PAPER EVIDENCE RANKING

论文证据排行榜

基于PaperMiner证据链动态评分。缺失证据保持未知，不等同于零分；不同任务论文不宜只凭总分直接比较。

综合侧重 科研价值 工程落地 综合影响
单项维度 可信度 可复现性 实验充分度 创新性 工程价值 影响力
评分版本：paper-evidence-v3 最低证据覆盖率：35%
排名 论文 得分 主要署名单位 任务 / 年份 覆盖率
1 Unsupervised Anomaly Detection in Brain MRI via Disentangled Anatomy Learning⋆ 65.69 School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China; School of Computer Science, The University of Sydney, Sydney, Australia; Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, China; Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China; Biomedical Engineering Department, Tulane University, New Orleans, USA. AI医疗 · 2025 100%
2 Decoding the Sequence Determinants of Locus-Specific DNA Methylation Across Human Tissues 65.63 Shandong University, Chinese Academy of Sciences, Macao Polytechnic University, University of Electronic Science and Technology of China, Tianjin University AI科研 100%
3 Highly accurate protein structure prediction for the human proteome 65.55 DeepMind, European Bioinformatics Institute (EMBL-EBI) AI科研 100%
4 Flow cytometry with event-based vision and spiking neuromorphic hardware 65.46 University of Groningen, Ghent University - imec 类脑计算 100%
5 LitBench: A Graph-Centric Large Language Model Benchmarking Tool For Literature Tasks 65.46 Yale University 数据集 · 2026 100%
6 The limits of fair medical imaging AI in real-world generalization 65.41 Massachusetts Institute of Technology, Emory University, Stanford University AI医疗 100%
7 Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art 65.35 Immersive Media Design University of Maryland College Park, Center for the Study of the Force Majeure University of California, Santa Cruz, Virtual Planet Technologies Agent · 2025 100%
8 Building Low-Altitude Communication Networks: A Digital Twin-Based Optimization Framework 65.34 中国电子科技大学深圳高等研究院，香港中文大学（深圳），香港科技大学，中国移动通信集团广东有限公司深圳分公司，香港中文大学 AI应用 · 2026 100%
9 StyleDoctor: Towards Specialist Reward Model for Style-centric Generation Tasks 65.33 Mohamed bin Zayed University of Artificial Intelligence, MMLab, The Chinese University of Hong Kong 图像生成 100%
10 Beyond Fine-Tuning: Robust Food Entity Linking under Ontology Drift with FoodOntoRAG 65.32 Jožef Stefan International Postgraduate School, Jožef Stefan Institute, Ljubljana, Slovenia NLP · 2026 100%
11 DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression 65.32 City University of Hong Kong, Hong Kong SAR, China; Peking University Shenzhen Graduate School, China; University of Missouri-Kansas City, USA; Tencent Media Laboratory, USA 3D渲染 · 2026 100%
12 Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies 65.28 HSE University AI应用 · 2026 100%
13 C2|Q⟩: A Robust Framework for Bridging Classical and Quantum Software Development — RCR Report 65.24 M3S Research Group, SEIS Unit, University of Oulu, Finland; Nano and Molecular Systems Research Unit, University of Oulu, Finland; School of Computer Science, Wuhan University, China; Software Engineering Department, Lappeenranta-Lahti University of Technology, Finland; Department of Computer Science, Aalto University, Finland 量子计算AI · 2026 100%
14 Multivalent ion binding site identification with structure-based deep learning 65.2 Constructor University Bremen gGmbH, Constructor Labs AI科研 100%
15 Multi-modal learning with incomplete data 65.17 University of Oslo 多模态 100%
16 LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning 65.13 East China Normal University, Shanghai Jiao Tong University AI应用 · 2026 100%
17 MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation 65.03 上海科学智能研究院， 南洋理工大学， 复旦大学 数据集 · 2025 100%
18 Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents 64.92 Southern University of Science and Technology, Ant Group Agent · 2026 100%
19 FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data 64.84 Peking University, Fuyao Group, University of Southampton AI应用 · 2026 100%
20 Towards Expressive and Faithful Audio-to-Image Generation: A Unified Multimodal Dataset and Synthesis Framework 64.75 University of Science and Technology of China, Institute of Artificial Intelligence, China Telecom (TeleAI), Northwest Polytechnical University 数据集 · 2026 100%
21 Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels 64.73 Apple 大语言模型 · 2026 100%
22 Post-Earthquake Restoration of Electricity-Gas Distribution Systems with Damage Information Collection and Repair Vehicle Routing 64.71 Tsinghua University, Beijing Jiaotong University, State Grid Shanghai Municipal Electric Power Company AI应用 · 2026 100%
23 RealHD: A High-Quality Dataset for Robust Detection of State-of-the-Art AI-Generated Images 64.69 Zhejiang University of Technology, Intel Corporation 数据集 · 2026 100%
24 Feature Slice Matching for Precise Bug Detection 64.61 Renmin University of China, Institute of Software, Chinese Academy of Sciences, University of Trento 软件安全 · 2025 100%
25 Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank 64.56 Stanford University 模型架构 100%
26 DepthAnything and SAM for UIE: Exploring Large Model Information Contributes to Underwater Image Restoration 64.5 Sun Yat-sen University, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) 图像增强 100%
27 Cost-Efective Repository Exploration for Agentic Issue Localization 64.5 ITMO University Agent · 2026 100%
28 NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results 64.41 Lomonosov Moscow State University, MSU Institute for Artificial Intelligence, AIRI, Innopolis University, University of Würzburg, Tencent, Alibaba Group, Beihang University, Longyuan (Beijing) New Energy Engineering Technology Co., Ltd., China Telecom Digital Intelligence Technology Co., Ltd., Key Laboratory of Optical Astronomy, National Astronomical Observatories, Chinese Academy of Sciences, University of Science and Technology of China, ByteDance Inc, Texas A&M University, The Hong Kong Polytechnic University, Northeastern University 视频增强 · 2025 100%
29 OmniPhys: Knowledge-Graph-Driven Benchmarking and Collective Optimization for Physical Commonsense in Text-to-Image Generation 64.4 浙江大学；曼彻斯特大学；爱丁堡大学；蚂蚁集团 图像生成 · 2026 100%
30 Solaris: Building a Multiplayer Video World Model in Minecraft 64.34 New York University 视频生成 · 2026 100%
31 Visual Indicators to Increase the Detection of Linguistic Media Bias 64.33 University of Konstanz, University of Göttingen, National Institute of Informatics (JAPAN), Shanghai Academy of AI for Science (SAIS) (部分作者) AI应用 · 2026 100%
32 Deterministic access to global viral sequence data enables robust agent-driven scientific discovery 64.27 Broad Institute of MIT and Harvard, NCBI, Robert Koch Institute, Shanghai Academy of AI for Science (SAIS) AI科研 · 2026 100%
33 A Framework for Switchable LLM Alignment via CITA – Contrastive Instruction-Tuned Alignment 64.27 1San José State University, USA 2Google, USA 3Apple, USA 4Pragya Lab, BITS Pilani Goa, India 大语言模型 · 2026 100%
34 Liberals are less willing to buy Teslas than other electric vehicles, moderated by perceptions of Elon Musk 64.25 Nature Communications, University of Colorado Boulder, Vanderbilt University 预测模型 100%
35 "DIVE" into Hydrogen Storage Materials Discovery with AI Agents 64.23 Advanced Institute for Materials Research (WPI-AIMR), Tohoku University, Sendai 980-8577, Japan; Frontier Research Institute for Interdisciplinary Sciences (FRIS), Tohoku University, Sendai 980-8577, Japan; Department of Materials Engineering, The University of Tokyo, Tokyo 113-8656, Japan; Institute of Fluid Science, Tohoku University, Sendai, 980-8577, Japan; Institute for Materials Research (IMR), Tohoku University, Sendai, 980-8577, Japan Agent · 2025 100%
36 Approaching Low-Cost Cardiac Intelligence with Semi-Supervised Knowledge Distillation 64.21 Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China; Hong Kong Center for Cerebro-Cardiovascular Health Engineering, Hong Kong Science Park, Hong Kong, China; Hong Kong Institutes of Medical Engineering, Hong Kong, China; Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China; the AICARE Bay Lab,Guangdong Medical University, Dong Guan, China; Department of Electrical and Computer Engineering and School of Biomedical Engineering, McMaster University, Hamilton, ON, Canada; Department of Data Science, City University of Hong Kong, Hong Kong, China AI医疗 · 2025 100%
37 DepthAnything and SAM for UIE: Exploring Large Model Information Contributes to Underwater Image Restoration 64.21 Sun Yat-sen University, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) 图像增强 100%
38 SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? 64.2 Shanghai Innovation Institute, Fudan University AI科研 · 2026 100%
39 Hand Held Multi-Object Tracking Dataset in American Football 64.19 Keio University 数据集 · 2025 100%
40 Brain-Grounded Axes for Reading and Steering LLM States 64.18 NYU 大语言模型 · 2025 100%
41 Self-Supervised Z-Slice Augmentation for 3D Bio-Imaging via Knowledge Distillation 64.17 Center for Interdisciplinary Research in Biology (CIRB), Collège de France, Université PSL, CNRS, INSERM, 75005 Paris, France; Université Grenoble-Alpes, CEA, CNRS, INRA, Interdisciplinary Research Institute of Grenoble, CytoMorpho Lab, Grenoble, France; Laboratory of Developmental Biology of the Villefranche-sur-Mer, Institute of Villefranche-sur-Mer, Sorbonne University, CNRS, Villefranche-sur-Mer, France; Laboratory of Molecular Biology, National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, 20892, USA; Department of Reproductive Medicine, Hospices Civils de Lyon, Bron, France; INSERM U1208 Stem Cells and Brain Institute, Bron, France; Claude Bernard Lyon 1 University, Lyon, France. AI医疗 · 2025 100%
42 MADD: Multi-Agent Drug Discovery Orchestra 64.15 ITMO University, Saint Petersburg, Russia; Sber AI Lab, Moscow, Russia; D ONE AG, Zurich, Switzerland; HSE University, Moscow, Russia AI医疗 · 2025 100%
43 Analytic Fourier ptychotomography for volumetric refractive index imaging 64.15 Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, USA; Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, CA, USA AI医疗 · 2025 100%
44 Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction 64.11 University of Washington, World Labs 视频生成 · 2026 100%
45 Trade Execution Flow as the Underlying Source of Market Dynamics 64.09 Lomonosov Moscow State University, Autretech Group, Peter the Great St. Petersburg Polytechnic University, Ioffe Institute AI金融 · 2025 100%
46 Crystal structure prediction with nuclear quantum and finite-temperature effects via deep free energy learning 64.08 Institute of Applied Physics and Computational Mathematics, Artificial Intelligence for Science Institute, Jilin University, Ecole Polytechnique Fédérale de Lausanne (EPFL), Institute of Physics, Chinese Academy of Sciences, Peking University AI科研 · 2026 100%
47 Institutional Books — Visual Elements: An open-source pipeline for extracting, classifying, deduplicating, and captioning visual elements from digital book collections. 64.07 Harvard Law School Library, Harvard Library, Harvard Law School, Harvard School of Engineering and Applied Sciences, Harvard Kennedy School 数据集 · 2026 100%
48 SIDME: Self-supervised Image Demoiréing via Masked EncoderDecoder Reconstruction 64.07 College of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China; College of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai 200030, China; College of Information, Shanghai Ocean University, Shanghai 201306, China; College of Computer, Beijing University of Posts and Telecommunications, Beijing 100876, China 未分类 · 2025 100%
49 ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development 64.06 Fudan University, Shanghai Qiji Zhifeng Co., Ltd., Shanghai Innovation Institute Agent · 2026 100%
50 System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5 64.06 The Hangzhou International Innovation Institute Beihang University China 大语言模型 · 2026 100%

排名用于发现值得进一步核查的论文，不替代同行评审。评分会随新增引用、复现、实验验证、新闻评价和落地证据持续更新。

社区反馈如何参与？

PaperMiner MCP已开放结构化论文反馈。可提交复现成功或失败、代码可运行或失效、Benchmark纠错、链接纠错和部署结果。

不直接改分反馈独立形成“社区信号”，与六维证据评分隔离。
必须带依据需要公开链接或实验结果哈希；无依据的点赞不进入系统。
自动交叉验证至少两个独立账号给出同类结论后，才标记为已有多人印证。
自动防刷个人密钥限频、去重；新账号和利益相关反馈自动降低权重。

MCP接口：submit_paper_feedback、get_paper_community_feedback

权限：有效PaperMiner账号获配的个人MCP密钥可提交；公共代理和共享只读密钥只能查询。每个账号每天最多提交5条新反馈。