{"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/cola","name":"CoLA","full_name":"Corpus of Linguistic Acceptability","description_markdown":"The **Corpus of Linguistic Acceptability** (**CoLA**) consists of 10657 sentences from 23 linguistics publications, expertly annotated for acceptability (grammaticality) by their original authors. The public version contains 9594 sentences belonging to training and development sets, and excludes 1063 sentences belonging to a held out test set.\r\n\r\nSource: [https://nyu-mll.github.io/CoLA/](https://nyu-mll.github.io/CoLA/)\r\nImage Source: [https://arxiv.org/pdf/1805.12471.pdf](https://arxiv.org/pdf/1805.12471.pdf)","description_withheld":null,"homepage":"https://nyu-mll.github.io/CoLA/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/neural-network-acceptability-judgments","title":"Neural Network Acceptability Judgments","first_author":"Alex Warstadt","url":null},"license":{"name":"Custom","url":"https://nyu-mll.github.io/CoLA/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Stochastic Optimization","url":"/task/stochastic-optimization","datasets_with_task":"/datasets/task/stochastic-optimization"},{"name":"Linguistic Acceptability","url":"/task/linguistic-acceptability","datasets_with_task":"/datasets/task/linguistic-acceptability"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"}],"variants":["CoLA","CoLA Dev"],"data_loaders":[],"num_papers_in_archive":710,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset_variant":"CoLA","rows":43,"metrics":["Accuracy","MCC"],"first_row_in_archive_order":{"model":"En-BERT + TDA + PCA","paper":"/paper/acceptability-judgements-via-examining-the","metrics":{"Accuracy":"88.6%"},"code_links":[{"title":"danchern97/tda4la","url":"https://github.com/danchern97/tda4la"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/linguistic-acceptability-on-cola-dev","task":"Linguistic Acceptability","dataset_variant":"CoLA Dev","rows":6,"metrics":["Accuracy","MCC"],"first_row_in_archive_order":{"model":"En-BERT + TDA","paper":"/paper/acceptability-judgements-via-examining-the","metrics":{"Accuracy":"88.6","MCC":"0.725"},"code_links":[{"title":"danchern97/tda4la","url":"https://github.com/danchern97/tda4la"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/stochastic-optimization-on-cola","task":"Stochastic Optimization","dataset_variant":"CoLA","rows":1,"metrics":["Accuracy (max)","Accuracy (mean)"],"first_row_in_archive_order":{"model":"Bert","paper":"/paper/mixing-adam-and-sgd-a-combined-optimization","metrics":{"Accuracy (max)":"86.34","Accuracy (mean)":"87.66"},"code_links":[{"title":"nicolalandro/multi_optimizer","url":"https://gitlab.com/nicolalandro/multi_optimizer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-cola","task":"Text Generation","dataset_variant":"CoLA","rows":0,"metrics":["acc"],"first_row_in_archive_order":null,"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":35,"of":35,"counts":{"papers_with_a_benchmark_row":35,"with_a_code_link":31,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":35,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/not-all-layers-are-equally-as-important-every","slug":"not-all-layers-are-equally-as-important-every","title":"Not all layers are equally as important: Every Layer Counts BERT","date":"2023-11-03","arxiv_id":"2311.02265","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/lm-cppf-paraphrasing-guided-data-augmentation","slug":"lm-cppf-paraphrasing-guided-data-augmentation","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","date":"2023-05-29","arxiv_id":"2305.18169","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/can-bert-eat-rucola-topological-data-analysis","slug":"can-bert-eat-rucola-topological-data-analysis","title":"Can BERT eat RuCoLA? Topological Data Analysis to Explain","date":"2023-04-04","arxiv_id":"2304.01680","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/texttt-tasksource-structured-dataset","slug":"texttt-tasksource-structured-dataset","title":"tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation","date":"2023-01-14","arxiv_id":"2301.05948","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["sileod/tasksource"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/texttt-tasksource-structured-dataset#ran","syntology_url":"https://syntology.ai/paper/2301.05948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.05948"}}}},{"paper":"/paper/rucola-russian-corpus-of-linguistic","slug":"rucola-russian-corpus-of-linguistic","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","date":"2022-10-23","arxiv_id":"2210.12814","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/llm-int8-8-bit-matrix-multiplication-for","slug":"llm-int8-8-bit-matrix-multiplication-for","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","date":"2022-08-15","arxiv_id":"2208.07339","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["timdettmers/bitsandbytes"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llm-int8-8-bit-matrix-multiplication-for#ran","syntology_url":"https://syntology.ai/paper/2208.07339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07339"}}}},{"paper":"/paper/acceptability-judgements-via-examining-the","slug":"acceptability-judgements-via-examining-the","title":"Acceptability Judgements via Examining the Topology of Attention Maps","date":"2022-05-19","arxiv_id":"2205.09630","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/data2vec-a-general-framework-for-self-1","slug":"data2vec-a-general-framework-for-self-1","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","date":"2022-02-07","arxiv_id":"2202.03555","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/data2vec-a-general-framework-for-self-1#ran","syntology_url":"https://syntology.ai/paper/2202.03555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03555"}}}},{"paper":"/paper/charformer-fast-character-transformers-via","slug":"charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","arxiv_id":"2106.12672","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/charformer-fast-character-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2106.12672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12672"}}}},{"paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","slug":"fnet-mixing-tokens-with-fourier-transforms","title":"FNet: Mixing Tokens with Fourier Transforms","date":"2021-05-09","arxiv_id":"2105.03824","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fnet-mixing-tokens-with-fourier-transforms#ran","syntology_url":"https://syntology.ai/paper/2105.03824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03824"}}}},{"paper":"/paper/entailment-as-few-shot-learner","slug":"entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","arxiv_id":"2104.14690","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/entailment-as-few-shot-learner#ran","syntology_url":"https://syntology.ai/paper/2104.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14690"}}}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/clear-contrastive-learning-for-sentence","slug":"clear-contrastive-learning-for-sentence","title":"CLEAR: Contrastive Learning for Sentence Representation","date":"2020-12-31","arxiv_id":"2012.15466","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/mixing-adam-and-sgd-a-combined-optimization","slug":"mixing-adam-and-sgd-a-combined-optimization","title":"Mixing ADAM and SGD: a Combined Optimization Method","date":"2020-11-16","arxiv_id":"2011.08042","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-statistical-framework-for-low-bitwidth","slug":"a-statistical-framework-for-low-bitwidth","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","date":"2020-10-27","arxiv_id":"2010.14298","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["cjf00000/StatQuant"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-statistical-framework-for-low-bitwidth#ran","syntology_url":"https://syntology.ai/paper/2010.14298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14298"}}}},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","slug":"squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["huggingface/transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/squeezebert-what-can-computer-vision-teach#ran","syntology_url":"https://syntology.ai/paper/2006.11316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11316"}}}},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":3,"official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"paper":"/paper/synthesizer-rethinking-self-attention-in","slug":"synthesizer-rethinking-self-attention-in","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","date":"2020-05-02","arxiv_id":"2005.00743","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/synthesizer-rethinking-self-attention-in#ran","syntology_url":"https://syntology.ai/paper/2005.00743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00743"}}}},{"paper":"/paper/learning-to-encode-position-for-transformer","slug":"learning-to-encode-position-for-transformer","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","date":"2020-03-13","arxiv_id":"2003.09229","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-to-encode-position-for-transformer#ran","syntology_url":"https://syntology.ai/paper/2003.09229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.09229"}}}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","rows_on_this_dataset":5,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":1,"samples_unverified":10,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}}}},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/q8bert-quantized-8bit-bert#ran","syntology_url":"https://syntology.ai/paper/1910.06188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06188"}}}},{"paper":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":27,"samples_ran":21,"samples_constructed":5,"samples_ran_checked":12,"samples_ran_instrument_failed":9,"samples_unverified":6,"pointer_only_for_licence":2,"official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilbert-a-distilled-version-of-bert#ran","syntology_url":"https://syntology.ai/paper/1910.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01108"}}}},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","rows_on_this_dataset":1,"code_links":48,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":126,"samples_ran":81,"samples_constructed":17,"samples_ran_checked":56,"samples_ran_instrument_failed":25,"samples_unverified":45,"pointer_only_for_licence":28,"official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/albert-a-lite-bert-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/1909.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11942"}}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190910351#ran","syntology_url":"https://syntology.ai/paper/1909.10351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10351"}}}},{"paper":"/paper/q-bert-hessian-based-ultra-low-precision","slug":"q-bert-hessian-based-ultra-low-precision","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","date":"2019-09-12","arxiv_id":"1909.05840","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","rows_on_this_dataset":2,"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":1,"official":{"repos":["PaddlePaddle/ERNIE"],"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/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}}}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":6,"official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}}}},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":15,"samples_constructed":2,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":9,"pointer_only_for_licence":4,"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}}}},{"paper":"/paper/ernie-enhanced-language-representation-with","slug":"ernie-enhanced-language-representation-with","title":"ERNIE: Enhanced Language Representation with Informative Entities","date":"2019-05-17","arxiv_id":"1905.07129","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["thunlp/ERNIE"],"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","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-enhanced-language-representation-with#ran","syntology_url":"https://syntology.ai/paper/1905.07129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07129"}}}},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["namisan/mt-dnn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-task-deep-neural-networks-for-natural#ran","syntology_url":"https://syntology.ai/paper/1901.11504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11504"}}}},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":659,"samples_ran":300,"samples_constructed":75,"samples_ran_checked":234,"samples_ran_instrument_failed":66,"samples_unverified":359,"pointer_only_for_licence":164,"official":{"repos":["google-research/bert"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/not-all-layers-are-equally-as-important-every","slug":"not-all-layers-are-equally-as-important-every","title":"Not all layers are equally as important: Every Layer Counts BERT","date":"2023-11-03","arxiv_id":"2311.02265","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/lm-cppf-paraphrasing-guided-data-augmentation","slug":"lm-cppf-paraphrasing-guided-data-augmentation","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","date":"2023-05-29","arxiv_id":"2305.18169","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/can-bert-eat-rucola-topological-data-analysis","slug":"can-bert-eat-rucola-topological-data-analysis","title":"Can BERT eat RuCoLA? Topological Data Analysis to Explain","date":"2023-04-04","arxiv_id":"2304.01680","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/texttt-tasksource-structured-dataset","slug":"texttt-tasksource-structured-dataset","title":"tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation","date":"2023-01-14","arxiv_id":"2301.05948","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["sileod/tasksource"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/texttt-tasksource-structured-dataset#ran","syntology_url":"https://syntology.ai/paper/2301.05948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.05948"}}}},{"paper":"/paper/rucola-russian-corpus-of-linguistic","slug":"rucola-russian-corpus-of-linguistic","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","date":"2022-10-23","arxiv_id":"2210.12814","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/llm-int8-8-bit-matrix-multiplication-for","slug":"llm-int8-8-bit-matrix-multiplication-for","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","date":"2022-08-15","arxiv_id":"2208.07339","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["timdettmers/bitsandbytes"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llm-int8-8-bit-matrix-multiplication-for#ran","syntology_url":"https://syntology.ai/paper/2208.07339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07339"}}}},{"paper":"/paper/acceptability-judgements-via-examining-the","slug":"acceptability-judgements-via-examining-the","title":"Acceptability Judgements via Examining the Topology of Attention Maps","date":"2022-05-19","arxiv_id":"2205.09630","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/data2vec-a-general-framework-for-self-1","slug":"data2vec-a-general-framework-for-self-1","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","date":"2022-02-07","arxiv_id":"2202.03555","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/data2vec-a-general-framework-for-self-1#ran","syntology_url":"https://syntology.ai/paper/2202.03555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03555"}}}},{"paper":"/paper/charformer-fast-character-transformers-via","slug":"charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","arxiv_id":"2106.12672","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/charformer-fast-character-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2106.12672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12672"}}}},{"paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","slug":"fnet-mixing-tokens-with-fourier-transforms","title":"FNet: Mixing Tokens with Fourier Transforms","date":"2021-05-09","arxiv_id":"2105.03824","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fnet-mixing-tokens-with-fourier-transforms#ran","syntology_url":"https://syntology.ai/paper/2105.03824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03824"}}}},{"paper":"/paper/entailment-as-few-shot-learner","slug":"entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","arxiv_id":"2104.14690","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/entailment-as-few-shot-learner#ran","syntology_url":"https://syntology.ai/paper/2104.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14690"}}}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/clear-contrastive-learning-for-sentence","slug":"clear-contrastive-learning-for-sentence","title":"CLEAR: Contrastive Learning for Sentence Representation","date":"2020-12-31","arxiv_id":"2012.15466","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/mixing-adam-and-sgd-a-combined-optimization","slug":"mixing-adam-and-sgd-a-combined-optimization","title":"Mixing ADAM and SGD: a Combined Optimization Method","date":"2020-11-16","arxiv_id":"2011.08042","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-statistical-framework-for-low-bitwidth","slug":"a-statistical-framework-for-low-bitwidth","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","date":"2020-10-27","arxiv_id":"2010.14298","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["cjf00000/StatQuant"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-statistical-framework-for-low-bitwidth#ran","syntology_url":"https://syntology.ai/paper/2010.14298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14298"}}}},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","slug":"squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["huggingface/transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/squeezebert-what-can-computer-vision-teach#ran","syntology_url":"https://syntology.ai/paper/2006.11316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11316"}}}},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":3,"official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"paper":"/paper/synthesizer-rethinking-self-attention-in","slug":"synthesizer-rethinking-self-attention-in","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","date":"2020-05-02","arxiv_id":"2005.00743","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/synthesizer-rethinking-self-attention-in#ran","syntology_url":"https://syntology.ai/paper/2005.00743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00743"}}}},{"paper":"/paper/learning-to-encode-position-for-transformer","slug":"learning-to-encode-position-for-transformer","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","date":"2020-03-13","arxiv_id":"2003.09229","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-to-encode-position-for-transformer#ran","syntology_url":"https://syntology.ai/paper/2003.09229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.09229"}}}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","rows_on_this_dataset":5,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":1,"samples_unverified":10,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}}}},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/q8bert-quantized-8bit-bert#ran","syntology_url":"https://syntology.ai/paper/1910.06188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06188"}}}},{"paper":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":27,"samples_ran":21,"samples_constructed":5,"samples_ran_checked":12,"samples_ran_instrument_failed":9,"samples_unverified":6,"pointer_only_for_licence":2,"official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilbert-a-distilled-version-of-bert#ran","syntology_url":"https://syntology.ai/paper/1910.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01108"}}}},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","rows_on_this_dataset":1,"code_links":48,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":126,"samples_ran":81,"samples_constructed":17,"samples_ran_checked":56,"samples_ran_instrument_failed":25,"samples_unverified":45,"pointer_only_for_licence":28,"official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/albert-a-lite-bert-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/1909.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11942"}}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190910351#ran","syntology_url":"https://syntology.ai/paper/1909.10351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10351"}}}},{"paper":"/paper/q-bert-hessian-based-ultra-low-precision","slug":"q-bert-hessian-based-ultra-low-precision","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","date":"2019-09-12","arxiv_id":"1909.05840","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","rows_on_this_dataset":2,"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":1,"official":{"repos":["PaddlePaddle/ERNIE"],"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/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}}}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":6,"official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}}}},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":15,"samples_constructed":2,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":9,"pointer_only_for_licence":4,"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}}}},{"paper":"/paper/ernie-enhanced-language-representation-with","slug":"ernie-enhanced-language-representation-with","title":"ERNIE: Enhanced Language Representation with Informative Entities","date":"2019-05-17","arxiv_id":"1905.07129","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["thunlp/ERNIE"],"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","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-enhanced-language-representation-with#ran","syntology_url":"https://syntology.ai/paper/1905.07129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07129"}}}},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["namisan/mt-dnn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-task-deep-neural-networks-for-natural#ran","syntology_url":"https://syntology.ai/paper/1901.11504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11504"}}}},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":659,"samples_ran":300,"samples_constructed":75,"samples_ran_checked":234,"samples_ran_instrument_failed":66,"samples_unverified":359,"pointer_only_for_licence":164,"official":{"repos":["google-research/bert"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}}}}],"papers_where_code_ran":22,"papers_where_code_ran_first_page":"/dataset/cola/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/cola/papers/ran/1","json":"/dataset/cola/papers/ran/1.json","rows":22}],"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":24,"samples_harvested":1032,"samples_ran":547,"samples_constructed":117,"samples_ran_checked":409,"samples_ran_instrument_failed":138,"samples_unverified":485,"pointer_only_for_licence":269,"papers_with_no_sample_that_ran":2,"papers_with_a_sample_that_ran":22,"papers_with_a_run_with_no_instrument_failure":19,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"7609ab3536324f1c78d738137e92202da787ae84c59f8ee855cdc81203df2f81","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}