{"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/xnli","name":"XNLI","full_name":"Cross-lingual Natural Language Inference","description_markdown":"The **Cross-lingual Natural Language Inference** (**XNLI**) corpus is the extension of the Multi-Genre NLI (MultiNLI) corpus to 15 languages. The dataset was created by manually translating the validation and test sets of MultiNLI into each of those 15 languages. The English training set was machine translated for all languages. The dataset is composed of 122k train, 2490 validation and 5010 test examples.\r\n\r\nSource: [CamemBERT: a Tasty French Language Model](https://arxiv.org/abs/1911.03894)\r\nImage Source: [https://github.com/facebookresearch/XNLI](https://github.com/facebookresearch/XNLI)","description_withheld":null,"homepage":"https://github.com/facebookresearch/XNLI","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/xnli-evaluating-cross-lingual-sentence","title":"XNLI: Evaluating Cross-lingual Sentence Representations","first_author":"Alexis Conneau","url":null},"license":{"name":"Attribution-NonCommercial 4.0 International","url":"https://github.com/facebookresearch/XNLI/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Chinese Sentence Pair Classification","url":"/task/chinese-sentence-pair-classification","datasets_with_task":"/datasets/task/chinese-sentence-pair-classification"},{"name":"FLUE","url":"/task/flue","datasets_with_task":"/datasets/task/flue"},{"name":"Cross-Lingual Natural Language Inference","url":"/task/cross-lingual-natural-language-inference","datasets_with_task":"/datasets/task/cross-lingual-natural-language-inference"}],"languages":[{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Multilingual","url":"/datasets/language/multilingual"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Bulgarian","url":"/datasets/language/bulgarian"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Urdu","url":"/datasets/language/urdu"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"},{"name":"Greek","url":"/datasets/language/greek"},{"name":"Swahili","url":"/datasets/language/swahili"}],"variants":["XNLI Zero-Shot English-to-French","XNLI French","XNLI Dev","XNLI Chinese","XNLI Chinese Dev","XNLI Zero-Shot English-to-German","XNLI Zero-Shot English-to-Spanish","XNLI"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/juletxara/xnli_mt","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/xnli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mteb/xnli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/facebook/xnli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Mathoctopus/msvamp","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/xnli","frameworks":["tf","jax"]},{"repo":"https://github.com/facebookresearch/XNLI","url":"https://github.com/facebookresearch/XNLI","frameworks":[]}],"num_papers_in_archive":349,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/natural-language-inference-on-xnli-french","task":"Natural Language Inference","dataset_variant":"XNLI French","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CamemBERT (large)","paper":"/paper/camembert-a-tasty-french-language-model","metrics":{"Accuracy":"85.7"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"anaishoareau/french_preprocessing","url":"https://github.com/anaishoareau/french_preprocessing"},{"title":"bourrel/French-News-Clustering","url":"https://github.com/bourrel/French-News-Clustering"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/camembert"},{"title":"hbaflast/bert-sentiment-analysis-pytorch","url":"https://github.com/hbaflast/bert-sentiment-analysis-pytorch"},{"title":"hbaflast/bert-sentiment-analysis-tensorflow","url":"https://github.com/hbaflast/bert-sentiment-analysis-tensorflow"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/camembert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-4","task":"Cross-Lingual Natural Language Inference","dataset_variant":"XNLI","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ByT5 XXL","paper":"/paper/byt5-towards-a-token-free-future-with-pre","metrics":{"Accuracy":"83.7"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers/tree/master/src/transformers/models/byt5"},{"title":"google-research/byt5","url":"https://github.com/google-research/byt5"},{"title":"ufal/multilexnorm2021","url":"https://github.com/ufal/multilexnorm2021"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/byt5"},{"title":"yoreG123/Paddle-ByT5","url":"https://github.com/yoreG123/Paddle-ByT5"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-1","task":"Cross-Lingual Natural Language Inference","dataset_variant":"XNLI Zero-Shot English-to-Spanish","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"XLM-R R4F","paper":"/paper/better-fine-tuning-by-reducing","metrics":{"Accuracy":"85.2%"},"code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/rxf"},{"title":"cosmoquester/2021-dialogue-summary-competition","url":"https://github.com/cosmoquester/2021-dialogue-summary-competition"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-3","task":"Cross-Lingual Natural Language Inference","dataset_variant":"XNLI Zero-Shot English-to-German","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"XLM-R R4F","paper":"/paper/better-fine-tuning-by-reducing","metrics":{"Accuracy":"84.2%"},"code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/rxf"},{"title":"cosmoquester/2021-dialogue-summary-competition","url":"https://github.com/cosmoquester/2021-dialogue-summary-competition"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on","task":"Cross-Lingual Natural Language Inference","dataset_variant":"XNLI Zero-Shot English-to-French","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"XLM-R R4F","paper":"/paper/better-fine-tuning-by-reducing","metrics":{"Accuracy":"84.7%"},"code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/rxf"},{"title":"cosmoquester/2021-dialogue-summary-competition","url":"https://github.com/cosmoquester/2021-dialogue-summary-competition"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-inference-on-xnli-chinese","task":"Natural Language Inference","dataset_variant":"XNLI Chinese Dev","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ERNIE 2.0 Large","paper":"/paper/ernie-20-a-continual-pre-training-framework","metrics":{"Accuracy":"82.6"},"code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0"},{"title":"PaddlePaddle/ERNIE","url":"https://github.com/PaddlePaddle/ERNIE"},{"title":"DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc.","url":"https://github.com/DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc."}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-inference-on-xnli-chinese-1","task":"Natural Language Inference","dataset_variant":"XNLI Chinese","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ERNIE 2.0 Large","paper":"/paper/ernie-20-a-continual-pre-training-framework","metrics":{"Accuracy":"81"},"code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0"},{"title":"PaddlePaddle/ERNIE","url":"https://github.com/PaddlePaddle/ERNIE"},{"title":"DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc.","url":"https://github.com/DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc."}]},"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":12,"of":12,"counts":{"papers_with_a_benchmark_row":12,"with_a_code_link":12,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/mgpt-few-shot-learners-go-multilingual","slug":"mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/byt5"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/byt5-towards-a-token-free-future-with-pre#ran","syntology_url":"https://syntology.ai/paper/2105.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13626"}}}},{"paper":"/paper/rethinking-embedding-coupling-in-pre-trained-1","slug":"rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","arxiv_id":"2010.12821","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/better-fine-tuning-by-reducing","slug":"better-fine-tuning-by-reducing","title":"Better Fine-Tuning by Reducing Representational Collapse","date":"2020-08-06","arxiv_id":"2008.03156","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/flaubert-unsupervised-language-model-pre","slug":"flaubert-unsupervised-language-model-pre","title":"FlauBERT: Unsupervised Language Model Pre-training for French","date":"2019-12-11","arxiv_id":"1912.05372","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["getalp/Flaubert"],"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/flaubert-unsupervised-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/1912.05372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05372"}}}},{"paper":"/paper/camembert-a-tasty-french-language-model","slug":"camembert-a-tasty-french-language-model","title":"CamemBERT: a Tasty French Language Model","date":"2019-11-10","arxiv_id":"1911.03894","rows_on_this_dataset":2,"code_links":8,"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":4,"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/ernie-enhanced-representation-through","slug":"ernie-enhanced-representation-through","title":"ERNIE: Enhanced Representation through Knowledge Integration","date":"2019-04-19","arxiv_id":"1904.09223","rows_on_this_dataset":2,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["PaddlePaddle/PaddleNLP"],"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/ernie-enhanced-representation-through#ran","syntology_url":"https://syntology.ai/paper/1904.09223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09223"}}}},{"paper":"/paper/cross-lingual-language-model-pretraining","slug":"cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","arxiv_id":"1901.07291","rows_on_this_dataset":1,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-lingual-language-model-pretraining#ran","syntology_url":"https://syntology.ai/paper/1901.07291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07291"}}}},{"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":2,"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"}}}},{"paper":"/paper/xnli-evaluating-cross-lingual-sentence","slug":"xnli-evaluating-cross-lingual-sentence","title":"XNLI: Evaluating Cross-lingual Sentence Representations","date":"2018-09-13","arxiv_id":"1809.05053","rows_on_this_dataset":1,"code_links":9,"syntology":null},{"paper":"/paper/supervised-learning-of-universal-sentence","slug":"supervised-learning-of-universal-sentence","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","date":"2017-05-05","arxiv_id":"1705.02364","rows_on_this_dataset":6,"code_links":23,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["facebookresearch/InferSent","facebookresearch/SentEval"],"state":"official (archive's flag): 3 ran","n_ran":3,"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/supervised-learning-of-universal-sentence#ran","syntology_url":"https://syntology.ai/paper/1705.02364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.02364"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/mgpt-few-shot-learners-go-multilingual","slug":"mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/byt5"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/byt5-towards-a-token-free-future-with-pre#ran","syntology_url":"https://syntology.ai/paper/2105.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13626"}}}},{"paper":"/paper/rethinking-embedding-coupling-in-pre-trained-1","slug":"rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","arxiv_id":"2010.12821","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/better-fine-tuning-by-reducing","slug":"better-fine-tuning-by-reducing","title":"Better Fine-Tuning by Reducing Representational Collapse","date":"2020-08-06","arxiv_id":"2008.03156","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/flaubert-unsupervised-language-model-pre","slug":"flaubert-unsupervised-language-model-pre","title":"FlauBERT: Unsupervised Language Model Pre-training for French","date":"2019-12-11","arxiv_id":"1912.05372","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["getalp/Flaubert"],"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/flaubert-unsupervised-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/1912.05372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05372"}}}},{"paper":"/paper/camembert-a-tasty-french-language-model","slug":"camembert-a-tasty-french-language-model","title":"CamemBERT: a Tasty French Language Model","date":"2019-11-10","arxiv_id":"1911.03894","rows_on_this_dataset":2,"code_links":8,"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":4,"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/ernie-enhanced-representation-through","slug":"ernie-enhanced-representation-through","title":"ERNIE: Enhanced Representation through Knowledge Integration","date":"2019-04-19","arxiv_id":"1904.09223","rows_on_this_dataset":2,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["PaddlePaddle/PaddleNLP"],"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/ernie-enhanced-representation-through#ran","syntology_url":"https://syntology.ai/paper/1904.09223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09223"}}}},{"paper":"/paper/cross-lingual-language-model-pretraining","slug":"cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","arxiv_id":"1901.07291","rows_on_this_dataset":1,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-lingual-language-model-pretraining#ran","syntology_url":"https://syntology.ai/paper/1901.07291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07291"}}}},{"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":2,"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"}}}},{"paper":"/paper/xnli-evaluating-cross-lingual-sentence","slug":"xnli-evaluating-cross-lingual-sentence","title":"XNLI: Evaluating Cross-lingual Sentence Representations","date":"2018-09-13","arxiv_id":"1809.05053","rows_on_this_dataset":1,"code_links":9,"syntology":null},{"paper":"/paper/supervised-learning-of-universal-sentence","slug":"supervised-learning-of-universal-sentence","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","date":"2017-05-05","arxiv_id":"1705.02364","rows_on_this_dataset":6,"code_links":23,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["facebookresearch/InferSent","facebookresearch/SentEval"],"state":"official (archive's flag): 3 ran","n_ran":3,"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/supervised-learning-of-universal-sentence#ran","syntology_url":"https://syntology.ai/paper/1705.02364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.02364"}}}}],"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/dataset/xnli/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/xnli/papers/ran/1","json":"/dataset/xnli/papers/ran/1.json","rows":6}],"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":7,"samples_harvested":696,"samples_ran":329,"samples_constructed":75,"samples_ran_checked":259,"samples_ran_instrument_failed":70,"samples_unverified":367,"pointer_only_for_licence":174,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":6,"papers_with_a_run_with_no_instrument_failure":6,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-4","since_archive":"/sota/cross-lingual-natural-language-inference-on-4#since-judged","papers_judged":2,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"41bf221bdf4a4a3b78ee0f5c6a522bc2017db7d14d0547e2bce142e9e27fc3e1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}