{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/wikihop","name":"WikiHop","full_name":null,"description_markdown":"**WikiHop** is a multi-hop question-answering dataset. The query of WikiHop is constructed with entities and relations from WikiData, while supporting documents are from WikiReading. A bipartite graph connecting entities and documents is first built and the answer for each query is located by traversal on this graph. Candidates that are type-consistent with the answer and share the same relation in query with the answer are included, resulting in a set of candidates. Thus, WikiHop is a multi-choice style reading comprehension data set. There are totally about 43K samples in training set, 5K samples in development set and 2.5K samples in test set. The test set is not provided. The task is to predict the correct answer given a query and multiple supporting documents.\r\n\r\nThe dataset includes a masked variant, where all candidates and their mentions in the supporting documents are replaced by random but consistent placeholder tokens.\r\n\r\nSource: [Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs](https://arxiv.org/abs/1905.07374)\r\nImage Source: [http://qangaroo.cs.ucl.ac.uk/](http://qangaroo.cs.ucl.ac.uk/)","description_withheld":null,"homepage":"http://qangaroo.cs.ucl.ac.uk/","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/constructing-datasets-for-multi-hop-reading","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","first_author":"Johannes Welbl","url":null},"license":{"name":"CC BY-SA 3.0","url":"http://qangaroo.cs.ucl.ac.uk/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiHop"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wiki_hop","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/KETI-AIR/wiki_hop","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/KETI-AIR/kor_wiki_hop","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/QAngaroo/wiki_hop","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/rc/dataset_readers/qangaroo/","frameworks":["pytorch"]}],"num_papers_in_archive":66,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-wikihop","task":"Question Answering","dataset_variant":"WikiHop","rows":9,"metrics":["Test"],"first_row_in_archive_order":{"model":"BigBird-etc","paper":"/paper/big-bird-transformers-for-longer-sequences","metrics":{"Test":"82.3"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp/projects/bigbird"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/bigbird"},{"title":"facebookresearch/xformers","url":"https://github.com/facebookresearch/xformers"},{"title":"google-research/bigbird","url":"https://github.com/google-research/bigbird"},{"title":"monologg/kobigbird","url":"https://github.com/monologg/kobigbird"},{"title":"mim-solutions/bert_for_longer_texts","url":"https://github.com/mim-solutions/bert_for_longer_texts"},{"title":"mim-solutions/roberta_for_longer_texts","url":"https://github.com/mim-solutions/roberta_for_longer_texts"},{"title":"sajjjadayobi/ParsBigBird","url":"https://github.com/sajjjadayobi/ParsBigBird"},{"title":"thefonseca/factorsum","url":"https://github.com/thefonseca/factorsum"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/big_bird"},{"title":"sergeykramp/mthesis-bigbird-embeddings","url":"https://github.com/sergeykramp/mthesis-bigbird-embeddings"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/big_bird"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/bigbird_pegasus"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/paraphrase-identification-on-wikihop","task":"Paraphrase Identification","dataset_variant":"WikiHop","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"StructBERTRoBERTa ensemble","paper":"/paper/structbert-incorporating-language-structures","metrics":{"Accuracy":"90.7%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":10,"of":10,"counts":{"papers_with_a_benchmark_row":10,"with_a_code_link":4,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":10,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/luke-graph-a-transformer-based-approach-with","slug":"luke-graph-a-transformer-based-approach-with","title":"LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension","date":"2023-03-12","arxiv_id":"2303.06675","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/longformer-the-long-document-transformer","slug":"longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","arxiv_id":"2004.05150","rows_on_this_dataset":1,"code_links":22,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":35,"samples_ran":22,"samples_constructed":4,"samples_ran_checked":14,"samples_ran_instrument_failed":8,"samples_unverified":13,"pointer_only_for_licence":5,"official":{"repos":["allenai/longformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/longformer-the-long-document-transformer#ran","syntology_url":"https://syntology.ai/paper/2004.05150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05150"}}}},{"paper":"/paper/multi-hop-question-answering-via-reasoning","slug":"multi-hop-question-answering-via-reasoning","title":"Multi-hop Question Answering via Reasoning Chains","date":"2019-10-07","arxiv_id":"1910.02610","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/coarse-grain-fine-grain-coattention-network","slug":"coarse-grain-fine-grain-coattention-network","title":"Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering","date":"2019-01-03","arxiv_id":"1901.00603","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/commonsense-for-generative-multi-hop-question","slug":"commonsense-for-generative-multi-hop-question","title":"Commonsense for Generative Multi-Hop Question Answering Tasks","date":"2018-09-17","arxiv_id":"1809.06309","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["yicheng-w/CommonSenseMultiHopQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/commonsense-for-generative-multi-hop-question#ran","syntology_url":"https://syntology.ai/paper/1809.06309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.06309"}}}},{"paper":"/paper/exploring-graph-structured-passage","slug":"exploring-graph-structured-passage","title":"Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks","date":"2018-09-06","arxiv_id":"1809.02040","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/neural-models-for-reasoning-over-multiple","slug":"neural-models-for-reasoning-over-multiple","title":"Neural Models for Reasoning over Multiple Mentions using Coreference","date":"2018-04-16","arxiv_id":"1804.05922","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/constructing-datasets-for-multi-hop-reading","slug":"constructing-datasets-for-multi-hop-reading","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","date":"2017-10-17","arxiv_id":"1710.06481","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/luke-graph-a-transformer-based-approach-with","slug":"luke-graph-a-transformer-based-approach-with","title":"LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension","date":"2023-03-12","arxiv_id":"2303.06675","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/longformer-the-long-document-transformer","slug":"longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","arxiv_id":"2004.05150","rows_on_this_dataset":1,"code_links":22,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":35,"samples_ran":22,"samples_constructed":4,"samples_ran_checked":14,"samples_ran_instrument_failed":8,"samples_unverified":13,"pointer_only_for_licence":5,"official":{"repos":["allenai/longformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/longformer-the-long-document-transformer#ran","syntology_url":"https://syntology.ai/paper/2004.05150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05150"}}}},{"paper":"/paper/multi-hop-question-answering-via-reasoning","slug":"multi-hop-question-answering-via-reasoning","title":"Multi-hop Question Answering via Reasoning Chains","date":"2019-10-07","arxiv_id":"1910.02610","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/coarse-grain-fine-grain-coattention-network","slug":"coarse-grain-fine-grain-coattention-network","title":"Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering","date":"2019-01-03","arxiv_id":"1901.00603","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/commonsense-for-generative-multi-hop-question","slug":"commonsense-for-generative-multi-hop-question","title":"Commonsense for Generative Multi-Hop Question Answering Tasks","date":"2018-09-17","arxiv_id":"1809.06309","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["yicheng-w/CommonSenseMultiHopQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/commonsense-for-generative-multi-hop-question#ran","syntology_url":"https://syntology.ai/paper/1809.06309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.06309"}}}},{"paper":"/paper/exploring-graph-structured-passage","slug":"exploring-graph-structured-passage","title":"Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks","date":"2018-09-06","arxiv_id":"1809.02040","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/neural-models-for-reasoning-over-multiple","slug":"neural-models-for-reasoning-over-multiple","title":"Neural Models for Reasoning over Multiple Mentions using Coreference","date":"2018-04-16","arxiv_id":"1804.05922","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/constructing-datasets-for-multi-hop-reading","slug":"constructing-datasets-for-multi-hop-reading","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","date":"2017-10-17","arxiv_id":"1710.06481","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/wikihop/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/wikihop/papers/ran/1","json":"/dataset/wikihop/papers/ran/1.json","rows":3}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":3,"samples_harvested":57,"samples_ran":37,"samples_constructed":5,"samples_ran_checked":21,"samples_ran_instrument_failed":16,"samples_unverified":20,"pointer_only_for_licence":16,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"60947e7e86e91c3150ceb7cfa407dc6b3be5dbe337f6ad98c353a219b2461424","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}