{"id":"https://openalex.org/W7168019556","doi":"https://doi.org/10.1145/3806645.3807587","title":"Merkle-Tree Weight Snapshot Deduplication for Provenance-Aware Auditing of Neural Network Training","display_name":"Merkle-Tree Weight Snapshot Deduplication for Provenance-Aware Auditing of Neural Network Training","publication_year":2026,"publication_date":"2026-07-11","ids":{"openalex":"https://openalex.org/W7168019556","doi":"https://doi.org/10.1145/3806645.3807587"},"language":null,"primary_location":{"id":"doi:10.1145/3806645.3807587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3807587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3806645.3807587","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036896676","display_name":"Kin Wai Ng","orcid":"https://orcid.org/0000-0001-9784-8427"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kin Wai Ng","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0001-9784-8427","affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, TN, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030560727","display_name":"Francesco Antici","orcid":"https://orcid.org/0000-0002-1125-0588"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Francesco Antici","raw_affiliation_strings":["Riken R-CCS, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1125-0588","affiliations":[{"raw_affiliation_string":"Riken R-CCS, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019570466","display_name":"Nigel Tan","orcid":"https://orcid.org/0000-0003-4699-8657"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nigel Tan","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":"https://orcid.org/0000-0003-4699-8657","affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093240750","display_name":"Befikir Bogale","orcid":"https://orcid.org/0000-0003-1007-9384"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Befikir Bogale","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0003-1007-9384","affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140459144","display_name":"Caleb Han","orcid":"https://orcid.org/0009-0001-5970-5684"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caleb Han","raw_affiliation_strings":["University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":"https://orcid.org/0009-0001-5970-5684","affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090638713","display_name":"Florence Tama","orcid":"https://orcid.org/0000-0003-2021-5618"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Florence Tama","raw_affiliation_strings":["Riken R-CCS, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2021-5618","affiliations":[{"raw_affiliation_string":"Riken R-CCS, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036207834","display_name":"Osamu Miyashita","orcid":"https://orcid.org/0000-0002-2530-5674"},"institutions":[{"id":"https://openalex.org/I4210162022","display_name":"RIKEN Nishina Center","ror":"https://ror.org/05tqx4s13","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210162022"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Osamu Miyashita","raw_affiliation_strings":["Riken R-CCS, Wako, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2530-5674","affiliations":[{"raw_affiliation_string":"Riken R-CCS, Wako, Japan","institution_ids":["https://openalex.org/I4210162022"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085745891","display_name":"Bogdan Nicolae","orcid":"https://orcid.org/0000-0002-0661-7509"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bogdan Nicolae","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0661-7509","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078387820","display_name":"Michela Taufer","orcid":"https://orcid.org/0000-0002-0031-6377"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michela Taufer","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-0031-6377","affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, TN, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.3926999866962433,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.3926999866962433,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.2994000017642975,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10857","display_name":"Advanced Electron Microscopy Techniques and Applications","score":0.049400001764297485,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9602000117301941},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7340999841690063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.625},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5920000076293945},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.4584999978542328},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4124999940395355},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.37279999256134033},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36579999327659607},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.35760000348091125}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9602000117301941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797999978065491},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7340999841690063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.625},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5920000076293945},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45019999146461487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42980000376701355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C13926793","wikidata":"https://www.wikidata.org/wiki/Q3507155","display_name":"Group method of data handling","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C84418412","wikidata":"https://www.wikidata.org/wiki/Q3246940","display_name":"Digital forensics","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3806645.3807587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3807587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3806645.3807587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3807587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.6599414944648743}],"awards":[{"id":"https://openalex.org/G1183150320","display_name":"SHF: Small: Methods, Workflows, and Data Commons for Reducing Training Costs in Neural Architecture Search on High-Performance Computing Platforms","funder_award_id":"2223704","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2919610627","display_name":"Collaborative Research: SHF: Small: Model-driven Design and Optimization of Dataflows for Scientific Applications","funder_award_id":"2331152","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G40042181","display_name":"POSE: Phase I: Towards an Open-Source Ecosystem for Accelerating High-Resolution Terrain Parameter Computation in Earth Science Applications","funder_award_id":"2449103","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7460037537","display_name":"CICI:TCR:SAFARI: Scientific Analytics, Forensics, and Reproducibility for Workflows in CI","funder_award_id":"2530461","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1600255172","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W1988545508","https://openalex.org/W2023727573","https://openalex.org/W2145607950","https://openalex.org/W2625759119","https://openalex.org/W2780813414","https://openalex.org/W2803609932","https://openalex.org/W2912218663","https://openalex.org/W2954234207","https://openalex.org/W2964023000","https://openalex.org/W2966284335","https://openalex.org/W3008591352","https://openalex.org/W3045677590","https://openalex.org/W3090519803","https://openalex.org/W4386707631","https://openalex.org/W4386707668","https://openalex.org/W4388894101","https://openalex.org/W4404788078"],"related_works":[],"abstract_inverted_index":{"Weight":[0],"snapshots":[1,47],"taken":[2],"during":[3,18],"neural":[4],"network":[5],"training":[6,74,139,162],"provide":[7,124],"a":[8,63,152],"foundation":[9],"for":[10,13],"reproducibility":[11],"and":[12,36,41,58,77,86,93,123,160],"understanding":[14],"how":[15],"models":[16,45],"evolve":[17],"learning.":[19],"They":[20],"indicate":[21],"whether":[22],"networks":[23],"progress":[24],"toward":[25,30],"higher":[26],"accuracy":[27,116,143],"or":[28,109],"diverge":[29],"poor":[31],"generalization,":[32],"yet":[33],"their":[34],"size":[35],"frequency":[37],"impose":[38],"severe":[39],"storage":[40,82],"I/O":[42],"burdens.":[43],"As":[44],"scale,":[46],"exhibit":[48],"substantial":[49],"cross-epoch":[50],"redundancy,":[51],"making":[52],"them":[53],"increasingly":[54],"difficult":[55],"to":[56,129,155],"archive":[57],"analyze":[59],"efficiently.":[60],"We":[61],"introduce":[62],"Merkle-tree":[64,100,149],"deduplication":[65,92,150],"pipeline":[66],"that":[67,148],"removes":[68],"redundancy":[69],"while":[70],"exposing":[71],"metadata":[72,101],"about":[73],"dynamics.":[75],"Chunking":[76],"deduplicating":[78],"weights":[79],"yields":[80],"70\u201380%":[81],"savings":[83,134],"across":[84],"CIFAR-10/100":[85],"protein":[87],"diffraction":[88],"datasets,":[89],"outperforming":[90],"list-based":[91],"per-snapshot":[94],"compression":[95],"baselines.":[96],"Beyond":[97],"space":[98],"savings,":[99],"categorizes":[102],"chunks":[103],"as":[104],"fixed":[105],"duplicates,":[106,108],"shifted":[107],"first":[110],"occurrences.":[111],"These":[112],"signals":[113],"predict":[114],"validation":[115],"with":[117,141],"mean":[118],"absolute":[119],"error":[120,166],"below":[121],"1%":[122],"an":[125],"optional,":[126],"metadata-driven":[127],"signal":[128],"inform":[130],"early":[131],"stopping,":[132],"enabling":[133],"of":[135,137],"16\u201372%":[136],"the":[138,170],"epochs":[140],"negligible":[142],"loss.":[144],"Our":[145],"work":[146],"demonstrates":[147],"provides":[151],"unified":[153],"approach":[154],"reduce":[156],"overhead,":[157],"preserve":[158],"reproducibility,":[159],"explain":[161],"dynamics":[163],"within":[164],"user-defined":[165],"tolerances,":[167],"without":[168],"disrupting":[169],"learning":[171],"loop.":[172]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-12T00:00:00"}