{"id":"https://openalex.org/W3138331935","doi":"https://doi.org/10.1109/bigdata50022.2020.9378128","title":"~PB&J~ - Easy Automation of Data Science/Machine Learning Workflows","display_name":"~PB&J~ - Easy Automation of Data Science/Machine Learning Workflows","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3138331935","doi":"https://doi.org/10.1109/bigdata50022.2020.9378128","mag":"3138331935"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079851149","display_name":"Buvaneswari Ramanan","orcid":null},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Buvaneswari Ramanan","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040352022","display_name":"Lawrence Drabeck","orcid":null},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence Drabeck","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069403056","display_name":"Thomas Woo","orcid":"https://orcid.org/0009-0003-2028-5533"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Woo","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060799266","display_name":"Troy Cauble","orcid":null},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Troy Cauble","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005614987","display_name":"Anil Rana","orcid":"https://orcid.org/0000-0001-7476-6234"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anil Rana","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079851149"],"corresponding_institution_ids":["https://openalex.org/I72090969"],"apc_list":null,"apc_paid":null,"fwci":2.0781,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92214263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9991999864578247,"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":0.9991999864578247,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9815999865531921,"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"}},{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.8153093457221985},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7322238087654114},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6801485419273376},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.552935779094696},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.48878905177116394},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4655730426311493},{"id":"https://openalex.org/keywords/unix","display_name":"Unix","score":0.46344518661499023},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.4507109224796295},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4199143946170807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3804343342781067},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.38029247522354126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3715311288833618},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3417311906814575},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33828097581863403},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09598270058631897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153093457221985},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7322238087654114},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6801485419273376},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.552935779094696},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.48878905177116394},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4655730426311493},{"id":"https://openalex.org/C112968700","wikidata":"https://www.wikidata.org/wiki/Q11368","display_name":"Unix","level":3,"score":0.46344518661499023},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.4507109224796295},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4199143946170807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3804343342781067},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.38029247522354126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3715311288833618},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3417311906814575},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33828097581863403},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09598270058631897},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1971514365","https://openalex.org/W2089554624","https://openalex.org/W2111823238","https://openalex.org/W2112912048","https://openalex.org/W2115022330","https://openalex.org/W2194775991","https://openalex.org/W2735078864","https://openalex.org/W2963122170","https://openalex.org/W3007380371","https://openalex.org/W3014769316","https://openalex.org/W6620707391","https://openalex.org/W6676647902"],"related_works":["https://openalex.org/W2350278424","https://openalex.org/W2033889310","https://openalex.org/W2071432835","https://openalex.org/W644889988","https://openalex.org/W4239401009","https://openalex.org/W4234371507","https://openalex.org/W2341492732","https://openalex.org/W2086577855","https://openalex.org/W3083262785","https://openalex.org/W2736113231"],"abstract_inverted_index":{"The":[0],"ability":[1,126],"to":[2,67,102,127,140,175],"process":[3],"large":[4],"amounts":[5],"of":[6,46,75,95,115,163,190,192],"data":[7,76,143,169],"efficiently":[8],"is":[9,31,65,100,138],"a":[10,58,83,117],"must":[11],"in":[12,188],"modern":[13],"Big":[14],"Data,":[15],"Data":[16],"Science":[17],"and":[18,23,39,53,72,91,131,154,161,185,196],"Machine":[19],"Learning":[20,168],"(ML).":[21],"Easy":[22],"succinct":[24,89],"workflow":[25,70],"expression":[26],"with":[27,61,97,112,124,134,165],"highly":[28],"efficient":[29],"scaling":[30],"key.":[32],"Existing":[33],"systems":[34],"such":[35,178],"as":[36,104,179],"Apache":[37,180,182,186],"Spark":[38],"Beam":[40],"were":[41],"created":[42],"for":[43],"this":[44],"type":[45],"work":[47],"but":[48],"have":[49],"steep":[50],"learning":[51],"curve":[52],"tremendous":[54],"operating":[55],"complexity.":[56],"Having":[57],"simpler":[59],"tool":[60],"less":[62],"overhead":[63],"that":[64,87],"well-matched":[66,139],"the":[68,108,113,141,149,159],"typical":[69,142],"definition":[71,90],"execution":[73,94],"requirements":[74,146],"science/ML":[77,144],"projects":[78],"will":[79],"be":[80],"beneficial.We":[81],"propose":[82],"new":[84],"framework":[85],"PB&J":[86,99,120,164],"enables":[88],"data-parallel":[92],"scale-out":[93],"workflows":[96],"ease.":[98],"easy":[101],"learn":[103],"it":[105,174],"builds":[106],"on":[107],"native":[109],"Unix":[110],"shell,":[111],"addition":[114],"just":[116],"few":[118],"operators.":[119],"supports":[121],"Maximal":[122],"Parallelism":[123],"its":[125],"do":[128],"true":[129],"pipelining,":[130],"fault":[132,197],"recovery":[133],"Minimal":[135],"Redo.":[136],"It":[137],"processing":[145,170],"by":[147],"leveraging":[148],"existing":[150,176],"command":[151],"line":[152],"executables":[153],"Python":[155],"modules.":[156],"We":[157,172],"illustrate":[158],"features":[160],"strengths":[162],"real-life":[166],"Deep":[167],"workflows.":[171],"compare":[173],"frameworks":[177],"Spark,":[181],"Beam,":[183],"Swift/T":[184],"Airflow":[187],"terms":[189],"ease":[191],"authoring,":[193],"efficiency,":[194],"scalability":[195],"recovery.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}