{"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/squad","name":"SQuAD","full_name":"Stanford Question Answering Dataset","description_markdown":"The **Stanford Question Answering Dataset** (**SQuAD**) is a collection of question-answer pairs derived from Wikipedia articles. In SQuAD, the correct answers of questions can be any sequence of tokens in the given text. Because the questions and answers are produced by humans through crowdsourcing, it is more diverse than some other question-answering datasets. SQuAD 1.1 contains 107,785 question-answer pairs on 536 articles. SQuAD2.0 (open-domain SQuAD, SQuAD-Open), the latest version, combines the 100,000 questions in SQuAD1.1 with over 50,000 un-answerable questions written adversarially by crowdworkers in forms that are similar to the answerable ones.\r\n\r\nSource: [Deep Learning Based Text Classification: A Comprehensive Review](https://arxiv.org/abs/2004.03705)\r\nImage Source: [https://rajpurkar.github.io/SQuAD-explorer/explore/v2.0/dev/Prime_number.html](https://rajpurkar.github.io/SQuAD-explorer/explore/v2.0/dev/Prime_number.html)","description_withheld":null,"homepage":"https://rajpurkar.github.io/SQuAD-explorer/","introduced_date":"2024-02-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/0-1-laws-for-pattern-occurrences-in","title":"0-1 laws for pattern occurrences in phylogenetic trees and networks","first_author":"François Bienvenu","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","datasets_with_task":"/datasets/task/open-domain-question-answering"},{"name":"Question Generation","url":"/task/question-generation","datasets_with_task":"/datasets/task/question-generation"},{"name":"Data-free Knowledge Distillation","url":"/task/data-free-knowledge-distillation","datasets_with_task":"/datasets/task/data-free-knowledge-distillation"},{"name":"text2text-generation","url":"/task/text2text-generation","datasets_with_task":"/datasets/task/text2text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["squad_bn","squad_adversarial","qg_squad","The Stanford Question Answering Dataset","squad_v2","SQuAD","SQuAD2.0 dev","SQuAD2.0","SQuAD1.1 dev","SQuAD1.1"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Kamitor/fwdhjlkfhqwiljfhqowiks","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/christti/squad-augmented-v2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/davidgturner/squad_adv","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cjaniake/squad_v2_pt","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/rajpurkar/squad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/rajpurkar/squad_v2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Z-Jafari/PersianQuAD","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Liu123456789/test","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Liu123456789/a","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/squad_v2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/squad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/qwant/squad_fr","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/tdklab/Hebrew_Squad_v1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/GEM/squad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/GEM/squad_v2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Sampson2022/demo","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Lexi/NQ_squad_format","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Lexi/spanextract","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lewtun/autoevaluate__squad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/PiC/phrase_retrieval","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/weijiang2009/AlgmonQuestioningAnsweringDataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Gholamreza/pquad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/abhijitt/sq_got","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Yulong-W/squadori","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Yulong-W/squadpara","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/badokorach/NewQA","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/TUKE-DeutscheTelekom/skquad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fedryanto/qas","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lhoestq/squad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MajdTannous/Dataset2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#squad2","frameworks":["pytorch"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#squad","frameworks":["pytorch"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/squad-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/squad","frameworks":["tf","jax"]},{"repo":"https://github.com/pytorch/text","url":"https://pytorch.org/text/stable/datasets.html#torchtext.datasets.SQuAD2","frameworks":["pytorch"]},{"repo":"https://github.com/pytorch/text","url":"https://pytorch.org/text/stable/datasets.html#torchtext.datasets.SQuAD1","frameworks":["pytorch"]},{"repo":"https://github.com/RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox/blob/main/docs/utilization/supported-datasets.md","frameworks":["pytorch"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/rc/dataset_readers/squad/","frameworks":["pytorch"]}],"num_papers_in_archive":151,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-squad20","task":"Question Answering","dataset_variant":"SQuAD2.0","rows":286,"metrics":["EM","F1"],"first_row_in_archive_order":{"model":"IE-Net (ensemble)","paper":null,"metrics":{"EM":"90.939","F1":"93.214"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset_variant":"SQuAD1.1","rows":213,"metrics":["EM","F1","Hardware Burden","Exact Match","Operations per network pass"],"first_row_in_archive_order":{"model":"{ANNA} (single model)","paper":null,"metrics":{"EM":"90.622","F1":"95.719"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset_variant":"SQuAD1.1 dev","rows":55,"metrics":["EM","F1"],"first_row_in_archive_order":{"model":"T5-11B","paper":"/paper/exploring-the-limits-of-transfer-learning","metrics":{"EM":"90.06","F1":"95.64"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5"},{"title":"google-research/text-to-text-transfer-transformer","url":"https://github.com/google-research/text-to-text-transfer-transformer"},{"title":"amazon-science/chronos-forecasting","url":"https://github.com/amazon-science/chronos-forecasting"},{"title":"google-research/t5x","url":"https://github.com/google-research/t5x"},{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"Ki6an/fastT5","url":"https://github.com/Ki6an/fastT5"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"facebookresearch/atlas","url":"https://github.com/facebookresearch/atlas"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"asahi417/lm-question-generation","url":"https://github.com/asahi417/lm-question-generation"},{"title":"abelriboulot/onnxt5","url":"https://github.com/abelriboulot/onnxt5"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"airc-keti/ke-t5","url":"https://github.com/airc-keti/ke-t5"},{"title":"yizhongw/tk-instruct","url":"https://github.com/yizhongw/tk-instruct"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"gulucaptain/dynamictrl","url":"https://github.com/gulucaptain/dynamictrl"},{"title":"google-research/t5x_retrieval","url":"https://github.com/google-research/t5x_retrieval"},{"title":"bigscience-workshop/architecture-objective","url":"https://github.com/bigscience-workshop/architecture-objective"},{"title":"dawn0815/UniSA","url":"https://github.com/dawn0815/UniSA"},{"title":"ibm/graph_ensemble_learning","url":"https://github.com/ibm/graph_ensemble_learning"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"safakkbilici/Academic-Paper-Title-Recommendation","url":"https://github.com/safakkbilici/Academic-Paper-Title-Recommendation"},{"title":"bayer-science-for-a-better-life/data2text-bioleaflets","url":"https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets"},{"title":"allenai/c4-documentation","url":"https://github.com/allenai/c4-documentation"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"lesterpjy/numeric-t5","url":"https://github.com/lesterpjy/numeric-t5"},{"title":"zhiqic/chartreader","url":"https://github.com/zhiqic/chartreader"},{"title":"LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer","url":"https://github.com/LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer"},{"title":"s-nlp/russe_detox_2022","url":"https://github.com/s-nlp/russe_detox_2022"},{"title":"skoltech-nlp/russe_detox_2022","url":"https://github.com/skoltech-nlp/russe_detox_2022"},{"title":"jongwooko/nash-pruning-official","url":"https://github.com/jongwooko/nash-pruning-official"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/t5"},{"title":"luomancs/retriever_reader_for_okvqa","url":"https://github.com/luomancs/retriever_reader_for_okvqa"},{"title":"qipengguo/p2_webnlg2020","url":"https://github.com/qipengguo/p2_webnlg2020"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Sharif-SLPL/t5-fa","url":"https://github.com/Sharif-SLPL/t5-fa"},{"title":"shivamraval98/multitask-t5_ae","url":"https://github.com/shivamraval98/multitask-t5_ae"},{"title":"junnyu/paddle_t5","url":"https://github.com/junnyu/paddle_t5"},{"title":"ChernovAndrey/chronos-forecasting-wasserstein","url":"https://github.com/ChernovAndrey/chronos-forecasting-wasserstein"},{"title":"cccntu/ft5-demo","url":"https://github.com/cccntu/ft5-demo"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/t5"},{"title":"cccntu/ft5-demo-space","url":"https://github.com/cccntu/ft5-demo-space"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"vgaraujov/seq2seq-spanish-plms","url":"https://github.com/vgaraujov/seq2seq-spanish-plms"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"thecodemasterk/Text-to-Text-transfer-transformers","url":"https://github.com/thecodemasterk/Text-to-Text-transfer-transformers"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5"},{"title":"KAGUYAHONGLAI/SRC","url":"https://github.com/KAGUYAHONGLAI/SRC"},{"title":"Nimesh-Patel/text-to-text-transfer-transformer","url":"https://github.com/Nimesh-Patel/text-to-text-transfer-transformer"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"itzprashu1/prashant","url":"https://github.com/itzprashu1/prashant"},{"title":"2023-MindSpore-1/ms-code-164","url":"https://github.com/2023-MindSpore-1/ms-code-164"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-squad20-dev","task":"Question Answering","dataset_variant":"SQuAD2.0 dev","rows":13,"metrics":["F1","EM"],"first_row_in_archive_order":{"model":"XLNet (single model)","paper":"/paper/xlnet-generalized-autoregressive-pretraining","metrics":{"EM":"87.9","F1":"90.6"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/xlnet"},{"title":"zihangdai/xlnet","url":"https://github.com/zihangdai/xlnet"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"graykode/xlnet-Pytorch","url":"https://github.com/graykode/xlnet-Pytorch"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms/blob/master/bert4ms/models/xlnet.py"},{"title":"huggingface/xlnet","url":"https://github.com/huggingface/xlnet"},{"title":"cuhksz-nlp/SAPar","url":"https://github.com/cuhksz-nlp/SAPar"},{"title":"joshuaWang-bit/Textclassification-pytorch","url":"https://github.com/joshuaWang-bit/Textclassification-pytorch"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"https-seyhan/BugAI","url":"https://github.com/https-seyhan/BugAI"},{"title":"NathanDuran/Sentence-Encoding-for-DA-Classification","url":"https://github.com/NathanDuran/Sentence-Encoding-for-DA-Classification"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"chesterdu/contrastive_summary","url":"https://github.com/chesterdu/contrastive_summary"},{"title":"pauldevos/python-notes","url":"https://github.com/pauldevos/python-notes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlnet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/xlnet"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlnet"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"SambhawDrag/XLNet.jl","url":"https://github.com/SambhawDrag/XLNet.jl"},{"title":"tomgoter/nlp_finalproject","url":"https://github.com/tomgoter/nlp_finalproject"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/xlnet"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"jonahwinninghoff/Text-Summarization","url":"https://github.com/jonahwinninghoff/Text-Summarization"},{"title":"listenviolet/XLNet","url":"https://github.com/listenviolet/XLNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-generation-on-squad11","task":"Question Generation","dataset_variant":"SQuAD1.1","rows":13,"metrics":["BLEU-4","METEOR","ROUGE-L"],"first_row_in_archive_order":{"model":"ERNIE-GENLARGE (beam size=5)","paper":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","metrics":{"BLEU-4":"25.41"},"code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/ernie_gen/modeling.py"},{"title":"Sharpiless/Versailles-text-generation-with-paddlepaddle","url":"https://github.com/Sharpiless/Versailles-text-generation-with-paddlepaddle"},{"title":"https-github-com-GiangHoang9912/ernie-gen","url":"https://github.com/https-github-com-GiangHoang9912/ernie-gen"},{"title":"MindSpore-scientific/code-12","url":"https://github.com/MindSpore-scientific/code-12/tree/main/FDDE/train-fine"},{"title":"MindCode-4/code-10","url":"https://github.com/MindCode-4/code-10/tree/main/FDDE/train-fine"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/data-free-knowledge-distillation-on-squad","task":"Data-free Knowledge Distillation","dataset_variant":"SQuAD","rows":4,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"GOLD (T5-base)","paper":"/paper/gold-generalized-knowledge-distillation-via","metrics":{"Exact Match":"75.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-domain-question-answering-on-squad1-1","task":"Open-Domain Question Answering","dataset_variant":"SQuAD1.1 dev","rows":4,"metrics":["EM"],"first_row_in_archive_order":{"model":"SPARTA","paper":"/paper/sparta-efficient-open-domain-question","metrics":{"EM":"59.3"},"code_links":[{"title":"soco-ai/SF-QA","url":"https://github.com/soco-ai/SF-QA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-domain-question-answering-on-squad11","task":"Open-Domain Question Answering","dataset_variant":"SQuAD1.1","rows":3,"metrics":["EM"],"first_row_in_archive_order":{"model":"DrQA","paper":"/paper/reading-wikipedia-to-answer-open-domain","metrics":{"EM":"70.0"},"code_links":[{"title":"facebookresearch/ParlAI","url":"https://github.com/facebookresearch/ParlAI"},{"title":"facebookresearch/DrQA","url":"https://github.com/facebookresearch/DrQA"},{"title":"hitvoice/DrQA","url":"https://github.com/hitvoice/DrQA"},{"title":"HKUST-KnowComp/MnemonicReader","url":"https://github.com/HKUST-KnowComp/MnemonicReader"},{"title":"xiangyue9607/CliniRC","url":"https://github.com/xiangyue9607/CliniRC"},{"title":"Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-","url":"https://github.com/Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-"},{"title":"iCompass-ai/TunBERT","url":"https://github.com/iCompass-ai/TunBERT"},{"title":"aaronbae/AnaQA","url":"https://github.com/aaronbae/AnaQA"},{"title":"BAJUKA/SQuAD-NLP","url":"https://github.com/BAJUKA/SQuAD-NLP"},{"title":"sachit-n/drqa_doc_reader","url":"https://github.com/sachit-n/drqa_doc_reader"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-squad-1","task":"Question Answering","dataset_variant":"SQuAD","rows":2,"metrics":["Exact Match","F1"],"first_row_in_archive_order":{"model":"Blended RAG","paper":"/paper/blended-rag-improving-rag-retriever-augmented","metrics":{"Exact Match":"57.63"},"code_links":[{"title":"ibm-ecosystem-engineering/blended-rag","url":"https://github.com/ibm-ecosystem-engineering/blended-rag"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-generation-on-squad","task":"Question Generation","dataset_variant":"SQuAD","rows":2,"metrics":["QAE","R-QAE"],"first_row_in_archive_order":{"model":"Info-HCVAE","paper":"/paper/generating-diverse-and-consistent-qa-pairs","metrics":{"QAE":"71.18","R-QAE":"38.8"},"code_links":[{"title":"seanie12/Info-HCVAE","url":"https://github.com/seanie12/Info-HCVAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-squad-adversarial","task":"Question Answering","dataset_variant":"squad_adversarial","rows":0,"metrics":["Exact Match","F1"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-squad-v2","task":"Question Answering","dataset_variant":"squad_v2","rows":0,"metrics":["Exact Match","f1","total"],"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":82,"of":82,"counts":{"papers_with_a_benchmark_row":82,"with_a_code_link":63,"where_syntology_ran_a_sample":32,"not_listed_spam_title":0,"listed":82,"listed_where_code_ran":32,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":29,"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/gold-generalized-knowledge-distillation-via","slug":"gold-generalized-knowledge-distillation-via","title":"GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation","date":"2024-03-28","arxiv_id":"2403.19754","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/blended-rag-improving-rag-retriever-augmented","slug":"blended-rag-improving-rag-retriever-augmented","title":"Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers","date":"2024-03-22","arxiv_id":"2404.07220","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["ibm-ecosystem-engineering/blended-rag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/blended-rag-improving-rag-retriever-augmented#ran","syntology_url":"https://syntology.ai/paper/2404.07220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07220"}}}},{"paper":"/paper/prompt2model-generating-deployable-models","slug":"prompt2model-generating-deployable-models","title":"Prompt2Model: Generating Deployable Models from Natural Language Instructions","date":"2023-08-23","arxiv_id":"2308.12261","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textbox-2-0-a-text-generation-library-with","slug":"textbox-2-0-a-text-generation-library-with","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","date":"2022-12-26","arxiv_id":"2212.13005","rows_on_this_dataset":2,"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":{"repos":["RUCAIBox/TextBox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/textbox-2-0-a-text-generation-library-with#ran","syntology_url":"https://syntology.ai/paper/2212.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13005"}}}},{"paper":"/paper/dyrex-dynamic-query-representation-for","slug":"dyrex-dynamic-query-representation-for","title":"DyREx: Dynamic Query Representation for Extractive Question Answering","date":"2022-10-26","arxiv_id":"2210.15048","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["urchade/dyrex"],"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":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dyrex-dynamic-query-representation-for#ran","syntology_url":"https://syntology.ai/paper/2210.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15048"}}}},{"paper":"/paper/progen-progressive-zero-shot-dataset","slug":"progen-progressive-zero-shot-dataset","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","date":"2022-10-22","arxiv_id":"2210.12329","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/enhancing-pre-trained-models-with-text","slug":"enhancing-pre-trained-models-with-text","title":"Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation","date":"2022-09-09","arxiv_id":"2209.04179","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"paper":"/paper/zerogen-efficient-zero-shot-learning-via","slug":"zerogen-efficient-zero-shot-learning-via","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","date":"2022-02-16","arxiv_id":"2202.07922","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":7,"official":{"repos":["HKUNLP/zerogen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zerogen-efficient-zero-shot-learning-via#ran","syntology_url":"https://syntology.ai/paper/2202.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.07922"}}}},{"paper":"/paper/information-theoretic-representation","slug":"information-theoretic-representation","title":"Information Theoretic Representation Distillation","date":"2021-12-01","arxiv_id":"2112.00459","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","rows_on_this_dataset":9,"code_links":2,"syntology":null},{"paper":"/paper/ensemble-albert-on-squad-2-0","slug":"ensemble-albert-on-squad-2-0","title":"Ensemble ALBERT on SQuAD 2.0","date":"2021-10-19","arxiv_id":"2110.09665","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fine-tune-the-entire-rag-architecture","slug":"fine-tune-the-entire-rag-architecture","title":"Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering","date":"2021-06-22","arxiv_id":"2106.11517","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pay-attention-to-mlps","slug":"pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","arxiv_id":"2105.08050","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":44,"samples_ran":34,"samples_constructed":15,"samples_ran_checked":31,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":11,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pay-attention-to-mlps#ran","syntology_url":"https://syntology.ai/paper/2105.08050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08050"}}}},{"paper":"/paper/a-large-batch-optimizer-reality-check","slug":"a-large-batch-optimizer-reality-check","title":"A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes","date":"2021-02-12","arxiv_id":"2102.06356","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficientqa-a-roberta-based-phrase-indexed","slug":"efficientqa-a-roberta-based-phrase-indexed","title":"EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System","date":"2021-01-06","arxiv_id":"2101.02157","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-to-generate-questions-by-recovering","slug":"learning-to-generate-questions-by-recovering","title":"Learning to Generate Questions by Recovering Answer-containing Sentences","date":"2021-01-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-dense-representations-of-phrases-at","slug":"learning-dense-representations-of-phrases-at","title":"Learning Dense Representations of Phrases at Scale","date":"2020-12-23","arxiv_id":"2012.12624","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/luke-deep-contextualized-entity","slug":"luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","rows_on_this_dataset":7,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["studio-ousia/luke"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/luke-deep-contextualized-entity#ran","syntology_url":"https://syntology.ai/paper/2010.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01057"}}}},{"paper":"/paper/sparta-efficient-open-domain-question","slug":"sparta-efficient-open-domain-question","title":"SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval","date":"2020-09-28","arxiv_id":"2009.13013","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/generating-diverse-and-consistent-qa-pairs","slug":"generating-diverse-and-consistent-qa-pairs","title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","date":"2020-05-28","arxiv_id":"2005.13837","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":3,"official":{"repos":["seanie12/Info-HCVAE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generating-diverse-and-consistent-qa-pairs#ran","syntology_url":"https://syntology.ai/paper/2005.13837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13837"}}}},{"paper":"/paper/harvesting-and-refining-question-answer-pairs","slug":"harvesting-and-refining-question-answer-pairs","title":"Harvesting and Refining Question-Answer Pairs for Unsupervised QA","date":"2020-05-06","arxiv_id":"2005.02925","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unilmv2-pseudo-masked-language-models-for","slug":"unilmv2-pseudo-masked-language-models-for","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","date":"2020-02-28","arxiv_id":"2002.12804","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unilmv2-pseudo-masked-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2002.12804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12804"}}}},{"paper":"/paper/retrospective-reader-for-machine-reading","slug":"retrospective-reader-for-machine-reading","title":"Retrospective Reader for Machine Reading Comprehension","date":"2020-01-27","arxiv_id":"2001.09694","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","slug":"ernie-gen-an-enhanced-multi-flow-pre-training","title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","date":"2020-01-26","arxiv_id":"2001.11314","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/prophetnet-predicting-future-n-gram-for","slug":"prophetnet-predicting-future-n-gram-for","title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","date":"2020-01-13","arxiv_id":"2001.04063","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","slug":"dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","arxiv_id":"1911.02855","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ShannonAI/dice_loss_for_NLP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dice-loss-for-data-imbalanced-nlp-tasks#ran","syntology_url":"https://syntology.ai/paper/1911.02855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02855"}}}},{"paper":"/paper/a-recurrent-bert-based-model-for-question","slug":"a-recurrent-bert-based-model-for-question","title":"A Recurrent BERT-based Model for Question Generation","date":"2019-11-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bart-denoising-sequence-to-sequence-pre","slug":"bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":53,"samples_ran":40,"samples_constructed":7,"samples_ran_checked":30,"samples_ran_instrument_failed":10,"samples_unverified":13,"pointer_only_for_licence":13,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bart-denoising-sequence-to-sequence-pre#ran","syntology_url":"https://syntology.ai/paper/1910.13461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13461"}}}},{"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/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":2,"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":6,"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/semantics-aware-bert-for-language","slug":"semantics-aware-bert-for-language","title":"Semantics-aware BERT for Language Understanding","date":"2019-09-05","arxiv_id":"1909.02209","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":3,"official":{"repos":["cooelf/SemBERT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/semantics-aware-bert-for-language#ran","syntology_url":"https://syntology.ai/paper/1909.02209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02209"}}}},{"paper":"/paper/mixture-content-selection-for-diverse","slug":"mixture-content-selection-for-diverse","title":"Mixture Content Selection for Diverse Sequence Generation","date":"2019-09-04","arxiv_id":"1909.01953","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sg-net-syntax-guided-machine-reading","slug":"sg-net-syntax-guided-machine-reading","title":"SG-Net: Syntax-Guided Machine Reading Comprehension","date":"2019-08-14","arxiv_id":"1908.05147","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"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":2,"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":3,"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":4,"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/adaptation-of-deep-bidirectional-multilingual","slug":"adaptation-of-deep-bidirectional-multilingual","title":"Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language","date":"2019-05-17","arxiv_id":"1905.07213","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unified-language-model-pre-training-for","slug":"unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","rows_on_this_dataset":1,"code_links":9,"syntology":null},{"paper":"/paper/data-augmentation-for-bert-fine-tuning-in","slug":"data-augmentation-for-bert-fine-tuning-in","title":"Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering","date":"2019-04-14","arxiv_id":"1904.06652","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reducing-bert-pre-training-time-from-3-days","slug":"reducing-bert-pre-training-time-from-3-days","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","date":"2019-04-01","arxiv_id":"1904.00962","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":9,"official":{"repos":["tensorflow/addons"],"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/reducing-bert-pre-training-time-from-3-days#ran","syntology_url":"https://syntology.ai/paper/1904.00962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00962"}}}},{"paper":"/paper/evaluating-rewards-for-question-generation","slug":"evaluating-rewards-for-question-generation","title":"Evaluating Rewards for Question Generation Models","date":"2019-02-28","arxiv_id":"1902.11049","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-open-domain-question-answering","slug":"end-to-end-open-domain-question-answering","title":"End-to-End Open-Domain Question Answering with BERTserini","date":"2019-02-05","arxiv_id":"1902.01718","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["rsvp-ai/bertserini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/1902.01718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01718"}}}},{"paper":"/paper/a-fully-attention-based-information-retriever","slug":"a-fully-attention-based-information-retriever","title":"A Fully Attention-Based Information Retriever","date":"2018-10-22","arxiv_id":"1810.09580","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/u-net-machine-reading-comprehension-with","slug":"u-net-machine-reading-comprehension-with","title":"U-Net: Machine Reading Comprehension with Unanswerable Questions","date":"2018-10-12","arxiv_id":"1810.06638","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":6,"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/exploring-machine-reading-comprehension-with","slug":"exploring-machine-reading-comprehension-with","title":"Explicit Utilization of General Knowledge in Machine Reading Comprehension","date":"2018-09-10","arxiv_id":"1809.03449","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/read-verify-machine-reading-comprehension","slug":"read-verify-machine-reading-comprehension","title":"Read + Verify: Machine Reading Comprehension with Unanswerable Questions","date":"2018-08-17","arxiv_id":"1808.05759","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-multi-stage-memory-augmented-neural-network","slug":"a-multi-stage-memory-augmented-neural-network","title":"A Multi-Stage Memory Augmented Neural Network for Machine Reading Comprehension","date":"2018-07-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/leveraging-context-information-for-natural","slug":"leveraging-context-information-for-natural","title":"Leveraging Context Information for Natural Question Generation","date":"2018-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/qanet-combining-local-convolution-with-global","slug":"qanet-combining-local-convolution-with-global","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","date":"2018-04-23","arxiv_id":"1804.09541","rows_on_this_dataset":4,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":4,"samples_unverified":5,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qanet-combining-local-convolution-with-global#ran","syntology_url":"https://syntology.ai/paper/1804.09541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09541"}}}},{"paper":"/paper/deep-contextualized-word-representations","slug":"deep-contextualized-word-representations","title":"Deep contextualized word representations","date":"2018-02-15","arxiv_id":"1802.05365","rows_on_this_dataset":4,"code_links":46,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":30,"samples_constructed":12,"samples_ran_checked":24,"samples_ran_instrument_failed":6,"samples_unverified":28,"pointer_only_for_licence":25,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-contextualized-word-representations#ran","syntology_url":"https://syntology.ai/paper/1802.05365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05365"}}}},{"paper":"/paper/contextualized-word-representations-for","slug":"contextualized-word-representations-for","title":"Contextualized Word Representations for Reading Comprehension","date":"2017-12-10","arxiv_id":"1712.03609","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/stochastic-answer-networks-for-machine","slug":"stochastic-answer-networks-for-machine","title":"Stochastic Answer Networks for Machine Reading Comprehension","date":"2017-12-10","arxiv_id":"1712.03556","rows_on_this_dataset":5,"code_links":6,"syntology":null},{"paper":"/paper/fusionnet-fusing-via-fully-aware-attention","slug":"fusionnet-fusing-via-fully-aware-attention","title":"FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension","date":"2017-11-16","arxiv_id":"1711.07341","rows_on_this_dataset":4,"code_links":3,"syntology":null},{"paper":"/paper/dcn-mixed-objective-and-deep-residual","slug":"dcn-mixed-objective-and-deep-residual","title":"DCN+: Mixed Objective and Deep Residual Coattention for Question Answering","date":"2017-10-31","arxiv_id":"1711.00106","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/simple-and-effective-multi-paragraph-reading","slug":"simple-and-effective-multi-paragraph-reading","title":"Simple and Effective Multi-Paragraph Reading Comprehension","date":"2017-10-29","arxiv_id":"1710.10723","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["allenai/document-qa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-effective-multi-paragraph-reading#ran","syntology_url":"https://syntology.ai/paper/1710.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10723"}}}},{"paper":"/paper/phase-conductor-on-multi-layered-attentions","slug":"phase-conductor-on-multi-layered-attentions","title":"Phase Conductor on Multi-layered Attentions for Machine Comprehension","date":"2017-10-28","arxiv_id":"1710.10504","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/smarnet-teaching-machines-to-read-and","slug":"smarnet-teaching-machines-to-read-and","title":"Smarnet: Teaching Machines to Read and Comprehend Like Human","date":"2017-10-08","arxiv_id":"1710.02772","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/simple-recurrent-units-for-highly","slug":"simple-recurrent-units-for-highly","title":"Simple Recurrent Units for Highly Parallelizable Recurrence","date":"2017-09-08","arxiv_id":"1709.02755","rows_on_this_dataset":2,"code_links":11,"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":["asappresearch/sru"],"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/simple-recurrent-units-for-highly#ran","syntology_url":"https://syntology.ai/paper/1709.02755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.02755"}}}},{"paper":"/paper/learned-in-translation-contextualized-word","slug":"learned-in-translation-contextualized-word","title":"Learned in Translation: Contextualized Word Vectors","date":"2017-08-01","arxiv_id":"1708.00107","rows_on_this_dataset":2,"code_links":5,"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":2,"official":{"repos":["salesforce/cove"],"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/learned-in-translation-contextualized-word#ran","syntology_url":"https://syntology.ai/paper/1708.00107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.00107"}}}},{"paper":"/paper/memen-multi-layer-embedding-with-memory","slug":"memen-multi-layer-embedding-with-memory","title":"MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension","date":"2017-07-28","arxiv_id":"1707.09098","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/gated-self-matching-networks-for-reading","slug":"gated-self-matching-networks-for-reading","title":"Gated Self-Matching Networks for Reading Comprehension and Question Answering","date":"2017-07-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-to-compute-word-embeddings-on-the","slug":"learning-to-compute-word-embeddings-on-the","title":"Learning to Compute Word Embeddings On the Fly","date":"2017-06-01","arxiv_id":"1706.00286","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/reinforced-mnemonic-reader-for-machine","slug":"reinforced-mnemonic-reader-for-machine","title":"Reinforced Mnemonic Reader for Machine Reading Comprehension","date":"2017-05-08","arxiv_id":"1705.02798","rows_on_this_dataset":5,"code_links":3,"syntology":null},{"paper":"/paper/ruminating-reader-reasoning-with-gated-multi","slug":"ruminating-reader-reasoning-with-gated-multi","title":"Ruminating Reader: Reasoning with Gated Multi-Hop Attention","date":"2017-04-24","arxiv_id":"1704.07415","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/neural-question-generation-from-text-a","slug":"neural-question-generation-from-text-a","title":"Neural Question Generation from Text: A Preliminary Study","date":"2017-04-06","arxiv_id":"1704.01792","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":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["magic282/NQG"],"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/neural-question-generation-from-text-a#ran","syntology_url":"https://syntology.ai/paper/1704.01792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.01792"}}}},{"paper":"/paper/reading-wikipedia-to-answer-open-domain","slug":"reading-wikipedia-to-answer-open-domain","title":"Reading Wikipedia to Answer Open-Domain Questions","date":"2017-03-31","arxiv_id":"1704.00051","rows_on_this_dataset":3,"code_links":10,"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":1,"official":{"repos":["facebookresearch/DrQA"],"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/reading-wikipedia-to-answer-open-domain#ran","syntology_url":"https://syntology.ai/paper/1704.00051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.00051"}}}},{"paper":"/paper/exploring-question-understanding-and","slug":"exploring-question-understanding-and","title":"Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering","date":"2017-03-14","arxiv_id":"1703.04617","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/making-neural-qa-as-simple-as-possible-but","slug":"making-neural-qa-as-simple-as-possible-but","title":"Making Neural QA as Simple as Possible but not Simpler","date":"2017-03-14","arxiv_id":"1703.04816","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/making-neural-qa-as-simple-as-possible-but#ran","syntology_url":"https://syntology.ai/paper/1703.04816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04816"}}}},{"paper":"/paper/structural-embedding-of-syntactic-trees-for","slug":"structural-embedding-of-syntactic-trees-for","title":"Structural Embedding of Syntactic Trees for Machine Comprehension","date":"2017-03-02","arxiv_id":"1703.00572","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/multi-perspective-context-matching-for","slug":"multi-perspective-context-matching-for","title":"Multi-Perspective Context Matching for Machine Comprehension","date":"2016-12-13","arxiv_id":"1612.04211","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/words-or-characters-fine-grained-gating-for","slug":"words-or-characters-fine-grained-gating-for","title":"Words or Characters? Fine-grained Gating for Reading Comprehension","date":"2016-11-06","arxiv_id":"1611.01724","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/bidirectional-attention-flow-for-machine","slug":"bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","arxiv_id":"1611.01603","rows_on_this_dataset":3,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["allenai/bi-att-flow"],"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/bidirectional-attention-flow-for-machine#ran","syntology_url":"https://syntology.ai/paper/1611.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01603"}}}},{"paper":"/paper/dynamic-coattention-networks-for-question","slug":"dynamic-coattention-networks-for-question","title":"Dynamic Coattention Networks For Question Answering","date":"2016-11-05","arxiv_id":"1611.01604","rows_on_this_dataset":4,"code_links":6,"syntology":null},{"paper":"/paper/learning-recurrent-span-representations-for","slug":"learning-recurrent-span-representations-for","title":"Learning Recurrent Span Representations for Extractive Question Answering","date":"2016-11-04","arxiv_id":"1611.01436","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/end-to-end-answer-chunk-extraction-and","slug":"end-to-end-answer-chunk-extraction-and","title":"End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension","date":"2016-10-31","arxiv_id":"1610.09996","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/reasonet-learning-to-stop-reading-in-machine","slug":"reasonet-learning-to-stop-reading-in-machine","title":"ReasoNet: Learning to Stop Reading in Machine Comprehension","date":"2016-09-17","arxiv_id":"1609.05284","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/machine-comprehension-using-match-lstm-and","slug":"machine-comprehension-using-match-lstm-and","title":"Machine Comprehension Using Match-LSTM and Answer Pointer","date":"2016-08-29","arxiv_id":"1608.07905","rows_on_this_dataset":5,"code_links":5,"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":3,"official":{"repos":["shuohangwang/SeqMatchSeq"],"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":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/machine-comprehension-using-match-lstm-and#ran","syntology_url":"https://syntology.ai/paper/1608.07905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.07905"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/gold-generalized-knowledge-distillation-via","slug":"gold-generalized-knowledge-distillation-via","title":"GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation","date":"2024-03-28","arxiv_id":"2403.19754","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/blended-rag-improving-rag-retriever-augmented","slug":"blended-rag-improving-rag-retriever-augmented","title":"Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers","date":"2024-03-22","arxiv_id":"2404.07220","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["ibm-ecosystem-engineering/blended-rag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/blended-rag-improving-rag-retriever-augmented#ran","syntology_url":"https://syntology.ai/paper/2404.07220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07220"}}}},{"paper":"/paper/prompt2model-generating-deployable-models","slug":"prompt2model-generating-deployable-models","title":"Prompt2Model: Generating Deployable Models from Natural Language Instructions","date":"2023-08-23","arxiv_id":"2308.12261","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textbox-2-0-a-text-generation-library-with","slug":"textbox-2-0-a-text-generation-library-with","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","date":"2022-12-26","arxiv_id":"2212.13005","rows_on_this_dataset":2,"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":{"repos":["RUCAIBox/TextBox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/textbox-2-0-a-text-generation-library-with#ran","syntology_url":"https://syntology.ai/paper/2212.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13005"}}}},{"paper":"/paper/dyrex-dynamic-query-representation-for","slug":"dyrex-dynamic-query-representation-for","title":"DyREx: Dynamic Query Representation for Extractive Question Answering","date":"2022-10-26","arxiv_id":"2210.15048","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["urchade/dyrex"],"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":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dyrex-dynamic-query-representation-for#ran","syntology_url":"https://syntology.ai/paper/2210.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15048"}}}},{"paper":"/paper/progen-progressive-zero-shot-dataset","slug":"progen-progressive-zero-shot-dataset","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","date":"2022-10-22","arxiv_id":"2210.12329","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/enhancing-pre-trained-models-with-text","slug":"enhancing-pre-trained-models-with-text","title":"Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation","date":"2022-09-09","arxiv_id":"2209.04179","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"paper":"/paper/zerogen-efficient-zero-shot-learning-via","slug":"zerogen-efficient-zero-shot-learning-via","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","date":"2022-02-16","arxiv_id":"2202.07922","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":7,"official":{"repos":["HKUNLP/zerogen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zerogen-efficient-zero-shot-learning-via#ran","syntology_url":"https://syntology.ai/paper/2202.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.07922"}}}},{"paper":"/paper/information-theoretic-representation","slug":"information-theoretic-representation","title":"Information Theoretic Representation Distillation","date":"2021-12-01","arxiv_id":"2112.00459","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","rows_on_this_dataset":9,"code_links":2,"syntology":null},{"paper":"/paper/ensemble-albert-on-squad-2-0","slug":"ensemble-albert-on-squad-2-0","title":"Ensemble ALBERT on SQuAD 2.0","date":"2021-10-19","arxiv_id":"2110.09665","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fine-tune-the-entire-rag-architecture","slug":"fine-tune-the-entire-rag-architecture","title":"Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering","date":"2021-06-22","arxiv_id":"2106.11517","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pay-attention-to-mlps","slug":"pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","arxiv_id":"2105.08050","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":44,"samples_ran":34,"samples_constructed":15,"samples_ran_checked":31,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":11,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pay-attention-to-mlps#ran","syntology_url":"https://syntology.ai/paper/2105.08050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08050"}}}},{"paper":"/paper/a-large-batch-optimizer-reality-check","slug":"a-large-batch-optimizer-reality-check","title":"A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes","date":"2021-02-12","arxiv_id":"2102.06356","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficientqa-a-roberta-based-phrase-indexed","slug":"efficientqa-a-roberta-based-phrase-indexed","title":"EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System","date":"2021-01-06","arxiv_id":"2101.02157","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-to-generate-questions-by-recovering","slug":"learning-to-generate-questions-by-recovering","title":"Learning to Generate Questions by Recovering Answer-containing Sentences","date":"2021-01-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-dense-representations-of-phrases-at","slug":"learning-dense-representations-of-phrases-at","title":"Learning Dense Representations of Phrases at Scale","date":"2020-12-23","arxiv_id":"2012.12624","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/luke-deep-contextualized-entity","slug":"luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","rows_on_this_dataset":7,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["studio-ousia/luke"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/luke-deep-contextualized-entity#ran","syntology_url":"https://syntology.ai/paper/2010.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01057"}}}},{"paper":"/paper/sparta-efficient-open-domain-question","slug":"sparta-efficient-open-domain-question","title":"SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval","date":"2020-09-28","arxiv_id":"2009.13013","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/generating-diverse-and-consistent-qa-pairs","slug":"generating-diverse-and-consistent-qa-pairs","title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","date":"2020-05-28","arxiv_id":"2005.13837","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":3,"official":{"repos":["seanie12/Info-HCVAE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generating-diverse-and-consistent-qa-pairs#ran","syntology_url":"https://syntology.ai/paper/2005.13837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13837"}}}},{"paper":"/paper/harvesting-and-refining-question-answer-pairs","slug":"harvesting-and-refining-question-answer-pairs","title":"Harvesting and Refining Question-Answer Pairs for Unsupervised QA","date":"2020-05-06","arxiv_id":"2005.02925","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unilmv2-pseudo-masked-language-models-for","slug":"unilmv2-pseudo-masked-language-models-for","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","date":"2020-02-28","arxiv_id":"2002.12804","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unilmv2-pseudo-masked-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2002.12804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12804"}}}},{"paper":"/paper/retrospective-reader-for-machine-reading","slug":"retrospective-reader-for-machine-reading","title":"Retrospective Reader for Machine Reading Comprehension","date":"2020-01-27","arxiv_id":"2001.09694","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","slug":"ernie-gen-an-enhanced-multi-flow-pre-training","title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","date":"2020-01-26","arxiv_id":"2001.11314","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/prophetnet-predicting-future-n-gram-for","slug":"prophetnet-predicting-future-n-gram-for","title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","date":"2020-01-13","arxiv_id":"2001.04063","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","slug":"dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","arxiv_id":"1911.02855","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ShannonAI/dice_loss_for_NLP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dice-loss-for-data-imbalanced-nlp-tasks#ran","syntology_url":"https://syntology.ai/paper/1911.02855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02855"}}}},{"paper":"/paper/a-recurrent-bert-based-model-for-question","slug":"a-recurrent-bert-based-model-for-question","title":"A Recurrent BERT-based Model for Question Generation","date":"2019-11-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bart-denoising-sequence-to-sequence-pre","slug":"bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":53,"samples_ran":40,"samples_constructed":7,"samples_ran_checked":30,"samples_ran_instrument_failed":10,"samples_unverified":13,"pointer_only_for_licence":13,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bart-denoising-sequence-to-sequence-pre#ran","syntology_url":"https://syntology.ai/paper/1910.13461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13461"}}}},{"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/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":2,"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":6,"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/semantics-aware-bert-for-language","slug":"semantics-aware-bert-for-language","title":"Semantics-aware BERT for Language Understanding","date":"2019-09-05","arxiv_id":"1909.02209","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":3,"official":{"repos":["cooelf/SemBERT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/semantics-aware-bert-for-language#ran","syntology_url":"https://syntology.ai/paper/1909.02209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02209"}}}},{"paper":"/paper/mixture-content-selection-for-diverse","slug":"mixture-content-selection-for-diverse","title":"Mixture Content Selection for Diverse Sequence Generation","date":"2019-09-04","arxiv_id":"1909.01953","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sg-net-syntax-guided-machine-reading","slug":"sg-net-syntax-guided-machine-reading","title":"SG-Net: Syntax-Guided Machine Reading Comprehension","date":"2019-08-14","arxiv_id":"1908.05147","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"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":2,"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":3,"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":4,"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/adaptation-of-deep-bidirectional-multilingual","slug":"adaptation-of-deep-bidirectional-multilingual","title":"Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language","date":"2019-05-17","arxiv_id":"1905.07213","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unified-language-model-pre-training-for","slug":"unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","rows_on_this_dataset":1,"code_links":9,"syntology":null},{"paper":"/paper/data-augmentation-for-bert-fine-tuning-in","slug":"data-augmentation-for-bert-fine-tuning-in","title":"Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering","date":"2019-04-14","arxiv_id":"1904.06652","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reducing-bert-pre-training-time-from-3-days","slug":"reducing-bert-pre-training-time-from-3-days","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","date":"2019-04-01","arxiv_id":"1904.00962","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":9,"official":{"repos":["tensorflow/addons"],"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/reducing-bert-pre-training-time-from-3-days#ran","syntology_url":"https://syntology.ai/paper/1904.00962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00962"}}}},{"paper":"/paper/evaluating-rewards-for-question-generation","slug":"evaluating-rewards-for-question-generation","title":"Evaluating Rewards for Question Generation Models","date":"2019-02-28","arxiv_id":"1902.11049","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-open-domain-question-answering","slug":"end-to-end-open-domain-question-answering","title":"End-to-End Open-Domain Question Answering with BERTserini","date":"2019-02-05","arxiv_id":"1902.01718","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["rsvp-ai/bertserini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/1902.01718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01718"}}}},{"paper":"/paper/a-fully-attention-based-information-retriever","slug":"a-fully-attention-based-information-retriever","title":"A Fully Attention-Based Information Retriever","date":"2018-10-22","arxiv_id":"1810.09580","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/u-net-machine-reading-comprehension-with","slug":"u-net-machine-reading-comprehension-with","title":"U-Net: Machine Reading Comprehension with Unanswerable Questions","date":"2018-10-12","arxiv_id":"1810.06638","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":6,"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/exploring-machine-reading-comprehension-with","slug":"exploring-machine-reading-comprehension-with","title":"Explicit Utilization of General Knowledge in Machine Reading Comprehension","date":"2018-09-10","arxiv_id":"1809.03449","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/read-verify-machine-reading-comprehension","slug":"read-verify-machine-reading-comprehension","title":"Read + Verify: Machine Reading Comprehension with Unanswerable Questions","date":"2018-08-17","arxiv_id":"1808.05759","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-multi-stage-memory-augmented-neural-network","slug":"a-multi-stage-memory-augmented-neural-network","title":"A Multi-Stage Memory Augmented Neural Network for Machine Reading Comprehension","date":"2018-07-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/leveraging-context-information-for-natural","slug":"leveraging-context-information-for-natural","title":"Leveraging Context Information for Natural Question Generation","date":"2018-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/qanet-combining-local-convolution-with-global","slug":"qanet-combining-local-convolution-with-global","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","date":"2018-04-23","arxiv_id":"1804.09541","rows_on_this_dataset":4,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":4,"samples_unverified":5,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qanet-combining-local-convolution-with-global#ran","syntology_url":"https://syntology.ai/paper/1804.09541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09541"}}}},{"paper":"/paper/deep-contextualized-word-representations","slug":"deep-contextualized-word-representations","title":"Deep contextualized word representations","date":"2018-02-15","arxiv_id":"1802.05365","rows_on_this_dataset":4,"code_links":46,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":30,"samples_constructed":12,"samples_ran_checked":24,"samples_ran_instrument_failed":6,"samples_unverified":28,"pointer_only_for_licence":25,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-contextualized-word-representations#ran","syntology_url":"https://syntology.ai/paper/1802.05365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05365"}}}},{"paper":"/paper/contextualized-word-representations-for","slug":"contextualized-word-representations-for","title":"Contextualized Word Representations for Reading Comprehension","date":"2017-12-10","arxiv_id":"1712.03609","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/stochastic-answer-networks-for-machine","slug":"stochastic-answer-networks-for-machine","title":"Stochastic Answer Networks for Machine Reading Comprehension","date":"2017-12-10","arxiv_id":"1712.03556","rows_on_this_dataset":5,"code_links":6,"syntology":null},{"paper":"/paper/fusionnet-fusing-via-fully-aware-attention","slug":"fusionnet-fusing-via-fully-aware-attention","title":"FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension","date":"2017-11-16","arxiv_id":"1711.07341","rows_on_this_dataset":4,"code_links":3,"syntology":null},{"paper":"/paper/dcn-mixed-objective-and-deep-residual","slug":"dcn-mixed-objective-and-deep-residual","title":"DCN+: Mixed Objective and Deep Residual Coattention for Question Answering","date":"2017-10-31","arxiv_id":"1711.00106","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/simple-and-effective-multi-paragraph-reading","slug":"simple-and-effective-multi-paragraph-reading","title":"Simple and Effective Multi-Paragraph Reading Comprehension","date":"2017-10-29","arxiv_id":"1710.10723","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["allenai/document-qa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-effective-multi-paragraph-reading#ran","syntology_url":"https://syntology.ai/paper/1710.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10723"}}}},{"paper":"/paper/phase-conductor-on-multi-layered-attentions","slug":"phase-conductor-on-multi-layered-attentions","title":"Phase Conductor on Multi-layered Attentions for Machine Comprehension","date":"2017-10-28","arxiv_id":"1710.10504","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/smarnet-teaching-machines-to-read-and","slug":"smarnet-teaching-machines-to-read-and","title":"Smarnet: Teaching Machines to Read and Comprehend Like Human","date":"2017-10-08","arxiv_id":"1710.02772","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/simple-recurrent-units-for-highly","slug":"simple-recurrent-units-for-highly","title":"Simple Recurrent Units for Highly Parallelizable Recurrence","date":"2017-09-08","arxiv_id":"1709.02755","rows_on_this_dataset":2,"code_links":11,"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":["asappresearch/sru"],"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/simple-recurrent-units-for-highly#ran","syntology_url":"https://syntology.ai/paper/1709.02755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.02755"}}}},{"paper":"/paper/learned-in-translation-contextualized-word","slug":"learned-in-translation-contextualized-word","title":"Learned in Translation: Contextualized Word Vectors","date":"2017-08-01","arxiv_id":"1708.00107","rows_on_this_dataset":2,"code_links":5,"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":2,"official":{"repos":["salesforce/cove"],"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/learned-in-translation-contextualized-word#ran","syntology_url":"https://syntology.ai/paper/1708.00107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.00107"}}}},{"paper":"/paper/memen-multi-layer-embedding-with-memory","slug":"memen-multi-layer-embedding-with-memory","title":"MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension","date":"2017-07-28","arxiv_id":"1707.09098","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/gated-self-matching-networks-for-reading","slug":"gated-self-matching-networks-for-reading","title":"Gated Self-Matching Networks for Reading Comprehension and Question Answering","date":"2017-07-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-to-compute-word-embeddings-on-the","slug":"learning-to-compute-word-embeddings-on-the","title":"Learning to Compute Word Embeddings On the Fly","date":"2017-06-01","arxiv_id":"1706.00286","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/reinforced-mnemonic-reader-for-machine","slug":"reinforced-mnemonic-reader-for-machine","title":"Reinforced Mnemonic Reader for Machine Reading Comprehension","date":"2017-05-08","arxiv_id":"1705.02798","rows_on_this_dataset":5,"code_links":3,"syntology":null},{"paper":"/paper/ruminating-reader-reasoning-with-gated-multi","slug":"ruminating-reader-reasoning-with-gated-multi","title":"Ruminating Reader: Reasoning with Gated Multi-Hop Attention","date":"2017-04-24","arxiv_id":"1704.07415","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/neural-question-generation-from-text-a","slug":"neural-question-generation-from-text-a","title":"Neural Question Generation from Text: A Preliminary Study","date":"2017-04-06","arxiv_id":"1704.01792","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":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["magic282/NQG"],"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/neural-question-generation-from-text-a#ran","syntology_url":"https://syntology.ai/paper/1704.01792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.01792"}}}},{"paper":"/paper/reading-wikipedia-to-answer-open-domain","slug":"reading-wikipedia-to-answer-open-domain","title":"Reading Wikipedia to Answer Open-Domain Questions","date":"2017-03-31","arxiv_id":"1704.00051","rows_on_this_dataset":3,"code_links":10,"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":1,"official":{"repos":["facebookresearch/DrQA"],"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/reading-wikipedia-to-answer-open-domain#ran","syntology_url":"https://syntology.ai/paper/1704.00051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.00051"}}}},{"paper":"/paper/exploring-question-understanding-and","slug":"exploring-question-understanding-and","title":"Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering","date":"2017-03-14","arxiv_id":"1703.04617","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/making-neural-qa-as-simple-as-possible-but","slug":"making-neural-qa-as-simple-as-possible-but","title":"Making Neural QA as Simple as Possible but not Simpler","date":"2017-03-14","arxiv_id":"1703.04816","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/making-neural-qa-as-simple-as-possible-but#ran","syntology_url":"https://syntology.ai/paper/1703.04816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04816"}}}},{"paper":"/paper/structural-embedding-of-syntactic-trees-for","slug":"structural-embedding-of-syntactic-trees-for","title":"Structural Embedding of Syntactic Trees for Machine Comprehension","date":"2017-03-02","arxiv_id":"1703.00572","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/multi-perspective-context-matching-for","slug":"multi-perspective-context-matching-for","title":"Multi-Perspective Context Matching for Machine Comprehension","date":"2016-12-13","arxiv_id":"1612.04211","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/words-or-characters-fine-grained-gating-for","slug":"words-or-characters-fine-grained-gating-for","title":"Words or Characters? Fine-grained Gating for Reading Comprehension","date":"2016-11-06","arxiv_id":"1611.01724","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/bidirectional-attention-flow-for-machine","slug":"bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","arxiv_id":"1611.01603","rows_on_this_dataset":3,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["allenai/bi-att-flow"],"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/bidirectional-attention-flow-for-machine#ran","syntology_url":"https://syntology.ai/paper/1611.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01603"}}}},{"paper":"/paper/dynamic-coattention-networks-for-question","slug":"dynamic-coattention-networks-for-question","title":"Dynamic Coattention Networks For Question Answering","date":"2016-11-05","arxiv_id":"1611.01604","rows_on_this_dataset":4,"code_links":6,"syntology":null},{"paper":"/paper/learning-recurrent-span-representations-for","slug":"learning-recurrent-span-representations-for","title":"Learning Recurrent Span Representations for Extractive Question Answering","date":"2016-11-04","arxiv_id":"1611.01436","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/end-to-end-answer-chunk-extraction-and","slug":"end-to-end-answer-chunk-extraction-and","title":"End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension","date":"2016-10-31","arxiv_id":"1610.09996","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/reasonet-learning-to-stop-reading-in-machine","slug":"reasonet-learning-to-stop-reading-in-machine","title":"ReasoNet: Learning to Stop Reading in Machine Comprehension","date":"2016-09-17","arxiv_id":"1609.05284","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/machine-comprehension-using-match-lstm-and","slug":"machine-comprehension-using-match-lstm-and","title":"Machine Comprehension Using Match-LSTM and Answer Pointer","date":"2016-08-29","arxiv_id":"1608.07905","rows_on_this_dataset":5,"code_links":5,"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":3,"official":{"repos":["shuohangwang/SeqMatchSeq"],"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":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/machine-comprehension-using-match-lstm-and#ran","syntology_url":"https://syntology.ai/paper/1608.07905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.07905"}}}}],"papers_where_code_ran":32,"papers_where_code_ran_first_page":"/dataset/squad/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/squad/papers/ran/1","json":"/dataset/squad/papers/ran/1.json","rows":32}],"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":33,"samples_harvested":1235,"samples_ran":677,"samples_constructed":147,"samples_ran_checked":523,"samples_ran_instrument_failed":154,"samples_unverified":558,"pointer_only_for_licence":331,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":32,"papers_with_a_run_with_no_instrument_failure":29,"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":3,"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/question-answering-on-squad11","since_archive":"/sota/question-answering-on-squad11#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/question-answering-on-squad11-dev","since_archive":"/sota/question-answering-on-squad11-dev#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/open-domain-question-answering-on-squad1-1","since_archive":"/sota/open-domain-question-answering-on-squad1-1#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/open-domain-question-answering-on-squad11","since_archive":"/sota/open-domain-question-answering-on-squad11#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"3f3712ea8fcf3ca76f26bc9063f0c31e6e4211e4b98f35efee41a6ba9dd88baf","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}