{"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/wsc","name":"WSC","full_name":"Winograd Schema Challenge","description_markdown":"The **Winograd Schema Challenge** was introduced both as an alternative to the Turing Test and as a test of a system’s ability to do commonsense reasoning. A Winograd schema is a pair of sentences differing in one or two words with a highly ambiguous pronoun, resolved differently in the two sentences, that appears to require commonsense knowledge to be resolved correctly. The examples were designed to be easily solvable by humans but difficult for machines, in principle requiring a deep understanding of the content of the text and the situation it describes.\r\n\r\nThe original Winograd Schema Challenge dataset consisted of 100 Winograd schemas constructed manually by AI experts. As of 2020 there are 285 examples available; however, the last 12 examples were only added recently. To ensure consistency with earlier models, several authors often prefer to report the performance on the first 273 examples only. These datasets are usually referred to as **WSC**285 and WSC273, respectively.\r\n\r\nSource: [https://arxiv.org/pdf/2004.13831.pdf](https://arxiv.org/pdf/2004.13831.pdf)\r\nImage Source: [https://arxiv.org/pdf/1907.11983.pdf](https://arxiv.org/pdf/1907.11983.pdf)","description_withheld":null,"homepage":"https://cs.nyu.edu/faculty/davise/papers/WinogradSchemas/WS.html","introduced_date":"2012-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"The Winograd Schema Challenge","first_author":null,"url":"http://www.aaai.org/ocs/index.php/KR/KR12/paper/view/4492"},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Winograd Schema Challenge","WSC","winograd_wsc"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/winograd_wsc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/coref-data/winograd_wsc_raw","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/coref-data/winograd_wsc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/coref-data/davis_wsc_raw","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ErnestSDavis/winograd_wsc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/wsc273","frameworks":["tf","jax"]}],"num_papers_in_archive":361,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset_variant":"Winograd Schema Challenge","rows":82,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM 540B (fine-tuned)","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","metrics":{"Accuracy":"100"},"code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/classification-on-wsc","task":"Classification","dataset_variant":"WSC","rows":2,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"OPT-1.3B","paper":"/paper/achieving-dimension-free-communication-in","metrics":{"Test Accuracy":"64.16%"},"code_links":[{"title":"ZidongLiu/DeComFL","url":"https://github.com/ZidongLiu/DeComFL"}]},"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":38,"of":38,"counts":{"papers_with_a_benchmark_row":38,"with_a_code_link":31,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":38,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":14,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":14,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/achieving-dimension-free-communication-in","slug":"achieving-dimension-free-communication-in","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","date":"2024-05-24","arxiv_id":"2405.15861","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":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ZidongLiu/DeComFL"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/achieving-dimension-free-communication-in#ran","syntology_url":"https://syntology.ai/paper/2405.15861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15861"}}}},{"paper":"/paper/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/pythia-a-suite-for-analyzing-large-language","slug":"pythia-a-suite-for-analyzing-large-language","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","date":"2023-04-03","arxiv_id":"2304.01373","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/paper/exploring-the-benefits-of-training-expert","slug":"exploring-the-benefits-of-training-expert","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","date":"2023-02-07","arxiv_id":"2302.03202","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["joeljang/elm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}}}},{"paper":"/paper/hungry-hungry-hippos-towards-language","slug":"hungry-hungry-hippos-towards-language","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","date":"2022-12-28","arxiv_id":"2212.14052","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["hazyresearch/h3"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"paper":"/paper/toward-efficient-language-model-pretraining","slug":"toward-efficient-language-model-pretraining","title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","date":"2022-12-04","arxiv_id":"2212.01853","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/knowledge-in-context-towards-knowledgeable","slug":"knowledge-in-context-towards-knowledgeable","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","date":"2022-10-28","arxiv_id":"2210.16433","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/scaling-instruction-finetuned-language-models","slug":"scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":8,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":7,"samples_unverified":9,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-instruction-finetuned-language-models#ran","syntology_url":"https://syntology.ai/paper/2210.11416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11416"}}}},{"paper":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ask-me-anything-a-simple-strategy-for","slug":"ask-me-anything-a-simple-strategy-for","title":"Ask Me Anything: A simple strategy for prompting language models","date":"2022-10-05","arxiv_id":"2210.02441","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["hazyresearch/ama_prompting"],"state":"official (archive's flag): 2 ran","n_ran":2,"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/ask-me-anything-a-simple-strategy-for#ran","syntology_url":"https://syntology.ai/paper/2210.02441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02441"}}}},{"paper":"/paper/alexatm-20b-few-shot-learning-using-a-large","slug":"alexatm-20b-few-shot-learning-using-a-large","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","date":"2022-08-02","arxiv_id":"2208.01448","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/alexatm-20b-few-shot-learning-using-a-large#ran","syntology_url":"https://syntology.ai/paper/2208.01448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01448"}}}},{"paper":"/paper/n-grammer-augmenting-transformers-with-latent-1","slug":"n-grammer-augmenting-transformers-with-latent-1","title":"N-Grammer: Augmenting Transformers with latent n-grams","date":"2022-07-13","arxiv_id":"2207.06366","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["tensorflow/lingvo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/n-grammer-augmenting-transformers-with-latent-1#ran","syntology_url":"https://syntology.ai/paper/2207.06366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06366"}}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}}}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","rows_on_this_dataset":4,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":32,"samples_constructed":16,"samples_ran_checked":24,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"paper":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["tensorflow/mesh"],"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/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}}}},{"paper":"/paper/on-generalization-in-coreference-resolution","slug":"on-generalization-in-coreference-resolution","title":"On Generalization in Coreference Resolution","date":"2021-09-20","arxiv_id":"2109.09667","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/back-to-square-one-bias-detection-training","slug":"back-to-square-one-bias-detection-training","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","date":"2021-04-16","arxiv_id":"2104.08161","rows_on_this_dataset":7,"code_links":0,"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/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"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/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/g-daug-generative-data-augmentation-for","slug":"g-daug-generative-data-augmentation-for","title":"Generative Data Augmentation for Commonsense Reasoning","date":"2020-04-24","arxiv_id":"2004.11546","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":0,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/g-daug-generative-data-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/2004.11546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11546"}}}},{"paper":"/paper/tttttackling-winogrande-schemas","slug":"tttttackling-winogrande-schemas","title":"TTTTTackling WinoGrande Schemas","date":"2020-03-18","arxiv_id":"2003.08380","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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":1,"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/a-hybrid-neural-network-model-for-commonsense","slug":"a-hybrid-neural-network-model-for-commonsense","title":"A Hybrid Neural Network Model for Commonsense Reasoning","date":"2019-07-27","arxiv_id":"1907.11983","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["namisan/mt-dnn"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-hybrid-neural-network-model-for-commonsense#ran","syntology_url":"https://syntology.ai/paper/1907.11983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11983"}}}},{"paper":"/paper/winogrande-an-adversarial-winograd-schema","slug":"winogrande-an-adversarial-winograd-schema","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","date":"2019-07-24","arxiv_id":"1907.10641","rows_on_this_dataset":4,"code_links":10,"syntology":null},{"paper":"/paper/attention-is-not-all-you-need-for-commonsense","slug":"attention-is-not-all-you-need-for-commonsense","title":"Attention Is (not) All You Need for Commonsense Reasoning","date":"2019-05-31","arxiv_id":"1905.13497","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/a-surprisingly-robust-trick-for-winograd","slug":"a-surprisingly-robust-trick-for-winograd","title":"A Surprisingly Robust Trick for Winograd Schema Challenge","date":"2019-05-15","arxiv_id":"1905.06290","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/socialiqa-commonsense-reasoning-about-social","slug":"socialiqa-commonsense-reasoning-about-social","title":"SocialIQA: Commonsense Reasoning about Social Interactions","date":"2019-04-22","arxiv_id":"1904.09728","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/socialiqa-commonsense-reasoning-about-social#ran","syntology_url":"https://syntology.ai/paper/1904.09728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09728"}}}},{"paper":"/paper/unsupervised-deep-structured-semantic-models","slug":"unsupervised-deep-structured-semantic-models","title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","date":"2019-04-03","arxiv_id":"1904.01938","rows_on_this_dataset":5,"code_links":0,"syntology":null},{"paper":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"rows_on_this_dataset":1,"code_links":21,"syntology":null},{"paper":"/paper/on-the-evaluation-of-common-sense-reasoning","slug":"on-the-evaluation-of-common-sense-reasoning","title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","date":"2018-11-05","arxiv_id":"1811.01778","rows_on_this_dataset":4,"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":1,"code_links":534,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":659,"samples_ran":300,"samples_constructed":75,"samples_ran_checked":234,"samples_ran_instrument_failed":66,"samples_unverified":359,"pointer_only_for_licence":164,"official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}}}},{"paper":"/paper/a-knowledge-hunting-framework-for-common","slug":"a-knowledge-hunting-framework-for-common","title":"A Knowledge Hunting Framework for Common Sense Reasoning","date":"2018-10-02","arxiv_id":"1810.01375","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-simple-method-for-commonsense-reasoning","slug":"a-simple-method-for-commonsense-reasoning","title":"A Simple Method for Commonsense Reasoning","date":"2018-06-07","arxiv_id":"1806.02847","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-simple-method-for-commonsense-reasoning#ran","syntology_url":"https://syntology.ai/paper/1806.02847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02847"}}}},{"paper":"/paper/attention-is-all-you-need","slug":"attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","arxiv_id":"1706.03762","rows_on_this_dataset":1,"code_links":595,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":946,"samples_ran":610,"samples_constructed":293,"samples_ran_checked":529,"samples_ran_instrument_failed":81,"samples_unverified":336,"pointer_only_for_licence":451,"official":{"repos":["tensorflow/tensor2tensor"],"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/attention-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/1706.03762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03762"}}}},{"paper":"/paper/commonsense-knowledge-enhanced-embeddings-for","slug":"commonsense-knowledge-enhanced-embeddings-for","title":"Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge","date":"2016-11-13","arxiv_id":"1611.04146","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/achieving-dimension-free-communication-in","slug":"achieving-dimension-free-communication-in","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","date":"2024-05-24","arxiv_id":"2405.15861","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":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ZidongLiu/DeComFL"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/achieving-dimension-free-communication-in#ran","syntology_url":"https://syntology.ai/paper/2405.15861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15861"}}}},{"paper":"/paper/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/pythia-a-suite-for-analyzing-large-language","slug":"pythia-a-suite-for-analyzing-large-language","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","date":"2023-04-03","arxiv_id":"2304.01373","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/paper/exploring-the-benefits-of-training-expert","slug":"exploring-the-benefits-of-training-expert","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","date":"2023-02-07","arxiv_id":"2302.03202","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["joeljang/elm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}}}},{"paper":"/paper/hungry-hungry-hippos-towards-language","slug":"hungry-hungry-hippos-towards-language","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","date":"2022-12-28","arxiv_id":"2212.14052","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["hazyresearch/h3"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"paper":"/paper/toward-efficient-language-model-pretraining","slug":"toward-efficient-language-model-pretraining","title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","date":"2022-12-04","arxiv_id":"2212.01853","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/knowledge-in-context-towards-knowledgeable","slug":"knowledge-in-context-towards-knowledgeable","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","date":"2022-10-28","arxiv_id":"2210.16433","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/scaling-instruction-finetuned-language-models","slug":"scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":8,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":7,"samples_unverified":9,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-instruction-finetuned-language-models#ran","syntology_url":"https://syntology.ai/paper/2210.11416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11416"}}}},{"paper":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ask-me-anything-a-simple-strategy-for","slug":"ask-me-anything-a-simple-strategy-for","title":"Ask Me Anything: A simple strategy for prompting language models","date":"2022-10-05","arxiv_id":"2210.02441","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["hazyresearch/ama_prompting"],"state":"official (archive's flag): 2 ran","n_ran":2,"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/ask-me-anything-a-simple-strategy-for#ran","syntology_url":"https://syntology.ai/paper/2210.02441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02441"}}}},{"paper":"/paper/alexatm-20b-few-shot-learning-using-a-large","slug":"alexatm-20b-few-shot-learning-using-a-large","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","date":"2022-08-02","arxiv_id":"2208.01448","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/alexatm-20b-few-shot-learning-using-a-large#ran","syntology_url":"https://syntology.ai/paper/2208.01448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01448"}}}},{"paper":"/paper/n-grammer-augmenting-transformers-with-latent-1","slug":"n-grammer-augmenting-transformers-with-latent-1","title":"N-Grammer: Augmenting Transformers with latent n-grams","date":"2022-07-13","arxiv_id":"2207.06366","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["tensorflow/lingvo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/n-grammer-augmenting-transformers-with-latent-1#ran","syntology_url":"https://syntology.ai/paper/2207.06366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06366"}}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}}}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","rows_on_this_dataset":4,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":32,"samples_constructed":16,"samples_ran_checked":24,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"paper":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["tensorflow/mesh"],"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/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}}}},{"paper":"/paper/on-generalization-in-coreference-resolution","slug":"on-generalization-in-coreference-resolution","title":"On Generalization in Coreference Resolution","date":"2021-09-20","arxiv_id":"2109.09667","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/back-to-square-one-bias-detection-training","slug":"back-to-square-one-bias-detection-training","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","date":"2021-04-16","arxiv_id":"2104.08161","rows_on_this_dataset":7,"code_links":0,"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/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"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/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/g-daug-generative-data-augmentation-for","slug":"g-daug-generative-data-augmentation-for","title":"Generative Data Augmentation for Commonsense Reasoning","date":"2020-04-24","arxiv_id":"2004.11546","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":0,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/g-daug-generative-data-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/2004.11546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11546"}}}},{"paper":"/paper/tttttackling-winogrande-schemas","slug":"tttttackling-winogrande-schemas","title":"TTTTTackling WinoGrande Schemas","date":"2020-03-18","arxiv_id":"2003.08380","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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":1,"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/a-hybrid-neural-network-model-for-commonsense","slug":"a-hybrid-neural-network-model-for-commonsense","title":"A Hybrid Neural Network Model for Commonsense Reasoning","date":"2019-07-27","arxiv_id":"1907.11983","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["namisan/mt-dnn"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-hybrid-neural-network-model-for-commonsense#ran","syntology_url":"https://syntology.ai/paper/1907.11983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11983"}}}},{"paper":"/paper/winogrande-an-adversarial-winograd-schema","slug":"winogrande-an-adversarial-winograd-schema","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","date":"2019-07-24","arxiv_id":"1907.10641","rows_on_this_dataset":4,"code_links":10,"syntology":null},{"paper":"/paper/attention-is-not-all-you-need-for-commonsense","slug":"attention-is-not-all-you-need-for-commonsense","title":"Attention Is (not) All You Need for Commonsense Reasoning","date":"2019-05-31","arxiv_id":"1905.13497","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/a-surprisingly-robust-trick-for-winograd","slug":"a-surprisingly-robust-trick-for-winograd","title":"A Surprisingly Robust Trick for Winograd Schema Challenge","date":"2019-05-15","arxiv_id":"1905.06290","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/socialiqa-commonsense-reasoning-about-social","slug":"socialiqa-commonsense-reasoning-about-social","title":"SocialIQA: Commonsense Reasoning about Social Interactions","date":"2019-04-22","arxiv_id":"1904.09728","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/socialiqa-commonsense-reasoning-about-social#ran","syntology_url":"https://syntology.ai/paper/1904.09728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09728"}}}},{"paper":"/paper/unsupervised-deep-structured-semantic-models","slug":"unsupervised-deep-structured-semantic-models","title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","date":"2019-04-03","arxiv_id":"1904.01938","rows_on_this_dataset":5,"code_links":0,"syntology":null},{"paper":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"rows_on_this_dataset":1,"code_links":21,"syntology":null},{"paper":"/paper/on-the-evaluation-of-common-sense-reasoning","slug":"on-the-evaluation-of-common-sense-reasoning","title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","date":"2018-11-05","arxiv_id":"1811.01778","rows_on_this_dataset":4,"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":1,"code_links":534,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":659,"samples_ran":300,"samples_constructed":75,"samples_ran_checked":234,"samples_ran_instrument_failed":66,"samples_unverified":359,"pointer_only_for_licence":164,"official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}}}},{"paper":"/paper/a-knowledge-hunting-framework-for-common","slug":"a-knowledge-hunting-framework-for-common","title":"A Knowledge Hunting Framework for Common Sense Reasoning","date":"2018-10-02","arxiv_id":"1810.01375","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-simple-method-for-commonsense-reasoning","slug":"a-simple-method-for-commonsense-reasoning","title":"A Simple Method for Commonsense Reasoning","date":"2018-06-07","arxiv_id":"1806.02847","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-simple-method-for-commonsense-reasoning#ran","syntology_url":"https://syntology.ai/paper/1806.02847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02847"}}}},{"paper":"/paper/attention-is-all-you-need","slug":"attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","arxiv_id":"1706.03762","rows_on_this_dataset":1,"code_links":595,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":946,"samples_ran":610,"samples_constructed":293,"samples_ran_checked":529,"samples_ran_instrument_failed":81,"samples_unverified":336,"pointer_only_for_licence":451,"official":{"repos":["tensorflow/tensor2tensor"],"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/attention-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/1706.03762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03762"}}}},{"paper":"/paper/commonsense-knowledge-enhanced-embeddings-for","slug":"commonsense-knowledge-enhanced-embeddings-for","title":"Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge","date":"2016-11-13","arxiv_id":"1611.04146","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":18,"papers_where_code_ran_first_page":"/dataset/wsc/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/wsc/papers/ran/1","json":"/dataset/wsc/papers/ran/1.json","rows":18}],"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":20,"samples_harvested":1840,"samples_ran":1071,"samples_constructed":385,"samples_ran_checked":885,"samples_ran_instrument_failed":186,"samples_unverified":769,"pointer_only_for_licence":639,"papers_with_no_sample_that_ran":2,"papers_with_a_sample_that_ran":18,"papers_with_a_run_with_no_instrument_failure":14,"papers_where_every_run_was_an_instrument_failure":4,"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":1,"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/classification-on-wsc","since_archive":"/sota/classification-on-wsc#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":"ff93e8b3b9da5dab1f1be2b5f183c4f59bba694db9d6c4bee3cd1aa68025f8a8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}