{"id":"https://openalex.org/W7170055485","doi":"https://doi.org/10.1145/3785462.3815793","title":"Semantically-Aligned Data Carving for Robust Reproducibility","display_name":"Semantically-Aligned Data Carving for Robust Reproducibility","publication_year":2026,"publication_date":"2026-07-22","ids":{"openalex":"https://openalex.org/W7170055485","doi":"https://doi.org/10.1145/3785462.3815793"},"language":null,"primary_location":{"id":"doi:10.1145/3785462.3815793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815793","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 Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3785462.3815793","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107820907","display_name":"Raffay Atiq","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raffay Atiq","raw_affiliation_strings":["SRI, Menlo Park, CA, USA"],"raw_orcid":"https://orcid.org/0009-0008-1315-0557","affiliations":[{"raw_affiliation_string":"SRI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035466033","display_name":"Ashish Gehani","orcid":"https://orcid.org/0000-0002-3940-2467"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Gehani","raw_affiliation_strings":["SRI, Menlo Park, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3940-2467","affiliations":[{"raw_affiliation_string":"SRI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071436717","display_name":"Tanu Malik","orcid":"https://orcid.org/0009-0007-9656-727X"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanu Malik","raw_affiliation_strings":["School of Computing, University of Missouri, Columbia, MO, USA"],"raw_orcid":"https://orcid.org/0009-0007-9656-727X","affiliations":[{"raw_affiliation_string":"School of Computing, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051828613","display_name":"Muhammad Fareed Zaffar","orcid":"https://orcid.org/0000-0002-1270-5513"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Fareed Zaffar","raw_affiliation_strings":["Lahore University of Management Sciences, Lahore, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-1270-5513","affiliations":[{"raw_affiliation_string":"Lahore University of Management Sciences, Lahore, Pakistan","institution_ids":["https://openalex.org/I207789805"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/carving","display_name":"Carving","score":0.9164000153541565},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.7128999829292297},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6474000215530396},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.569100022315979},{"id":"https://openalex.org/keywords/seam-carving","display_name":"Seam carving","score":0.4142000079154968},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.37630000710487366}],"concepts":[{"id":"https://openalex.org/C2777370761","wikidata":"https://www.wikidata.org/wiki/Q18448934","display_name":"Carving","level":2,"score":0.9164000153541565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524999976158142},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.7128999829292297},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6474000215530396},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C23746413","wikidata":"https://www.wikidata.org/wiki/Q1141379","display_name":"Seam carving","level":3,"score":0.4142000079154968},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3806999921798706},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C154556556","wikidata":"https://www.wikidata.org/wiki/Q192969","display_name":"Computer multitasking","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C153914771","wikidata":"https://www.wikidata.org/wiki/Q5227343","display_name":"Data reduction","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3785462.3815793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815793","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 Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3785462.3815793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815793","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 Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G72274764","display_name":null,"funder_award_id":"AIST-21-0095","funder_id":"https://openalex.org/F4320334116","funder_display_name":"NASA Headquarters"}],"funders":[{"id":"https://openalex.org/F4320334116","display_name":"NASA Headquarters","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W168132470","https://openalex.org/W2032756564","https://openalex.org/W2088628452","https://openalex.org/W2141992894","https://openalex.org/W2161522188","https://openalex.org/W2343262332","https://openalex.org/W2516285678","https://openalex.org/W2888445849","https://openalex.org/W2901078705","https://openalex.org/W4313477313","https://openalex.org/W4313547623","https://openalex.org/W4403212361","https://openalex.org/W4414898322"],"related_works":[],"abstract_inverted_index":{"Reproducibility":[0],"is":[1,57],"integral":[2],"to":[3,19,89],"scientific":[4,8],"progress.":[5],"Containerization":[6],"facilitates":[7],"reproducibility":[9],"but":[10],"often":[11],"results":[12],"in":[13],"excessive":[14],"storage":[15],"footprints":[16],"when":[17,62],"applied":[18],"data-intensive":[20],"workflows,":[21],"as":[22],"entire":[23],"datasets":[24,120],"are":[25],"frequently":[26],"packaged":[27],"despite":[28],"only":[29,97,122],"partial":[30],"access":[31],"at":[32],"runtime.":[33],"While":[34],"data":[35,54,70,100,114,127],"carving":[36,55,108,163],"can":[37],"mitigate":[38],"this,":[39],"distinct":[40,60],"file":[41],"formats":[42,61],"typically":[43],"require":[44],"specialized":[45],"reduction":[46],"tools.":[47],"This":[48],"paper":[49],"demonstrates":[50],"that":[51,85,144],"a":[52,63,83],"unified":[53,146],"architecture":[56],"achievable":[58],"for":[59],"principled":[64],"mapping":[65,88],"exists":[66],"between":[67,77],"their":[68],"underlying":[69],"models.":[71],"Focusing":[72],"on":[73,91,111,138],"the":[74,98,107,112,123,134,161],"structural":[75],"correspondence":[76],"HDF5":[78],"and":[79,94,126,140,165],"netCDF4,":[80],"we":[81],"introduce":[82],"framework":[84],"leverages":[86],"this":[87,145],"interpose":[90],"library":[92],"calls":[93],"selectively":[95],"extract":[96],"format-defined":[99],"objects":[101],"accessed":[102],"during":[103,160,168],"execution.":[104],"By":[105],"abstracting":[106],"logic":[109],"based":[110],"shared":[113],"model,":[115],"our":[116],"system":[117],"produces":[118],"slimmed-down":[119],"containing":[121],"necessary":[124],"files":[125],"objects,":[128],"regardless":[129],"of":[130],"which":[131],"high-level":[132],"API":[133],"application":[135,154],"utilizes.":[136],"Evaluation":[137],"geophysical":[139],"climate":[141],"workloads":[142],"confirms":[143],"approach":[147],"substantially":[148],"reduces":[149],"container":[150],"size":[151],"while":[152],"maintaining":[153],"correctness,":[155],"incurring":[156],"moderate":[157],"I/O":[158],"overhead":[159,167],"initial":[162],"phase":[164],"minimal":[166],"re-execution.":[169]},"counts_by_year":[],"updated_date":"2026-07-23T06:02:39.697066","created_date":"2026-07-23T00:00:00"}
