{"paper":{"title":"A Critical Field Guide for Working with Machine Learning Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Kate Crawford, Mike Ananny, Sarah Ciston","submitted_at":"2025-01-26T11:43:33Z","abstract_excerpt":"Machine learning datasets are powerful but unwieldy. Despite the fact that large datasets commonly contain problematic material--whether from a technical, legal, or ethical perspective--datasets are valuable resources when handled carefully and critically. A Critical Field Guide for Working with Machine Learning Datasets suggests practical guidance for conscientious dataset stewardship. It offers questions, suggestions, strategies, and resources for working with existing machine learning datasets at every phase of their lifecycle. It combines critical AI theories and applied data science conce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15491","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.15491/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}