Research papers are filled with citations, but clicking on any of them makes you lose your place in the paper We made citations much easier to navigate, with extra information on hover including authors and institutions Now, you can hover over any in-text citation to instantly preview the referenced paper, jump directly to the full citation, and return to exactly where you left off with a single click This includes quick access to the authors and their organizations, so you can understand the people behind the research without breaking your reading flow Try it now on any paper at

AI systems now write research papers autonomously — yet phantom references, method-code misalignment, and unreproducible scores have become endemic failures undermining scientific integrity. Title: Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence Google Cloud's Science One Framework treats verifiability as a first-class architectural constraint through the Chain-of-Evidence principle, solving the trustworthiness crisis in autonomous AI research at its root. 🔍 Highlight 1 — Chain-of-Evidence (CoE): two foundational principles Completeness: every claim carries a recorded evidence chain. Correctness: each chain genuinely supports its claim. These two principles eliminate phantom references entirely — baseline systems showed rates up to 21% — while achieving best-in-class method-code alignment across all evaluated systems. The key difference from prior work: evidence chains are constructed at claim-generation time, not retrofitted as a post-hoc check. 🏗 Highlight 2 — Three-module architecture Problem Investigator builds citation graphs from up to 100 full-text PDFs via Semantic Scholar API, grounding every reference in retrieved data rather than model memory. Discovery Engine explores parallel solution branches while keeping immutable records of all raw evaluator outputs. Paper Writer and Claim Verifier binds every factual claim to specific workspace artifacts and conservatively reconciles misalignments rather than deleting them — preserving scientific transparency. 🏆 Highlight 3 — MLE-Bench and Parameter-Golf results Across five Kaggle competitions covering medical imaging, fine-grained recognition, and 3D perception: two Gold Medals and two Silver Medals. Won the 3D Object Detection task where every baseline system failed completely. On Parameter-Golf — a live LLM training competition under strict hardware and file-size constraints — achieved state-of-the-art as of April 27, 2026, while baselines could not produce valid submissions at all. Rigor and capability don't trade off. Science One outperformed five state-of-the-art systems including AI Scientist v2, AutoResearchClaw, and DeepScientist, setting a new standard for verifiable autonomous research. #AIResearch# #AutonomousScience#

for anyone doing research or reproducing papers, i came across this new tool that automates a big part of the painful setup work. alphaXiv turns research papers + code into runnable experiments. instead of manually fixing broken setups, an agent can now: - Clone the repo - Read the paper + code - Fix the environment - Run the experiments end-to-end it works by changing repo URLs (e.g. github → argithub, arxiv→ autoarxiv), which triggers the agent. GLM 5.2 was able to run real multi-node training on its own with this setup. having 1M context helps a lot since the whole project stays in view.

Introducing DeepSeek-V4.1-Flash for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references Check it out on any paper on

🚨 A computer science hypothesis underpinning hundreds of research papers is being challenged by AI. OpenAI announced that its AI found an algorithm that refutes the Exponential Time Hypothesis (ETH), which concerns how the difficulty of solving certain computational problems grows with their size. The company says the result was obtained on October 16 and formally verified using Lean the following day. The paper and proof have been published on GitHub. The hypothesis’s originators, Russell Impagliazzo and Ramamohan Paturi, will lead the review alongside MIT’s Ryan Williams. If confirmed, the finding would require conclusions that rely on ETH to be reassessed. Whether it translates into practical algorithmic speedups remains an open research question. The company also reported proofs of the Kakeya conjecture in all dimensions and the “existence” component of the Yang–Mills Millennium Prize Problem. The latter has not yet been released publicly and will undergo verification led by Nobel laureate David Gross. These reported breakthroughs still await further independent scrutiny from the academic community. #AI# #OpenAI# #oncoin# #Mathematics#