{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:35:15Z","timestamp":1780511715634,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["PHY-2112890"],"award-info":[{"award-number":["PHY-2112890"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DARPA Grant through Modeling and Measuring Scientific Creativity"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/jstsp.2025.3626264","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:12:04Z","timestamp":1761930724000},"page":"1338-1348","source":"Crossref","is-referenced-by-count":4,"title":["An Information Theory of Compute-Optimal Size Scaling, Emergence, and Plateaus in Language Models"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7657-4348","authenticated-orcid":false,"given":"Anuj K.","family":"Nayak","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2798-5308","authenticated-orcid":false,"given":"Lav R.","family":"Varshney","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref2","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5962\/bhl.title.11332"},{"key":"ref4","first-page":"425","article-title":"On being the right size","volume":"152","author":"Haldane","year":"1926","journal-title":"Harpers Mag."},{"key":"ref5","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022"},{"key":"ref6","first-page":"55565","article-title":"Are emergent abilities of large language models a mirage?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Schaeffer","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/9789814415255_0002"},{"key":"ref8","article-title":"AI doom from an LLM-plateau-ist perspective","author":"Byrnes","year":"2023"},{"key":"ref9","article-title":"The first wave of AI innovation is over. heres what comes next","author":"Ritter","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511606267"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/339693a0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511791338"},{"key":"ref13","volume-title":"Network Science","author":"Barabsi","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref15","article-title":"Transformers are universal predictors","volume-title":"Proc. Neural Compression Workshop at ICML","author":"Basu","year":"2023"},{"key":"ref16","article-title":"A theory for emergence of complex skills in language models","author":"Arora","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3559118"},{"key":"ref18","first-page":"28699","article-title":"The quantization model of neural scaling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Michaud","year":"2023"},{"key":"ref19","article-title":"Skill-mix: A flexible and expandable family of evaluations for AI models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2024"},{"key":"ref20","first-page":"4345","article-title":"A dynamical model of neural scaling laws","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Bordelon","year":"2024"},{"key":"ref21","article-title":"Circuit tracing: Revealing computational graphs in language models","author":"Marks","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref23","volume-title":"Unified Theories of Cognition","author":"Newell","year":"1990"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(87)90050-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.4324\/9781315806938"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1207\/s15327051hci1204_4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2002.1003839"},{"key":"ref28","article-title":"Algorithmic progress in language models","author":"Ho","year":"2024"},{"key":"ref29","article-title":"On the limitations of compute thresholds as a governance strategy","author":"Hooker","year":"2024"},{"key":"ref30","article-title":"Iterative quantization using codes on graphs","volume-title":"Proc. 41st Annu. Allerton Conf. Communication, Control, Comput.","author":"Martinian","year":"2003"},{"key":"ref31","first-page":"1682","article-title":"Noise-enhanced associative memories","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Karbasi","year":"2013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14277"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2008.2009580"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ITA50056.2020.9245012"},{"key":"ref35","article-title":"Unified view of grokking, double descent and emergent abilities: A comprehensive study on algorithm task","volume-title":"Proc. Conf. Lang. Model.","author":"Huang","year":"2024"},{"issue":"47","key":"ref36","first-page":"1","article-title":"A group-theoretic approach to computational abstraction: Symmetry-driven hierarchical clustering","volume":"24","author":"Yu","year":"2023","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/4200690\/11320985\/11223775-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11320985\/11223775.pdf?arnumber=11223775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T20:59:48Z","timestamp":1770929988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223775\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":36,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3626264","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}