system modeling.
The paper introduces the Quantum Feature Amplification Network (QFAN), an autoregressive quantum generative model that overcomes the register-size bottleneck in calorimeter shower simulation by generating images as sequences of blocks using a fixed-size quantum circuit, successfully demonstrating its ability to reproduce key physical distributions on both simulators and IBM quantum hardware.
This paper introduces Painless Activation Steering (PAS), a fully automated and lightweight method that constructs activation vectors from labeled datasets without human intervention to effectively steer large language models toward desired behaviors, outperforming existing techniques in controllability and efficiency while demonstrating specific efficacy for behavior-oriented tasks.
This paper proposes a fairness-aware retrieval framework for Retrieval-Augmented Generation (RAG) that mitigates bias propagation in top-k settings through a scalable optimization approach called FARO, effectively balancing relevance and fairness without compromising generation quality.