{"entities":[{"id":"deepseek-v3-report","name":"DeepSeek-V3 Technical Report","type":"document"},{"id":"deepseek-r1-report","name":"DeepSeek-R1 research report","type":"document"},{"id":"ernie-5-report","name":"ERNIE 5.0 Technical Report","type":"document"},{"id":"kimi-k2-report","name":"Kimi K2: Open Agentic Intelligence","type":"document"},{"id":"sail-frontier-ai-risk-management-framework-v1-0","name":"Frontier AI Risk Management Framework (v1.0)","shortName":"Frontier AI Risk Management Framework · v1.0","type":"document","documentVersion":{"family":"sail-frontier-ai-risk-management-framework","label":"v1.0","publisherId":"shanghai-ai-lab","publishedAt":"2025-07","dateNote":"The document's citation line gives July 2025; no day is stated in the inspected text. A Chinese edition and a later v1.5 technical report exist but were not inspected."}},{"id":"seed-18-model-card","name":"Seed1.8 Model Card: Towards Generalized Real-World Agency","type":"document"},{"id":"kp-mmlu-pro-more-robust-challenging-2024","name":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","type":"document","subtype":"Research paper","description":"Work-level record. Its arXiv versions and any conference or journal version are listed as sources, each with its own date. A citation to the work does not identify which version the citing author read.","sourceIds":["source-kp-mmlu-pro-more-robust-challenging-2024-v1"]}],"claims":[{"id":"kp-states-mmlu-pro-more-robust-challenging-2024-1","subject":"kp-mmlu-pro-more-robust-challenging-2024","predicate":"states_contribution","object":{"kind":"literal","value":"The paper introduces MMLU-Pro, a dataset that extends the MMLU benchmark with more reasoning-focused questions and expands the answer choices from four to ten."},"topic":"ideas","statement":"The paper introduces MMLU-Pro, a dataset that extends the MMLU benchmark with more reasoning-focused questions and expands the answer choices from four to ten.","time":{"kind":"event","date":"2024-06-03","basis":"publication","note":"Date of the arXiv version quoted, submitted 3 June 2024 (UTC); later versions may word it differently."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-states-mmlu-pro-more-robust-challenging-2024-1-1"]},{"id":"kp-cites-deepseek-v3-report-mmlu-pro-more-robust-challenging-2024","subject":"deepseek-v3-report","predicate":"cites","object":{"kind":"entity","entityId":"kp-mmlu-pro-more-robust-challenging-2024"},"topic":"ideas","statement":"DeepSeek-V3 Technical Report cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.","time":{"kind":"event","date":"2024-12-27","basis":"publication","note":"Date of the citing source as recorded in the dataset; unknown where the dataset has none."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-cites-deepseek-v3-report-mmlu-pro-more-robust-challenging-2024-1"]},{"id":"kp-cites-deepseek-r1-report-mmlu-pro-more-robust-challenging-2024","subject":"deepseek-r1-report","predicate":"cites","object":{"kind":"entity","entityId":"kp-mmlu-pro-more-robust-challenging-2024"},"topic":"ideas","statement":"DeepSeek-R1 research report cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.","time":{"kind":"event","date":"2025-01-22","basis":"publication","note":"Date of the citing source as recorded in the dataset; unknown where the dataset has none."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-cites-deepseek-r1-report-mmlu-pro-more-robust-challenging-2024-1"]},{"id":"kp-cites-ernie-5-report-mmlu-pro-more-robust-challenging-2024","subject":"ernie-5-report","predicate":"cites","object":{"kind":"entity","entityId":"kp-mmlu-pro-more-robust-challenging-2024"},"topic":"ideas","statement":"ERNIE 5.0 Technical Report cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.","time":{"kind":"event","date":"2026-02-04","basis":"publication","note":"Date of the citing source as recorded in the dataset; unknown where the dataset has none."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-cites-ernie-5-report-mmlu-pro-more-robust-challenging-2024-1"]},{"id":"kp-cites-kimi-k2-report-mmlu-pro-more-robust-challenging-2024","subject":"kimi-k2-report","predicate":"cites","object":{"kind":"entity","entityId":"kp-mmlu-pro-more-robust-challenging-2024"},"topic":"ideas","statement":"Kimi K2: Open Agentic Intelligence cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.","time":{"kind":"event","date":"2025-07-28","basis":"publication","note":"Date of the citing source as recorded in the dataset; unknown where the dataset has none."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-cites-kimi-k2-report-mmlu-pro-more-robust-challenging-2024-1"]},{"id":"kp-cites-sail-frontier-ai-risk-management-framework-v1-0-mmlu-pro-more-robust-challenging-2024","subject":"sail-frontier-ai-risk-management-framework-v1-0","predicate":"cites","object":{"kind":"entity","entityId":"kp-mmlu-pro-more-robust-challenging-2024"},"topic":"ideas","statement":"Frontier AI Risk Management Framework (v1.0) cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.","time":{"kind":"event","date":"2025-07","basis":"publication","note":"Date of the citing source as recorded in the dataset; unknown where the dataset has none."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-cites-sail-frontier-ai-risk-management-framework-v1-0-mmlu-pro-more-robust-challenging-2024-1"]},{"id":"kp-cites-seed-18-model-card-mmlu-pro-more-robust-challenging-2024","subject":"seed-18-model-card","predicate":"cites","object":{"kind":"entity","entityId":"kp-mmlu-pro-more-robust-challenging-2024"},"topic":"ideas","statement":"Seed1.8 Model Card: Towards Generalized Real-World Agency cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.","time":{"kind":"event","date":"2026-03-21","basis":"publication","note":"Date of the citing source as recorded in the dataset; unknown where the dataset has none."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-cites-seed-18-model-card-mmlu-pro-more-robust-challenging-2024-1"]}],"sources":[{"id":"source-kp-mmlu-pro-more-robust-challenging-2024-abs","documentId":"kp-mmlu-pro-more-robust-challenging-2024","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","authors":["arXiv"],"publisher":"arXiv","publicationDate":"2024-06-03","version":"arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 1a27b66c661db5cdcd1448e98ab515354377e8de82a275875213a9af50c70953). Submission history as arXiv records it (UTC): v1 3 June 2024; v2 4 June 2024; v3 5 June 2024; v4 23 June 2024; v5 7 October 2024; v6 6 November 2024. The page serves the latest version; each version is a separate expression, and only the one a record names was read.","evidenceUrl":"https://arxiv.org/abs/2406.01574","language":"en"},{"id":"source-kp-mmlu-pro-more-robust-challenging-2024-v1","documentId":"kp-mmlu-pro-more-robust-challenging-2024","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","authors":["Yubo Wang","Xueguang Ma","Ge Zhang","Yuansheng Ni","Abhranil Chandra","Shiguang Guo","Weiming Ren","Aaran Arulraj","Xuan He","Ziyan Jiang","Tianle Li","Max Ku","Kai Wang","Alex Zhuang","Rongqi Fan","Xiang Yue","Wenhu Chen"],"publisher":"arXiv","publicationDate":"2024-06-03","version":"arXiv:2406.01574v1, submitted 3 June 2024 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 9bf7b08bf1c220cb6c1ed0dcafb7d10848a21178137e13dd5e13981d8ecd15e3). The author list is the byline as printed on the first page.","evidenceUrl":"https://arxiv.org/pdf/2406.01574v1","language":"en"},{"id":"source-kp-mmlu-pro-more-robust-challenging-2024-a043","documentId":"kp-mmlu-pro-more-robust-challenging-2024","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","authors":["Neural Information Processing Systems"],"publisher":"Neural Information Processing Systems","publicationDate":"2024","version":"Advances in Neural Information Processing Systems 37, Datasets and Benchmarks Track. Located by the cross-family machine check on 2026-10-30 (item A043; Proceedings heading), at the precision of its source; not read again at admission.","evidenceUrl":"https://proceedings.neurips.cc/paper_files/paper/2024/hash/ad236edc564f3e3156e1b2feafb99a24-Abstract-Datasets_and_Benchmarks_Track.html","language":"en"}],"evidence":[{"id":"evidence-kp-states-mmlu-pro-more-robust-challenging-2024-1-1","claimId":"kp-states-mmlu-pro-more-robust-challenging-2024-1","sourceId":"source-kp-mmlu-pro-more-robust-challenging-2024-v1","sourceRole":"primary","support":"supports","locator":"arXiv v1, PDF p. 1, abstract","passage":"This paper introduces MMLU-Pro, an enhanced dataset designed to extend the mostly knowledge-driven MMLU benchmark by integrating more challenging, reasoning-focused questions and expanding the choice set from four to ten options.","verification":"machine_checked"},{"id":"evidence-kp-cites-deepseek-v3-report-mmlu-pro-more-robust-challenging-2024-1","claimId":"kp-cites-deepseek-v3-report-mmlu-pro-more-robust-challenging-2024","sourceId":"source-cn-v3","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-cites-deepseek-r1-report-mmlu-pro-more-robust-challenging-2024-1","claimId":"kp-cites-deepseek-r1-report-mmlu-pro-more-robust-challenging-2024","sourceId":"source-cn-r1","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-cites-ernie-5-report-mmlu-pro-more-robust-challenging-2024-1","claimId":"kp-cites-ernie-5-report-mmlu-pro-more-robust-challenging-2024","sourceId":"c2-src-ernie5-arxiv-v1","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-cites-kimi-k2-report-mmlu-pro-more-robust-challenging-2024-1","claimId":"kp-cites-kimi-k2-report-mmlu-pro-more-robust-challenging-2024","sourceId":"c2-src-kimi-k2-pdf-v1","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-cites-sail-frontier-ai-risk-management-framework-v1-0-mmlu-pro-more-robust-challenging-2024-1","claimId":"kp-cites-sail-frontier-ai-risk-management-framework-v1-0-mmlu-pro-more-robust-challenging-2024","sourceId":"c2-src-sail-frmf-v1-en","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-cites-seed-18-model-card-mmlu-pro-more-robust-challenging-2024-1","claimId":"kp-cites-seed-18-model-card-mmlu-pro-more-robust-challenging-2024","sourceId":"c2-src-seed-18-arxiv-v1","sourceRole":"primary","support":"supports","verification":"machine_checked"}],"at":{"entities":[175,176,952,964,989,991,1473],"claims":[3795,4235,4236,4237,4238,4239,4240],"sources":[1311,1312,1313],"evidence":[5253,5693,5694,5695,5696,5697,5698]},"index":{"byClaim":[],"marks":[],"chronicle":{"years":[{"year":1863,"topics":{"ideas":5},"stated":0},{"year":1865,"topics":{"ideas":1},"stated":0},{"year":1872,"topics":{"ideas":7},"stated":0},{"year":1943,"topics":{"ideas":1},"stated":0},{"year":1947,"topics":{"ideas":2},"stated":0},{"year":1950,"topics":{"ideas":7},"stated":0},{"year":1951,"topics":{"ideas":5},"stated":0},{"year":1952,"topics":{"ideas":2},"stated":0},{"year":1955,"topics":{"ideas":31},"stated":0},{"year":1956,"topics":{"ideas":1},"stated":0},{"year":1957,"topics":{"ideas":1},"stated":0},{"year":1958,"topics":{"ideas":3},"stated":0},{"year":1959,"topics":{"ideas":6},"stated":0},{"year":1960,"topics":{"ideas":11},"stated":0},{"year":1961,"topics":{"ideas":10},"stated":0},{"year":1965,"topics":{"ideas":8},"stated":0},{"year":1966,"topics":{"ideas":20},"stated":0},{"year":1968,"topics":{"ideas":5},"stated":0},{"year":1969,"topics":{"ideas":2},"stated":0},{"year":1971,"topics":{"ideas":4},"stated":0},{"year":1972,"topics":{"ideas":1},"stated":0},{"year":1973,"topics":{"ideas":2},"stated":0},{"year":1974,"topics":{"ideas":2},"stated":0},{"year":1975,"topics":{"ideas":1},"stated":0},{"year":1976,"topics":{"ideas":1},"stated":0},{"year":1977,"topics":{"people":2,"ideas":8},"stated":0},{"year":1979,"topics":{"ideas":4},"stated":0},{"year":1980,"topics":{"ideas":2},"stated":0},{"year":1981,"topics":{"people":2},"stated":0},{"year":1982,"topics":{"ideas":4},"stated":0},{"year":1983,"topics":{"ideas":4},"stated":0},{"year":1984,"topics":{"ideas":21},"stated":0},{"year":1985,"topics":{"ideas":9},"stated":0},{"year":1986,"topics":{"ideas":18},"stated":0},{"year":1987,"topics":{"ideas":1},"stated":0},{"year":1988,"topics":{"ideas":6},"stated":0},{"year":1989,"topics":{"ideas":8},"stated":0},{"year":1990,"topics":{"ideas":5},"stated":0},{"year":1991,"topics":{"ideas":11},"stated":0},{"year":1992,"topics":{"ideas":9},"stated":0},{"year":1993,"topics":{"ideas":14,"people":3},"stated":0},{"year":1994,"topics":{"ideas":14},"stated":0},{"year":1995,"topics":{"ideas":10,"people":1},"stated":0},{"year":1996,"topics":{"ideas":71},"stated":0},{"year":1997,"topics":{"ideas":12},"stated":0},{"year":1998,"topics":{"ideas":49},"stated":0},{"year":1999,"topics":{"ideas":27,"people":1,"institutions":1},"stated":0},{"year":2000,"topics":{"ideas":62},"stated":0},{"year":2001,"topics":{"ideas":39},"stated":0},{"year":2002,"topics":{"ideas":30},"stated":0},{"year":2003,"topics":{"ideas":8},"stated":0},{"year":2004,"topics":{"ideas":12,"people":3},"stated":0},{"year":2005,"topics":{"ideas":10,"people":1},"stated":0},{"year":2006,"topics":{"ideas":26,"people":1},"stated":0},{"year":2007,"topics":{"ideas":20},"stated":0},{"year":2008,"topics":{"ideas":57,"people":3,"institutions":1},"stated":0},{"year":2009,"topics":{"ideas":10,"people":1},"stated":0},{"year":2010,"topics":{"people":3,"ideas":11,"institutions":1,"governance":4},"stated":0},{"year":2011,"topics":{"people":3,"ideas":7,"institutions":2},"stated":0},{"year":2012,"topics":{"people":4,"ideas":17,"institutions":2},"stated":0},{"year":2013,"topics":{"ideas":46,"people":4,"institutions":2,"capital":1},"stated":0},{"year":2014,"topics":{"institutions":2,"ideas":54,"people":5},"stated":0},{"year":2015,"topics":{"people":22,"ideas":122,"institutions":3,"capital":1},"stated":0},{"year":2016,"topics":{"ideas":88,"people":2},"stated":0},{"year":2017,"topics":{"people":16,"institutions":2,"ideas":128,"governance":2},"stated":0},{"year":2018,"topics":{"people":8,"ideas":158,"institutions":8,"governance":1},"stated":0},{"year":2019,"topics":{"capital":1,"compute":1,"people":10,"governance":19,"ideas":175,"institutions":4},"stated":0},{"year":2020,"topics":{"people":6,"ideas":98,"institutions":1,"governance":2},"stated":0},{"year":2021,"topics":{"people":27,"ideas":177,"compute":1,"institutions":23,"governance":4,"capital":6},"stated":0},{"year":2022,"topics":{"people":15,"ideas":217,"institutions":6,"governance":3,"compute":2,"capital":1},"stated":0},{"year":2023,"topics":{"capital":5,"compute":7,"institutions":23,"people":51,"governance":179,"ideas":389},"stated":0},{"year":2024,"topics":{"capital":12,"compute":19,"governance":282,"people":80,"ideas":178,"institutions":28},"stated":1},{"year":2025,"topics":{"governance":547,"compute":69,"capital":34,"people":90,"institutions":18,"ideas":178},"stated":7},{"year":2026,"topics":{"governance":442,"capital":8,"compute":32,"institutions":21,"ideas":91,"people":107},"stated":19},{"year":2027,"topics":{},"stated":9},{"year":2028,"topics":{},"stated":6},{"year":2029,"topics":{},"stated":3},{"year":2030,"topics":{},"stated":3},{"year":2032,"topics":{},"stated":2},{"year":2035,"topics":{},"stated":2},{"year":2039,"topics":{},"stated":1},{"year":2042,"topics":{},"stated":1},{"year":2050,"topics":{},"stated":1}],"scheduled":[],"statedBy":[]},"collections":[{"target":{"kind":"propositions","id":"superintelligence"},"title":"Propositions about superintelligence, 1863–2022","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"risk-debate"},"title":"Arguments about catastrophic risk from advanced AI","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"yudkowsky-arguments"},"title":"Eliezer Yudkowsky’s arguments on common claims about AI, 1996–2026","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"economics-of-machine-intelligence"},"title":"Economics of machine intelligence","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"orbital-compute-arguments"},"title":"Arguments about compute in orbit","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"ai-bio-arguments"},"title":"Arguments about AI and biological risk","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"ai-in-science"},"title":"AI in science","claimIds":[],"records":[]},{"target":{"kind":"documents"},"title":"Frontier safety frameworks","claimIds":[]},{"target":{"kind":"compare","id":"frontier-safety-frameworks"},"title":"Compare frameworks","claimIds":[]},{"target":{"kind":"control","id":"openai"},"title":"OpenAI’s control structure, 2015–2026","claimIds":[]},{"target":{"kind":"control","id":"anthropic"},"title":"Anthropic’s control structure, 2021–2026","claimIds":[]},{"target":{"kind":"commitments"},"title":"External commitments and obligations","claimIds":[]},{"target":{"kind":"question","id":"frameworks-to-obligations"},"title":"Frameworks, commitments and legal obligations, 2023–2026","claimIds":[]},{"target":{"kind":"reading"},"title":"Founding and early leadership","claimIds":[]}]},"version":"131evrz"}