{"total":16,"rows":[{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243,"area":null},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"area":null},{"id":"2206.15076","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2502.02379","title":"No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets","created":"2025-02-04","cited_by_count":16,"area":null},{"id":"2110.03111","title":"Cut the CARP: Fishing for zero-shot story evaluation","created":"2021-10-06","cited_by_count":14,"area":null},{"id":"2201.07406","title":"Fooling MOSS Detection with Pretrained Language Models","created":"2022-01-19","cited_by_count":12,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2301.10516","title":"What are the Machine Learning best practices reported by practitioners on Stack Exchange?","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2309.03617","title":"NeuroCodeBench: a plain C neural network benchmark for software verification","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2405.08848","title":"Automated Repair of AI Code with Large Language Models and Formal Verification","created":"2024-05-14","cited_by_count":3,"area":null},{"id":"2604.28053","title":"To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2110.06592","title":"Life is not black and white -- Combining Semi-Supervised Learning with fuzzy labels","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2206.04731","title":"Leveraging Centric Data Federated Learning Using Blockchain For Integrity Assurance","created":"2022-06-09","cited_by_count":0,"area":null},{"id":"2305.00233","title":"Towards machine learning guided by best practices","created":"2023-04-29","cited_by_count":0,"area":null},{"id":"2411.19304","title":"Perspective of Software Engineering Researchers on Machine Learning Practices Regarding Research, Review, and Education","created":"2024-11-28","cited_by_count":0,"area":null}],"next_cursor":null}