{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T05:12:26Z","timestamp":1783746746458,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2223704"],"award-info":[{"award-number":["2223704"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2331152"],"award-info":[{"award-number":["2331152"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2449103"],"award-info":[{"award-number":["2449103"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2530461"],"award-info":[{"award-number":["2530461"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,13]]},"DOI":"10.1145\/3806645.3807587","type":"proceedings-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:21:11Z","timestamp":1783743671000},"page":"279-291","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Merkle-Tree Weight Snapshot Deduplication for Provenance-Aware Auditing of Neural Network Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9784-8427","authenticated-orcid":false,"given":"Kin Wai","family":"Ng","sequence":"first","affiliation":[{"name":"University of Tennessee, Knoxville, Knoxville, TN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1125-0588","authenticated-orcid":false,"given":"Francesco","family":"Antici","sequence":"additional","affiliation":[{"name":"Riken R-CCS, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4699-8657","authenticated-orcid":false,"given":"Nigel","family":"Tan","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1007-9384","authenticated-orcid":false,"given":"Befikir","family":"Bogale","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Knoxville, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5970-5684","authenticated-orcid":false,"given":"Caleb","family":"Han","sequence":"additional","affiliation":[{"name":"University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2021-5618","authenticated-orcid":false,"given":"Florence","family":"Tama","sequence":"additional","affiliation":[{"name":"Riken R-CCS, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2530-5674","authenticated-orcid":false,"given":"Osamu","family":"Miyashita","sequence":"additional","affiliation":[{"name":"Riken R-CCS, Wako, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7509","authenticated-orcid":false,"given":"Bogdan","family":"Nicolae","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0031-6377","authenticated-orcid":false,"given":"Michela","family":"Taufer","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Knoxville, TN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTERWorkshops61457.2023.00020"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Bj\u00f6rn Barz and Joachim Denzler. 2020. Do We Train on Test Data? Purging CIFAR of Near-duplicates. Journal of Imaging 6 6 (2020).","DOI":"10.3390\/jimaging6060041"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063427"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605636"},{"key":"e_1_3_3_2_6_2","unstructured":"Georgia Channing Ria Patel and Michela Taufer. 2023. Architecture Descriptions Model Checkpoints and Training Histories for A4NN Workflow on Protein Diffraction Data. https:\/\/doi.org\/10.7910\/DVN\/JS9FR6. Harvard Dataverse."},{"key":"e_1_3_3_2_7_2","unstructured":"V\u00edctor Cuevas-Vicentt\u00edn Bertram Lud\u00e4scher Paolo Missier Khalid Belhajjame Fernando Chirigati Yaxing Wei Saumen Dey Parisa Kianmajd David Koop Shawn Bowers Ilkay Altintas Christopher Jones Matthew\u00a0B. Jones Lauren Walker Peter Slaughter Ben Leinfelder and Yang Cao. 2016. ProvONE: A PROV Extension Data Model for Scientific Workflow Provenance. https:\/\/jenkins-1.dataone.org\/jenkins\/job\/ProvONE-Documentation-1.0.0\/ws\/provenance\/ProvONE\/v1\/provone.html. Version 1."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376772"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.5555\/2832581.2832731"},{"key":"e_1_3_3_2_10_2","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Eisenman Assaf","year":"2022","unstructured":"Assaf Eisenman, Kiran\u00a0Kumar Matam, Steven Ingram, Dheevatsa Mudigere, Raghuraman Krishnamoorthi, Krishnakumar Nair, Misha Smelyanskiy, and Murali Annavaram. 2022. Check-N-Run: a Checkpointing System for Training Deep Learning Recommendation Models. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, USA."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807612"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Xin He Kaiyong Zhao and Xiaowen Chu. 2021. AutoML: A Survey of the State-of-the-Art. Knowledge-based Systems 212 (2021).","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"e_1_3_3_2_13_2","unstructured":"Konstantinos Katsiapis Abhijit Karmarkar Ahmet Altay Aleksandr Zaks Neoklis Polyzotis Anusha Ramesh Ben Mathes Gautam Vasudevan Irene Giannoumis Jarek Wilkiewicz Jiri Simsa Justin Hong Mitchell Trott No\u00e9 Lutz Pavel\u00a0A. Dournov Robert Crowe Sarah Sirajuddin Tris\u00a0Brian Warkentin and Zhitao Li. 2020. Towards ML Engineering: A Brief History Of TensorFlow Extended (TFX). arxiv:https:\/\/arXiv.org\/abs\/2010.02013https:\/\/arxiv.org\/pdf\/2010.02013"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Ravneet Kaur Inderveer Chana and Jhilik Bhattacharya. 2018. Data Deduplication Techniques for Efficient Cloud Storage Management: A Systematic Review. The Journal of Supercomputing 74 5 (2018).","DOI":"10.1007\/s11227-017-2210-8"},{"key":"e_1_3_3_2_15_2","volume-title":"International Conference on Learning Representations","author":"Klein Aaron","year":"2017","unstructured":"Aaron Klein, Stefan Falkner, Jost\u00a0Tobias Springenberg, and Frank Hutter. 2017. Learning Curve Prediction with Bayesian Neural Networks. In International Conference on Learning Representations. OpenReview.net, Toulon, France."},{"key":"e_1_3_3_2_16_2","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning Multiple Layers of Features from Tiny Images. https:\/\/www.cs.toronto.edu\/\u00a0kriz\/learning-features-2009-TR.pdf. Technical report University of Toronto."},{"key":"e_1_3_3_2_17_2","volume-title":"12th USENIX Conference on File and Storage Technologies (FAST 14)","author":"Lin Xing","year":"2014","unstructured":"Xing Lin, Guanlin Lu, Fred Douglis, Philip Shilane, and Grant Wallace. 2014. Migratory Compression: Coarse-grained Data Reordering to Improve Compressibility. In 12th USENIX Conference on File and Storage Technologies (FAST 14). USENIX Association, Santa Clara, CA, USA."},{"key":"e_1_3_3_2_18_2","volume-title":"International Conference on Learning Representations","author":"Liu Hanxiao","year":"2019","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2019. DARTS: Differentiable Architecture Search. In International Conference on Learning Representations. OpenReview.net, New Orleans, LA, USA."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321729"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Peter Mattson Vijay\u00a0Janapa Reddi Christine Cheng Cody Coleman Greg Diamos David Kanter Paulius Micikevicius David Patterson Guenther Schmuelling Hanlin Tang Gu-Yeon Wei and Carole-Jean Wu. 2020. MLPerf: An Industry Standard Benchmark Suite for Machine Learning Performance. IEEE Micro 40 2 (2020).","DOI":"10.1109\/MM.2020.2974843"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48184-2_32"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Wellington Oliveira Daniel\u00a0De Oliveira and Vanessa Braganholo. 2018. Provenance Analytics for Workflow-Based Computational Experiments: A Survey. Comput. Surveys 51 (2018).","DOI":"10.1145\/3184900"},{"key":"e_1_3_3_2_25_2","volume-title":"2020 USENIX Conference on Operational Machine Learning (OpML 20)","author":"Ormenisan Alexandru\u00a0A.","year":"2020","unstructured":"Alexandru\u00a0A. Ormenisan, Moritz Meister, Fabio Buso, Robin Andersson, Seif Haridi, and Jim Dowling. 2020. Time Travel and Provenance for Machine Learning Pipelines. In 2020 USENIX Conference on Operational Machine Learning (OpML 20). USENIX Association, Virtual."},{"key":"e_1_3_3_2_26_2","volume-title":"NIPS 2017 Workshop on Autodiff","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic Differentiation in PyTorch. In NIPS 2017 Workshop on Autodiff. OpenReview.net, Long Beach, CA, USA."},{"key":"e_1_3_3_2_27_2","series-title":"Proceedings of Machine Learning Research","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Pham Hieu","year":"2018","unstructured":"Hieu Pham, Melody Guan, Barret Zoph, Quoc Le, and Jeff Dean. 2018. Efficient Neural Architecture Search via Parameters Sharing. In Proceedings of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a080). PMLR, Stockholm, Sweden."},{"key":"e_1_3_3_2_28_2","unstructured":"Joelle Pineau Philippe Vincent-Lamarre Koustuv Sinha Vincent Larivi\u00e8re Alina Beygelzimer Florence d\u2019Alch\u00e9 Buc Emily Fox and Hugo Larochelle. 2021. Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program). The Journal of Machine Learning Research 22 1 (2021)."},{"key":"e_1_3_3_2_29_2","volume-title":"Conference on File and Storage Technologies (FAST 02)","author":"Quinlan Sean","year":"2002","unstructured":"Sean Quinlan and Sean Dorward. 2002. Venti: A New Approach to Archival Data Storage. In Conference on File and Storage Technologies (FAST 02). USENIX Association, Monterey, CA, USA."},{"key":"e_1_3_3_2_30_2","unstructured":"Elvis Rojas Albert\u00a0Njoroge Kahira Esteban Meneses Leonardo\u00a0Bautista Gomez and Rosa\u00a0M Badia. 2020. A Study of Checkpointing in Large Scale Training of Deep Learning Models. https:\/\/arxiv.org\/abs\/2012.00825"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Florian Scheidegger Roxana Istrate Giovanni Mariani Luca Benini Costas Bekas and Cristiano Malossi. 2020. Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-learning Accuracy. The Visual Computer 37 (2020).","DOI":"10.1007\/s00371-020-01922-5"},{"key":"e_1_3_3_2_32_2","volume-title":"Workshop on Machine Learning Systems (LearningSys) at the 31st Conference on Neural Information Processing Systems (NIPS 2017)","author":"Schelter Sebastian","year":"2017","unstructured":"Sebastian Schelter and Jan B\u00f6se. 2017. Automatically Tracking Metadata and Provenance of Machine Learning Experiments. In Workshop on Machine Learning Systems (LearningSys) at the 31st Conference on Neural Information Processing Systems (NIPS 2017). Association for Computing Machinery, Long Beach, CA, USA."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Renan Souza Leonardo\u00a0G. Azevedo V\u00edtor Louren\u00e7o Elton Soares Raphael Thiago Rafael Brand\u00e3o Daniel Civitarese Emilio Vital\u00a0Brazil Marcio Moreno Patrick Valduriez Marta Mattoso Renato Cerqueira and Marco A.\u00a0S. Netto. 2022. Workflow Provenance in the Lifecycle of Scientific Machine Learning. Concurrency and Computation: Practice and Experience 34 14 (2022).","DOI":"10.1002\/cpe.6544"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652892.3700780"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605639"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.115"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Dingwen Tao Sheng Di Xin Liang Zizhong Chen and Franck Cappello. 2019. Optimizing Lossy Compression Rate-Distortion from Automatic Online Selection between SZ and ZFP. IEEE Transactions on Parallel and Distributed Systems 30 8 (2019).","DOI":"10.1109\/TPDS.2019.2894404"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Antonio Torralba Rob Fergus and William\u00a0T Freeman. 2008. 80 Million Tiny Images: A Large Dataset for Nonparametric Object and Scene Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 30 11 (2008).","DOI":"10.1109\/TPAMI.2008.128"},{"key":"e_1_3_3_2_39_2","unstructured":"Mark\u00a0D. Wilkinson Michel Dumontier IJsbrand\u00a0Jan Aalbersberg Gabrielle Appleton Myles Axton Arie Baak Niklas Blomberg Jan-Willem Boiten Luiz\u00a0Bonino da Silva\u00a0Santos Philip\u00a0E. Bourne Jildau Bouwman Anthony\u00a0J. Brookes Tim Clark Merce Crosas Ingrid Dillo Olivier Dumon Scott Edmunds Chris\u00a0T. Evelo Richard Finkers Alejandra Gonzalez-Beltran Alasdair J.\u00a0G. Gray Paul Groth Carole Goble Jeffrey\u00a0S. Grethe Jaap Heringa Peter A.\u00a0C. \u2019t Hoen Rob Hooft Tobias Kuhn Ruben Kok Joost Kok Scott\u00a0J. Lusher Maryann\u00a0E. Martone Albert Mons Abel\u00a0L. Packer Bengt Persson Philippe Rocca-Serra Marco Roos Rene van Schaik Susanna-Assunta Sansone Erik Schultes Thierry Sengstag Ted Slater George Strawn Morris\u00a0A. Swertz Mark Thompson Johan van\u00a0der Lei Erik van Mulligen Jan Velterop Andra Waagmeester Peter Wittenburg Katherine Wolstencroft Jun Zhao and Barend Mons. 2016. The FAIR Guiding Principles for Scientific Data Management and Stewardship. Scientific Data 3 1 (2016)."},{"key":"e_1_3_3_2_40_2","volume-title":"International Conference on Learning Representations","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc Le. 2017. Neural Architecture Search with Reinforcement Learning. In International Conference on Learning Representations. OpenReview.net, Toulon, France."}],"event":{"name":"HPDC '26: 35th International Symposium on High-Performance Parallel and Distributed Computing","location":"Cleveland USA","acronym":"HPDC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:24:52Z","timestamp":1783743892000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806645.3807587"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":39,"alternative-id":["10.1145\/3806645.3807587","10.1145\/3806645"],"URL":"https:\/\/doi.org\/10.1145\/3806645.3807587","relation":{},"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"2026-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}