{"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":"/paper/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","arxiv_id":null,"date":"2019-02-14","proceeding":"Preprint 2019 2","authors":["Alec Radford","Jeffrey Wu","Rewon Child","David Luan","Dario Amodei","Ilya Sutskever"],"abstract":"Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically\r\napproached with supervised learning on taskspecific datasets. We demonstrate that language\r\nmodels begin to learn these tasks without any explicit supervision when trained on a new dataset\r\nof millions of webpages called WebText. When\r\nconditioned on a document plus questions, the answers generated by the language model reach 55\r\nF1 on the CoQA dataset - matching or exceeding\r\nthe performance of 3 out of 4 baseline systems\r\nwithout using the 127,000+ training examples.\r\nThe capacity of the language model is essential\r\nto the success of zero-shot task transfer and increasing it improves performance in a log-linear\r\nfashion across tasks. Our largest model, GPT-2,\r\nis a 1.5B parameter Transformer that achieves\r\nstate of the art results on 7 out of 8 tested language modeling datasets in a zero-shot setting\r\nbut still underfits WebText. Samples from the\r\nmodel reflect these improvements and contain coherent paragraphs of text. These findings suggest\r\na promising path towards building language processing systems which learn to perform tasks from\r\ntheir naturally occurring demonstrations.","url_abs":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","url_pdf":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/openai/gpt-2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/2023-MindSpore-1/ms-code-154","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/MS-P3/code5/tree/main/gpt2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/VachanVY/gpt.jax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/aananda-giri/gpt2-nepali","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/abhaskumarsinha/Corpus2GPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/abhaskumarsinha/MinimalGPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/affjljoo3581/GPT2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/akanyaani/gpt-2-tensorflow2.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/akanyaani/minGPTF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/huggingface/swift-coreml-transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/imcaspar/gpt2-ml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/jankrepl/mildlyoverfitted","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/lvyufeng/bert4ms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/milmor/GPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/mindspore-ai/models/blob/master/research/nlp/gpt2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/minimaxir/gpt-2-simple","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/ramanakshay/nanogpt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-models-are-unsupervised-multitask","repo_url":"https://github.com/varun-suresh/experiments-with-gpt2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[{"slug":"webtext","name":"WebText","full_name":""}],"methods_introduced":[{"slug":"gpt-2","name":"GPT-2","full_name":"GPT-2"}],"results":[{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"GPT-2-XL 1.5B","rank_in_archive_order":33,"of":82,"metrics":{"Accuracy":"70.7"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-state-tracking-on-simmc2-0","task":"Dialogue State Tracking","dataset":"SIMMC2.0","model":"GPT-2","rank_in_archive_order":4,"of":5,"metrics":{"Act F1":"94.5","Slot F1":"81.7"},"uses_additional_data":false},{"leaderboard":"/sota/document-summarization-on-cnn-daily-mail","task":"Document Summarization","dataset":"CNN / Daily Mail","model":"GPT-2","rank_in_archive_order":26,"of":26,"metrics":{"ROUGE-1":"29.34","ROUGE-2":"8.27","ROUGE-L":"26.58"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"GPT-2 1.5B (Zero Shot)","rank_in_archive_order":29,"of":37,"metrics":{"Accuracy":"63.24","Perplexity":"8.63"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"GPT-2","rank_in_archive_order":23,"of":27,"metrics":{"Number of params":"1.54B","PPL":"42.16"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-penn-treebank-word","task":"Language Modelling","dataset":"Penn Treebank (Word Level)","model":"GPT-2","rank_in_archive_order":3,"of":43,"metrics":{"Params":"1542M","Test perplexity":"35.76"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-text8","task":"Language Modelling","dataset":"Text8","model":"GPT-2","rank_in_archive_order":1,"of":24,"metrics":{"Bit per Character (BPC)":"0.98","Number of params":"1542M"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"GPT-2 Full","rank_in_archive_order":25,"of":89,"metrics":{"Number of params":"1542M","Test perplexity":"17.48"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"GPT-2 Large","rank_in_archive_order":46,"of":89,"metrics":{"Number of params":"774M","Test perplexity":"22.05"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"GPT-2 Medium","rank_in_archive_order":63,"of":89,"metrics":{"Number of params":"355M","Test perplexity":"26.37"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"GPT-2 Small","rank_in_archive_order":79,"of":89,"metrics":{"Number of params":"124M","Test perplexity":"37.50"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"GPT-2","rank_in_archive_order":6,"of":38,"metrics":{"Number of params":"1542M","Test perplexity":"18.34"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"GPT-2 (large)","rank_in_archive_order":7,"of":38,"metrics":{"Number of params":"762M","Test perplexity":"19.93"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"GPT-2 (medium)","rank_in_archive_order":8,"of":38,"metrics":{"Number of params":"345M","Test perplexity":"22.76"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"GPT-2 (small)","rank_in_archive_order":9,"of":38,"metrics":{"Number of params":"117M","Test perplexity":"29.41"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-enwiki8","task":"Language Modelling","dataset":"enwik8","model":"GPT-2 (48 layers, h=1600)","rank_in_archive_order":1,"of":42,"metrics":{"Bit per Character (BPC)":"0.93","Number of params":"1542M"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-fever","task":"Question Answering","dataset":"FEVER","model":"Zero-shot","rank_in_archive_order":7,"of":8,"metrics":{"EM":"50"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-webquestions","task":"Question Answering","dataset":"WebQuestions","model":"Zero-shot","rank_in_archive_order":12,"of":37,"metrics":{"EM":"43"},"uses_additional_data":false},{"leaderboard":"/sota/response-generation-on-simmc2-0","task":"Response Generation","dataset":"SIMMC2.0","model":"GPT-2","rank_in_archive_order":5,"of":5,"metrics":{"BLEU":"19.2"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"GPT-2 Finetuned","rank_in_archive_order":31,"of":49,"metrics":{"Accuracy":"92.36"},"uses_additional_data":false},{"leaderboard":"/sota/text-generation-on-openwebtext","task":"Text Generation","dataset":"OpenWebText","model":"GPT2-124M","rank_in_archive_order":3,"of":3,"metrics":{"eval_loss":"3.12"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"openai/gpt-2","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2601.10926"],"harvested_for_calls":[{"arxiv_id":"2601.10926","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2601.10926"},"call":"get_harvested_code_for_paper(arxiv_id=\"2601.10926\")"}]},{"repo":"2023-MindSpore-1/ms-code-154","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MS-P3/code5","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.18386"],"harvested_for_calls":[{"arxiv_id":"2405.18386","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.18386"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.18386\")"}]},{"repo":"PaddlePaddle/PaddleNLP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.03416"],"harvested_for_calls":[{"arxiv_id":"2301.03416","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.03416"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.03416\")"}]},{"repo":"VachanVY/gpt.jax","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2005.14165"],"harvested_for_calls":[{"arxiv_id":"2005.14165","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2005.14165"},"call":"get_harvested_code_for_paper(arxiv_id=\"2005.14165\")"}]},{"repo":"aananda-giri/gpt2-nepali","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"abhaskumarsinha/Corpus2GPT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2005.14165","2302.13971"],"harvested_for_calls":[{"arxiv_id":"2005.14165","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2005.14165"},"call":"get_harvested_code_for_paper(arxiv_id=\"2005.14165\")"},{"arxiv_id":"2302.13971","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2302.13971"},"call":"get_harvested_code_for_paper(arxiv_id=\"2302.13971\")"}]},{"repo":"abhaskumarsinha/MinimalGPT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1706.03762","2005.14165"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"},{"arxiv_id":"2005.14165","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2005.14165"},"call":"get_harvested_code_for_paper(arxiv_id=\"2005.14165\")"}]},{"repo":"affjljoo3581/GPT2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"akanyaani/gpt-2-tensorflow2.0","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"akanyaani/minGPTF","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1706.03762"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"}]},{"repo":"huggingface/swift-coreml-transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1910.01108"],"harvested_for_calls":[{"arxiv_id":"1910.01108","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.01108"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.01108\")"}]},{"repo":"huggingface/transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1706.03762","1910.03771","2006.03654","2010.01057"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"},{"arxiv_id":"1910.03771","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.03771"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.03771\")"},{"arxiv_id":"2006.03654","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.03654"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.03654\")"},{"arxiv_id":"2010.01057","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.01057"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.01057\")"}]},{"repo":"imcaspar/gpt2-ml","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jankrepl/mildlyoverfitted","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":9,"harvested_for":["1703.01365","1710.09412","1803.03635","2006.09661","2010.11929","2104.14294","2105.01601","2107.05407","2109.02869"],"harvested_for_calls":[{"arxiv_id":"1703.01365","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1703.01365"},"call":"get_harvested_code_for_paper(arxiv_id=\"1703.01365\")"},{"arxiv_id":"1710.09412","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.09412"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.09412\")"},{"arxiv_id":"1803.03635","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.03635"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.03635\")"},{"arxiv_id":"2006.09661","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.09661"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.09661\")"},{"arxiv_id":"2010.11929","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.11929"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.11929\")"},{"arxiv_id":"2104.14294","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.14294"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.14294\")"},{"arxiv_id":"2105.01601","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.01601"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.01601\")"},{"arxiv_id":"2107.05407","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2107.05407"},"call":"get_harvested_code_for_paper(arxiv_id=\"2107.05407\")"},{"arxiv_id":"2109.02869","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2109.02869"},"call":"get_harvested_code_for_paper(arxiv_id=\"2109.02869\")"}]},{"repo":"lvyufeng/bert4ms","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1907.11692"],"harvested_for_calls":[{"arxiv_id":"1907.11692","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1907.11692"},"call":"get_harvested_code_for_paper(arxiv_id=\"1907.11692\")"}]},{"repo":"milmor/GPT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mindspore-ai/models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2208.08084"],"harvested_for_calls":[{"arxiv_id":"2208.08084","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.08084"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.08084\")"}]},{"repo":"minimaxir/gpt-2-simple","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ramanakshay/nanogpt","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2005.14165"],"harvested_for_calls":[{"arxiv_id":"2005.14165","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2005.14165"},"call":"get_harvested_code_for_paper(arxiv_id=\"2005.14165\")"}]},{"repo":"varun-suresh/experiments-with-gpt2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"be99f718517869bfa7af17af0d1b7ff9f49036a7b63acd3b8aa069b3cb433065","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}