{"id":"https://openalex.org/W3215435519","doi":"https://doi.org/10.48550/arxiv.2112.01273","title":"RawArray: A Simple, Fast, and Extensible Archival Format for Numeric Data","display_name":"RawArray: A Simple, Fast, and Extensible Archival Format for Numeric Data","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W3215435519","doi":"https://doi.org/10.48550/arxiv.2112.01273","mag":"3215435519"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2112.01273","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.01273","pdf_url":"https://arxiv.org/pdf/2112.01273","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.01273","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Smith, David S.","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Smith, David S.","raw_affiliation_strings":["Institute of Imaging Science , Vanderbilt University Medical Center , Nashville , TN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Imaging Science , Vanderbilt University Medical Center , Nashville , TN , USA","institution_ids":["https://openalex.org/I901861585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I901861585"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.5356000065803528,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.5356000065803528,"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/T11937","display_name":"Research Data Management Practices","score":0.3091000020503998,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.08290000259876251,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-formats","display_name":"data formats","score":0.4099999964237213},{"id":"https://openalex.org/keywords/archival-storage","display_name":"archival storage","score":0.5649999976158142},{"id":"https://openalex.org/keywords/metadata","display_name":"metadata","score":0.5320000052452087},{"id":"https://openalex.org/keywords/deep-learning-dataset","display_name":"deep learning dataset","score":0.703000009059906},{"id":"https://openalex.org/keywords/mnist","display_name":"MNIST","score":0.7689999938011169},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.9070000052452087},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.6499999761581421},{"id":"https://openalex.org/keywords/scientific-data-storage","display_name":"scientific data storage","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322561979293823},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.6827169060707092},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6753249764442444},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5888311862945557},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.5879537463188171},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.49611911177635193},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4546038508415222},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.4414641857147217},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4347928762435913},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3702743351459503},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2971234917640686},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27018412947654724},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23953759670257568},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2112.01273","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.01273","pdf_url":"https://arxiv.org/pdf/2112.01273","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3215435519","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2112.01273.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2112.01273","doi":"https://doi.org/10.48550/arxiv.2112.01273","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2112.01273","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.01273","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.01273","pdf_url":"https://arxiv.org/pdf/2112.01273","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G525736961","display_name":"Applying Compressed Sensing to Dynamic Contrast Enhanced MRI of Breast Cancer","funder_award_id":"K25CA176219","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1555182132","https://openalex.org/W2084562911","https://openalex.org/W2081904791","https://openalex.org/W2628629421","https://openalex.org/W6893203619","https://openalex.org/W6950443927","https://openalex.org/W6906736791","https://openalex.org/W2912224977","https://openalex.org/W4389495564","https://openalex.org/W2296554964"],"abstract_inverted_index":{"Raw":[0],"data":[1,28,82,95],"sizes":[2,138],"are":[3],"growing":[4],"and":[5,26,33,40,56,80,139,154],"proliferating":[6],"in":[7,146],"scientific":[8],"research,":[9],"driven":[10],"by":[11],"the":[12,50,148],"success":[13],"of":[14,24,62,76,128,136,142],"data-hungry":[15],"computational":[16],"methods,":[17],"such":[18],"as":[19],"machine":[20],"learning.":[21],"The":[22,68,84,93],"preponderance":[23],"proprietary":[25],"shoehorned":[27],"formats":[29],"make":[30,34],"computations":[31],"slower":[32],"it":[35],"harder":[36],"to":[37,41,44,105,113,144],"reproduce":[38],"research":[39],"port":[42],"methods":[43],"new":[45],"platforms.":[46],"Here":[47],"we":[48],"present":[49,123],"RawArray":[51,69,107],"format:":[52],"a":[53,73,77,81,126,134,140],"simple,":[54],"fast,":[55],"extensible":[57],"format":[58,71],"for":[59,111,133],"archival":[60],"storage":[61],"multidimensional":[63],"numeric":[64],"arrays":[65],"on":[66],"disk.":[67],"file":[70,108],"is":[72],"simple":[74],"concatenation":[75],"header":[78,85],"array":[79,94,137],"array.":[83],"comprises":[86],"seven":[87],"or":[88,119],"more":[89],"64-bit":[90],"unsigned":[91],"integers.":[92],"can":[96,102],"be":[97,103],"anything.":[98],"Arbitrary":[99],"user":[100],"metadata":[101],"appended":[104],"an":[106],"if":[109],"desired,":[110],"example":[112],"store":[114],"measurement":[115],"details,":[116],"color":[117],"palettes,":[118],"geolocation":[120],"data.":[121],"We":[122],"benchmarks":[124],"showing":[125],"factor":[127],"2--3$\\times$":[129],"speedup":[130,141],"over":[131],"HDF5":[132],"range":[135],"up":[143],"20$\\times$":[145],"reading":[147],"common":[149],"deep":[150],"learning":[151],"datasets":[152],"MNIST":[153],"CIFAR10.":[155]},"counts_by_year":[],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2021-12-06T00:00:00"}
