{"list":"other","total":55,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2210.07182","title":"PDEBENCH: An Extensive Benchmark for Scientific Machine Learning","created":"2022-10-13","cited_by_count":413},{"id":"2010.09990","title":"The Open Catalyst 2020 (OC20) Dataset and Community Challenges","created":"2020-10-20","cited_by_count":246},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243},{"id":"1911.02549","title":"MLPerf Inference Benchmark","created":"2019-11-06","cited_by_count":199},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178},{"id":"2412.00568","title":"The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning","created":"2024-11-30","cited_by_count":145},{"id":"2106.07597","title":"MLPerf Tiny Benchmark","created":"2021-06-14","cited_by_count":124},{"id":"1910.01500","title":"MLPerf Training Benchmark","created":"2019-10-02","cited_by_count":115},{"id":"2206.08917","title":"The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts","created":"2022-06-17","cited_by_count":95},{"id":"2110.01406","title":"MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation","created":"2021-09-29","cited_by_count":88},{"id":"2403.07059","title":"Better than classical? The subtle art of benchmarking quantum machine learning models","created":"2024-03-11","cited_by_count":85},{"id":"1712.03641","title":"DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics","created":"2017-12-11","cited_by_count":79},{"id":"2505.09598","title":"How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference","created":"2025-05-14","cited_by_count":76},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75},{"id":"2110.12773","title":"Scientific Machine Learning Benchmarks","created":"2021-10-25","cited_by_count":60},{"id":"2307.01909","title":"ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling","created":"2023-07-04","cited_by_count":47},{"id":"2310.05963","title":"CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics","created":"2023-09-13","cited_by_count":46},{"id":"2410.23326","title":"MassSpecGym: A benchmark for the discovery and identification of molecules","created":"2024-10-30","cited_by_count":38},{"id":"2410.21611","title":"CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation","created":"2024-10-28","cited_by_count":35},{"id":"1810.01993","title":"Exascale Deep Learning for Climate Analytics","created":"2018-10-03","cited_by_count":28},{"id":"2503.13517","title":"CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning","created":"2025-03-14","cited_by_count":28},{"id":"2301.11259","title":"Domain-Agnostic Molecular Generation with Chemical Feedback","created":"2023-01-26","cited_by_count":22},{"id":"2504.06260","title":"FEABench: Evaluating Language Models on Multiphysics Reasoning Ability","created":"2025-04-08","cited_by_count":22},{"id":"2410.12032","title":"MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI","created":"2024-10-15","cited_by_count":16},{"id":"2110.11466","title":"MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems","created":"2021-10-21","cited_by_count":15},{"id":"2304.11619","title":"SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models","created":"2023-04-23","cited_by_count":15},{"id":"2007.03152","title":"The gem5 Simulator: Version 20.0+","created":"2020-07-07","cited_by_count":14},{"id":"2008.08198","title":"BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning","created":"2020-08-18","cited_by_count":14},{"id":"2207.07958","title":"FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learning","created":"2022-07-16","cited_by_count":12},{"id":"1811.08933","title":"Analyzing Machine Learning Workloads Using a Detailed GPU Simulator","created":"2018-11-18","cited_by_count":9},{"id":"2208.11035","title":"Not All GPUs Are Created Equal: Characterizing Variability in Large-Scale, Accelerator-Rich Systems","created":"2022-08-23","cited_by_count":9},{"id":"2501.14663","title":"End-to-end workflow for machine learning-based qubit readout with QICK and hls4ml","created":"2025-01-24","cited_by_count":8},{"id":"2312.00128","title":"Low latency optical-based mode tracking with machine learning deployed on FPGAs on a tokamak","created":"2023-11-30","cited_by_count":7},{"id":"2505.08341","title":"Benchmarking AI scientists for omics data driven biological discovery","created":"2025-05-13","cited_by_count":7},{"id":"2411.00172","title":"SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey","created":"2024-10-31","cited_by_count":6},{"id":"2101.08359","title":"BOOSTR: A Dataset for Accelerator Control Systems","created":"2021-01-20","cited_by_count":5},{"id":"2501.05515","title":"Neural Architecture Codesign for Fast Physics Applications","created":"2025-01-09","cited_by_count":5},{"id":"2503.02112","title":"Building Machine Learning Challenges for Anomaly Detection in Science","created":"2025-03-03","cited_by_count":5},{"id":"2310.08677","title":"GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts","created":"2023-10-12","cited_by_count":4},{"id":"2410.05133","title":"A Digital Twin Framework for Liquid-cooled Supercomputers as Demonstrated at Exascale","created":"2024-10-07","cited_by_count":3},{"id":"2501.04845","title":"Intelligent experiments through real-time AI: Fast Data Processing and Autonomous Detector Control for sPHENIX and future EIC detectors","created":"2025-01-08","cited_by_count":3},{"id":"2508.20016","title":"HPC Digital Twins for Evaluating Scheduling Policies, Incentive Structures and their Impact on Power and Cooling","created":"2025-08-27","cited_by_count":3},{"id":"2408.11919","title":"PAL: A Variability-Aware Policy for Scheduling ML Workloads in GPU Clusters","created":"2024-08-21","cited_by_count":2},{"id":"2511.05614","title":"An MLCommons Scientific Benchmarks Ontology","created":"2025-11-06","cited_by_count":2},{"id":"1307.5448","title":"Software Carpentry: Lessons Learned","created":"2013-07-20","cited_by_count":1},{"id":"2509.16513","title":"Trace Replay Simulation of MIT SuperCloud for Studying Optimal Sustainability Policies","created":"2025-09-20","cited_by_count":1}],"next_cursor":null}