{"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/wikitext-2","name":"WikiText-2","full_name":"WikiText-2","description_markdown":"The WikiText language modeling dataset is a collection of over 100 million tokens extracted from the set of verified Good and Featured articles on Wikipedia. The dataset is available under the Creative Commons Attribution-ShareAlike License.\r\n\r\nCompared to the preprocessed version of Penn Treebank (PTB), WikiText-2 is over 2 times larger and WikiText-103 is over 110 times larger. The WikiText dataset also features a far larger vocabulary and retains the original case, punctuation and numbers - all of which are removed in PTB. As it is composed of full articles, the dataset is well suited for models that can take advantage of long term dependencies.\r\n\r\nSource: [The WikiText Long Term Dependency Language Modeling Dataset](https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/)\r\nImage Source: [https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/](https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/)","description_withheld":null,"homepage":"https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/","introduced_date":"2016-09-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/pointer-sentinel-mixture-models","title":"Pointer Sentinel Mixture Models","first_author":"Stephen Merity","url":null},"license":{"name":"CC BY-SA 3.0","url":"https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/"},"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"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Swedish","url":"/datasets/language/swedish"}],"variants":["WikiText-103","WikiText-2","wikitext wikitext-2-raw-v1"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Salesforce/wikitext","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wikitext","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Nart/abkhaz","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/rajeshradhakrishnan/malayalam_wiki","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/meliascosta/wiki_academic_subjects","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/bfattori/wikitext_document_level","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/alexkueck/tis","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mindchain/wikitext2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/pytorch/text","url":"https://pytorch.org/text/stable/datasets.html#torchtext.datasets.WikiText2","frameworks":["pytorch"]}],"num_papers_in_archive":1081,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset_variant":"WikiText-2","rows":38,"metrics":["Test perplexity","Validation perplexity","Number of params"],"first_row_in_archive_order":{"model":"SparseGPT (175B, 50% Sparsity)","paper":"/paper/massive-language-models-can-be-accurately","metrics":{"Test perplexity":"8.21"},"code_links":[{"title":"nvidia/tensorrt-model-optimizer","url":"https://github.com/nvidia/tensorrt-model-optimizer"},{"title":"ist-daslab/sparsegpt","url":"https://github.com/ist-daslab/sparsegpt"},{"title":"nvlabs/maskllm","url":"https://github.com/nvlabs/maskllm"},{"title":"baithebest/adagp","url":"https://github.com/baithebest/adagp"},{"title":"baithebest/sparsellm","url":"https://github.com/baithebest/sparsellm"},{"title":"eth-easl/deltazip","url":"https://github.com/eth-easl/deltazip"}]},"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":23,"of":23,"counts":{"papers_with_a_benchmark_row":23,"with_a_code_link":22,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":23,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"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/advancing-state-of-the-art-in-language","slug":"advancing-state-of-the-art-in-language","title":"Advancing State of the Art in Language Modeling","date":"2023-11-28","arxiv_id":"2312.03735","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/massive-language-models-can-be-accurately","slug":"massive-language-models-can-be-accurately","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","date":"2023-01-02","arxiv_id":"2301.00774","rows_on_this_dataset":5,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"paper":"/paper/egru-event-based-gru-for-activity-sparse","slug":"egru-event-based-gru-for-activity-sparse","title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","date":"2022-06-13","arxiv_id":"2206.06178","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hydra-a-system-for-large-multi-model-deep","slug":"hydra-a-system-for-large-multi-model-deep","title":"Hydra: A System for Large Multi-Model Deep Learning","date":"2021-10-16","arxiv_id":"2110.08633","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-associative-inference-using-fast-1","slug":"learning-associative-inference-using-fast-1","title":"Learning Associative Inference Using Fast Weight Memory","date":"2020-11-16","arxiv_id":"2011.07831","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ischlag/Fast-Weight-Memory-public"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-associative-inference-using-fast-1#ran","syntology_url":"https://syntology.ai/paper/2011.07831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.07831"}}}},{"paper":"/paper/alleviating-sequence-information-loss-with","slug":"alleviating-sequence-information-loss-with","title":"Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes","date":"2019-09-18","arxiv_id":"1909.08700","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mogrifier-lstm","slug":"mogrifier-lstm","title":"Mogrifier LSTM","date":"2019-09-04","arxiv_id":"1909.01792","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/improving-neural-language-modeling-via","slug":"improving-neural-language-modeling-via","title":"Improving Neural Language Modeling via Adversarial Training","date":"2019-06-10","arxiv_id":"1906.03805","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-residual-output-layers-for-neural","slug":"deep-residual-output-layers-for-neural","title":"Deep Residual Output Layers for Neural Language Generation","date":"2019-05-14","arxiv_id":"1905.05513","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/190409408","slug":"190409408","title":"Language Models with Transformers","date":"2019-04-20","arxiv_id":"1904.09408","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["cgraywang/gluon-nlp-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190409408#ran","syntology_url":"https://syntology.ai/paper/1904.09408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09408"}}}},{"paper":"/paper/partially-shuffling-the-training-data-to-1","slug":"partially-shuffling-the-training-data-to-1","title":"Partially Shuffling the Training Data to Improve Language Models","date":"2019-03-11","arxiv_id":"1903.04167","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":4,"code_links":21,"syntology":null},{"paper":"/paper/frage-frequency-agnostic-word-representation","slug":"frage-frequency-agnostic-word-representation","title":"FRAGE: Frequency-Agnostic Word Representation","date":"2018-09-18","arxiv_id":"1809.06858","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/direct-output-connection-for-a-high-rank","slug":"direct-output-connection-for-a-high-rank","title":"Direct Output Connection for a High-Rank Language Model","date":"2018-08-30","arxiv_id":"1808.10143","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/improved-language-modeling-by-decoding-the","slug":"improved-language-modeling-by-decoding-the","title":"Improved Language Modeling by Decoding the Past","date":"2018-08-14","arxiv_id":"1808.05908","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/breaking-the-softmax-bottleneck-a-high-rank","slug":"breaking-the-softmax-bottleneck-a-high-rank","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","date":"2017-11-10","arxiv_id":"1711.03953","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":23,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":1,"official":{"repos":["zihangdai/mos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/breaking-the-softmax-bottleneck-a-high-rank#ran","syntology_url":"https://syntology.ai/paper/1711.03953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.03953"}}}},{"paper":"/paper/fraternal-dropout","slug":"fraternal-dropout","title":"Fraternal Dropout","date":"2017-10-31","arxiv_id":"1711.00066","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dynamic-evaluation-of-neural-sequence-models","slug":"dynamic-evaluation-of-neural-sequence-models","title":"Dynamic Evaluation of Neural Sequence Models","date":"2017-09-21","arxiv_id":"1709.07432","rows_on_this_dataset":1,"code_links":3,"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":["benkrause/dynamic-evaluation"],"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/dynamic-evaluation-of-neural-sequence-models#ran","syntology_url":"https://syntology.ai/paper/1709.07432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.07432"}}}},{"paper":"/paper/gradual-learning-of-recurrent-neural-networks","slug":"gradual-learning-of-recurrent-neural-networks","title":"Gradual Learning of Recurrent Neural Networks","date":"2017-08-29","arxiv_id":"1708.08863","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/regularizing-and-optimizing-lstm-language","slug":"regularizing-and-optimizing-lstm-language","title":"Regularizing and Optimizing LSTM Language Models","date":"2017-08-07","arxiv_id":"1708.02182","rows_on_this_dataset":2,"code_links":45,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["salesforce/awd-lstm-lm"],"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/regularizing-and-optimizing-lstm-language#ran","syntology_url":"https://syntology.ai/paper/1708.02182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02182"}}}},{"paper":"/paper/on-the-state-of-the-art-of-evaluation-in","slug":"on-the-state-of-the-art-of-evaluation-in","title":"On the State of the Art of Evaluation in Neural Language Models","date":"2017-07-18","arxiv_id":"1707.05589","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-neural-language-models-with-a","slug":"improving-neural-language-models-with-a","title":"Improving Neural Language Models with a Continuous Cache","date":"2016-12-13","arxiv_id":"1612.04426","rows_on_this_dataset":2,"code_links":14,"syntology":null},{"paper":"/paper/tying-word-vectors-and-word-classifiers-a","slug":"tying-word-vectors-and-word-classifiers-a","title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","date":"2016-11-04","arxiv_id":"1611.01462","rows_on_this_dataset":2,"code_links":5,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/advancing-state-of-the-art-in-language","slug":"advancing-state-of-the-art-in-language","title":"Advancing State of the Art in Language Modeling","date":"2023-11-28","arxiv_id":"2312.03735","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/massive-language-models-can-be-accurately","slug":"massive-language-models-can-be-accurately","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","date":"2023-01-02","arxiv_id":"2301.00774","rows_on_this_dataset":5,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"paper":"/paper/egru-event-based-gru-for-activity-sparse","slug":"egru-event-based-gru-for-activity-sparse","title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","date":"2022-06-13","arxiv_id":"2206.06178","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hydra-a-system-for-large-multi-model-deep","slug":"hydra-a-system-for-large-multi-model-deep","title":"Hydra: A System for Large Multi-Model Deep Learning","date":"2021-10-16","arxiv_id":"2110.08633","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-associative-inference-using-fast-1","slug":"learning-associative-inference-using-fast-1","title":"Learning Associative Inference Using Fast Weight Memory","date":"2020-11-16","arxiv_id":"2011.07831","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ischlag/Fast-Weight-Memory-public"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-associative-inference-using-fast-1#ran","syntology_url":"https://syntology.ai/paper/2011.07831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.07831"}}}},{"paper":"/paper/alleviating-sequence-information-loss-with","slug":"alleviating-sequence-information-loss-with","title":"Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes","date":"2019-09-18","arxiv_id":"1909.08700","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mogrifier-lstm","slug":"mogrifier-lstm","title":"Mogrifier LSTM","date":"2019-09-04","arxiv_id":"1909.01792","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/improving-neural-language-modeling-via","slug":"improving-neural-language-modeling-via","title":"Improving Neural Language Modeling via Adversarial Training","date":"2019-06-10","arxiv_id":"1906.03805","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-residual-output-layers-for-neural","slug":"deep-residual-output-layers-for-neural","title":"Deep Residual Output Layers for Neural Language Generation","date":"2019-05-14","arxiv_id":"1905.05513","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/190409408","slug":"190409408","title":"Language Models with Transformers","date":"2019-04-20","arxiv_id":"1904.09408","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["cgraywang/gluon-nlp-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190409408#ran","syntology_url":"https://syntology.ai/paper/1904.09408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09408"}}}},{"paper":"/paper/partially-shuffling-the-training-data-to-1","slug":"partially-shuffling-the-training-data-to-1","title":"Partially Shuffling the Training Data to Improve Language Models","date":"2019-03-11","arxiv_id":"1903.04167","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":4,"code_links":21,"syntology":null},{"paper":"/paper/frage-frequency-agnostic-word-representation","slug":"frage-frequency-agnostic-word-representation","title":"FRAGE: Frequency-Agnostic Word Representation","date":"2018-09-18","arxiv_id":"1809.06858","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/direct-output-connection-for-a-high-rank","slug":"direct-output-connection-for-a-high-rank","title":"Direct Output Connection for a High-Rank Language Model","date":"2018-08-30","arxiv_id":"1808.10143","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/improved-language-modeling-by-decoding-the","slug":"improved-language-modeling-by-decoding-the","title":"Improved Language Modeling by Decoding the Past","date":"2018-08-14","arxiv_id":"1808.05908","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/breaking-the-softmax-bottleneck-a-high-rank","slug":"breaking-the-softmax-bottleneck-a-high-rank","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","date":"2017-11-10","arxiv_id":"1711.03953","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":23,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":1,"official":{"repos":["zihangdai/mos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/breaking-the-softmax-bottleneck-a-high-rank#ran","syntology_url":"https://syntology.ai/paper/1711.03953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.03953"}}}},{"paper":"/paper/fraternal-dropout","slug":"fraternal-dropout","title":"Fraternal Dropout","date":"2017-10-31","arxiv_id":"1711.00066","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dynamic-evaluation-of-neural-sequence-models","slug":"dynamic-evaluation-of-neural-sequence-models","title":"Dynamic Evaluation of Neural Sequence Models","date":"2017-09-21","arxiv_id":"1709.07432","rows_on_this_dataset":1,"code_links":3,"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":["benkrause/dynamic-evaluation"],"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/dynamic-evaluation-of-neural-sequence-models#ran","syntology_url":"https://syntology.ai/paper/1709.07432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.07432"}}}},{"paper":"/paper/gradual-learning-of-recurrent-neural-networks","slug":"gradual-learning-of-recurrent-neural-networks","title":"Gradual Learning of Recurrent Neural Networks","date":"2017-08-29","arxiv_id":"1708.08863","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/regularizing-and-optimizing-lstm-language","slug":"regularizing-and-optimizing-lstm-language","title":"Regularizing and Optimizing LSTM Language Models","date":"2017-08-07","arxiv_id":"1708.02182","rows_on_this_dataset":2,"code_links":45,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["salesforce/awd-lstm-lm"],"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/regularizing-and-optimizing-lstm-language#ran","syntology_url":"https://syntology.ai/paper/1708.02182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02182"}}}},{"paper":"/paper/on-the-state-of-the-art-of-evaluation-in","slug":"on-the-state-of-the-art-of-evaluation-in","title":"On the State of the Art of Evaluation in Neural Language Models","date":"2017-07-18","arxiv_id":"1707.05589","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-neural-language-models-with-a","slug":"improving-neural-language-models-with-a","title":"Improving Neural Language Models with a Continuous Cache","date":"2016-12-13","arxiv_id":"1612.04426","rows_on_this_dataset":2,"code_links":14,"syntology":null},{"paper":"/paper/tying-word-vectors-and-word-classifiers-a","slug":"tying-word-vectors-and-word-classifiers-a","title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","date":"2016-11-04","arxiv_id":"1611.01462","rows_on_this_dataset":2,"code_links":5,"syntology":null}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/wikitext-2/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/wikitext-2/papers/ran/1","json":"/dataset/wikitext-2/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":48,"samples_ran":31,"samples_constructed":0,"samples_ran_checked":23,"samples_ran_instrument_failed":8,"samples_unverified":17,"pointer_only_for_licence":19,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":5,"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":12,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/language-modelling-on-wikitext-2","since_archive":"/sota/language-modelling-on-wikitext-2#since-judged","papers_judged":12,"placed":1}]},"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":"284a7af1a8e90d296b4ace10c23e9f595507c0edc46619a625a4cc3134d0f795","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}