{"url":"/dataset/gap","name":"GAP","full_name":"GAP Benchmark Suite","description_markdown":"**GAP** is a graph processing benchmark suite with the goal of helping to standardize graph processing evaluations. Fewer differences between graph processing evaluations will make it easier to compare different research efforts and quantify improvements. The benchmark not only specifies graph kernels, input graphs, and evaluation methodologies, but it also provides optimized baseline implementations. These baseline implementations are representative of state-of-the-art performance, and thus new contributions should outperform them to demonstrate an improvement. The input graphs are sized appropriately for shared memory platforms, but any implementation on any platform that conforms to the benchmark's specifications could be compared. This benchmark suite can be used in a variety of settings. Graph framework developers can demonstrate the generality of their programming model by implementing all of the benchmark's kernels and delivering competitive performance on all of the benchmark's graphs. Algorithm designers can use the input graphs and the baseline implementations to demonstrate their contribution. Platform designers and performance analysts can use the suite as a workload representative of graph processing.","description_withheld":null,"homepage":"http://gap.cs.berkeley.edu/benchmark.html","introduced_date":"2015-08-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-gap-benchmark-suite","title":"The GAP Benchmark Suite","first_author":null,"url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"}],"languages":[],"variants":["GAP"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/gap","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/gap","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/gap","frameworks":["tf","jax"]}],"num_papers_in_archive":60,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/coreference-resolution-on-gap-1","task":"Coreference Resolution","dataset_variant":"GAP","rows":5,"metrics":["Overall F1","Masculine F1 (M)","Feminine F1 (F)","Bias (F/M)","F1"],"first_row_in_archive_order":{"model":"Coref-MTL","paper":null,"metrics":{"Bias (F/M)":"0.99","Feminine F1 (F)":"92.45","Masculine F1 (M)":"92.65","Overall F1":"92.72"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/2407-21489","title":"Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends","date":"2024-07-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/petra-a-sparsely-supervised-memory-model-for","title":"PeTra: A Sparsely Supervised Memory Model for People Tracking","date":"2020-05-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gendered-ambiguous-pronouns-shared-task","title":"Gendered Ambiguous Pronouns Shared Task: Boosting Model Confidence by Evidence Pooling","date":"2019-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gendered-pronoun-resolution-using-bert-and-an","title":"Gendered Pronoun Resolution using BERT and an extractive question answering formulation","date":"2019-06-09","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":11,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}