1986 papers
The journey from chemical synthesis to complex biological systems is captured in the "Cs — Se" category, bridging materials science, organic chemistry, and biochemistry. This diverse collection explores how scientists design new molecules, understand their reactions, and apply these insights to develop better medicines or sustainable materials. It represents the dynamic frontier where atomic precision meets real-world innovation.
Gist.Science brings these discoveries to you by processing every new preprint in this field directly from arXiv. We transform dense academic manuscripts into accessible plain-language overviews alongside detailed technical summaries, ensuring that both experts and curious minds can grasp the latest breakthroughs without getting lost in jargon. Below are the latest papers in the "Cs — Se" collection, curated to keep you informed on the most recent advancements.
This paper introduces ACCESS, an engineering methodology and tool suite that enables the development of safety-critical systems through evolving, model-based assurance cases capable of tracing heterogeneous artifacts, integrating formal methods, and supporting automatic evaluation at both development and runtime, as demonstrated by an Autonomous Underwater Vehicle case study.
This paper presents a long-term research vision for integrating artificial intelligence with formal methods to create a knowledge-driven verification ecosystem that synthesizes contracts, reuses semantic artifacts via hybrid learning-symbolic frameworks, and evolves systematically through compositional reasoning.
This paper introduces DeNovoSWE, a large-scale, automatically curated dataset of 4,818 whole-repository generation instances designed to train LLM agents for long-horizon software engineering tasks, which significantly boosts performance on the BeyondSWE-Doc2Repo benchmark from 5.8% to 47.2%.
This controlled pilot study demonstrates that while explicit software delegation contracts do not improve the objective correctness of AI coding agents' outputs, they significantly enhance the reviewability of their work by increasing evidence sufficiency and reducing ambiguity, albeit at the cost of increased token usage and execution time.
This paper argues that in stateful computing environments where adaptive mechanisms bias absolute performance measurements, software benchmarking should be reframed as a decision problem focused on identifying the fastest program through experiment designs that yield consistent estimates of performance differentials rather than absolute values.
This paper presents the first comprehensive systematization of knowledge on AI-augmented binary reversing by analyzing 144 research papers to establish a unified taxonomy that connects traditional techniques with modern AI approaches, thereby clarifying the field's evolution, identifying persistent challenges, and guiding future research.
This paper introduces a curriculum-grounded, configurable LLM-as-Judge pipeline that systematically aligns automated question-level marking with authorized educational standards and syllabus artefacts, achieving consistency comparable to human tutors while providing more traceable justifications for exam preparation.
This paper introduces a distribution-aware execution modeling approach for concurrent Go programs that leverages scheduler nondeterminism to fine-tune a 7B model on empirical event distributions, achieving state-of-the-art accuracy and improved calibration on real-world bug predictions while also providing formal guarantees for detecting specific goroutine leaks.
The paper proposes OmniDroneX, a unified Drone-as-a-Service ecosystem that leverages large language models and a formal abstraction model to transform fixed-function drones into dynamically composable, self-evolving entities capable of executing complex missions through natural language interaction and multi-layered service composition.
FacProcessTwin is an LLM-based system that significantly accelerates the development of process twins by automatically generating accurate process models from documentation and binding them to live data, while employing human-in-the-loop governance to ensure safety-critical decision accuracy in real-world manufacturing environments.