{"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/billion-word-benchmark","name":"Billion Word Benchmark","full_name":null,"description_markdown":"The **One Billion Word** dataset is a dataset for language modeling. The training/held-out data was produced from the WMT 2011 News Crawl data using a combination of Bash shell and Perl scripts.","description_withheld":null,"homepage":"https://code.google.com/archive/p/1-billion-word-language-modeling-benchmark/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/one-billion-word-benchmark-for-measuring","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","first_author":"Ciprian Chelba","url":null},"license":{"name":"Apache-2","url":"https://github.com/ciprian-chelba/1-billion-word-language-modeling-benchmark"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["One Billion Word","Billion Word Benchmark"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/billion-word-benchmark/lm1b","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lm1b","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/lm1b","frameworks":["tf","jax"]}],"num_papers_in_archive":141,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset_variant":"One Billion Word","rows":27,"metrics":["PPL","Number of params","Validation perplexity"],"first_row_in_archive_order":{"model":"MDLM (AR baseline)","paper":"/paper/simple-and-effective-masked-diffusion","metrics":{"Number of params":"110M","PPL":"20.09"},"code_links":[{"title":"kuleshov-group/mdlm","url":"https://github.com/kuleshov-group/mdlm"},{"title":"masa-ue/svdd","url":"https://github.com/masa-ue/svdd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-one-billion-word","task":"Text Generation","dataset_variant":"One Billion Word","rows":1,"metrics":["JS-4"],"first_row_in_archive_order":{"model":"WGANGP + DGflow","paper":"/paper/refining-deep-generative-models-via-1","metrics":{"JS-4":"0.186"},"code_links":[{"title":"clear-nus/DGflow","url":"https://github.com/clear-nus/DGflow"}]},"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":17,"of":17,"counts":{"papers_with_a_benchmark_row":17,"with_a_code_link":16,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":17,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/simple-and-effective-masked-diffusion","slug":"simple-and-effective-masked-diffusion","title":"Simple and Effective Masked Diffusion Language Models","date":"2024-06-11","arxiv_id":"2406.07524","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["kuleshov-group/mdlm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-effective-masked-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.07524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07524"}}}},{"paper":"/paper/h-transformer-1d-fast-one-dimensional","slug":"h-transformer-1d-fast-one-dimensional","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","date":"2021-07-25","arxiv_id":"2107.11906","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":1,"samples_ran_checked":6,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/h-transformer-1d-fast-one-dimensional#ran","syntology_url":"https://syntology.ai/paper/2107.11906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.11906"}}}},{"paper":"/paper/omninet-omnidirectional-representations-from","slug":"omninet-omnidirectional-representations-from","title":"OmniNet: Omnidirectional Representations from Transformers","date":"2021-03-01","arxiv_id":"2103.01075","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/when-attention-meets-fast-recurrence-training","slug":"when-attention-meets-fast-recurrence-training","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","date":"2021-02-24","arxiv_id":"2102.12459","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/refining-deep-generative-models-via-1","slug":"refining-deep-generative-models-via-1","title":"Refining Deep Generative Models via Discriminator Gradient Flow","date":"2020-12-01","arxiv_id":"2012.00780","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["clear-nus/DGflow"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/refining-deep-generative-models-via-1#ran","syntology_url":"https://syntology.ai/paper/2012.00780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.00780"}}}},{"paper":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"rows_on_this_dataset":1,"code_links":21,"syntology":null},{"paper":"/paper/the-evolved-transformer","slug":"the-evolved-transformer","title":"The Evolved Transformer","date":"2019-01-30","arxiv_id":"1901.11117","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pay-less-attention-with-lightweight-and","slug":"pay-less-attention-with-lightweight-and","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","date":"2019-01-29","arxiv_id":"1901.10430","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/transformer-xl-attentive-language-models","slug":"transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","arxiv_id":"1901.02860","rows_on_this_dataset":2,"code_links":37,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":143,"samples_ran":67,"samples_constructed":37,"samples_ran_checked":49,"samples_ran_instrument_failed":18,"samples_unverified":76,"pointer_only_for_licence":43,"official":{"repos":["kimiyoung/transformer-xl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/transformer-xl-attentive-language-models#ran","syntology_url":"https://syntology.ai/paper/1901.02860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.02860"}}}},{"paper":"/paper/mesh-tensorflow-deep-learning-for","slug":"mesh-tensorflow-deep-learning-for","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","date":"2018-11-05","arxiv_id":"1811.02084","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-input-representations-for-neural","slug":"adaptive-input-representations-for-neural","title":"Adaptive Input Representations for Neural Language Modeling","date":"2018-09-28","arxiv_id":"1809.10853","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/factorization-tricks-for-lstm-networks","slug":"factorization-tricks-for-lstm-networks","title":"Factorization tricks for LSTM networks","date":"2017-03-31","arxiv_id":"1703.10722","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/outrageously-large-neural-networks-the","slug":"outrageously-large-neural-networks-the","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","date":"2017-01-23","arxiv_id":"1701.06538","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/outrageously-large-neural-networks-the#ran","syntology_url":"https://syntology.ai/paper/1701.06538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.06538"}}}},{"paper":"/paper/language-modeling-with-gated-convolutional","slug":"language-modeling-with-gated-convolutional","title":"Language Modeling with Gated Convolutional Networks","date":"2016-12-23","arxiv_id":"1612.08083","rows_on_this_dataset":1,"code_links":11,"syntology":null},{"paper":"/paper/exploring-the-limits-of-language-modeling","slug":"exploring-the-limits-of-language-modeling","title":"Exploring the Limits of Language Modeling","date":"2016-02-07","arxiv_id":"1602.02410","rows_on_this_dataset":3,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-language-modeling#ran","syntology_url":"https://syntology.ai/paper/1602.02410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.02410"}}}},{"paper":"/paper/skip-gram-language-modeling-using-sparse-non","slug":"skip-gram-language-modeling-using-sparse-non","title":"Skip-gram Language Modeling Using Sparse Non-negative Matrix Probability Estimation","date":"2014-12-03","arxiv_id":"1412.1454","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/one-billion-word-benchmark-for-measuring","slug":"one-billion-word-benchmark-for-measuring","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","date":"2013-12-11","arxiv_id":"1312.3005","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/simple-and-effective-masked-diffusion","slug":"simple-and-effective-masked-diffusion","title":"Simple and Effective Masked Diffusion Language Models","date":"2024-06-11","arxiv_id":"2406.07524","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["kuleshov-group/mdlm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-effective-masked-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.07524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07524"}}}},{"paper":"/paper/h-transformer-1d-fast-one-dimensional","slug":"h-transformer-1d-fast-one-dimensional","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","date":"2021-07-25","arxiv_id":"2107.11906","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":1,"samples_ran_checked":6,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/h-transformer-1d-fast-one-dimensional#ran","syntology_url":"https://syntology.ai/paper/2107.11906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.11906"}}}},{"paper":"/paper/omninet-omnidirectional-representations-from","slug":"omninet-omnidirectional-representations-from","title":"OmniNet: Omnidirectional Representations from Transformers","date":"2021-03-01","arxiv_id":"2103.01075","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/when-attention-meets-fast-recurrence-training","slug":"when-attention-meets-fast-recurrence-training","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","date":"2021-02-24","arxiv_id":"2102.12459","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/refining-deep-generative-models-via-1","slug":"refining-deep-generative-models-via-1","title":"Refining Deep Generative Models via Discriminator Gradient Flow","date":"2020-12-01","arxiv_id":"2012.00780","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["clear-nus/DGflow"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/refining-deep-generative-models-via-1#ran","syntology_url":"https://syntology.ai/paper/2012.00780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.00780"}}}},{"paper":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"rows_on_this_dataset":1,"code_links":21,"syntology":null},{"paper":"/paper/the-evolved-transformer","slug":"the-evolved-transformer","title":"The Evolved Transformer","date":"2019-01-30","arxiv_id":"1901.11117","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pay-less-attention-with-lightweight-and","slug":"pay-less-attention-with-lightweight-and","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","date":"2019-01-29","arxiv_id":"1901.10430","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/transformer-xl-attentive-language-models","slug":"transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","arxiv_id":"1901.02860","rows_on_this_dataset":2,"code_links":37,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":143,"samples_ran":67,"samples_constructed":37,"samples_ran_checked":49,"samples_ran_instrument_failed":18,"samples_unverified":76,"pointer_only_for_licence":43,"official":{"repos":["kimiyoung/transformer-xl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/transformer-xl-attentive-language-models#ran","syntology_url":"https://syntology.ai/paper/1901.02860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.02860"}}}},{"paper":"/paper/mesh-tensorflow-deep-learning-for","slug":"mesh-tensorflow-deep-learning-for","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","date":"2018-11-05","arxiv_id":"1811.02084","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-input-representations-for-neural","slug":"adaptive-input-representations-for-neural","title":"Adaptive Input Representations for Neural Language Modeling","date":"2018-09-28","arxiv_id":"1809.10853","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/factorization-tricks-for-lstm-networks","slug":"factorization-tricks-for-lstm-networks","title":"Factorization tricks for LSTM networks","date":"2017-03-31","arxiv_id":"1703.10722","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/outrageously-large-neural-networks-the","slug":"outrageously-large-neural-networks-the","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","date":"2017-01-23","arxiv_id":"1701.06538","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/outrageously-large-neural-networks-the#ran","syntology_url":"https://syntology.ai/paper/1701.06538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.06538"}}}},{"paper":"/paper/language-modeling-with-gated-convolutional","slug":"language-modeling-with-gated-convolutional","title":"Language Modeling with Gated Convolutional Networks","date":"2016-12-23","arxiv_id":"1612.08083","rows_on_this_dataset":1,"code_links":11,"syntology":null},{"paper":"/paper/exploring-the-limits-of-language-modeling","slug":"exploring-the-limits-of-language-modeling","title":"Exploring the Limits of Language Modeling","date":"2016-02-07","arxiv_id":"1602.02410","rows_on_this_dataset":3,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-language-modeling#ran","syntology_url":"https://syntology.ai/paper/1602.02410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.02410"}}}},{"paper":"/paper/skip-gram-language-modeling-using-sparse-non","slug":"skip-gram-language-modeling-using-sparse-non","title":"Skip-gram Language Modeling Using Sparse Non-negative Matrix Probability Estimation","date":"2014-12-03","arxiv_id":"1412.1454","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/one-billion-word-benchmark-for-measuring","slug":"one-billion-word-benchmark-for-measuring","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","date":"2013-12-11","arxiv_id":"1312.3005","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/billion-word-benchmark/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/billion-word-benchmark/papers/ran/1","json":"/dataset/billion-word-benchmark/papers/ran/1.json","rows":5}],"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":6,"samples_harvested":169,"samples_ran":85,"samples_constructed":42,"samples_ran_checked":61,"samples_ran_instrument_failed":24,"samples_unverified":84,"pointer_only_for_licence":51,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":1,"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":"5c34696ca184b2af3deb80a81db3b7d3632a78c3a9bbb7c6c38dd781038ca686","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}