{"url":"/task/odd-one-out","name":"Odd One Out","slug":"odd-one-out","description_markdown":"This task tests to what extent a language model is able to identify the odd word.\r\n\r\nSource: [BIG-bench](https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/odd_one_out)","categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":21,"papers_with_code":12,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/odd-one-out-on-big-bench","slug":"odd-one-out-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla-70B (few-shot, k=5)","paper_title":"Training Compute-Optimal Large Language Models","paper_url":"/paper/training-compute-optimal-large-language","paper_date":"2022-03-29","arxiv_id":"2203.15556","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":4}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[],"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":12,"of":12,"tagged_in_all":21,"items":[{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/vice-variational-inference-for-concept-1","title":"VICE: Variational Interpretable Concept Embeddings","date":"2022-05-02","arxiv_id":"2205.00756","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":10}},{"url":"/paper/training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/do-saliency-models-detect-odd-one-out-targets","title":"Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations","date":"2020-05-13","arxiv_id":"2005.06583","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/odd-one-out-anomaly-detection-by-comparing","title":"Odd-One-Out: Anomaly Detection by Comparing with Neighbors","date":"2024-06-28","arxiv_id":"2406.20099","repositories_listed":1,"syntology":null},{"url":"/paper/towards-generative-abstract-reasoning","title":"Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection","date":"2024-01-18","arxiv_id":"2401.09966","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/one-self-configurable-model-to-solve-many","title":"One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems","date":"2023-12-15","arxiv_id":"2312.09997","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":9}},{"url":"/paper/regularized-complete-cycle-consistent-gan-for","title":"Spot The Odd One Out: Regularized Complete Cycle Consistent Anomaly Detector GAN","date":"2023-04-16","arxiv_id":"2304.07769","repositories_listed":1,"syntology":null},{"url":"/paper/human-alignment-of-neural-network","title":"Human alignment of neural network representations","date":"2022-11-02","arxiv_id":"2211.01201","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tell-me-why-explanations-support-learning-of","title":"Tell me why! Explanations support learning relational and causal structure","date":"2021-12-07","arxiv_id":"2112.03753","repositories_listed":1,"syntology":null},{"url":"/paper/odd-one-out-representation-learning","title":"Odd-One-Out Representation Learning","date":"2020-12-14","arxiv_id":"2012.07966","repositories_listed":1,"syntology":null},{"url":"/paper/we-have-so-much-in-common-modeling-semantic","title":"We Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos","date":"2020-08-12","arxiv_id":"2008.05596","repositories_listed":1,"syntology":null}],"syntology_records":6,"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"}}