{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T19:49:17Z","timestamp":1792007357986,"version":"4.4.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/tdmrep.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/iri69576.2026.00092","type":"proceedings-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T19:08:56Z","timestamp":1788980936000},"page":"466-471","source":"Crossref","is-referenced-by-count":0,"title":["SynthLineage: Submodular-Guided Corpus Distillation and Knowledge Graph Provenance for Collapse-Resistant LLM Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Vikash","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07566-y"},{"key":"ref2","article-title":"Is model collapse inevitable? Breaking the curse of recursion by accumulating real and synthetic data","volume-title":"Proc. Conf. Language Modeling (COLM)","author":"Gerstgrasser","year":"2024"},{"key":"ref3","article-title":"A tale of tails: Model collapse as a change of scaling laws","volume-title":"Proc. ICML","author":"Dohmatob","year":"2024"},{"key":"ref4","article-title":"A watermark for large language models","volume-title":"Proc. ICML","author":"Kirchenbauer","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588971"},{"key":"ref6","first-page":"427","article-title":"Adaptive submodularity: Theory and applications in active learning and stochastic optimization","volume":"42","author":"Golovin","year":"2011","journal-title":"J. Artif. Intell. Res."},{"key":"ref7","first-page":"510","article-title":"A class of submodular functions for document summarization","volume-title":"Proc. ACL","author":"Lin","year":"2011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00142"},{"key":"ref9","first-page":"6950","article-title":"Coresets for dataefficient training of machine learning models","volume-title":"Proc. ICML","author":"Mirzasoleiman","year":"2020"},{"issue":"140","key":"ref10","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","author":"Gao","year":"2021","journal-title":"The Pile: An 800GB dataset of diverse text for language modeling"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352100"},{"key":"ref14","article-title":"DetectGPT: Zero-shot machine-generated text detection using probability curvature","volume-title":"Proc. ICML","author":"Mitchell","year":"2023"},{"issue":"8","key":"ref15","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref16","author":"Sanh","year":"2019","journal-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter"},{"key":"ref17","article-title":"System Card: Claude Opus 4 & Claude Sonnet 4","volume-title":"Technical Report","year":"2025"}],"event":{"name":"2026 IEEE International Conference on Information Reuse and Integration for Data Science (IRI)","location":"Seattle, WA, USA","start":{"date-parts":[[2026,7,31]]},"end":{"date-parts":[[2026,8,2]]}},"container-title":["2026 IEEE International Conference on Information Reuse and Integration for Data Science (IRI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11676473\/11676601\/11676676.pdf?arnumber=11676676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T19:11:22Z","timestamp":1792005082000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11676676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iri69576.2026.00092","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}