{"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/text8","name":"Text8","full_name":null,"description_markdown":"Desc: [About of Text8](http://mattmahoney.net/dc/textdata.html)","description_withheld":null,"homepage":"http://mattmahoney.net/dc/textdata.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Text8"],"data_loaders":[],"num_papers_in_archive":22,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-text8","task":"Language Modelling","dataset_variant":"Text8","rows":24,"metrics":["Bit per Character (BPC)","Number of params"],"first_row_in_archive_order":{"model":"GPT-2","paper":"/paper/language-models-are-unsupervised-multitask","metrics":{"Bit per Character (BPC)":"0.98","Number of params":"1542M"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"openai/gpt-2","url":"https://github.com/openai/gpt-2"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt"},{"title":"minimaxir/gpt-2-simple","url":"https://github.com/minimaxir/gpt-2-simple"},{"title":"imcaspar/gpt2-ml","url":"https://github.com/imcaspar/gpt2-ml"},{"title":"huggingface/swift-coreml-transformers","url":"https://github.com/huggingface/swift-coreml-transformers"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/blob/master/research/nlp/gpt2"},{"title":"jankrepl/mildlyoverfitted","url":"https://github.com/jankrepl/mildlyoverfitted"},{"title":"affjljoo3581/GPT2","url":"https://github.com/affjljoo3581/GPT2"},{"title":"akanyaani/gpt-2-tensorflow2.0","url":"https://github.com/akanyaani/gpt-2-tensorflow2.0"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"aananda-giri/gpt2-nepali","url":"https://github.com/aananda-giri/gpt2-nepali"},{"title":"akanyaani/minGPTF","url":"https://github.com/akanyaani/minGPTF"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/gpt2"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"2023-MindSpore-1/ms-code-154","url":"https://github.com/2023-MindSpore-1/ms-code-154"},{"title":"varun-suresh/experiments-with-gpt2","url":"https://github.com/varun-suresh/experiments-with-gpt2"}]},"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":19,"of":19,"counts":{"papers_with_a_benchmark_row":19,"with_a_code_link":17,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":19,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"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/bayesian-flow-networks","slug":"bayesian-flow-networks","title":"Bayesian Flow Networks","date":"2023-08-14","arxiv_id":"2308.07037","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":8,"samples_unverified":1,"pointer_only_for_licence":9,"official":{"repos":["nnaisense/bayesian-flow-networks"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bayesian-flow-networks#ran","syntology_url":"https://syntology.ai/paper/2308.07037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07037"}}}},{"paper":"/paper/2305-14952","slug":"2305-14952","title":"Focus Your Attention (with Adaptive IIR Filters)","date":"2023-05-24","arxiv_id":"2305.14952","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/long-short-transformer-efficient-transformers","slug":"long-short-transformer-efficient-transformers","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","date":"2021-07-05","arxiv_id":"2107.02192","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["NVIDIA/transformer-ls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/long-short-transformer-efficient-transformers#ran","syntology_url":"https://syntology.ai/paper/2107.02192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02192"}}}},{"paper":"/paper/pay-attention-when-required","slug":"pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/recurrent-highway-networks-with-grouped","slug":"recurrent-highway-networks-with-grouped","title":"Recurrent Highway Networks with Grouped Auxiliary Memory","date":"2019-12-13","arxiv_id":null,"rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/bp-transformer-modelling-long-range-context","slug":"bp-transformer-modelling-long-range-context","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","date":"2019-11-11","arxiv_id":"1911.04070","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["yzh119/BPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bp-transformer-modelling-long-range-context#ran","syntology_url":"https://syntology.ai/paper/1911.04070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04070"}}}},{"paper":"/paper/augmenting-self-attention-with-persistent","slug":"augmenting-self-attention-with-persistent","title":"Augmenting Self-attention with Persistent Memory","date":"2019-07-02","arxiv_id":"1907.01470","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/augmenting-self-attention-with-persistent#ran","syntology_url":"https://syntology.ai/paper/1907.01470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.01470"}}}},{"paper":"/paper/discrete-flows-invertible-generative-models","slug":"discrete-flows-invertible-generative-models","title":"Discrete Flows: Invertible Generative Models of Discrete Data","date":"2019-05-24","arxiv_id":"1905.10347","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/adaptive-attention-span-in-transformers","slug":"adaptive-attention-span-in-transformers","title":"Adaptive Attention Span in Transformers","date":"2019-05-19","arxiv_id":"1905.07799","rows_on_this_dataset":2,"code_links":8,"syntology":null},{"paper":"/paper/dynamic-evaluation-of-transformer-language","slug":"dynamic-evaluation-of-transformer-language","title":"Dynamic Evaluation of Transformer Language Models","date":"2019-04-17","arxiv_id":"1904.08378","rows_on_this_dataset":1,"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":1,"code_links":21,"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":1,"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/character-level-language-modeling-with-deeper","slug":"character-level-language-modeling-with-deeper","title":"Character-Level Language Modeling with Deeper Self-Attention","date":"2018-08-09","arxiv_id":"1808.04444","rows_on_this_dataset":2,"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/multiplicative-lstm-for-sequence-modelling","slug":"multiplicative-lstm-for-sequence-modelling","title":"Multiplicative LSTM for sequence modelling","date":"2016-09-26","arxiv_id":"1609.07959","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-multiscale-recurrent-neural","slug":"hierarchical-multiscale-recurrent-neural","title":"Hierarchical Multiscale Recurrent Neural Networks","date":"2016-09-06","arxiv_id":"1609.01704","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/recurrent-highway-networks","slug":"recurrent-highway-networks","title":"Recurrent Highway Networks","date":"2016-07-12","arxiv_id":"1607.03474","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["julian121266/RecurrentHighwayNetworks"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recurrent-highway-networks#ran","syntology_url":"https://syntology.ai/paper/1607.03474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.03474"}}}},{"paper":"/paper/recurrent-batch-normalization","slug":"recurrent-batch-normalization","title":"Recurrent Batch Normalization","date":"2016-03-30","arxiv_id":"1603.09025","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recurrent-batch-normalization#ran","syntology_url":"https://syntology.ai/paper/1603.09025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.09025"}}}},{"paper":"/paper/architectural-complexity-measures-of","slug":"architectural-complexity-measures-of","title":"Architectural Complexity Measures of Recurrent Neural Networks","date":"2016-02-26","arxiv_id":"1602.08210","rows_on_this_dataset":2,"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/bayesian-flow-networks","slug":"bayesian-flow-networks","title":"Bayesian Flow Networks","date":"2023-08-14","arxiv_id":"2308.07037","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":8,"samples_unverified":1,"pointer_only_for_licence":9,"official":{"repos":["nnaisense/bayesian-flow-networks"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bayesian-flow-networks#ran","syntology_url":"https://syntology.ai/paper/2308.07037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07037"}}}},{"paper":"/paper/2305-14952","slug":"2305-14952","title":"Focus Your Attention (with Adaptive IIR Filters)","date":"2023-05-24","arxiv_id":"2305.14952","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/long-short-transformer-efficient-transformers","slug":"long-short-transformer-efficient-transformers","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","date":"2021-07-05","arxiv_id":"2107.02192","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["NVIDIA/transformer-ls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/long-short-transformer-efficient-transformers#ran","syntology_url":"https://syntology.ai/paper/2107.02192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02192"}}}},{"paper":"/paper/pay-attention-when-required","slug":"pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/recurrent-highway-networks-with-grouped","slug":"recurrent-highway-networks-with-grouped","title":"Recurrent Highway Networks with Grouped Auxiliary Memory","date":"2019-12-13","arxiv_id":null,"rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/bp-transformer-modelling-long-range-context","slug":"bp-transformer-modelling-long-range-context","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","date":"2019-11-11","arxiv_id":"1911.04070","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["yzh119/BPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bp-transformer-modelling-long-range-context#ran","syntology_url":"https://syntology.ai/paper/1911.04070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04070"}}}},{"paper":"/paper/augmenting-self-attention-with-persistent","slug":"augmenting-self-attention-with-persistent","title":"Augmenting Self-attention with Persistent Memory","date":"2019-07-02","arxiv_id":"1907.01470","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/augmenting-self-attention-with-persistent#ran","syntology_url":"https://syntology.ai/paper/1907.01470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.01470"}}}},{"paper":"/paper/discrete-flows-invertible-generative-models","slug":"discrete-flows-invertible-generative-models","title":"Discrete Flows: Invertible Generative Models of Discrete Data","date":"2019-05-24","arxiv_id":"1905.10347","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/adaptive-attention-span-in-transformers","slug":"adaptive-attention-span-in-transformers","title":"Adaptive Attention Span in Transformers","date":"2019-05-19","arxiv_id":"1905.07799","rows_on_this_dataset":2,"code_links":8,"syntology":null},{"paper":"/paper/dynamic-evaluation-of-transformer-language","slug":"dynamic-evaluation-of-transformer-language","title":"Dynamic Evaluation of Transformer Language Models","date":"2019-04-17","arxiv_id":"1904.08378","rows_on_this_dataset":1,"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":1,"code_links":21,"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":1,"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/character-level-language-modeling-with-deeper","slug":"character-level-language-modeling-with-deeper","title":"Character-Level Language Modeling with Deeper Self-Attention","date":"2018-08-09","arxiv_id":"1808.04444","rows_on_this_dataset":2,"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/multiplicative-lstm-for-sequence-modelling","slug":"multiplicative-lstm-for-sequence-modelling","title":"Multiplicative LSTM for sequence modelling","date":"2016-09-26","arxiv_id":"1609.07959","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-multiscale-recurrent-neural","slug":"hierarchical-multiscale-recurrent-neural","title":"Hierarchical Multiscale Recurrent Neural Networks","date":"2016-09-06","arxiv_id":"1609.01704","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/recurrent-highway-networks","slug":"recurrent-highway-networks","title":"Recurrent Highway Networks","date":"2016-07-12","arxiv_id":"1607.03474","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["julian121266/RecurrentHighwayNetworks"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recurrent-highway-networks#ran","syntology_url":"https://syntology.ai/paper/1607.03474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.03474"}}}},{"paper":"/paper/recurrent-batch-normalization","slug":"recurrent-batch-normalization","title":"Recurrent Batch Normalization","date":"2016-03-30","arxiv_id":"1603.09025","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recurrent-batch-normalization#ran","syntology_url":"https://syntology.ai/paper/1603.09025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.09025"}}}},{"paper":"/paper/architectural-complexity-measures-of","slug":"architectural-complexity-measures-of","title":"Architectural Complexity Measures of Recurrent Neural Networks","date":"2016-02-26","arxiv_id":"1602.08210","rows_on_this_dataset":2,"code_links":0,"syntology":null}],"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/dataset/text8/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/text8/papers/ran/1","json":"/dataset/text8/papers/ran/1.json","rows":7}],"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":8,"samples_harvested":181,"samples_ran":93,"samples_constructed":37,"samples_ran_checked":65,"samples_ran_instrument_failed":28,"samples_unverified":88,"pointer_only_for_licence":58,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":7,"papers_with_a_run_with_no_instrument_failure":6,"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":1,"papers_placed":0,"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-text8","since_archive":"/sota/language-modelling-on-text8#since-judged","papers_judged":1,"placed":0}]},"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":"8b4f5c0abdf054d3f6785254c0da04565d8dbf5b5723b3d867b31b605d871624","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}