{"entities":[{"id":"weak-strong-paper","name":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","type":"document"},{"id":"miri-ml-agenda","name":"Alignment for Advanced Machine Learning Systems","type":"document"},{"id":"kp-why-should-i-trust-you-2016","name":"“Why Should I Trust You?”: Explaining the Predictions of Any Classifier","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-why-should-i-trust-you-2016-v1"]}],"claims":[{"id":"kp-states-why-should-i-trust-you-2016-1","subject":"kp-why-should-i-trust-you-2016","predicate":"states_contribution","object":{"kind":"literal","value":"The paper proposes LIME, an explanation technique that explains the predictions of any classifier by learning an interpretable model locally around a prediction."},"topic":"ideas","statement":"The paper proposes LIME, an explanation technique that explains the predictions of any classifier by learning an interpretable model locally around a prediction.","time":{"kind":"event","date":"2016-02-16","basis":"publication","note":"Date of the arXiv version quoted, submitted 16 February 2016 (UTC); later versions may word it differently."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-states-why-should-i-trust-you-2016-1-1"]},{"id":"kp-cites-weak-strong-paper-why-should-i-trust-you-2016","subject":"weak-strong-paper","predicate":"cites","object":{"kind":"entity","entityId":"kp-why-should-i-trust-you-2016"},"topic":"ideas","statement":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision cites “Why Should I Trust You?”: Explaining the Predictions of Any Classifier.","time":{"kind":"event","date":"2023-12-14","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-weak-strong-paper-why-should-i-trust-you-2016-1"]},{"id":"kp-cites-miri-ml-agenda-why-should-i-trust-you-2016","subject":"miri-ml-agenda","predicate":"cites","object":{"kind":"entity","entityId":"kp-why-should-i-trust-you-2016"},"topic":"ideas","statement":"Alignment for Advanced Machine Learning Systems cites “Why Should I Trust You?”: Explaining the Predictions of Any Classifier.","time":{"kind":"event","date":"2016","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-miri-ml-agenda-why-should-i-trust-you-2016-1"]}],"sources":[{"id":"source-kp-why-should-i-trust-you-2016-abs","documentId":"kp-why-should-i-trust-you-2016","title":"“Why Should I Trust You?”: Explaining the Predictions of Any Classifier","authors":["arXiv"],"publisher":"arXiv","publicationDate":"2016-02-16","version":"arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 79f281d30dc822ac9bc3959961a000a81e5136c1665d4aa6ea636ec9e49b9083). Submission history as arXiv records it (UTC): v1 16 February 2016; v2 3 August 2016; v3 9 August 2016. 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/1602.04938","language":"en"},{"id":"source-kp-why-should-i-trust-you-2016-v1","documentId":"kp-why-should-i-trust-you-2016","title":"“Why Should I Trust You?”: Explaining the Predictions of Any Classifier","authors":["Marco Tulio Ribeiro","Sameer Singh","Carlos Guestrin"],"publisher":"arXiv","publicationDate":"2016-02-16","version":"arXiv:1602.04938v1, submitted 16 February 2016 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 12bd2eed5c5e4820781be105392546f51c2776b5b339b7b05bd81599af2cabab). The author list is the byline as printed on the first page.","evidenceUrl":"https://arxiv.org/pdf/1602.04938v1","language":"en"},{"id":"source-kp-why-should-i-trust-you-2016-crossref","documentId":"kp-why-should-i-trust-you-2016","title":"“Why Should I Trust You?”: Explaining the Predictions of Any Classifier","authors":["Crossref"],"publisher":"Crossref","publicationDate":"2016","version":"Crossref record of the conference version: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135-1144 (DOI 10.1145/2939672.2939778), retrieved for the candidate pack on 2026-10-28. The date is the publisher-deposited date, kept at year precision; it was not checked against the issue.","evidenceUrl":"https://api.crossref.org/works/10.1145/2939672.2939778","language":"en"}],"evidence":[{"id":"evidence-kp-states-why-should-i-trust-you-2016-1-1","claimId":"kp-states-why-should-i-trust-you-2016-1","sourceId":"source-kp-why-should-i-trust-you-2016-v1","sourceRole":"primary","support":"supports","locator":"arXiv v1, PDF p. 1, abstract","passage":"In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally around the prediction.","verification":"machine_checked"},{"id":"evidence-kp-cites-weak-strong-paper-why-should-i-trust-you-2016-1","claimId":"kp-cites-weak-strong-paper-why-should-i-trust-you-2016","sourceId":"source-weak-strong-paper-v1","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-cites-miri-ml-agenda-why-should-i-trust-you-2016-1","claimId":"kp-cites-miri-ml-agenda-why-should-i-trust-you-2016","sourceId":"source-miri-ml-agenda","sourceRole":"primary","support":"supports","verification":"machine_checked"}],"at":{"entities":[103,105,1528],"claims":[3873,4452,4453],"sources":[1455,1456,1457],"evidence":[5331,5910,5911]},"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"}