{"entities":[{"id":"reward-modeling-paper","name":"Scalable agent alignment via reward modeling: a research direction","type":"document"},{"id":"concrete-problems-paper","name":"Concrete Problems in AI Safety","type":"document"},{"id":"miri-ml-agenda","name":"Alignment for Advanced Machine Learning Systems","type":"document"},{"id":"christian-szegedy","name":"Christian Szegedy","type":"person"},{"id":"kp-explaining-harnessing-adversarial-examples-2014","name":"Explaining and Harnessing Adversarial Examples","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-explaining-harnessing-adversarial-examples-2014-v1"]}],"claims":[{"id":"kp-states-explaining-harnessing-adversarial-examples-2014-1","subject":"kp-explaining-harnessing-adversarial-examples-2014","predicate":"states_contribution","object":{"kind":"literal","value":"The authors argue that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature."},"topic":"ideas","statement":"The authors argue that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature.","time":{"kind":"event","date":"2014-12-20","basis":"publication","note":"Date of the arXiv version quoted, submitted 20 December 2014 (UTC); later versions may word it differently."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-states-explaining-harnessing-adversarial-examples-2014-1-1"]},{"id":"kp-states-explaining-harnessing-adversarial-examples-2014-2","subject":"kp-explaining-harnessing-adversarial-examples-2014","predicate":"states_contribution","object":{"kind":"literal","value":"The paper states that this view yields a simple and fast method for generating adversarial examples."},"topic":"ideas","statement":"The paper states that this view yields a simple and fast method for generating adversarial examples.","time":{"kind":"event","date":"2014-12-20","basis":"publication","note":"Date of the arXiv version quoted, submitted 20 December 2014 (UTC); later versions may word it differently."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-states-explaining-harnessing-adversarial-examples-2014-2-1"]},{"id":"kp-cites-reward-modeling-paper-explaining-harnessing-adversarial-examples-2014","subject":"reward-modeling-paper","predicate":"cites","object":{"kind":"entity","entityId":"kp-explaining-harnessing-adversarial-examples-2014"},"topic":"ideas","statement":"Scalable agent alignment via reward modeling: a research direction cites Explaining and Harnessing Adversarial Examples.","time":{"kind":"event","date":"2018-11-19","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-reward-modeling-paper-explaining-harnessing-adversarial-examples-2014-1"]},{"id":"kp-cites-concrete-problems-paper-explaining-harnessing-adversarial-examples-2014","subject":"concrete-problems-paper","predicate":"cites","object":{"kind":"entity","entityId":"kp-explaining-harnessing-adversarial-examples-2014"},"topic":"ideas","statement":"Concrete Problems in AI Safety cites Explaining and Harnessing Adversarial Examples.","time":{"kind":"event","date":"2016-06-21","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-concrete-problems-paper-explaining-harnessing-adversarial-examples-2014-1"]},{"id":"kp-cites-miri-ml-agenda-explaining-harnessing-adversarial-examples-2014","subject":"miri-ml-agenda","predicate":"cites","object":{"kind":"entity","entityId":"kp-explaining-harnessing-adversarial-examples-2014"},"topic":"ideas","statement":"Alignment for Advanced Machine Learning Systems cites Explaining and Harnessing Adversarial Examples.","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-explaining-harnessing-adversarial-examples-2014-1"]},{"id":"kp-authored-christian-szegedy-explaining-harnessing-adversarial-examples-2014","subject":"christian-szegedy","predicate":"authored","object":{"kind":"entity","entityId":"kp-explaining-harnessing-adversarial-examples-2014"},"topic":"ideas","statement":"Christian Szegedy is a credited author of Explaining and Harnessing Adversarial Examples.","time":{"kind":"event","date":"2014-12-20","basis":"publication","note":"Date of the work’s earliest recorded version, arXiv version 1, submitted 20 December 2014 (UTC)."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-kp-authored-christian-szegedy-explaining-harnessing-adversarial-examples-2014-1"]}],"sources":[{"id":"source-kp-explaining-harnessing-adversarial-examples-2014-abs","documentId":"kp-explaining-harnessing-adversarial-examples-2014","title":"Explaining and Harnessing Adversarial Examples","authors":["arXiv"],"publisher":"arXiv","publicationDate":"2014-12-20","version":"arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 1b7f4280a1f50b26a9d2679dc879d5c6d5578237438439a2788560240c5d35de). Submission history as arXiv records it (UTC): v1 20 December 2014; v2 25 February 2015; v3 20 March 2015. 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/1412.6572","language":"en"},{"id":"source-kp-explaining-harnessing-adversarial-examples-2014-v1","documentId":"kp-explaining-harnessing-adversarial-examples-2014","title":"Explaining and Harnessing Adversarial Examples","authors":["Ian J. Goodfellow","Jonathon Shlens","Christian Szegedy"],"publisher":"arXiv","publicationDate":"2014-12-20","version":"arXiv:1412.6572v1, submitted 20 December 2014 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 abef582a0fc65807d3509af5315e071b1356506b54ba31862bbd6f9d5bd657fd). The author list is the byline as printed on the first page.","evidenceUrl":"https://arxiv.org/pdf/1412.6572v1","language":"en"},{"id":"source-kp-explaining-harnessing-adversarial-examples-2014-a035","documentId":"kp-explaining-harnessing-adversarial-examples-2014","title":"Explaining and Harnessing Adversarial Examples","authors":["International Conference on Learning Representations"],"publisher":"International Conference on Learning Representations","publicationDate":"2015","version":"ICLR 2015 (conference poster programme). ICLR 2015 published no proceedings volume; the programme lists the paper. Located by the cross-family machine check on 2026-10-30 (item A035; Conference poster programme, title entry), at the precision of its source; not read again at admission.","evidenceUrl":"https://iclr.cc/archive/www/2015.html","language":"en"}],"evidence":[{"id":"evidence-kp-states-explaining-harnessing-adversarial-examples-2014-1-1","claimId":"kp-states-explaining-harnessing-adversarial-examples-2014-1","sourceId":"source-kp-explaining-harnessing-adversarial-examples-2014-v1","sourceRole":"primary","support":"supports","locator":"arXiv v1, PDF p. 1, abstract","passage":"We argue instead that the primary cause of neural networks’ vulnerability to adversarial perturbation is their linear nature.","verification":"machine_checked"},{"id":"evidence-kp-states-explaining-harnessing-adversarial-examples-2014-2-1","claimId":"kp-states-explaining-harnessing-adversarial-examples-2014-2","sourceId":"source-kp-explaining-harnessing-adversarial-examples-2014-v1","sourceRole":"primary","support":"supports","locator":"arXiv v1, PDF p. 1, abstract","passage":"Moreover, this view yields a simple and fast method of generating adversarial examples.","verification":"machine_checked"},{"id":"evidence-kp-cites-reward-modeling-paper-explaining-harnessing-adversarial-examples-2014-1","claimId":"kp-cites-reward-modeling-paper-explaining-harnessing-adversarial-examples-2014","sourceId":"source-reward-modeling-paper-v1","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-cites-concrete-problems-paper-explaining-harnessing-adversarial-examples-2014-1","claimId":"kp-cites-concrete-problems-paper-explaining-harnessing-adversarial-examples-2014","sourceId":"source-concrete-problems-paper-v1","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-cites-miri-ml-agenda-explaining-harnessing-adversarial-examples-2014-1","claimId":"kp-cites-miri-ml-agenda-explaining-harnessing-adversarial-examples-2014","sourceId":"source-miri-ml-agenda","sourceRole":"primary","support":"supports","verification":"machine_checked"},{"id":"evidence-kp-authored-christian-szegedy-explaining-harnessing-adversarial-examples-2014-1","claimId":"kp-authored-christian-szegedy-explaining-harnessing-adversarial-examples-2014","sourceId":"source-kp-explaining-harnessing-adversarial-examples-2014-v1","sourceRole":"primary","support":"supports","verification":"machine_checked"}],"at":{"entities":[101,104,105,146,1530],"claims":[3875,3876,4456,4457,4458,4694],"sources":[1460,1461,1462],"evidence":[5333,5334,5914,5915,5916,6152]},"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"}