{"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/question-answering-on-copa","task":{"name":"Question Answering","url":"/task/question-answering","note":null},"dataset":{"name":"COPA","url":"/dataset/copa"},"category":"Natural Language Processing","categories":["Miscellaneous","Natural Language Processing","Reasoning"],"category_note":null,"description":"Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include [SQuAD](/dataset/squad), [HotPotQA](/dataset/hotpotqa), [bAbI](/dataset/babi-1), [TriviaQA](/dataset/triviaqa), [WikiQA](/dataset/wikiqa), and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.\r\n\r\n( Image credit: [SQuAD](https://rajpurkar.github.io/mlx/qa-and-squad/) )","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":60,"rows_with_code":47,"rows_with_paper_page":60,"rows_dated":60,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PaLM 540B (finetuned)","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":"99.4"},"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":"ST-MoE-32B 269B (fine-tuned)","metrics":{"Accuracy":"99.2"},"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":4,"model":"UL2 20B (fine-tuned)","metrics":{"Accuracy":"99"},"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":5,"model":"DeBERTa-Ensemble","metrics":{"Accuracy":"98.4"},"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":6,"model":"Turing NLR v5 XXL 5.4B (fine-tuned)","metrics":{"Accuracy":"98.2"},"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":7,"model":"DeBERTa-1.5B","metrics":{"Accuracy":"96.8"},"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":8,"model":"PaLM 2-L (1-shot)","metrics":{"Accuracy":"96.0"},"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":9,"model":"T5-XXL 11B (fine-tuned)","metrics":{"Accuracy":"94.8"},"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":10,"model":"FLAN 137B (prompt-tuned)","metrics":{"Accuracy":"94"},"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":11,"model":"GPT-3 175B (few-shot, k=32)","metrics":{"Accuracy":"92"},"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":12,"model":"T5-XL 3B (fine-tuned)","metrics":{"Accuracy":"92"},"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":13,"model":"FLAN 137B (zero-shot)","metrics":{"Accuracy":"91"},"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":14,"model":"ST-MoE-L 4.1B (fine-tuned)","metrics":{"Accuracy":"91"},"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":15,"model":"GPT-3 175B (0-shot)","metrics":{"Accuracy":"91"},"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":16,"model":"T0-3B (CoT fine-tuned)","metrics":{"Accuracy":"90.9"},"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":17,"model":"RoBERTa-Winogrande-ft 355M (fine-tuned)","metrics":{"Accuracy":"90.6"},"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":18,"model":"PaLM 2-M (1-shot)","metrics":{"Accuracy":"90.0"},"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":"Flipped-3B","metrics":{"Accuracy":"89.88"},"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":20,"model":"PaLM 2-S (1-shot)","metrics":{"Accuracy":"89.0"},"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":21,"model":"GPT-NeoX (one-shot)","metrics":{"Accuracy":"88"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"FLAN 137B (few-shot, k=16)","metrics":{"Accuracy":"87"},"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":23,"model":"GPT-3 175B (1-shot)","metrics":{"Accuracy":"87"},"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":24,"model":"RoBERTa-ft 355M (fine-tuned)","metrics":{"Accuracy":"86.4"},"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":25,"model":"Bloomberg GPT (one-shot)","metrics":{"Accuracy":"86"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"OPT 66B (one-shot)","metrics":{"Accuracy":"86"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"GPT-3 13B (few-shot, k=32)","metrics":{"Accuracy":"86"},"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":28,"model":"KiC-770M","metrics":{"Accuracy":"85.30"},"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":29,"model":"UL2 20B (0-shot)","metrics":{"Accuracy":"85"},"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":30,"model":"RoBERTa-Winogrande 355M (fine-tuned)","metrics":{"Accuracy":"84.4"},"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":31,"model":"Neo-6B (QA + WS)","metrics":{"Accuracy":"84.0"},"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":32,"model":"BLOOM 176B (one-shot)","metrics":{"Accuracy":"84"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"T5-Large 770M (fine-tuned)","metrics":{"Accuracy":"83.4"},"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":34,"model":"BERT-SocialIQA 340M","metrics":{"Accuracy":"83.4"},"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":35,"model":"Hybrid H3 2.7B (0-shot, logit scoring)","metrics":{"Accuracy":"81"},"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":36,"model":"BERT-large 340M","metrics":{"Accuracy":"80.8"},"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":37,"model":"RoE-3B","metrics":{"Accuracy":"79.25"},"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":38,"model":"sMLP – deterministic 9.4B (0-shot)","metrics":{"Accuracy":"79"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"KELM (finetuning BERT-large based single model)","metrics":{"Accuracy":"78.0"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/kelm-knowledge-enhanced-pre-trained-language","paper_url":"https://arxiv.org/abs/2109.04223v2","paper_title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","code":"https://github.com/nlp-anonymous-happy/anonymous-kg-guided-nlp","n_code_links":1,"official":{"repos":["nlp-anonymous-happy/anonymous-kg-guided-nlp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":1,"sample_list":"/paper/kelm-knowledge-enhanced-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2109.04223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04223"}}}},{"rank_in_archive_order":40,"model":"AlexaTM 20B","metrics":{"Accuracy":"78.0"},"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":41,"model":"Neo-6B (few-shot)","metrics":{"Accuracy":"77.0"},"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":42,"model":"Hybrid H3 2.7B (3-shot, logit scoring)","metrics":{"Accuracy":"77"},"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":43,"model":"Causal Strength w/multi-word predicates (presumably on WinoGrande?)","metrics":{"Accuracy":"76.4"},"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":44,"model":"Gshard 9B","metrics":{"Accuracy":"76"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"Switch Transformer 9B","metrics":{"Accuracy":"75"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"GPT-3 Large 760M (0-shot)","metrics":{"Accuracy":"73.0"},"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":47,"model":"Causal Strength Computation w/multi-word predicates (on ClueWeb12)","metrics":{"Accuracy":"71.2"},"uses_additional_data":false,"paper_date":"2017-01-01","paper":"/paper/handling-multiword-expressions-in-causality","paper_url":"https://aclanthology.org/W17-6937","paper_title":"Handling Multiword Expressions in Causality Estimation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"T5-Base 220M (fine-tuned)","metrics":{"Accuracy":"71.2"},"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":49,"model":"Causal Strength Computation (on Causal Net)","metrics":{"Accuracy":"70.2"},"uses_additional_data":false,"paper_date":"2017-01-01","paper":"/paper/handling-multiword-expressions-in-causality","paper_url":"https://aclanthology.org/W17-6937","paper_title":"Handling Multiword Expressions in Causality Estimation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"Causal Strength Computation (on ClueWeb12)","metrics":{"Accuracy":"69.9"},"uses_additional_data":false,"paper_date":"2017-01-01","paper":"/paper/handling-multiword-expressions-in-causality","paper_url":"https://aclanthology.org/W17-6937","paper_title":"Handling Multiword Expressions in Causality Estimation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"Hybrid H3 125M (0-shot, logit scoring)","metrics":{"Accuracy":"67"},"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":52,"model":"Hybrid H3 125M (0-shot, rank classification)","metrics":{"Accuracy":"67"},"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":53,"model":"Pointwise Mutual Information (on 10M stories)","metrics":{"Accuracy":"65.4"},"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":54,"model":"HASH Layers 10B (0-shot)","metrics":{"Accuracy":"64"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"Base Layers 10B (0-shot)","metrics":{"Accuracy":"63"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"N-Grammer 343M","metrics":{"Accuracy":"60.0"},"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":57,"model":"Pointwise Mutual Information (on Project Gutenberg)","metrics":{"Accuracy":"58.8"},"uses_additional_data":false,"paper_date":"2017-01-01","paper":"/paper/handling-multiword-expressions-in-causality","paper_url":"https://aclanthology.org/W17-6937","paper_title":"Handling Multiword Expressions in Causality Estimation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"Neo-6B (QA)","metrics":{"Accuracy":"58.2"},"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":59,"model":"H3 125M (0-shot, rank classification)","metrics":{"Accuracy":"51"},"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":60,"model":"Random chance baseline","metrics":{"Accuracy":"50"},"uses_additional_data":false,"paper_date":"2017-01-01","paper":"/paper/handling-multiword-expressions-in-causality","paper_url":"https://aclanthology.org/W17-6937","paper_title":"Handling Multiword Expressions in Causality Estimation","code":null,"n_code_links":0,"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), 9 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 1,590 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 7 proposed a result; of those 7, 5 gave no cell that passed the extractor's own checks, 1 was rejected by the independent check, 1 awaits a verdict and 0 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":60,"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":1590,"candidates":9,"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":7,"no_cell_passed_checks":5,"rejected_by_independent_check":1,"accepted_not_placed":0,"awaiting_verdict":1,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 7 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":7,"shown_on_page":7,"no_cell_split":{"no_cell_passed_checks_in_ledger":5,"rows_refused_by_rule":5,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.15160","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2605.31164","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2605.24144","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.17849","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard"},{"arxiv_id":"2602.00942","outcome":"awaiting","reason":null},{"arxiv_id":"2601.21864","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2601.21579","outcome":"rejected","reason":null}]},"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":33,"rows_with_any_sample_ran":30,"rows_with_a_run_with_no_instrument_failure":25,"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":25,"rows_whose_official_repository_has_a_sample_that_ran":11,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":2,"rows_community_repositories_only":9,"rows_runs_from_other_or_unrecorded_repositories":2,"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":14,"distinct_papers_with_any_sample_ran":13,"distinct_papers_with_a_run_with_no_instrument_failure":10,"samples_over_distinct_papers":{"n_ran":152,"n_constructed":16,"n_ran_checked":121,"n_instrument":31,"n_unverified":59,"n_samples":211,"n_pointer_only_licence":19,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":456,"n_constructed":16,"n_ran_checked":367,"n_instrument":89,"n_unverified":218,"n_samples":674,"n_pointer_only_licence":55,"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":"cfa84bdad85b84c559ba43bd8c0c6f0c32d741b1498223dc5499687d08d44e59","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}