{"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/winogrande-an-adversarial-winograd-schema","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","arxiv_id":"1907.10641","date":"2019-07-24","proceeding":null,"authors":["Keisuke Sakaguchi","Ronan Le Bras","Chandra Bhagavatula","Yejin Choi"],"abstract":"The Winograd Schema Challenge (WSC) (Levesque, Davis, and Morgenstern 2011), a benchmark for commonsense reasoning, is a set of 273 expert-crafted pronoun resolution problems originally designed to be unsolvable for statistical models that rely on selectional preferences or word associations. However, recent advances in neural language models have already reached around 90% accuracy on variants of WSC. This raises an important question whether these models have truly acquired robust commonsense capabilities or whether they rely on spurious biases in the datasets that lead to an overestimation of the true capabilities of machine commonsense. To investigate this question, we introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original WSC design, but adjusted to improve both the scale and the hardness of the dataset. The key steps of the dataset construction consist of (1) a carefully designed crowdsourcing procedure, followed by (2) systematic bias reduction using a novel AfLite algorithm that generalizes human-detectable word associations to machine-detectable embedding associations. The best state-of-the-art methods on WinoGrande achieve 59.4-79.1%, which are 15-35% below human performance of 94.0%, depending on the amount of the training data allowed. Furthermore, we establish new state-of-the-art results on five related benchmarks - WSC (90.1%), DPR (93.1%), COPA (90.6%), KnowRef (85.6%), and Winogender (97.1%). These results have dual implications: on one hand, they demonstrate the effectiveness of WinoGrande when used as a resource for transfer learning. On the other hand, they raise a concern that we are likely to be overestimating the true capabilities of machine commonsense across all these benchmarks. We emphasize the importance of algorithmic bias reduction in existing and future benchmarks to mitigate such overestimation.","url_abs":"https://arxiv.org/abs/1907.10641v2","url_pdf":"https://arxiv.org/pdf/1907.10641v2.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":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/crherlihy/clinical_nli_artifacts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/swarnahub/explanationhardness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/vered1986/self_talk","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/MindCode-4/code-13/tree/main/WinoGrande","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/MindSpore-scientific-2/code-3/tree/main/WinoGrande","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/MindSpore-scientific/code-14/tree/main/WinoGrande","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/MindSpore-scientific/code-5/tree/main/WinoGrande","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/mindspore-ai/contrib/tree/master/application/WinoGrande","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/3/WinoGrande","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"winogrande-an-adversarial-winograd-schema","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/WinoGrande","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"winogrande","task_name":"Winogrande"}],"methods":[],"datasets_introduced":[{"slug":"winogrande","name":"WinoGrande","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"RoBERTa-Winogrande 355M (fine-tuned)","rank_in_archive_order":18,"of":77,"metrics":{"Accuracy":"79.1"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"BERT-Winogrande 345M (fine-tuned)","rank_in_archive_order":45,"of":77,"metrics":{"Accuracy":"64.9"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"RoBERTa-DPR 355M (0-shot)","rank_in_archive_order":53,"of":77,"metrics":{"Accuracy":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"BERT-large 345M (0-shot)","rank_in_archive_order":71,"of":77,"metrics":{"Accuracy":"51.9"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"BERT-DPR 345M (0-shot)","rank_in_archive_order":75,"of":77,"metrics":{"Accuracy":"51"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"RoBERTa-large 355M (0-shot)","rank_in_archive_order":77,"of":77,"metrics":{"Accuracy":"50"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"RoBERTa-WinoGrande 355M","rank_in_archive_order":9,"of":82,"metrics":{"Accuracy":"90.1"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"RoBERTa-DPR 355M","rank_in_archive_order":19,"of":82,"metrics":{"Accuracy":"83.1"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"WKH","rank_in_archive_order":67,"of":82,"metrics":{"Accuracy":"57.1"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"KEE+NKAM on WinoGrande","rank_in_archive_order":75,"of":82,"metrics":{"Accuracy":"52.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"RoBERTa-Winogrande-ft 355M (fine-tuned)","rank_in_archive_order":17,"of":60,"metrics":{"Accuracy":"90.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"RoBERTa-ft 355M (fine-tuned)","rank_in_archive_order":24,"of":60,"metrics":{"Accuracy":"86.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"RoBERTa-Winogrande 355M (fine-tuned)","rank_in_archive_order":30,"of":60,"metrics":{"Accuracy":"84.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"Causal Strength w/multi-word predicates (presumably on WinoGrande?)","rank_in_archive_order":43,"of":60,"metrics":{"Accuracy":"76.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"Pointwise Mutual Information (on 10M stories)","rank_in_archive_order":53,"of":60,"metrics":{"Accuracy":"65.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1907.10641","atlas_url":"https://app.syntology.ai/?focus=1907.10641","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1907.10641"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1907.10641\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1907.10641"},"call":"get_concepts_for_paper(arxiv_id=\"1907.10641\")"}],"by_repo":[{"repo":"crherlihy/clinical_nli_artifacts","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"swarnahub/explanationhardness","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2211.07517"],"harvested_for_calls":[{"arxiv_id":"2211.07517","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.07517"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.07517\")"}]},{"repo":"vered1986/self_talk","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.05483"],"harvested_for_calls":[{"arxiv_id":"2004.05483","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.05483"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.05483\")"}]},{"repo":"MindCode-4/code-13","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2212.08663"],"harvested_for_calls":[{"arxiv_id":"2212.08663","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2212.08663"},"call":"get_harvested_code_for_paper(arxiv_id=\"2212.08663\")"}]},{"repo":"MindSpore-scientific-2/code-3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.03045"],"harvested_for_calls":[{"arxiv_id":"2305.03045","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.03045"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.03045\")"}]},{"repo":"MindSpore-scientific/code-14","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.01116"],"harvested_for_calls":[{"arxiv_id":"2306.01116","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.01116"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.01116\")"}]},{"repo":"MindSpore-scientific/code-5","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.06329"],"harvested_for_calls":[{"arxiv_id":"2305.06329","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.06329"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.06329\")"}]},{"repo":"mindspore-ai/contrib","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.12102"],"harvested_for_calls":[{"arxiv_id":"2305.12102","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.12102"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.12102\")"}]},{"repo":"pwc-1/Paper-9","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.13719"],"harvested_for_calls":[{"arxiv_id":"1909.13719","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.13719"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.13719\")"}]}],"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":"24784e3b8b480f1d6410732af1b3fd9b784ba89b28449d1727fe71ecc8f023a3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}