arXiv AI
Jul 3
PreScience: A Dataset and Benchmark for Scientific Forecasting
arXiv:2602. 20459v2 Announce Type: replace Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow?
The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale
The paper introduces the Scientific Contribution Graph, a large-scale resource that extracts 6 million scientific contributions from 655 k open-access papers across multiple disciplines and links them with 36 million prerequisite edges. It frames automated technological roadmapping as the task of identifying contributions and their prerequisites, and presents a new scientific prerequisite prediction task where models forecast which existing technologies enable future discoveries. The authors report that current models achieve a 0.48 MAP score on temporally-filtered backtesting, indicating rapid progress in this area.
Related stories
arXiv Machine Learning
Oct 7
Learning Scientific Exploration from Human Research Decision Trajectories
arXiv:2610.07184v1 Announce Type: new Abstract: A key challenge in building AI systems for scientific research is enabling $\textit{scientific exploration}$: the systematic process of investigating u...
arXiv AI
Sep 25
Learning to Ideate for Scientific Impact
The paper "Learning to Ideate for Scientific Impact" explores using delayed signals of scientific uptake—specifically citation-normalized impact—as feedback to steer large language models toward generating high‑impact research ideas. The authors build a dataset of over 100,000 computer science papers, train a reward model to predict citation impact from goal‑idea pairs, and align an idea generator via supervised fine‑tuning and reinforcement learning. Evaluation with a reference‑grounded protocol shows that the RL‑tuned model consistently produces ideas with higher estimated impact than baseline models.
arXiv AI
Jun 16
Towards End-to-End Automation of AI Research
arXiv:2606. 15497v1 Announce Type: new Abstract: The automation of science is a long-standing ambition in the field of AI.
arXiv Computation and Language
Oct 8
LLM4Impact: Integrating Heterogeneous Information for Scientific Impact Prediction
arXiv:2610.10138v1 Announce Type: new Abstract: Predicting the future impact of a newly published paper is challenging because it must be inferred from heterogeneous evidence available at publication...
arXiv Machine Learning
Aug 11
ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery
arXiv:2605. 16902v2 Announce Type: replace Abstract: Scientific artifacts such as models and datasets are foundations for research.
arXiv Machine Learning
Sep 22
SCoR: A Hierarchical Framework for Forecasting Relations Between Scientific Concepts
arXiv:2609.22174v1 Announce Type: cross Abstract: Anticipating emerging research directions is a critical goal of AI-assisted science. Existing methods mainly predict which concepts will co-occur in...
arXiv Machine Learning
Sep 23
GitScholar: A Dataset for Predicting AI Research Impact from GitHub Engagement
arXiv:2609.26361v1 Announce Type: cross Abstract: With the rapid pace of AI research and the hundreds of daily new publications, staying up-to-date with the latest developments has become increasingl...
arXiv AI
Sep 25
AI in Science: Early Insights
The paper "AI in Science: Early Insights" analyzes AI’s impact on scientific work using data from 15 million Gemini interactions, 2,600 specialized AI models, and a survey of 600 scientists. It finds widespread AI adoption, complementary use of large language models and specialized tools, significant productivity gains of about seven hours per week, and a shift in research bottlenecks toward hypothesis backlog and verification needs. The study suggests AI can boost scientific productivity but its full effect depends on addressing new downstream challenges.
arXiv AI
Sep 10
From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles
The paper proposes a new method for credit scoring research articles that distinguishes between a paper’s original contribution and the prior work it builds upon. It introduces a hierarchical ‘contribution tree’ framework that conserves importance across a document’s structure and separates original from citation-derived credit. Large language models are employed as noisy comparative estimators to scale the analysis, and the approach is extended to collections of articles via weighted citation graphs to produce corpus-level contributions and normalized influence scores.
arXiv Machine Learning
Sep 3
Efficient Context-Limited Telescope Bibliography Classification for the WASP-2025 Shared Task Using SciBERT
The paper presents a SciBERT-based method for automatically classifying scientific papers into four telescope-related categories—science, instrumentation, mention, and not telescope—within strict 512-token limits. Despite truncation challenges, the approach achieved a macro F1 score of 0.89, topping the WASP-2025 leaderboard. The authors analyze truncation effects, compare chunking and long-context models, and offer insights into efficient scientific text curation.
arXiv Machine Learning
Sep 2
Modelpedia: A Catalog of Model Findings for the Meta-Science of AI
Modelpedia is an automated, LLM-assisted framework that extracts and organizes findings about AI models from published papers into a searchable public catalog. It links each finding to the relevant model, dataset, method, and concept, and has already extracted over a thousand findings from ICLR 2024 and 2025 papers. The authors invite the community to explore, contribute to, and build on this open catalog, positioning model findings as a shared foundation for the meta‑science of AI.