{"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/wiki-40b","name":"Wiki-40B","full_name":null,"description_markdown":"A new multilingual language model benchmark that is composed of 40+ languages spanning several scripts and linguistic families containing round 40 billion characters and aimed to accelerate the research of multilingual modeling.\r\n\r\nSource: [Wiki-40B: Multilingual Language Model Dataset](https://www.shaip.com/blog/multimodal-large-language-models-mllms/)","description_withheld":null,"homepage":"https://research.google/pubs/pub49029/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/wiki-40b-multilingual-language-model-dataset","title":"Wiki-40B: Multilingual Language Model Dataset","first_author":"M. Guo","url":null},"license":null,"modalities":[],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Quantization","url":"/task/quantization","datasets_with_task":"/datasets/task/quantization"},{"name":"Benchmarking","url":"/task/benchmarking","datasets_with_task":"/datasets/task/benchmarking"}],"languages":[],"variants":["Wiki-40B"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google/wiki40b","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wiki40b","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/wiki40b","frameworks":["tf","jax"]}],"num_papers_in_archive":30,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-wiki-40b","task":"Language Modelling","dataset_variant":"Wiki-40B","rows":3,"metrics":["Perplexity"],"first_row_in_archive_order":{"model":"FLASH-Quad-8k","paper":"/paper/transformer-quality-in-linear-time","metrics":{"Perplexity":"14.998"},"code_links":[{"title":"lucidrains/FLASH-pytorch","url":"https://github.com/lucidrains/FLASH-pytorch"},{"title":"zhuiyitechnology/gau-alpha","url":"https://github.com/zhuiyitechnology/gau-alpha"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/benchmarking-on-wiki-40b","task":"Benchmarking","dataset_variant":"Wiki-40B","rows":1,"metrics":["Perplexity"],"first_row_in_archive_order":{"model":"OutEffHop-Bert_base","paper":"/paper/outlier-efficient-hopfield-layers-for-large","metrics":{"Perplexity":"6.209"},"code_links":[{"title":"magics-lab/outeffhop","url":"https://github.com/magics-lab/outeffhop"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/quantization-on-wiki-40b","task":"Quantization","dataset_variant":"Wiki-40B","rows":1,"metrics":["Perplexity"],"first_row_in_archive_order":{"model":"OutEffHop-Bert_base","paper":"/paper/outlier-efficient-hopfield-layers-for-large","metrics":{"Perplexity":"6.295"},"code_links":[{"title":"magics-lab/outeffhop","url":"https://github.com/magics-lab/outeffhop"}]},"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":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"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/outlier-efficient-hopfield-layers-for-large","slug":"outlier-efficient-hopfield-layers-for-large","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","date":"2024-04-04","arxiv_id":"2404.03828","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["magics-lab/outeffhop"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/outlier-efficient-hopfield-layers-for-large#ran","syntology_url":"https://syntology.ai/paper/2404.03828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03828"}}}},{"paper":"/paper/transformer-quality-in-linear-time","slug":"transformer-quality-in-linear-time","title":"Transformer Quality in Linear Time","date":"2022-02-21","arxiv_id":"2202.10447","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/combiner-full-attention-transformer-with","slug":"combiner-full-attention-transformer-with","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","date":"2021-07-12","arxiv_id":"2107.05768","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/combiner-full-attention-transformer-with#ran","syntology_url":"https://syntology.ai/paper/2107.05768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05768"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/outlier-efficient-hopfield-layers-for-large","slug":"outlier-efficient-hopfield-layers-for-large","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","date":"2024-04-04","arxiv_id":"2404.03828","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["magics-lab/outeffhop"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/outlier-efficient-hopfield-layers-for-large#ran","syntology_url":"https://syntology.ai/paper/2404.03828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03828"}}}},{"paper":"/paper/transformer-quality-in-linear-time","slug":"transformer-quality-in-linear-time","title":"Transformer Quality in Linear Time","date":"2022-02-21","arxiv_id":"2202.10447","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/combiner-full-attention-transformer-with","slug":"combiner-full-attention-transformer-with","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","date":"2021-07-12","arxiv_id":"2107.05768","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/combiner-full-attention-transformer-with#ran","syntology_url":"https://syntology.ai/paper/2107.05768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05768"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/wiki-40b/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/wiki-40b/papers/ran/1","json":"/dataset/wiki-40b/papers/ran/1.json","rows":2}],"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":2,"samples_harvested":16,"samples_ran":11,"samples_constructed":5,"samples_ran_checked":6,"samples_ran_instrument_failed":5,"samples_unverified":5,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"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":"81b48ee536ffea12451b08731b2b2f94bc52528542c9d5b4dd91f647db1002bf","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}