{"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-triviaqa","task":{"name":"Question Answering","url":"/task/question-answering","note":null},"dataset":{"name":"TriviaQA","url":"/dataset/triviaqa"},"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":["EM","F1"],"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":{"EM":null,"F1":"higher"}},"counts":{"rows":56,"rows_with_code":36,"rows_with_paper_page":55,"rows_dated":55,"rows_using_additional_data":13},"rows":[{"rank_in_archive_order":1,"model":"Claude 2 (few-shot, k=5)","metrics":{"EM":"87.5"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"GPT-4-0613","metrics":{"EM":"87"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"Claude 1.3 (few-shot, k=5)","metrics":{"EM":"86.7"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"RankRAG-llama3-70b (Zero-Shot, KILT)","metrics":{"EM":"86.5"},"uses_additional_data":true,"paper_date":"2024-07-02","paper":"/paper/rankrag-unifying-context-ranking-with","paper_url":"https://arxiv.org/abs/2407.02485v1","paper_title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":5,"model":"PaLM 2-L (one-shot)","metrics":{"EM":"86.1"},"uses_additional_data":true,"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":6,"model":"ChatQA-1.5-llama3-70b (Zero-Shot, KILT)","metrics":{"EM":"85.6"},"uses_additional_data":true,"paper_date":"2024-01-18","paper":"/paper/chatqa-building-gpt-4-level-conversational-qa","paper_url":"https://arxiv.org/abs/2401.10225v5","paper_title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"LLaMA 2 70B (one-shot)","metrics":{"EM":"85"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","code":"https://github.com/facebookresearch/llama","n_code_links":19,"official":{"repos":["facebookresearch/llama"],"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":33,"n_constructed":7,"n_ran_checked":20,"n_instrument":13,"n_unverified":19,"n_samples":52,"n_pointer_only_licence":20,"sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"rank_in_archive_order":8,"model":"GPT-4-0613 (Zero-shot)","metrics":{"EM":"84.8"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/gpt-4-technical-report-1","paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","code":"https://github.com/openai/evals","n_code_links":11,"official":{"repos":["openai/evals"],"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":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1,"sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"rank_in_archive_order":9,"model":"RankRAG-llama3-8b (Zero-Shot, KILT)","metrics":{"EM":"82.9"},"uses_additional_data":true,"paper_date":"2024-07-02","paper":"/paper/rankrag-unifying-context-ranking-with","paper_url":"https://arxiv.org/abs/2407.02485v1","paper_title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":10,"model":"PaLM 2-M (one-shot)","metrics":{"EM":"81.7"},"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":11,"model":"PaLM-540B (Few-Shot)","metrics":{"EM":"81.4"},"uses_additional_data":true,"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 (One-Shot)","metrics":{"EM":"81.4"},"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":"ChatQA-1.5-llama3-8B (Zero-Shot, KILT)","metrics":{"EM":"81.0"},"uses_additional_data":true,"paper_date":"2024-01-18","paper":"/paper/chatqa-building-gpt-4-level-conversational-qa","paper_url":"https://arxiv.org/abs/2401.10225v5","paper_title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"GaC(Qwen2-72B-Instruct + Llama-3-70B-Instruct)","metrics":{"EM":"79.29"},"uses_additional_data":false,"paper_date":"2024-06-18","paper":"/paper/breaking-the-ceiling-of-the-llm-community-by","paper_url":"https://arxiv.org/abs/2406.12585v2","paper_title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","code":"https://github.com/yaoching0/gac","n_code_links":1,"official":{"repos":["yaoching0/gac"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/breaking-the-ceiling-of-the-llm-community-by#ran","syntology_url":"https://syntology.ai/paper/2406.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12585"}}}},{"rank_in_archive_order":15,"model":"Claude Instant 1.1 (few-shot, k=5)","metrics":{"EM":"78.9"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"code-davinci-002 175B + REPLUG LSR (Few-Shot)","metrics":{"EM":"77.3"},"uses_additional_data":false,"paper_date":"2023-01-30","paper":"/paper/replug-retrieval-augmented-black-box-language","paper_url":"https://arxiv.org/abs/2301.12652v4","paper_title":"REPLUG: Retrieval-Augmented Black-Box Language Models","code":"https://github.com/ruc-nlpir/flashrag","n_code_links":3,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":13,"sample_list":"/paper/replug-retrieval-augmented-black-box-language#ran","syntology_url":"https://syntology.ai/paper/2301.12652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12652"}}}},{"rank_in_archive_order":17,"model":"PaLM-540B (Zero-Shot)","metrics":{"EM":"76.9"},"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":18,"model":"code-davinci-002 175B + REPLUG (Few-Shot)","metrics":{"EM":"76.8"},"uses_additional_data":false,"paper_date":"2023-01-30","paper":"/paper/replug-retrieval-augmented-black-box-language","paper_url":"https://arxiv.org/abs/2301.12652v4","paper_title":"REPLUG: Retrieval-Augmented Black-Box Language Models","code":"https://github.com/ruc-nlpir/flashrag","n_code_links":3,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":13,"sample_list":"/paper/replug-retrieval-augmented-black-box-language#ran","syntology_url":"https://syntology.ai/paper/2301.12652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12652"}}}},{"rank_in_archive_order":19,"model":"GLaM 62B/64E (One-shot)","metrics":{"EM":"75.8"},"uses_additional_data":true,"paper_date":"2021-12-13","paper":"/paper/glam-efficient-scaling-of-language-models","paper_url":"https://arxiv.org/abs/2112.06905v2","paper_title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"GLaM 62B/64E (Few-shot)","metrics":{"EM":"75.8"},"uses_additional_data":false,"paper_date":"2021-12-13","paper":"/paper/glam-efficient-scaling-of-language-models","paper_url":"https://arxiv.org/abs/2112.06905v2","paper_title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"RA-DIT (Zero-Shot)","metrics":{"EM":"75.4"},"uses_additional_data":true,"paper_date":"2023-10-02","paper":"/paper/ra-dit-retrieval-augmented-dual-instruction","paper_url":"https://arxiv.org/abs/2310.01352v4","paper_title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"PaLM 2-S (one-shot)","metrics":{"EM":"75.2"},"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":23,"model":"LLaMA 65B (few-shot, k=64)","metrics":{"EM":"73.0"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"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":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":24,"model":"FiE+PAQ","metrics":{"EM":"72.6"},"uses_additional_data":false,"paper_date":"2022-11-18","paper":"/paper/fie-building-a-global-probability-space-by","paper_url":"https://arxiv.org/abs/2211.10147v1","paper_title":"FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"LLaMA 65B (few-shot, k=5)","metrics":{"EM":"72.6"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"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":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":26,"model":"RankRAG-llama3-70b (Zero-Shot, DPR)","metrics":{"EM":"72.6"},"uses_additional_data":true,"paper_date":"2024-07-02","paper":"/paper/rankrag-unifying-context-ranking-with","paper_url":"https://arxiv.org/abs/2407.02485v1","paper_title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"FiD+Distil","metrics":{"EM":"72.1"},"uses_additional_data":true,"paper_date":"2020-12-08","paper":"/paper/distilling-knowledge-from-reader-to-retriever-1","paper_url":"https://arxiv.org/abs/2012.04584v2","paper_title":"Distilling Knowledge from Reader to Retriever for Question Answering","code":"https://github.com/facebookresearch/FiD","n_code_links":4,"official":{"repos":["facebookresearch/FiD"],"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":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/distilling-knowledge-from-reader-to-retriever-1#ran","syntology_url":"https://syntology.ai/paper/2012.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04584"}}}},{"rank_in_archive_order":28,"model":"LLaMA 65B (one-shot)","metrics":{"EM":"71.6"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"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":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":29,"model":"EMDR2","metrics":{"EM":"71.4"},"uses_additional_data":false,"paper_date":"2021-06-09","paper":"/paper/end-to-end-training-of-multi-document-reader","paper_url":"https://arxiv.org/abs/2106.05346v2","paper_title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","code":"https://github.com/DevSinghSachan/emdr2","n_code_links":2,"official":{"repos":["DevSinghSachan/emdr2"],"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":["community","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/end-to-end-training-of-multi-document-reader#ran","syntology_url":"https://syntology.ai/paper/2106.05346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05346"}}}},{"rank_in_archive_order":30,"model":"GLaM 62B/64E (Zero-shot)","metrics":{"EM":"71.3"},"uses_additional_data":false,"paper_date":"2021-12-13","paper":"/paper/glam-efficient-scaling-of-language-models","paper_url":"https://arxiv.org/abs/2112.06905v2","paper_title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"GPT-3 175B (Few-Shot)","metrics":{"EM":"71.2"},"uses_additional_data":true,"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":32,"model":"Mistral 7B (5-shot)","metrics":{"EM":"69.9"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/mistral-7b","paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","code":"https://github.com/mistralai/mistral-src","n_code_links":6,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":2,"sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"rank_in_archive_order":33,"model":"ChatQA-1.5-llama3-70b (Zero-Shot, DPR)","metrics":{"EM":"69.0"},"uses_additional_data":false,"paper_date":"2024-01-18","paper":"/paper/chatqa-building-gpt-4-level-conversational-qa","paper_url":"https://arxiv.org/abs/2401.10225v5","paper_title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"LLaMA 65B (zero-shot)","metrics":{"EM":"68.2"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"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":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":35,"model":"Fusion-in-Decoder (large)","metrics":{"EM":"67.6"},"uses_additional_data":false,"paper_date":"2020-07-02","paper":"/paper/leveraging-passage-retrieval-with-generative","paper_url":"https://arxiv.org/abs/2007.01282v2","paper_title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","code":"https://github.com/jhyuklee/DensePhrases","n_code_links":8,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"MemoReader","metrics":{"EM":"67.21","F1":"73.26"},"uses_additional_data":true,"paper_date":"2018-10-01","paper":"/paper/memoreader-large-scale-reading-comprehension","paper_url":"https://aclanthology.org/D18-1237","paper_title":"MemoReader: Large-Scale Reading Comprehension through Neural Memory Controller","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"S-Norm","metrics":{"EM":"66.37","F1":"71.32"},"uses_additional_data":true,"paper_date":"2017-10-29","paper":"/paper/simple-and-effective-multi-paragraph-reading","paper_url":"http://arxiv.org/abs/1710.10723v2","paper_title":"Simple and Effective Multi-Paragraph Reading Comprehension","code":"https://github.com/allenai/document-qa","n_code_links":1,"official":{"repos":["allenai/document-qa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/simple-and-effective-multi-paragraph-reading#ran","syntology_url":"https://syntology.ai/paper/1710.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10723"}}}},{"rank_in_archive_order":38,"model":"TOME-2","metrics":{"EM":"65.8"},"uses_additional_data":false,"paper_date":"2021-10-12","paper":"/paper/mention-memory-incorporating-textual-1","paper_url":"https://arxiv.org/abs/2110.06176v2","paper_title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","code":"https://github.com/google-research/language/tree/master/language/mentionmemory","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"Shakti-LLM (2.5B)","metrics":{"EM":"58.2"},"uses_additional_data":false,"paper_date":"2024-10-15","paper":"/paper/shakti-a-2-5-billion-parameter-small-language","paper_url":"https://arxiv.org/abs/2410.11331v1","paper_title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"Branch-Train-MiX 4x7B (sampling top-2 experts)","metrics":{"EM":"57.1"},"uses_additional_data":false,"paper_date":"2024-03-12","paper":"/paper/branch-train-mix-mixing-expert-llms-into-a","paper_url":"https://arxiv.org/abs/2403.07816v1","paper_title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","code":"https://github.com/Leeroo-AI/mergoo","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"DPR","metrics":{"EM":"56.8"},"uses_additional_data":false,"paper_date":"2020-04-10","paper":"/paper/dense-passage-retrieval-for-open-domain","paper_url":"https://arxiv.org/abs/2004.04906v3","paper_title":"Dense Passage Retrieval for Open-Domain Question Answering","code":"https://github.com/huggingface/transformers","n_code_links":19,"official":{"repos":["facebookresearch/DPR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":6,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_samples":14,"n_pointer_only_licence":9,"sample_list":"/paper/dense-passage-retrieval-for-open-domain#ran","syntology_url":"https://syntology.ai/paper/2004.04906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04906"}}}},{"rank_in_archive_order":42,"model":"FLAN 137B (zero-shot)","metrics":{"EM":"56.7"},"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":43,"model":"RAG","metrics":{"EM":"56.1"},"uses_additional_data":false,"paper_date":"2020-05-22","paper":"/paper/retrieval-augmented-generation-for-knowledge","paper_url":"https://arxiv.org/abs/2005.11401v4","paper_title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","code":"https://github.com/huggingface/transformers","n_code_links":18,"official":null,"syntology":{"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/retrieval-augmented-generation-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2005.11401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11401"}}}},{"rank_in_archive_order":44,"model":"Reading Twice for NLU","metrics":{"EM":"50.56","F1":"56.73"},"uses_additional_data":false,"paper_date":"2017-06-08","paper":"/paper/dynamic-integration-of-background-knowledge","paper_url":"http://arxiv.org/abs/1706.02596v3","paper_title":"Dynamic Integration of Background Knowledge in Neural NLU Systems","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"Mnemonic Reader","metrics":{"EM":"46.94","F1":"52.85"},"uses_additional_data":false,"paper_date":"2017-05-08","paper":"/paper/reinforced-mnemonic-reader-for-machine","paper_url":"http://arxiv.org/abs/1705.02798v6","paper_title":"Reinforced Mnemonic Reader for Machine Reading Comprehension","code":"https://github.com/HKUST-KnowComp/MnemonicReader","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"ORQA","metrics":{"EM":"45"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/190600300","paper_url":"https://arxiv.org/abs/1906.00300v3","paper_title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","code":"https://github.com/google-research/language/tree/master/language/orqa","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"MEMEN","metrics":{"EM":"43.16","F1":"46.90"},"uses_additional_data":false,"paper_date":"2017-07-28","paper":"/paper/memen-multi-layer-embedding-with-memory","paper_url":"http://arxiv.org/abs/1707.09098v1","paper_title":"MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"SpanBERT","metrics":{"F1":"83.6"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/spanbert-improving-pre-training-by","paper_url":"https://arxiv.org/abs/1907.10529v3","paper_title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","code":"https://github.com/facebookresearch/SpanBERT","n_code_links":6,"official":{"repos":["facebookresearch/SpanBERT"],"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":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":6,"sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}}}},{"rank_in_archive_order":49,"model":"BigBird-etc","metrics":{"F1":"80.9"},"uses_additional_data":false,"paper_date":"2020-07-28","paper":"/paper/big-bird-transformers-for-longer-sequences","paper_url":"https://arxiv.org/abs/2007.14062v2","paper_title":"Big Bird: Transformers for Longer Sequences","code":"https://github.com/huggingface/transformers","n_code_links":14,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":1,"n_ran_checked":2,"n_instrument":8,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":11,"sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"rank_in_archive_order":50,"model":"DPA-RAG","metrics":{"F1":"80.1"},"uses_additional_data":false,"paper_date":"2024-06-26","paper":"/paper/understand-what-llm-needs-dual-preference","paper_url":"https://arxiv.org/abs/2406.18676v2","paper_title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","code":"https://github.com/dongguanting/dpa-rag","n_code_links":1,"official":{"repos":["dongguanting/dpa-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/understand-what-llm-needs-dual-preference#ran","syntology_url":"https://syntology.ai/paper/2406.18676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18676"}}}},{"rank_in_archive_order":51,"model":"LinkBERT (large)","metrics":{"F1":"78.2"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/linkbert-pretraining-language-models-with","paper_url":"https://arxiv.org/abs/2203.15827v1","paper_title":"LinkBERT: Pretraining Language Models with Document Links","code":"https://github.com/michiyasunaga/LinkBERT","n_code_links":1,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"n_samples":14,"n_pointer_only_licence":0,"sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"rank_in_archive_order":52,"model":"DyREX","metrics":{"F1":"77.37"},"uses_additional_data":false,"paper_date":"2022-10-26","paper":"/paper/dyrex-dynamic-query-representation-for","paper_url":"https://arxiv.org/abs/2210.15048v1","paper_title":"DyREx: Dynamic Query Representation for Extractive Question Answering","code":"https://github.com/urchade/dyrex","n_code_links":1,"official":{"repos":["urchade/dyrex"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/dyrex-dynamic-query-representation-for#ran","syntology_url":"https://syntology.ai/paper/2210.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15048"}}}},{"rank_in_archive_order":53,"model":"Search-o1","metrics":{"F1":"74.1"},"uses_additional_data":false,"paper_date":"2025-01-09","paper":"/paper/search-o1-agentic-search-enhanced-large","paper_url":"https://arxiv.org/abs/2501.05366v1","paper_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","code":"https://github.com/sunnynexus/search-o1","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"UnitedQA (Hybrid reader)","metrics":{"F1":"70.3"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/unitedqa-a-hybrid-approach-for-open-domain","paper_url":"https://arxiv.org/abs/2101.00178v2","paper_title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"ReasonBERTR","metrics":{"F1":"45.5"},"uses_additional_data":false,"paper_date":"2021-09-10","paper":"/paper/reasonbert-pre-trained-to-reason-with-distant","paper_url":"https://arxiv.org/abs/2109.04912v1","paper_title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","code":"https://github.com/sunlab-osu/reasonbert","n_code_links":1,"official":{"repos":["sunlab-osu/reasonbert"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/reasonbert-pre-trained-to-reason-with-distant#ran","syntology_url":"https://syntology.ai/paper/2109.04912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04912"}}}},{"rank_in_archive_order":56,"model":"ReasonBERTB","metrics":{"F1":"37.2"},"uses_additional_data":false,"paper_date":"2021-09-10","paper":"/paper/reasonbert-pre-trained-to-reason-with-distant","paper_url":"https://arxiv.org/abs/2109.04912v1","paper_title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","code":"https://github.com/sunlab-osu/reasonbert","n_code_links":1,"official":{"repos":["sunlab-osu/reasonbert"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/reasonbert-pre-trained-to-reason-with-distant#ran","syntology_url":"https://syntology.ai/paper/2109.04912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04912"}}}}],"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), 40 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 1,580 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 20 proposed a result; of those 20, 18 gave no cell that passed the extractor's own checks, 2 were rejected by the independent check, 0 await 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":56,"metric_columns":2,"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":1580,"candidates":40,"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":20,"no_cell_passed_checks":18,"rejected_by_independent_check":2,"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; 20 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":20,"shown_on_page":20,"no_cell_split":{"no_cell_passed_checks_in_ledger":18,"rows_refused_by_rule":18,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.15745","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2609.00543","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2606.10537","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2606.10298","outcome":"refused_by_rule","reason":"several configurations of the method, and no metric direction to pick one"},{"arxiv_id":"2605.26952","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.18792","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.04984","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2604.18235","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2604.17555","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2604.15771","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2603.22293","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at; one configuration gave two values for one column"},{"arxiv_id":"2602.18734","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.15763","outcome":"rejected","reason":null},{"arxiv_id":"2602.03784","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.03689","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2601.22139","outcome":"refused_by_rule","reason":"several configurations of the method, and no metric direction to pick one"},{"arxiv_id":"2601.05038","outcome":"rejected","reason":null},{"arxiv_id":"2510.16079","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2509.19633","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2509.16598","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"}]},"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":27,"rows_with_any_sample_ran":26,"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":21,"rows_whose_official_repository_has_a_sample_that_ran":10,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":6,"rows_community_repositories_only":4,"rows_runs_from_other_or_unrecorded_repositories":4,"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":20,"distinct_papers_with_any_sample_ran":19,"distinct_papers_with_a_run_with_no_instrument_failure":16,"samples_over_distinct_papers":{"n_ran":235,"n_constructed":42,"n_ran_checked":168,"n_instrument":67,"n_unverified":104,"n_samples":339,"n_pointer_only_licence":85,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":429,"n_constructed":101,"n_ran_checked":308,"n_instrument":121,"n_unverified":182,"n_samples":611,"n_pointer_only_licence":110,"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":"93081955cb736da4c4904aad8bc1a105b58e247f850f41d8a7b49a971f72380c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}