Tag
Maxime Rivest 发布了 ScienceMadeReadable：一个免费、开源的科学文献语义搜索 API，覆盖约 2 亿篇论文，可直接被 AI 代理调用，无需密钥或注册，嵌入由 LightOn 的 DenseOn 模型驱动。
A GitHub repository offering twenty standalone LaTeX examples to create vintage scientific paper aesthetics, incorporating MetaPost and LuaTeX for graphics and typesetting.
Astra is a tool for checking scientific papers that uncovered numerous coding errors in replication packages, some overturning central results in high-ranking journals, and revealed that many models were not run properly.
PaperGym is a framework that converts scientific papers into training environments by separating research questions from evaluation rubrics, enabling reinforcement learning to improve research planning. It demonstrates improved performance over existing methods, with trained models outperforming larger ones on benchmarks.
ResearchQA is a new benchmark of 6,211 single-paper question-answer pairs from 494 open-access papers across eight domains, designed to evaluate citation-grounded question-answering by requiring verifiable citations and supporting grounded refusal when evidence is insufficient.
A large-scale mapping of 11 million academic papers using semantic similarity and time-based slices, enabling analysis of research trends and connections.
This paper proposes a context-enhanced transformer using formulaic expression desensitization for extracting problem and method sentences from scientific papers, achieving improvements of 3.71% and 2.67% in macro F1 score on two datasets.
PDFMathTranslate is an open-source tool that translates scientific PDFs while preserving math formulas, charts, tables, and layout, accepted at EMNLP 2025 and freely available under MIT license.
A paper co-authored by 37 authors from Stanford, CMU, Michigan, etc. proposes ARA (Agent-native Research Artifact) to replace the traditional paper format, aiming to solve the narrative tax and engineering tax, enabling AI agents to understand, reproduce, and extend research.
This paper empirically evaluates the alignment between LLM-generated and human reviews for scientific papers, finding limited and variable alignment. It also shows that authors can 'game' LLM reviews by iteratively revising papers to improve scores, with up to 35% of papers seeing statistically significant score increases.
This paper introduces ResearchArena, a scaffold for evaluating auto-research agents, and finds that while agent-generated papers appear competitive under manuscript-only review, artifact-aware review reveals severe failures in experimental rigor, with no paper meeting top-tier acceptance standards.