{"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":"/sota/language-modelling-on-wikitext-103","task":{"name":"Language Modelling","url":"/task/language-modelling","note":null},"dataset":{"name":"WikiText-103","url":"/dataset/wikitext-103"},"category":"Natural Language Processing","categories":["Medical","Miscellaneous","Natural Language Processing"],"category_note":null,"description":"A language model is a model of natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation, natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, and information retrieval.\r\n\r\nLarge language models (LLMs), currently their most advanced form, are predominantly based on transformers trained on larger datasets (frequently using words scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word n-gram language model. \r\n\r\nSource: [Wikipedia](https://en.wikipedia.org/wiki/Language_model)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Test perplexity","Validation perplexity","Number of params"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Test perplexity":"lower","Validation perplexity":"lower","Number of params":"lower"}},"counts":{"rows":89,"rows_with_code":81,"rows_with_paper_page":89,"rows_dated":89,"rows_using_additional_data":15},"rows":[{"rank_in_archive_order":1,"model":"RETRO (7.5B)","metrics":{"Number of params":"7532M","Test perplexity":"2.4"},"uses_additional_data":true,"paper_date":"2021-12-08","paper":"/paper/improving-language-models-by-retrieving-from","paper_url":"https://arxiv.org/abs/2112.04426v3","paper_title":"Improving language models by retrieving from trillions of tokens","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":2,"official":null,"syntology":{"n_ran":16,"n_constructed":5,"n_ran_checked":14,"n_instrument":2,"n_unverified":7,"n_samples":23,"n_pointer_only_licence":3,"sample_list":"/paper/improving-language-models-by-retrieving-from#ran","syntology_url":"https://syntology.ai/paper/2112.04426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.04426"}}}},{"rank_in_archive_order":2,"model":"Hybrid H3 (2.7B)","metrics":{"Number of params":"2700M","Test perplexity":"10.6"},"uses_additional_data":true,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"official":{"repos":["hazyresearch/h3"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"rank_in_archive_order":3,"model":"Megatron-LM","metrics":{"Number of params":"8300M","Test perplexity":"10.81"},"uses_additional_data":true,"paper_date":"2019-09-17","paper":"/paper/megatron-lm-training-multi-billion-parameter","paper_url":"https://arxiv.org/abs/1909.08053v4","paper_title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","code":"https://github.com/NVIDIA/Megatron-LM","n_code_links":10,"official":{"repos":["NVIDIA/Megatron-LM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":35,"n_samples":47,"n_pointer_only_licence":15,"sample_list":"/paper/megatron-lm-training-multi-billion-parameter#ran","syntology_url":"https://syntology.ai/paper/1909.08053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08053"}}}},{"rank_in_archive_order":4,"model":"GLM-XXLarge (bidirectional)","metrics":{"Number of params":"10000M","Test perplexity":"11.33"},"uses_additional_data":true,"paper_date":"2021-03-18","paper":"/paper/all-nlp-tasks-are-generation-tasks-a-general","paper_url":"https://arxiv.org/abs/2103.10360v2","paper_title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","code":"https://github.com/thudm/chatglm2-6b","n_code_links":8,"official":{"repos":["THUDM/GLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/all-nlp-tasks-are-generation-tasks-a-general#ran","syntology_url":"https://syntology.ai/paper/2103.10360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10360"}}}},{"rank_in_archive_order":5,"model":"GLM-XXLarge (unidirectional)","metrics":{"Number of params":"10000M","Test perplexity":"12.22"},"uses_additional_data":true,"paper_date":"2021-03-18","paper":"/paper/all-nlp-tasks-are-generation-tasks-a-general","paper_url":"https://arxiv.org/abs/2103.10360v2","paper_title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","code":"https://github.com/thudm/chatglm2-6b","n_code_links":8,"official":{"repos":["THUDM/GLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/all-nlp-tasks-are-generation-tasks-a-general#ran","syntology_url":"https://syntology.ai/paper/2103.10360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10360"}}}},{"rank_in_archive_order":6,"model":"Hybrid H3 (1.3B)","metrics":{"Number of params":"1300M","Test perplexity":"12.5"},"uses_additional_data":true,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"official":{"repos":["hazyresearch/h3"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"rank_in_archive_order":7,"model":"Ensemble of All","metrics":{"Test perplexity":"13.29","Validation perplexity":"13.11"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/advancing-state-of-the-art-in-language","paper_url":"https://arxiv.org/abs/2312.03735v1","paper_title":"Advancing State of the Art in Language Modeling","code":"https://github.com/davidherel/sota_lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"GateLoop (125M)","metrics":{"Number of params":"125M","Test perplexity":"13.4"},"uses_additional_data":false,"paper_date":"2023-11-03","paper":"/paper/gateloop-fully-data-controlled-linear","paper_url":"https://arxiv.org/abs/2311.01927v2","paper_title":"GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling","code":"https://github.com/tobiaskatsch/GateLoop","n_code_links":3,"official":{"repos":["tobiaskatsch/GateLoop"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/gateloop-fully-data-controlled-linear#ran","syntology_url":"https://syntology.ai/paper/2311.01927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01927"}}}},{"rank_in_archive_order":9,"model":"kNN-LM w/ Adaptive Coefficient","metrics":{"Number of params":"247M","Test perplexity":"15.5","Validation perplexity":"15.72"},"uses_additional_data":false,"paper_date":"2022-10-28","paper":"/paper/you-can-t-pick-your-neighbors-or-can-you-when","paper_url":"https://arxiv.org/abs/2210.15859v1","paper_title":"You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM","code":"https://github.com/iesl/knnlm-retrieval-quality","n_code_links":1,"official":{"repos":["iesl/knnlm-retrieval-quality"],"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"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/you-can-t-pick-your-neighbors-or-can-you-when#ran","syntology_url":"https://syntology.ai/paper/2210.15859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15859"}}}},{"rank_in_archive_order":10,"model":"kNN-LM w/ Continuous Cache","metrics":{"Number of params":"247M","Test perplexity":"15.79","Validation perplexity":"15.81"},"uses_additional_data":false,"paper_date":"2019-11-01","paper":"/paper/generalization-through-memorization-nearest","paper_url":"https://arxiv.org/abs/1911.00172v2","paper_title":"Generalization through Memorization: Nearest Neighbor Language Models","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":5,"official":{"repos":["urvashik/knnlm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/generalization-through-memorization-nearest#ran","syntology_url":"https://syntology.ai/paper/1911.00172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00172"}}}},{"rank_in_archive_order":11,"model":"Routing Transformer","metrics":{"Test perplexity":"15.8"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/efficient-content-based-sparse-attention-with-1","paper_url":"https://arxiv.org/abs/2003.05997v5","paper_title":"Efficient Content-Based Sparse Attention with Routing Transformers","code":"https://github.com/lucidrains/local-attention","n_code_links":2,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/efficient-content-based-sparse-attention-with-1#ran","syntology_url":"https://syntology.ai/paper/2003.05997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05997"}}}},{"rank_in_archive_order":12,"model":"kNN-LM","metrics":{"Number of params":"247M","Test perplexity":"16.12","Validation perplexity":"16.06"},"uses_additional_data":false,"paper_date":"2019-11-01","paper":"/paper/generalization-through-memorization-nearest","paper_url":"https://arxiv.org/abs/1911.00172v2","paper_title":"Generalization through Memorization: Nearest Neighbor Language Models","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":5,"official":{"repos":["urvashik/knnlm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/generalization-through-memorization-nearest#ran","syntology_url":"https://syntology.ai/paper/1911.00172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00172"}}}},{"rank_in_archive_order":13,"model":"Transformer-XL (RMS dynamic eval)","metrics":{"Number of params":"257M","Test perplexity":"16.4","Validation perplexity":"15.8"},"uses_additional_data":true,"paper_date":"2019-04-17","paper":"/paper/dynamic-evaluation-of-transformer-language","paper_url":"http://arxiv.org/abs/1904.08378v1","paper_title":"Dynamic Evaluation of Transformer Language Models","code":"https://github.com/benkrause/dynamiceval-transformer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"[?]-former (SM)","metrics":{"Test perplexity":"16.61"},"uses_additional_data":false,"paper_date":"2021-09-01","paper":"/paper/infty-former-infinite-memory-transformer","paper_url":"https://arxiv.org/abs/2109.00301v3","paper_title":"$\\infty$-former: Infinite Memory Transformer","code":"https://github.com/deep-spin/infinite-former","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"-former (SM)","metrics":{"Test perplexity":"16.61"},"uses_additional_data":false,"paper_date":"2021-09-01","paper":"/paper/infty-former-infinite-memory-transformer","paper_url":"https://arxiv.org/abs/2109.00301v3","paper_title":"$\\infty$-former: Infinite Memory Transformer","code":"https://github.com/deep-spin/infinite-former","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"∞-former (Sticky memories + initialized GPT-2 Small)","metrics":{"Test perplexity":"16.61"},"uses_additional_data":true,"paper_date":"2021-09-01","paper":"/paper/infty-former-infinite-memory-transformer","paper_url":"https://arxiv.org/abs/2109.00301v3","paper_title":"$\\infty$-former: Infinite Memory Transformer","code":"https://github.com/deep-spin/infinite-former","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"∞-former (initialized GPT-2 Small)","metrics":{"Test perplexity":"16.64"},"uses_additional_data":true,"paper_date":"2021-09-01","paper":"/paper/infty-former-infinite-memory-transformer","paper_url":"https://arxiv.org/abs/2109.00301v3","paper_title":"$\\infty$-former: Infinite Memory Transformer","code":"https://github.com/deep-spin/infinite-former","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"Hybrid H3 (355M)","metrics":{"Number of params":"355M","Test perplexity":"16.9"},"uses_additional_data":true,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"official":{"repos":["hazyresearch/h3"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"rank_in_archive_order":19,"model":"Transformer-XL (SGD dynamic eval)","metrics":{"Number of params":"257M","Test perplexity":"17.0","Validation perplexity":"16.3"},"uses_additional_data":false,"paper_date":"2019-04-17","paper":"/paper/dynamic-evaluation-of-transformer-language","paper_url":"http://arxiv.org/abs/1904.08378v1","paper_title":"Dynamic Evaluation of Transformer Language Models","code":"https://github.com/benkrause/dynamiceval-transformer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"Compressive Transformer (18L, M=1024)","metrics":{"Test perplexity":"17.1","Validation perplexity":"16.0"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/compressive-transformers-for-long-range-1","paper_url":"https://arxiv.org/abs/1911.05507v1","paper_title":"Compressive Transformers for Long-Range Sequence Modelling","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":6,"official":null,"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/compressive-transformers-for-long-range-1#ran","syntology_url":"https://syntology.ai/paper/1911.05507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.05507"}}}},{"rank_in_archive_order":21,"model":"SRU++ Large","metrics":{"Number of params":"234M","Test perplexity":"17.1","Validation perplexity":"16.4"},"uses_additional_data":false,"paper_date":"2021-02-24","paper":"/paper/when-attention-meets-fast-recurrence-training","paper_url":"https://arxiv.org/abs/2102.12459v3","paper_title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","code":"https://github.com/asappresearch/sru","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"SegaTransformer-XL","metrics":{"Number of params":"257M","Test perplexity":"17.1"},"uses_additional_data":false,"paper_date":"2020-04-30","paper":"/paper/segabert-pre-training-of-segment-aware-bert","paper_url":"https://arxiv.org/abs/2004.14996v2","paper_title":"Segatron: Segment-Aware Transformer for Language Modeling and Understanding","code":"https://github.com/rsvp-ai/segatron_aaai","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"Transformer+SSA+Self-ensemble","metrics":{"Test perplexity":"17.18","Validation perplexity":"16.54"},"uses_additional_data":false,"paper_date":"2023-06-02","paper":"/paper/the-information-pathways-hypothesis","paper_url":"https://arxiv.org/abs/2306.01705v1","paper_title":"The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles","code":"https://github.com/shamim-hussain/ssa","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"Transformer-XL Large + Phrase Induction","metrics":{"Number of params":"257M","Test perplexity":"17.4"},"uses_additional_data":false,"paper_date":"2019-06-04","paper":"/paper/improving-neural-language-models-by","paper_url":"https://arxiv.org/abs/1906.01702v1","paper_title":"Improving Neural Language Models by Segmenting, Attending, and Predicting the Future","code":"https://github.com/luohongyin/PILM","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"GPT-2 Full","metrics":{"Number of params":"1542M","Test perplexity":"17.48"},"uses_additional_data":true,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"Staged Training","metrics":{"Number of params":"247M","Test perplexity":"17.56","Validation perplexity":"16.89"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/shortformer-better-language-modeling-using","paper_url":"https://arxiv.org/abs/2012.15832v2","paper_title":"Shortformer: Better Language Modeling using Shorter Inputs","code":"https://github.com/ofirpress/shortformer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"Transformer+SSA","metrics":{"Test perplexity":"17.60","Validation perplexity":"16.91"},"uses_additional_data":false,"paper_date":"2023-06-02","paper":"/paper/the-information-pathways-hypothesis","paper_url":"https://arxiv.org/abs/2306.01705v1","paper_title":"The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles","code":"https://github.com/shamim-hussain/ssa","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"Sandwich Transformer","metrics":{"Number of params":"247M","Test perplexity":"17.96"},"uses_additional_data":false,"paper_date":"2019-11-10","paper":"/paper/improving-transformer-models-by-reordering","paper_url":"https://arxiv.org/abs/1911.03864v2","paper_title":"Improving Transformer Models by Reordering their Sublayers","code":"https://github.com/ofirpress/sandwich_transformer","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"DIFFQ (λ=1, g=16)","metrics":{"Test perplexity":"18.0"},"uses_additional_data":false,"paper_date":"2021-04-20","paper":"/paper/differentiable-model-compression-via-pseudo","paper_url":"https://arxiv.org/abs/2104.09987v3","paper_title":"Differentiable Model Compression via Pseudo Quantization Noise","code":"https://github.com/facebookresearch/diffq","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"Mega","metrics":{"Number of params":"252M","Test perplexity":"18.07"},"uses_additional_data":false,"paper_date":"2022-09-21","paper":"/paper/mega-moving-average-equipped-gated-attention","paper_url":"https://arxiv.org/abs/2209.10655v3","paper_title":"Mega: Moving Average Equipped Gated Attention","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":{"repos":["facebookresearch/mega"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":12,"n_constructed":6,"n_ran_checked":7,"n_instrument":5,"n_unverified":1,"n_samples":13,"n_pointer_only_licence":11,"sample_list":"/paper/mega-moving-average-equipped-gated-attention#ran","syntology_url":"https://syntology.ai/paper/2209.10655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.10655"}}}},{"rank_in_archive_order":31,"model":"Shortformer","metrics":{"Number of params":"247M","Test perplexity":"18.15","Validation perplexity":"17.47"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/shortformer-better-language-modeling-using","paper_url":"https://arxiv.org/abs/2012.15832v2","paper_title":"Shortformer: Better Language Modeling using Shorter Inputs","code":"https://github.com/ofirpress/shortformer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"Feedback Transformer (8 layers)","metrics":{"Number of params":"139M","Test perplexity":"18.2","Validation perplexity":"17.5"},"uses_additional_data":false,"paper_date":"2020-02-21","paper":"/paper/accessing-higher-level-representations-in","paper_url":"https://arxiv.org/abs/2002.09402v3","paper_title":"Addressing Some Limitations of Transformers with Feedback Memory","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":4,"official":{"repos":["facebookresearch/transformer-sequential"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/accessing-higher-level-representations-in#ran","syntology_url":"https://syntology.ai/paper/2002.09402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09402"}}}},{"rank_in_archive_order":33,"model":"SRU++ Base","metrics":{"Number of params":"148M","Test perplexity":"18.3","Validation perplexity":"17.5"},"uses_additional_data":false,"paper_date":"2021-02-24","paper":"/paper/when-attention-meets-fast-recurrence-training","paper_url":"https://arxiv.org/abs/2102.12459v3","paper_title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","code":"https://github.com/asappresearch/sru","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"Transformer-XL Large","metrics":{"Number of params":"257M","Test perplexity":"18.3","Validation perplexity":"18.2"},"uses_additional_data":false,"paper_date":"2019-01-09","paper":"/paper/transformer-xl-attentive-language-models","paper_url":"https://arxiv.org/abs/1901.02860v3","paper_title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","code":"https://github.com/huggingface/transformers","n_code_links":37,"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"]},"syntology":{"n_ran":67,"n_constructed":37,"n_ran_checked":49,"n_instrument":18,"n_unverified":76,"n_samples":143,"n_pointer_only_licence":43,"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"}}}},{"rank_in_archive_order":35,"model":"PAR Transformer Large","metrics":{"Test perplexity":"18.4"},"uses_additional_data":false,"paper_date":"2020-09-09","paper":"/paper/pay-attention-when-required","paper_url":"https://arxiv.org/abs/2009.04534v3","paper_title":"Pay Attention when Required","code":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/LanguageModeling","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"Perceiver AR 358M","metrics":{"Test perplexity":"18.4"},"uses_additional_data":false,"paper_date":"2022-02-15","paper":"/paper/general-purpose-long-context-autoregressive","paper_url":"https://arxiv.org/abs/2202.07765v2","paper_title":"General-purpose, long-context autoregressive modeling with Perceiver AR","code":"https://github.com/krasserm/perceiver-io","n_code_links":3,"official":{"repos":["google-research/perceiver-ar"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":1,"sample_list":"/paper/general-purpose-long-context-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2202.07765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.07765"}}}},{"rank_in_archive_order":37,"model":"Hyena-3-slim","metrics":{"Test perplexity":"18.5"},"uses_additional_data":false,"paper_date":"2023-02-21","paper":"/paper/hyena-hierarchy-towards-larger-convolutional","paper_url":"https://arxiv.org/abs/2302.10866v3","paper_title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","code":"https://github.com/hazyresearch/safari","n_code_links":7,"official":{"repos":["hazyresearch/safari"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":4,"sample_list":"/paper/hyena-hierarchy-towards-larger-convolutional#ran","syntology_url":"https://syntology.ai/paper/2302.10866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10866"}}}},{"rank_in_archive_order":38,"model":"Hybrid H3 125M","metrics":{"Test perplexity":"18.5"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"official":{"repos":["hazyresearch/h3"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"rank_in_archive_order":39,"model":"Hyena-3","metrics":{"Test perplexity":"18.6"},"uses_additional_data":false,"paper_date":"2023-02-21","paper":"/paper/hyena-hierarchy-towards-larger-convolutional","paper_url":"https://arxiv.org/abs/2302.10866v3","paper_title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","code":"https://github.com/hazyresearch/safari","n_code_links":7,"official":{"repos":["hazyresearch/safari"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":4,"sample_list":"/paper/hyena-hierarchy-towards-larger-convolutional#ran","syntology_url":"https://syntology.ai/paper/2302.10866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10866"}}}},{"rank_in_archive_order":40,"model":"Transformer (Adaptive inputs)","metrics":{"Number of params":"247M","Test perplexity":"18.70","Validation perplexity":"17.97"},"uses_additional_data":false,"paper_date":"2018-09-28","paper":"/paper/adaptive-input-representations-for-neural","paper_url":"http://arxiv.org/abs/1809.10853v3","paper_title":"Adaptive Input Representations for Neural Language Modeling","code":"https://github.com/pytorch/fairseq","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"T2R + Pretrain","metrics":{"Test perplexity":"19.6","Validation perplexity":"19"},"uses_additional_data":false,"paper_date":"2021-03-24","paper":"/paper/finetuning-pretrained-transformers-into-rnns","paper_url":"https://arxiv.org/abs/2103.13076v2","paper_title":"Finetuning Pretrained Transformers into RNNs","code":"https://github.com/hazyresearch/lolcats","n_code_links":2,"official":null,"syntology":{"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":4,"sample_list":"/paper/finetuning-pretrained-transformers-into-rnns#ran","syntology_url":"https://syntology.ai/paper/2103.13076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13076"}}}},{"rank_in_archive_order":42,"model":"Subformer","metrics":{"Number of params":"96M","Test perplexity":"20.39"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/subformer-a-parameter-reduced-transformer","paper_url":"https://openreview.net/forum?id=6UurSaf08jx","paper_title":"Subformer: A Parameter Reduced Transformer","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"BERT-Large-CAS","metrics":{"Number of params":"395M","Test perplexity":"20.4","Validation perplexity":"19.6"},"uses_additional_data":false,"paper_date":"2019-04-20","paper":"/paper/190409408","paper_url":"https://arxiv.org/abs/1904.09408v2","paper_title":"Language Models with Transformers","code":"https://github.com/cgraywang/gluon-nlp-1","n_code_links":1,"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"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/190409408#ran","syntology_url":"https://syntology.ai/paper/1904.09408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09408"}}}},{"rank_in_archive_order":44,"model":"All-attention network (36 layers)","metrics":{"Number of params":"133M","Test perplexity":"20.6","Validation perplexity":"19.7"},"uses_additional_data":false,"paper_date":"2019-07-02","paper":"/paper/augmenting-self-attention-with-persistent","paper_url":"https://arxiv.org/abs/1907.01470v1","paper_title":"Augmenting Self-attention with Persistent Memory","code":"https://github.com/lucidrains/x-transformers","n_code_links":2,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":4,"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"}}}},{"rank_in_archive_order":45,"model":"S4","metrics":{"Number of params":"249M","Test perplexity":"21.28"},"uses_additional_data":false,"paper_date":"2021-10-31","paper":"/paper/efficiently-modeling-long-sequences-with-1","paper_url":"https://arxiv.org/abs/2111.00396v3","paper_title":"Efficiently Modeling Long Sequences with Structured State Spaces","code":"https://github.com/state-spaces/s4","n_code_links":8,"official":{"repos":["state-spaces/s4"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["community","listed","official"]},"syntology":{"n_ran":37,"n_constructed":8,"n_ran_checked":21,"n_instrument":16,"n_unverified":18,"n_samples":55,"n_pointer_only_licence":3,"sample_list":"/paper/efficiently-modeling-long-sequences-with-1#ran","syntology_url":"https://syntology.ai/paper/2111.00396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00396"}}}},{"rank_in_archive_order":46,"model":"GPT-2 Large","metrics":{"Number of params":"774M","Test perplexity":"22.05"},"uses_additional_data":true,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"Feedback Transformer (4 layers)","metrics":{"Number of params":"44M","Test perplexity":"22.4","Validation perplexity":"21.4"},"uses_additional_data":false,"paper_date":"2020-02-21","paper":"/paper/accessing-higher-level-representations-in","paper_url":"https://arxiv.org/abs/2002.09402v3","paper_title":"Addressing Some Limitations of Transformers with Feedback Memory","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":4,"official":{"repos":["facebookresearch/transformer-sequential"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/accessing-higher-level-representations-in#ran","syntology_url":"https://syntology.ai/paper/2002.09402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09402"}}}},{"rank_in_archive_order":48,"model":"PAR Transformer Base","metrics":{"Test perplexity":"22.7"},"uses_additional_data":false,"paper_date":"2020-09-09","paper":"/paper/pay-attention-when-required","paper_url":"https://arxiv.org/abs/2009.04534v3","paper_title":"Pay Attention when Required","code":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/LanguageModeling","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"Skip Cross-Head Transformer-XL","metrics":{"Number of params":"122M","Test perplexity":"22.91","Validation perplexity":"21.87"},"uses_additional_data":false,"paper_date":"2023-11-14","paper":"/paper/memory-efficient-stochastic-methods-for","paper_url":"https://arxiv.org/abs/2311.08123v1","paper_title":"Memory-efficient Stochastic methods for Memory-based Transformers","code":"https://github.com/vishwajit-vishnu/memory-efficient-stochastic-methods-for-memory-based-transformers","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"DEQ-Transformer (medium, adaptive embed)","metrics":{"Number of params":"110M","Test perplexity":"23.2"},"uses_additional_data":false,"paper_date":"2019-09-03","paper":"/paper/deep-equilibrium-models","paper_url":"https://arxiv.org/abs/1909.01377v2","paper_title":"Deep Equilibrium Models","code":"https://github.com/locuslab/deq","n_code_links":11,"official":{"repos":["locuslab/deq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":4,"sample_list":"/paper/deep-equilibrium-models#ran","syntology_url":"https://syntology.ai/paper/1909.01377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01377"}}}},{"rank_in_archive_order":51,"model":"TaLK Convolutions","metrics":{"Number of params":"240M","Test perplexity":"23.3"},"uses_additional_data":false,"paper_date":"2020-02-08","paper":"/paper/time-aware-large-kernel-convolutions","paper_url":"https://arxiv.org/abs/2002.03184v2","paper_title":"Time-aware Large Kernel Convolutions","code":"https://github.com/lioutasb/TaLKConvolutions","n_code_links":1,"official":{"repos":["lioutasb/TaLKConvolutions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":2,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":3,"sample_list":"/paper/time-aware-large-kernel-convolutions#ran","syntology_url":"https://syntology.ai/paper/2002.03184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.03184"}}}},{"rank_in_archive_order":52,"model":"Rfa-Gate-Gaussian-Stateful (Big)","metrics":{"Test perplexity":"23.5","Validation perplexity":"22"},"uses_additional_data":false,"paper_date":"2021-03-03","paper":"/paper/random-feature-attention-1","paper_url":"https://arxiv.org/abs/2103.02143v2","paper_title":"Random Feature Attention","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":53,"model":"Hybrid H3 (125M)","metrics":{"Number of params":"125M","Test perplexity":"23.7"},"uses_additional_data":true,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"official":{"repos":["hazyresearch/h3"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"rank_in_archive_order":54,"model":"Transformer-XL Standard","metrics":{"Number of params":"151M","Test perplexity":"24.0","Validation perplexity":"23.1"},"uses_additional_data":false,"paper_date":"2019-01-09","paper":"/paper/transformer-xl-attentive-language-models","paper_url":"https://arxiv.org/abs/1901.02860v3","paper_title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","code":"https://github.com/huggingface/transformers","n_code_links":37,"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"]},"syntology":{"n_ran":67,"n_constructed":37,"n_ran_checked":49,"n_instrument":18,"n_unverified":76,"n_samples":143,"n_pointer_only_licence":43,"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"}}}},{"rank_in_archive_order":55,"model":"DeLighT","metrics":{"Number of params":"99M","Test perplexity":"24.14"},"uses_additional_data":false,"paper_date":"2020-08-03","paper":"/paper/delight-very-deep-and-light-weight","paper_url":"https://arxiv.org/abs/2008.00623v2","paper_title":"DeLighT: Deep and Light-weight Transformer","code":"https://github.com/sacmehta/delight","n_code_links":2,"official":{"repos":["sacmehta/delight"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/delight-very-deep-and-light-weight#ran","syntology_url":"https://syntology.ai/paper/2008.00623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.00623"}}}},{"rank_in_archive_order":56,"model":"[?]-former (Sticky memories)","metrics":{"Test perplexity":"24.22"},"uses_additional_data":false,"paper_date":"2021-09-01","paper":"/paper/infty-former-infinite-memory-transformer","paper_url":"https://arxiv.org/abs/2109.00301v3","paper_title":"$\\infty$-former: Infinite Memory Transformer","code":"https://github.com/deep-spin/infinite-former","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"\\infty-former (Sticky memories)","metrics":{"Test perplexity":"24.22"},"uses_additional_data":false,"paper_date":"2021-09-01","paper":"/paper/infty-former-infinite-memory-transformer","paper_url":"https://arxiv.org/abs/2109.00301v3","paper_title":"$\\infty$-former: Infinite Memory Transformer","code":"https://github.com/deep-spin/infinite-former","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"∞-former (Sticky memories)","metrics":{"Test perplexity":"24.22"},"uses_additional_data":false,"paper_date":"2021-09-01","paper":"/paper/infty-former-infinite-memory-transformer","paper_url":"https://arxiv.org/abs/2109.00301v3","paper_title":"$\\infty$-former: Infinite Memory Transformer","code":"https://github.com/deep-spin/infinite-former","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"Transformer-N","metrics":{"Number of params":"148M","Test perplexity":"25.2","Validation perplexity":"24.1"},"uses_additional_data":false,"paper_date":"2021-04-08","paper":"/paper/revisiting-simple-neural-probabilistic","paper_url":"https://arxiv.org/abs/2104.03474v1","paper_title":"Revisiting Simple Neural Probabilistic Language Models","code":"https://github.com/SimengSun/revisit-nplm","n_code_links":1,"official":{"repos":["SimengSun/revisit-nplm"],"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"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/revisiting-simple-neural-probabilistic#ran","syntology_url":"https://syntology.ai/paper/2104.03474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03474"}}}},{"rank_in_archive_order":60,"model":"Linear Attention 125M","metrics":{"Test perplexity":"25.6"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/transformers-are-rnns-fast-autoregressive","paper_url":"https://arxiv.org/abs/2006.16236v3","paper_title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","code":"https://github.com/idiap/fast-transformers","n_code_links":8,"official":{"repos":["idiap/fast-transformers"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":3,"sample_list":"/paper/transformers-are-rnns-fast-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2006.16236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16236"}}}},{"rank_in_archive_order":61,"model":"FNetAR Medium","metrics":{"Number of params":"144.4M","Test perplexity":"25.81"},"uses_additional_data":false,"paper_date":"2021-07-22","paper":"/paper/fnetar-mixing-tokens-with-autoregressive","paper_url":"https://arxiv.org/abs/2107.10932v1","paper_title":"FNetAR: Mixing Tokens with Autoregressive Fourier Transforms","code":"https://github.com/MindCode-4/code-3/tree/main/fnet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"Reformer 125M","metrics":{"Test perplexity":"26.0"},"uses_additional_data":false,"paper_date":"2020-01-13","paper":"/paper/reformer-the-efficient-transformer-1","paper_url":"https://arxiv.org/abs/2001.04451v2","paper_title":"Reformer: The Efficient Transformer","code":"https://github.com/huggingface/transformers","n_code_links":10,"official":{"repos":["google/trax"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":6,"n_constructed":1,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/reformer-the-efficient-transformer-1#ran","syntology_url":"https://syntology.ai/paper/2001.04451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04451"}}}},{"rank_in_archive_order":63,"model":"GPT-2 Medium","metrics":{"Number of params":"355M","Test perplexity":"26.37"},"uses_additional_data":true,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"Performer 125M","metrics":{"Test perplexity":"26.8"},"uses_additional_data":false,"paper_date":"2020-09-30","paper":"/paper/rethinking-attention-with-performers","paper_url":"https://arxiv.org/abs/2009.14794v4","paper_title":"Rethinking Attention with Performers","code":"https://github.com/tensorflow/models/tree/master/official/nlp/modeling","n_code_links":7,"official":{"repos":["google-research/google-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":3,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_samples":16,"n_pointer_only_licence":6,"sample_list":"/paper/rethinking-attention-with-performers#ran","syntology_url":"https://syntology.ai/paper/2009.14794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14794"}}}},{"rank_in_archive_order":65,"model":"AdvSoft (+ 4 layer QRNN + dynamic eval)","metrics":{"Test perplexity":"28.0","Validation perplexity":"27.2"},"uses_additional_data":false,"paper_date":"2019-06-10","paper":"/paper/improving-neural-language-modeling-via","paper_url":"https://arxiv.org/abs/1906.03805v2","paper_title":"Improving Neural Language Modeling via Adversarial Training","code":"https://github.com/ChengyueGongR/advsoft","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"DEQ-TrellisNet","metrics":{"Number of params":"180M","Test perplexity":"29.0"},"uses_additional_data":false,"paper_date":"2019-09-03","paper":"/paper/deep-equilibrium-models","paper_url":"https://arxiv.org/abs/1909.01377v2","paper_title":"Deep Equilibrium Models","code":"https://github.com/locuslab/deq","n_code_links":11,"official":{"repos":["locuslab/deq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":4,"sample_list":"/paper/deep-equilibrium-models#ran","syntology_url":"https://syntology.ai/paper/1909.01377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01377"}}}},{"rank_in_archive_order":67,"model":"Trellis Network","metrics":{"Test perplexity":"29.19"},"uses_additional_data":false,"paper_date":"2018-10-15","paper":"/paper/trellis-networks-for-sequence-modeling","paper_url":"http://arxiv.org/abs/1810.06682v2","paper_title":"Trellis Networks for Sequence Modeling","code":"https://github.com/locuslab/trellisnet","n_code_links":1,"official":{"repos":["locuslab/trellisnet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":2,"sample_list":"/paper/trellis-networks-for-sequence-modeling#ran","syntology_url":"https://syntology.ai/paper/1810.06682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06682"}}}},{"rank_in_archive_order":68,"model":"LSTM (Hebbian, Cache, MbPA)","metrics":{"Test perplexity":"29.2","Validation perplexity":"29.0"},"uses_additional_data":false,"paper_date":"2018-03-27","paper":"/paper/fast-parametric-learning-with-activation","paper_url":"http://arxiv.org/abs/1803.10049v1","paper_title":"Fast Parametric Learning with Activation Memorization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"LSTM (Hebbian, Cache)","metrics":{"Test perplexity":"29.7","Validation perplexity":"29.9"},"uses_additional_data":false,"paper_date":"2018-03-27","paper":"/paper/fast-parametric-learning-with-activation","paper_url":"http://arxiv.org/abs/1803.10049v1","paper_title":"Fast Parametric Learning with Activation Memorization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"Rfa-Gate-Gaussian-Stateful (Small)","metrics":{"Test perplexity":"30.5","Validation perplexity":"29.4"},"uses_additional_data":false,"paper_date":"2021-03-03","paper":"/paper/random-feature-attention-1","paper_url":"https://arxiv.org/abs/2103.02143v2","paper_title":"Random Feature Attention","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"Primal.+Trans.","metrics":{"Test perplexity":"31.0"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/primal-attention-self-attention-through","paper_url":"https://arxiv.org/abs/2305.19798v2","paper_title":"Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation","code":"https://github.com/yingyichen-cyy/PrimalAttention","n_code_links":1,"official":{"repos":["yingyichen-cyy/PrimalAttention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/primal-attention-self-attention-through#ran","syntology_url":"https://syntology.ai/paper/2305.19798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19798"}}}},{"rank_in_archive_order":72,"model":"LSTM (RMC)","metrics":{"Test perplexity":"31.6","Validation perplexity":"30.8"},"uses_additional_data":false,"paper_date":"2018-06-05","paper":"/paper/relational-recurrent-neural-networks","paper_url":"http://arxiv.org/abs/1806.01822v2","paper_title":"Relational recurrent neural networks","code":"https://github.com/L0SG/relational-rnn-pytorch","n_code_links":2,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":1,"sample_list":"/paper/relational-recurrent-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1806.01822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01822"}}}},{"rank_in_archive_order":73,"model":"DEQ-Transformer (small)","metrics":{"Number of params":"138M","Test perplexity":"32.4"},"uses_additional_data":false,"paper_date":"2019-09-03","paper":"/paper/deep-equilibrium-models","paper_url":"https://arxiv.org/abs/1909.01377v2","paper_title":"Deep Equilibrium Models","code":"https://github.com/locuslab/deq","n_code_links":11,"official":{"repos":["locuslab/deq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":4,"sample_list":"/paper/deep-equilibrium-models#ran","syntology_url":"https://syntology.ai/paper/1909.01377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01377"}}}},{"rank_in_archive_order":74,"model":"AWD-LSTM-MoS + ATOI","metrics":{"Test perplexity":"32.85","Validation perplexity":"31.92"},"uses_additional_data":false,"paper_date":"2019-09-18","paper":"/paper/alleviating-sequence-information-loss-with","paper_url":"https://arxiv.org/abs/1909.08700v1","paper_title":"Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes","code":"https://github.com/nkcr/overlap-ml","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":75,"model":"4 layer QRNN","metrics":{"Number of params":"151M","Test perplexity":"33.0","Validation perplexity":"32.0"},"uses_additional_data":false,"paper_date":"2018-03-22","paper":"/paper/an-analysis-of-neural-language-modeling-at","paper_url":"http://arxiv.org/abs/1803.08240v1","paper_title":"An Analysis of Neural Language Modeling at Multiple Scales","code":"https://github.com/salesforce/awd-lstm-lm","n_code_links":12,"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"]},"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":4,"sample_list":"/paper/an-analysis-of-neural-language-modeling-at#ran","syntology_url":"https://syntology.ai/paper/1803.08240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08240"}}}},{"rank_in_archive_order":76,"model":"LSTM (Hebbian)","metrics":{"Test perplexity":"34.3","Validation perplexity":"34.1"},"uses_additional_data":false,"paper_date":"2018-03-27","paper":"/paper/fast-parametric-learning-with-activation","paper_url":"http://arxiv.org/abs/1803.10049v1","paper_title":"Fast Parametric Learning with Activation Memorization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"LSTM","metrics":{"Test perplexity":"36.4","Validation perplexity":"36.0"},"uses_additional_data":false,"paper_date":"2018-03-27","paper":"/paper/fast-parametric-learning-with-activation","paper_url":"http://arxiv.org/abs/1803.10049v1","paper_title":"Fast Parametric Learning with Activation Memorization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":78,"model":"GCNN-8","metrics":{"Test perplexity":"37.2","Validation perplexity":"-"},"uses_additional_data":false,"paper_date":"2016-12-23","paper":"/paper/language-modeling-with-gated-convolutional","paper_url":"http://arxiv.org/abs/1612.08083v3","paper_title":"Language Modeling with Gated Convolutional Networks","code":"https://github.com/facebookresearch/fairseq","n_code_links":11,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"GPT-2 Small","metrics":{"Number of params":"124M","Test perplexity":"37.50"},"uses_additional_data":true,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"Neural cache model (size = 2,000)","metrics":{"Test perplexity":"40.8"},"uses_additional_data":false,"paper_date":"2016-12-13","paper":"/paper/improving-neural-language-models-with-a","paper_url":"http://arxiv.org/abs/1612.04426v1","paper_title":"Improving Neural Language Models with a Continuous Cache","code":"https://github.com/dmlc/gluon-nlp","n_code_links":14,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"Neural cache model (size = 100)","metrics":{"Test perplexity":"44.8"},"uses_additional_data":false,"paper_date":"2016-12-13","paper":"/paper/improving-neural-language-models-with-a","paper_url":"http://arxiv.org/abs/1612.04426v1","paper_title":"Improving Neural Language Models with a Continuous Cache","code":"https://github.com/dmlc/gluon-nlp","n_code_links":14,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"GCNN-8","metrics":{"Test perplexity":"44.9"},"uses_additional_data":false,"paper_date":"2016-12-23","paper":"/paper/language-modeling-with-gated-convolutional","paper_url":"http://arxiv.org/abs/1612.08083v3","paper_title":"Language Modeling with Gated Convolutional Networks","code":"https://github.com/facebookresearch/fairseq","n_code_links":11,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"TCN","metrics":{"Test perplexity":"45.19"},"uses_additional_data":false,"paper_date":"2018-03-04","paper":"/paper/an-empirical-evaluation-of-generic","paper_url":"http://arxiv.org/abs/1803.01271v2","paper_title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","code":"https://github.com/timeseriesAI/tsai/tree/main/tsai/models","n_code_links":35,"official":{"repos":["locuslab/TCN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/an-empirical-evaluation-of-generic#ran","syntology_url":"https://syntology.ai/paper/1803.01271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.01271"}}}},{"rank_in_archive_order":84,"model":"Temporal CNN","metrics":{"Test perplexity":"45.2","Validation perplexity":"-"},"uses_additional_data":false,"paper_date":"2018-01-01","paper":"/paper/convolutional-sequence-modeling-revisited","paper_url":"https://openreview.net/forum?id=rk8wKk-R-","paper_title":"Convolutional Sequence Modeling Revisited","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":85,"model":"LSTM","metrics":{"Test perplexity":"48.7"},"uses_additional_data":false,"paper_date":"2016-12-13","paper":"/paper/improving-neural-language-models-with-a","paper_url":"http://arxiv.org/abs/1612.04426v1","paper_title":"Improving Neural Language Models with a Continuous Cache","code":"https://github.com/dmlc/gluon-nlp","n_code_links":14,"official":null,"syntology":null},{"rank_in_archive_order":86,"model":"Transformer  (Adaptive inputs)","metrics":{"Validation perplexity":"19.5"},"uses_additional_data":false,"paper_date":"2019-10-09","paper":"/paper/on-the-adequacy-of-untuned-warmup-for","paper_url":"https://arxiv.org/abs/1910.04209v3","paper_title":"On the adequacy of untuned warmup for adaptive optimization","code":"https://github.com/Tony-Y/pytorch_warmup","n_code_links":1,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/on-the-adequacy-of-untuned-warmup-for#ran","syntology_url":"https://syntology.ai/paper/1910.04209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04209"}}}},{"rank_in_archive_order":87,"model":"LSTM","metrics":{"Validation perplexity":"52.73"},"uses_additional_data":false,"paper_date":"2020-05-17","paper":"/paper/how-much-complexity-does-an-rnn-architecture","paper_url":"https://arxiv.org/abs/2005.08199v2","paper_title":"How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?","code":"https://github.com/bhattg/Decay-RNN-ACL-SRW2020","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"GRU","metrics":{"Validation perplexity":"53.78"},"uses_additional_data":false,"paper_date":"2020-05-17","paper":"/paper/how-much-complexity-does-an-rnn-architecture","paper_url":"https://arxiv.org/abs/2005.08199v2","paper_title":"How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?","code":"https://github.com/bhattg/Decay-RNN-ACL-SRW2020","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"Decay RNN","metrics":{"Validation perplexity":"76.67"},"uses_additional_data":false,"paper_date":"2020-05-17","paper":"/paper/how-much-complexity-does-an-rnn-architecture","paper_url":"https://arxiv.org/abs/2005.08199v2","paper_title":"How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?","code":"https://github.com/bhattg/Decay-RNN-ACL-SRW2020","n_code_links":1,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 10 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,592 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 6 proposed a result; of those 6, 6 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 0 were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":89,"metric_columns":3,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1592,"candidates":10,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":6,"no_cell_passed_checks":6,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 6 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"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","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":6,"shown_on_page":6,"no_cell_split":{"no_cell_passed_checks_in_ledger":6,"rows_refused_by_rule":6,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2606.24650","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.24042","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.03953","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the model gave no value to check against the cell"},{"arxiv_id":"2603.09555","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.03024","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2510.16138","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_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'","n_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)"},"rows_with_graph_line":42,"rows_with_any_sample_ran":42,"rows_with_a_run_with_no_instrument_failure":36,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":35,"rows_whose_official_repository_has_a_sample_that_ran":20,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":11,"rows_community_repositories_only":11,"rows_runs_from_other_or_unrecorded_repositories":3,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology 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","distinct_papers_with_graph_line":31,"distinct_papers_with_any_sample_ran":31,"distinct_papers_with_a_run_with_no_instrument_failure":28,"samples_over_distinct_papers":{"n_ran":278,"n_constructed":66,"n_ran_checked":191,"n_instrument":87,"n_unverified":183,"n_samples":461,"n_pointer_only_licence":122,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":403,"n_constructed":103,"n_ran_checked":268,"n_instrument":135,"n_unverified":297,"n_samples":700,"n_pointer_only_licence":179,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"a62813c5c2573def74c348b04879c4a6990d3d3306d334ac9bd970db31c6b00d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}