{"url":"/task/task-1-grouping","name":"Only Connect Walls Dataset Task 1 (Grouping)","slug":"task-1-grouping","description_markdown":"Split data into groups, taking into account knowledge in the form of constraints on points, groups of points, or clusters.","categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":10,"papers_with_code":10,"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":1},"benchmarks":[{"leaderboard":"/sota/task-1-grouping-on-ocw","slug":"task-1-grouping-on-ocw","dataset":"OCW","dataset_url":"/dataset/only-connect-wall-ocw-dataset","rows_in_archive":22,"metrics":[" Wasserstein Distance (WD)","# Correct Groups","Fowlkes Mallows Score (FMS)","Adjusted Rand Index (ARI)","Adjusted Mutual Information (AMI)","# Solved Walls","Wasserstein Distance (WD)"],"first_row_in_archive_order":{"model":"GPT-4 (5-shot)","paper_title":"GPT-4 Technical Report","paper_url":"/paper/gpt-4-technical-report-1","paper_date":"2023-03-15","arxiv_id":"2303.08774","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}}}],"datasets":[{"url":"/dataset/only-connect-wall-ocw-dataset","name":"OCW","full_name":"Only Connect Wall Dataset and creative problem solving tasks","num_papers_in_archive":10}],"subtasks":[],"parent_tasks":[{"url":"/task/constrained-clustering","name":"Constrained Clustering"}],"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":10,"of":10,"tagged_in_all":10,"items":[{"url":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","repositories_listed":67,"syntology":{"n":48,"n_ran":22,"n_unverified":26,"n_pointer_only":23}},{"url":"/paper/deep-contextualized-word-representations","title":"Deep contextualized word representations","date":"2018-02-15","arxiv_id":"1802.05365","repositories_listed":46,"syntology":{"n":58,"n_ran":23,"n_unverified":35,"n_pointer_only":25}},{"url":"/paper/distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","repositories_listed":37,"syntology":{"n":27,"n_ran":19,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/mpnet-masked-and-permuted-pre-training-for","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","date":"2020-04-20","arxiv_id":"2004.09297","repositories_listed":7,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/glove-global-vectors-for-word-representation","title":"GloVe: Global Vectors for Word Representation","date":"2014-10-01","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/learning-word-vectors-for-157-languages","title":"Learning Word Vectors for 157 Languages","date":"2018-02-19","arxiv_id":"1802.06893","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-models-are-fixated-by-red-1","title":"Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Dataset","date":"2023-06-19","arxiv_id":"2306.11167","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/text-embeddings-by-weakly-supervised","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","date":"2022-12-07","arxiv_id":"2212.03533","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-of-deep-bidirectional-protein","title":"Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information","date":"2019-11-25","arxiv_id":"1912.05625","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"}}