{"url":"/task/slice-discovery","name":"Slice Discovery","slug":"slice-discovery","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Knowledge Base","url":"/area/knowledge-base"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":10,"papers_with_code":6,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/xai","name":"Explainable Artificial Intelligence (XAI)"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":6,"of":6,"tagged_in_all":10,"items":[{"url":"/paper/where-does-my-model-underperform-a-human","title":"Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms","date":"2023-06-13","arxiv_id":"2306.08167","repositories_listed":2,"syntology":null},{"url":"/paper/domino-discovering-systematic-errors-with-1","title":"Domino: Discovering Systematic Errors with Cross-Modal Embeddings","date":"2022-03-24","arxiv_id":"2203.14960","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/language-driven-slice-discovery-and-error","title":"LADDER: Language Driven Slice Discovery and Error Rectification","date":"2024-07-31","arxiv_id":"2408.07832","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_unverified":2,"n_pointer_only":17}},{"url":"/paper/slicing-through-bias-explaining-performance","title":"Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods","date":"2024-06-17","arxiv_id":"2406.12142","repositories_listed":1,"syntology":null},{"url":"/paper/llm-as-dataset-analyst-subpopulation","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","date":"2024-05-03","arxiv_id":"2405.02363","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/vlslice-interactive-vision-and-language-slice","title":"VLSlice: Interactive Vision-and-Language Slice Discovery","date":"2023-09-13","arxiv_id":"2309.06703","repositories_listed":1,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}