Related papers: SciPaths: Forecasting Pathways to Scientific Disco…
Retrieving targeted pathways in biological knowledge bases, particularly when incorporating wet-lab experimental data, remains a challenging task and often requires downstream analyses and specialized expertise. In this paper, we frame this…
Scientific hypothesis generation is a critical bottleneck in accelerating research, yet existing datasets for training and evaluating hypothesis-generating models are limited to single domains and lack explicit reasoning traces connecting…
Large Language Models (LLMs) have recently achieved impressive performance in math and reasoning benchmarks. However, they often struggle with logic problems and puzzles that are relatively easy for humans. To further investigate this, we…
Scientific research is being reshaped by AI systems that move beyond isolated assistance toward longer-horizon workflows spanning literature grounding, hypothesis generation, experimentation, validation, reporting, and revision. This shift…
The rapid growth of scientific literature calls for automated methods to assess and predict research impact. Prior work has largely focused on citation-based metrics, leaving limited evaluation of models' capability to reason about other…
Scientific and technological frontiers advance through punctuated dynamics, yet the principles governing these dynamics remain poorly understood. Here we collect and analyze datasets tracking the evolution of frontiers across 9 different…
Scientists and inventors set the direction of their work amidst an evolving landscape of questions, opportunities, and challenges. This paper introduces a measurement framework to quantify how far researchers move from their existing…
Scientific talks are a growing medium for disseminating research, and automatically identifying relevant literature that grounds or enriches a talk would be highly valuable for researchers and students alike. We introduce Reference…
Scientific literature is growing exponentially, creating a critical bottleneck for researchers to efficiently synthesize knowledge. While general-purpose Large Language Models (LLMs) show potential in text processing, they often fail to…
One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used as aides to human scientists, e.g. for…
Generalisability and transportability of clinical prediction models (CPMs) refer to their ability to maintain predictive performance when applied to new populations. While CPMs may show good generalisability or transportability to a…
Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to…
Perceiving and autonomously navigating through work zones is a challenging and underexplored problem. Open datasets for this long-tailed scenario are scarce. We propose the ROADWork dataset to learn to recognize, observe, analyze, and drive…
AI agents have seen widespread adoption in information retrieval for scientific research, giving rise to tools such as Deep Research. However, existing retrieval agents mainly rely on keyword- or embedding-based methods. While effective at…
Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging because of the complexity of both statistical methodology and real-world data. Inspired by the success of artificial intelligence in…
Existing benchmarks for frontier models often test specialized, "PhD-level" knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark with 613 problems based on the NPR Sunday Puzzle Challenge that requires…
The field of AI research is advancing at an unprecedented pace, enabling automated hypothesis generation and experimental design across diverse domains such as biology, mathematics, and artificial intelligence. Despite these advancements,…
Advancements in Large Language Models (LLMs) drive interest in scientific applications, necessitating specialized benchmarks such as Earth science. Existing benchmarks either present a general science focus devoid of Earth science…
This research introduces a comprehensive system based on state-of-the-art natural language processing, semantic embedding, and efficient search techniques for retrieving similarities and thus generating actionable insights from raw textual…
Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary systems with tens or hundreds of billions of parameters. Such reliance limits reproducibility and…