{"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":"/sota/coreference-resolution-on-winograd-schema","task":{"name":"Coreference Resolution","url":"/task/coreference-resolution","note":null},"dataset":{"name":"Winograd Schema Challenge","url":"/dataset/wsc"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Coreference resolution is the task of clustering mentions in text that refer to the same underlying real world entities.\n\nExample:\n\n```\n               +-----------+\n               |           |\nI voted for Obama because he was most aligned with my values\", she said.\n |                                                 |            |\n +-------------------------------------------------+------------+\n```\n\n\"I\", \"my\", and \"she\" belong to the same cluster and \"Obama\" and \"he\" belong to the same cluster.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":82,"rows_with_code":64,"rows_with_paper_page":82,"rows_dated":82,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PaLM 540B (fine-tuned)","metrics":{"Accuracy":"100"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"official":null,"syntology":{"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":2,"model":"Vega v2 6B (KD-based prompt transfer)","metrics":{"Accuracy":"98.6"},"uses_additional_data":false,"paper_date":"2022-12-04","paper":"/paper/toward-efficient-language-model-pretraining","paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"UL2 20B (fine-tuned)","metrics":{"Accuracy":"98.1"},"uses_additional_data":false,"paper_date":"2022-05-10","paper":"/paper/unifying-language-learning-paradigms","paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","code":"https://github.com/google-research/google-research","n_code_links":2,"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"]},"syntology":{"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":1,"n_samples":16,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":4,"model":"Turing NLR v5 XXL 5.4B (fine-tuned)","metrics":{"Accuracy":"97.3"},"uses_additional_data":false,"paper_date":"2022-12-04","paper":"/paper/toward-efficient-language-model-pretraining","paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":5,"model":"ST-MoE-32B 269B (fine-tuned)","metrics":{"Accuracy":"96.6"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/designing-effective-sparse-expert-models","paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","code":"https://github.com/tensorflow/mesh","n_code_links":3,"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"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5,"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"}}}},{"rank_in_archive_order":6,"model":"DeBERTa-1.5B","metrics":{"Accuracy":"95.9"},"uses_additional_data":false,"paper_date":"2020-06-05","paper":"/paper/deberta-decoding-enhanced-bert-with","paper_url":"https://arxiv.org/abs/2006.03654v6","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","code":"https://github.com/huggingface/transformers","n_code_links":14,"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"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":7,"model":"T5-XXL 11B (fine-tuned)","metrics":{"Accuracy":"93.8"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":8,"model":"ST-MoE-L 4.1B (fine-tuned)","metrics":{"Accuracy":"93.3"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/designing-effective-sparse-expert-models","paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","code":"https://github.com/tensorflow/mesh","n_code_links":3,"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"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5,"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"}}}},{"rank_in_archive_order":9,"model":"RoBERTa-WinoGrande 355M","metrics":{"Accuracy":"90.1"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"official":null,"syntology":null},{"rank_in_archive_order":10,"model":"Flan-T5 XXL (zero -shot)","metrics":{"Accuracy":"89.82"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/scaling-instruction-finetuned-language-models","paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","code":"https://github.com/google-research/flan","n_code_links":9,"official":null,"syntology":{"n_ran":8,"n_constructed":1,"n_ran_checked":1,"n_instrument":7,"n_unverified":9,"n_samples":17,"n_pointer_only_licence":2,"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"}}}},{"rank_in_archive_order":11,"model":"PaLM 540B (5-shot)","metrics":{"Accuracy":"89.5"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"official":null,"syntology":{"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":12,"model":"PaLM 540B (0-shot)","metrics":{"Accuracy":"89.1"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"official":null,"syntology":{"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":13,"model":"PaLM 2-M (1-shot)","metrics":{"Accuracy":"88.1"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"PaLM 2-L (1-shot)","metrics":{"Accuracy":"86.9"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"FLAN 137B (prompt-tuned)","metrics":{"Accuracy":"86.5"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":16,"model":"PaLM 540B (1-shot)","metrics":{"Accuracy":"86.3"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"official":null,"syntology":{"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":17,"model":"TTTTT 3B (fine-tuned)","metrics":{"Accuracy":"84.6"},"uses_additional_data":false,"paper_date":"2020-03-18","paper":"/paper/tttttackling-winogrande-schemas","paper_url":"https://arxiv.org/abs/2003.08380v1","paper_title":"TTTTTackling WinoGrande Schemas","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"PaLM 2-S (1-shot)","metrics":{"Accuracy":"84.6"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"RoBERTa-DPR 355M","metrics":{"Accuracy":"83.1"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"FLAN 137B (zero-shot)","metrics":{"Accuracy":"80.8"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":21,"model":"GPT-3 175B (few-shot)","metrics":{"Accuracy":"80.1"},"uses_additional_data":false,"paper_date":"2020-05-28","paper":"/paper/language-models-are-few-shot-learners","paper_url":"https://arxiv.org/abs/2005.14165v4","paper_title":"Language Models are Few-Shot Learners","code":"https://github.com/ggml-org/llama.cpp","n_code_links":67,"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"]},"syntology":{"n_ran":45,"n_constructed":0,"n_ran_checked":37,"n_instrument":8,"n_unverified":20,"n_samples":65,"n_pointer_only_licence":7,"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"}}}},{"rank_in_archive_order":22,"model":"RoBERTa-large + G-DAug-Inf","metrics":{"Accuracy":"80"},"uses_additional_data":false,"paper_date":"2020-04-24","paper":"/paper/g-daug-generative-data-augmentation-for","paper_url":"https://arxiv.org/abs/2004.11546v3","paper_title":"Generative Data Augmentation for Commonsense Reasoning","code":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","n_code_links":1,"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"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4,"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"}}}},{"rank_in_archive_order":23,"model":"UL2 20B (0-shot)","metrics":{"Accuracy":"79.9"},"uses_additional_data":false,"paper_date":"2022-05-10","paper":"/paper/unifying-language-learning-paradigms","paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","code":"https://github.com/google-research/google-research","n_code_links":2,"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"]},"syntology":{"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":1,"n_samples":16,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":24,"model":"ALBERT-xxlarge 235M","metrics":{"Accuracy":"78.8"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"Neo-6B (QA + WS)","metrics":{"Accuracy":"77.9"},"uses_additional_data":false,"paper_date":"2022-10-05","paper":"/paper/ask-me-anything-a-simple-strategy-for","paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","code":"https://github.com/hazyresearch/ama_prompting","n_code_links":3,"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"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":26,"model":"HNN","metrics":{"Accuracy":"75.1"},"uses_additional_data":false,"paper_date":"2019-07-27","paper":"/paper/a-hybrid-neural-network-model-for-commonsense","paper_url":"https://arxiv.org/abs/1907.11983v1","paper_title":"A Hybrid Neural Network Model for Commonsense Reasoning","code":"https://github.com/namisan/mt-dnn","n_code_links":3,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":27,"model":"Neo-6B (QA)","metrics":{"Accuracy":"74.7"},"uses_additional_data":false,"paper_date":"2022-10-05","paper":"/paper/ask-me-anything-a-simple-strategy-for","paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","code":"https://github.com/hazyresearch/ama_prompting","n_code_links":3,"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"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":28,"model":"RoBERTa-large 354M","metrics":{"Accuracy":"73.9"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"GPT-2-XL 1.5B","metrics":{"Accuracy":"73.3"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"BERTwiki 340M (fine-tuned on WSCR)","metrics":{"Accuracy":"72.5"},"uses_additional_data":false,"paper_date":"2019-05-15","paper":"/paper/a-surprisingly-robust-trick-for-winograd","paper_url":"https://arxiv.org/abs/1905.06290v2","paper_title":"A Surprisingly Robust Trick for Winograd Schema Challenge","code":"https://github.com/vid-koci/bert-commonsense","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"BERT-SocialIQA 340M","metrics":{"Accuracy":"72.5"},"uses_additional_data":false,"paper_date":"2019-04-22","paper":"/paper/socialiqa-commonsense-reasoning-about-social","paper_url":"https://arxiv.org/abs/1904.09728v3","paper_title":"SocialIQA: Commonsense Reasoning about Social Interactions","code":"https://github.com/clear-nus/llm-human-model","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":32,"model":"BERT-large 340M (fine-tuned on WSCR)","metrics":{"Accuracy":"71.4"},"uses_additional_data":false,"paper_date":"2019-05-15","paper":"/paper/a-surprisingly-robust-trick-for-winograd","paper_url":"https://arxiv.org/abs/1905.06290v2","paper_title":"A Surprisingly Robust Trick for Winograd Schema Challenge","code":"https://github.com/vid-koci/bert-commonsense","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"GPT-2-XL 1.5B","metrics":{"Accuracy":"70.7"},"uses_additional_data":false,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"BERTwiki 340M (fine-tuned on half of WSCR)","metrics":{"Accuracy":"70.3"},"uses_additional_data":false,"paper_date":"2019-05-15","paper":"/paper/a-surprisingly-robust-trick-for-winograd","paper_url":"https://arxiv.org/abs/1905.06290v2","paper_title":"A Surprisingly Robust Trick for Winograd Schema Challenge","code":"https://github.com/vid-koci/bert-commonsense","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"LaMini-GPT 1.5B","metrics":{"Accuracy":"69.6"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"GPT-2 Medium 774M (partial scoring)","metrics":{"Accuracy":"69.2"},"uses_additional_data":false,"paper_date":"2018-11-05","paper":"/paper/on-the-evaluation-of-common-sense-reasoning","paper_url":"https://arxiv.org/abs/1811.01778v2","paper_title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","code":"https://github.com/ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"N-Grammer 343M","metrics":{"Accuracy":"68.3"},"uses_additional_data":false,"paper_date":"2022-07-13","paper":"/paper/n-grammer-augmenting-transformers-with-latent-1","paper_url":"https://arxiv.org/abs/2207.06366v1","paper_title":"N-Grammer: Augmenting Transformers with latent n-grams","code":"https://github.com/tensorflow/lingvo","n_code_links":2,"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"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":38,"model":"AlexaTM 20B","metrics":{"Accuracy":"68.3"},"uses_additional_data":false,"paper_date":"2022-08-02","paper":"/paper/alexatm-20b-few-shot-learning-using-a-large","paper_url":"https://arxiv.org/abs/2208.01448v2","paper_title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","code":"https://github.com/amazon-science/alexa-teacher-models","n_code_links":1,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":39,"model":"BERT-large 340M","metrics":{"Accuracy":"67"},"uses_additional_data":false,"paper_date":"2019-04-22","paper":"/paper/socialiqa-commonsense-reasoning-about-social","paper_url":"https://arxiv.org/abs/1904.09728v3","paper_title":"SocialIQA: Commonsense Reasoning about Social Interactions","code":"https://github.com/clear-nus/llm-human-model","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":40,"model":"T5-Large 738M","metrics":{"Accuracy":"66.7"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"T0-3B (CoT fine-tuned)","metrics":{"Accuracy":"66"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/the-cot-collection-improving-zero-shot-and","paper_url":"https://arxiv.org/abs/2305.14045v2","paper_title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","code":"https://github.com/kaistai/cot-collection","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"KiC-770M","metrics":{"Accuracy":"65.40"},"uses_additional_data":false,"paper_date":"2022-10-28","paper":"/paper/knowledge-in-context-towards-knowledgeable","paper_url":"https://arxiv.org/abs/2210.16433v3","paper_title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"GPT-2 Medium 774M (full scoring)","metrics":{"Accuracy":"64.5"},"uses_additional_data":false,"paper_date":"2018-11-05","paper":"/paper/on-the-evaluation-of-common-sense-reasoning","paper_url":"https://arxiv.org/abs/1811.01778v2","paper_title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","code":"https://github.com/ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"LaMini-F-T5 783M","metrics":{"Accuracy":"64.1"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"Ensemble of 14 LMs","metrics":{"Accuracy":"63.7"},"uses_additional_data":false,"paper_date":"2018-06-07","paper":"/paper/a-simple-method-for-commonsense-reasoning","paper_url":"https://arxiv.org/abs/1806.02847v2","paper_title":"A Simple Method for Commonsense Reasoning","code":"https://github.com/tensorflow/models/tree/master/research/lm_commonsense","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":46,"model":"H3 125M (3-shot, rank classification)","metrics":{"Accuracy":"63.5"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"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"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":47,"model":"DSSM","metrics":{"Accuracy":"63.0"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/unsupervised-deep-structured-semantic-models","paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"RoBERTa-base 125M","metrics":{"Accuracy":"63"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"Word-level CNN+LSTM (partial scoring)","metrics":{"Accuracy":"62.6"},"uses_additional_data":false,"paper_date":"2018-06-07","paper":"/paper/a-simple-method-for-commonsense-reasoning","paper_url":"https://arxiv.org/abs/1806.02847v2","paper_title":"A Simple Method for Commonsense Reasoning","code":"https://github.com/tensorflow/models/tree/master/research/lm_commonsense","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":50,"model":"UDSSM-II (ensemble)","metrics":{"Accuracy":"62.4"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/unsupervised-deep-structured-semantic-models","paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"BERT-base 110M (fine-tuned on WSCR)","metrics":{"Accuracy":"62.3"},"uses_additional_data":false,"paper_date":"2019-05-15","paper":"/paper/a-surprisingly-robust-trick-for-winograd","paper_url":"https://arxiv.org/abs/1905.06290v2","paper_title":"A Surprisingly Robust Trick for Winograd Schema Challenge","code":"https://github.com/vid-koci/bert-commonsense","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"RoE-3B","metrics":{"Accuracy":"62.21"},"uses_additional_data":false,"paper_date":"2023-02-07","paper":"/paper/exploring-the-benefits-of-training-expert","paper_url":"https://arxiv.org/abs/2302.03202v2","paper_title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","code":"https://github.com/joeljang/rlphf","n_code_links":2,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":53,"model":"BERT-large 340M","metrics":{"Accuracy":"62.0"},"uses_additional_data":false,"paper_date":"2018-10-11","paper":"/paper/bert-pre-training-of-deep-bidirectional","paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":534,"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"]},"syntology":{"n_ran":300,"n_constructed":75,"n_ran_checked":234,"n_instrument":66,"n_unverified":359,"n_samples":659,"n_pointer_only_licence":164,"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"}}}},{"rank_in_archive_order":54,"model":"GPT-2 Small 117M (partial scoring)","metrics":{"Accuracy":"61.5"},"uses_additional_data":false,"paper_date":"2018-11-05","paper":"/paper/on-the-evaluation-of-common-sense-reasoning","paper_url":"https://arxiv.org/abs/1811.01778v2","paper_title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","code":"https://github.com/ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"H3 125M (0-shot, rank classification)","metrics":{"Accuracy":"61.5"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"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"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":56,"model":"BERT-large 340M","metrics":{"Accuracy":"61.4"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"BERT-base 110M + MAS","metrics":{"Accuracy":"60.3"},"uses_additional_data":false,"paper_date":"2019-05-31","paper":"/paper/attention-is-not-all-you-need-for-commonsense","paper_url":"https://arxiv.org/abs/1905.13497v1","paper_title":"Attention Is (not) All You Need for Commonsense Reasoning","code":"https://github.com/SAP-samples/acl2020-commonsense","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"longdoc S (OntoNotes + PreCo + LitBank)","metrics":{"Accuracy":"60.1"},"uses_additional_data":false,"paper_date":"2021-09-20","paper":"/paper/on-generalization-in-coreference-resolution","paper_url":"https://arxiv.org/abs/2109.09667v1","paper_title":"On Generalization in Coreference Resolution","code":"https://github.com/shtoshni/fast-coref","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"longdoc S (ON + PreCo + LitBank + 30k pseudo-singletons)","metrics":{"Accuracy":"59.4"},"uses_additional_data":false,"paper_date":"2021-09-20","paper":"/paper/on-generalization-in-coreference-resolution","paper_url":"https://arxiv.org/abs/2109.09667v1","paper_title":"On Generalization in Coreference Resolution","code":"https://github.com/shtoshni/fast-coref","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":60,"model":"UDSSM-II","metrics":{"Accuracy":"59.2"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/unsupervised-deep-structured-semantic-models","paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"LaMini-T5 738M","metrics":{"Accuracy":"59"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"Flipped-3B","metrics":{"Accuracy":"58.37"},"uses_additional_data":false,"paper_date":"2022-10-06","paper":"/paper/guess-the-instruction-making-language-models","paper_url":"https://arxiv.org/abs/2210.02969v4","paper_title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","code":"https://github.com/seonghyeonye/flipped-learning","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"KEE+NKAM winner of the WSC2016","metrics":{"Accuracy":"58.3"},"uses_additional_data":false,"paper_date":"2016-11-13","paper":"/paper/commonsense-knowledge-enhanced-embeddings-for","paper_url":"http://arxiv.org/abs/1611.04146v2","paper_title":"Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"Char-level CNN+LSTM (partial scoring)","metrics":{"Accuracy":"57.9"},"uses_additional_data":false,"paper_date":"2018-06-07","paper":"/paper/a-simple-method-for-commonsense-reasoning","paper_url":"https://arxiv.org/abs/1806.02847v2","paper_title":"A Simple Method for Commonsense Reasoning","code":"https://github.com/tensorflow/models/tree/master/research/lm_commonsense","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":65,"model":"UDSSM-I (ensemble)","metrics":{"Accuracy":"57.1"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/unsupervised-deep-structured-semantic-models","paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"Knowledge Hunter","metrics":{"Accuracy":"57.1"},"uses_additional_data":false,"paper_date":"2018-10-02","paper":"/paper/a-knowledge-hunting-framework-for-common","paper_url":"http://arxiv.org/abs/1810.01375v1","paper_title":"A Knowledge Hunting Framework for Common Sense Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"WKH","metrics":{"Accuracy":"57.1"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"official":null,"syntology":null},{"rank_in_archive_order":68,"model":"BERT-base 110M","metrics":{"Accuracy":"56.5"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"GPT-2 Small 117M (full scoring)","metrics":{"Accuracy":"55.7"},"uses_additional_data":false,"paper_date":"2018-11-05","paper":"/paper/on-the-evaluation-of-common-sense-reasoning","paper_url":"https://arxiv.org/abs/1811.01778v2","paper_title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","code":"https://github.com/ptrichel/How-Reasonable-are-Common-Sense-Reasoning-Tasks","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"ALBERT-base 11M","metrics":{"Accuracy":"55.4"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"Pythia 12B (0-shot)","metrics":{"Accuracy":"54.8"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/pythia-a-suite-for-analyzing-large-language","paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","code":"https://github.com/Lightning-AI/lit-gpt","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":72,"model":"UDSSM-I","metrics":{"Accuracy":"54.5"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/unsupervised-deep-structured-semantic-models","paper_url":"http://arxiv.org/abs/1904.01938v1","paper_title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":73,"model":"Subword-level Transformer LM","metrics":{"Accuracy":"54.1"},"uses_additional_data":false,"paper_date":"2017-06-12","paper":"/paper/attention-is-all-you-need","paper_url":"https://arxiv.org/abs/1706.03762v7","paper_title":"Attention Is All You Need","code":"https://github.com/huggingface/transformers","n_code_links":595,"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"]},"syntology":{"n_ran":610,"n_constructed":293,"n_ran_checked":529,"n_instrument":81,"n_unverified":336,"n_samples":946,"n_pointer_only_licence":451,"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"}}}},{"rank_in_archive_order":74,"model":"USSM + Supervised DeepNet + KB","metrics":{"Accuracy":"52.8"},"uses_additional_data":false,"paper_date":"2019-05-31","paper":"/paper/attention-is-not-all-you-need-for-commonsense","paper_url":"https://arxiv.org/abs/1905.13497v1","paper_title":"Attention Is (not) All You Need for Commonsense Reasoning","code":"https://github.com/SAP-samples/acl2020-commonsense","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":75,"model":"KEE+NKAM on WinoGrande","metrics":{"Accuracy":"52.8"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"USSM + KB","metrics":{"Accuracy":"52"},"uses_additional_data":false,"paper_date":"2019-05-31","paper":"/paper/attention-is-not-all-you-need-for-commonsense","paper_url":"https://arxiv.org/abs/1905.13497v1","paper_title":"Attention Is (not) All You Need for Commonsense Reasoning","code":"https://github.com/SAP-samples/acl2020-commonsense","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"Random chance baseline","metrics":{"Accuracy":"50"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":78,"model":"Hybrid H3 125M (3-shot, logit scoring)","metrics":{"Accuracy":"43.3"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"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"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":79,"model":"Pythia 2.8B (0-shot)","metrics":{"Accuracy":"38.5"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/pythia-a-suite-for-analyzing-large-language","paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","code":"https://github.com/Lightning-AI/lit-gpt","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"Neo-6B (few-shot)","metrics":{"Accuracy":"36.5"},"uses_additional_data":false,"paper_date":"2022-10-05","paper":"/paper/ask-me-anything-a-simple-strategy-for","paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","code":"https://github.com/hazyresearch/ama_prompting","n_code_links":3,"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"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":81,"model":"Pythia 6.9B (0-shot)","metrics":{"Accuracy":"36.5"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/pythia-a-suite-for-analyzing-large-language","paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","code":"https://github.com/Lightning-AI/lit-gpt","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"Pythia 12B (5-shot)","metrics":{"Accuracy":"36.5"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/pythia-a-suite-for-analyzing-large-language","paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","code":"https://github.com/Lightning-AI/lit-gpt","n_code_links":4,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 6 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,594 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and none proposed a result, so none await a verdict and none were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":82,"metric_columns":1,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1594,"candidates":6,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":0,"no_cell_passed_checks":0,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; no newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables a model judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"a model","models_as_recorded":[],"a_record_without_a_model":false,"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","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":0,"shown_on_page":0,"no_cell_split":{"no_cell_passed_checks_in_ledger":0,"rows_refused_by_rule":0,"rows_no_cell_passed_checks":0},"rows":[]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_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'","n_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)"},"rows_with_graph_line":32,"rows_with_any_sample_ran":29,"rows_with_a_run_with_no_instrument_failure":23,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":20,"rows_whose_official_repository_has_a_sample_that_ran":9,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":1,"rows_community_repositories_only":5,"rows_runs_from_other_or_unrecorded_repositories":3,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology 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","distinct_papers_with_graph_line":19,"distinct_papers_with_any_sample_ran":17,"distinct_papers_with_a_run_with_no_instrument_failure":13,"samples_over_distinct_papers":{"n_ran":1070,"n_constructed":385,"n_ran_checked":884,"n_instrument":186,"n_unverified":769,"n_samples":1839,"n_pointer_only_licence":639,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1217,"n_constructed":433,"n_ran_checked":993,"n_instrument":224,"n_unverified":813,"n_samples":2030,"n_pointer_only_licence":644,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"eda5fb9e4d2ae966e73d4dea0ef0c17fbedff1ebbea90a59bb6132393bfe38ba","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}