{"id":"https://openalex.org/W2705062272","doi":"https://doi.org/10.1145/3078597.3078603","title":"Diagnosing Machine Learning Pipelines with Fine-grained Lineage","display_name":"Diagnosing Machine Learning Pipelines with Fine-grained Lineage","publication_year":2017,"publication_date":"2017-06-23","ids":{"openalex":"https://openalex.org/W2705062272","doi":"https://doi.org/10.1145/3078597.3078603","mag":"2705062272"},"language":"en","primary_location":{"id":"doi:10.1145/3078597.3078603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3078597.3078603","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3078603&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3078603&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100422999","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0001-9768-3095"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042005594","display_name":"Evan Sparks","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evan R. Sparks","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090643027","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0001-9600-4150"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100422999"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":4.8317,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95397715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9962000250816345,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.8311911225318909},{"id":"https://openalex.org/keywords/lineage","display_name":"Lineage (genetic)","score":0.8064320087432861},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7376025319099426},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6004370450973511},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4545412063598633},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33708417415618896},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2949482202529907},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20122042298316956},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11526989936828613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311911225318909},{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.8064320087432861},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7376025319099426},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6004370450973511},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4545412063598633},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33708417415618896},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2949482202529907},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20122042298316956},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11526989936828613},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3078597.3078603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3078597.3078603","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3078603&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3078597.3078603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3078597.3078603","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3078603&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2063665203","display_name":null,"funder_award_id":"NetApp","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3145906079","display_name":null,"funder_award_id":"SN10040, DE-SC0012463","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4360165785","display_name":null,"funder_award_id":"A8750-12-2-0331","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4654920669","display_name":null,"funder_award_id":"CCF-1139158","funder_id":"https://openalex.org/F4320332169","funder_display_name":"Directorate for Computer and Information Science and Engineering"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G579401873","display_name":null,"funder_award_id":"NSF CISE Expeditions Award CCF-1139158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G589244659","display_name":null,"funder_award_id":"XData Award FA8750-12-2-0331","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6284359468","display_name":null,"funder_award_id":"Award 7076018","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G6398089940","display_name":"Making Sense at Scale with Algorithms, Machines, and People","funder_award_id":"1139158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7103680314","display_name":null,"funder_award_id":"FA8750-12-2-0331","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8560804567","display_name":null,"funder_award_id":"7076018","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G900736768","display_name":null,"funder_award_id":"CCF-1139158","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"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320312638","display_name":"Thomas and Stacey Siebel Foundation","ror":null},{"id":"https://openalex.org/F4320316505","display_name":"NetApp","ror":"https://ror.org/05c4cm338"},{"id":"https://openalex.org/F4320316785","display_name":"VMware","ror":null},{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2705062272.pdf","grobid_xml":"https://content.openalex.org/works/W2705062272.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W69843719","https://openalex.org/W126044612","https://openalex.org/W135267584","https://openalex.org/W180519810","https://openalex.org/W1486776102","https://openalex.org/W1574590769","https://openalex.org/W1582664144","https://openalex.org/W1780933788","https://openalex.org/W1899647947","https://openalex.org/W1983704199","https://openalex.org/W1994326726","https://openalex.org/W2014830756","https://openalex.org/W2019379313","https://openalex.org/W2030433745","https://openalex.org/W2035168235","https://openalex.org/W2037227137","https://openalex.org/W2038157364","https://openalex.org/W2044547639","https://openalex.org/W2098935637","https://openalex.org/W2100153179","https://openalex.org/W2101234009","https://openalex.org/W2102458936","https://openalex.org/W2107571548","https://openalex.org/W2118052422","https://openalex.org/W2118269922","https://openalex.org/W2119738171","https://openalex.org/W2124386111","https://openalex.org/W2126778319","https://openalex.org/W2127218421","https://openalex.org/W2127279146","https://openalex.org/W2129167530","https://openalex.org/W2131620262","https://openalex.org/W2131975293","https://openalex.org/W2133986470","https://openalex.org/W2134318033","https://openalex.org/W2151135734","https://openalex.org/W2157917411","https://openalex.org/W2171588311","https://openalex.org/W2172143128","https://openalex.org/W2186094539","https://openalex.org/W2294556882","https://openalex.org/W2299467264","https://openalex.org/W2912412735","https://openalex.org/W2997591727","https://openalex.org/W4365786623","https://openalex.org/W6605500462"],"related_works":["https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2155788121","https://openalex.org/W4235469518","https://openalex.org/W2387706296","https://openalex.org/W2501188010","https://openalex.org/W2480201319"],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,7,43,46,50,65,88,107,115,121],"Hippo":[3,20,67,118],"system":[4],"to":[5,32,63,135],"enable":[6,136],"diagnosis":[8,72,138],"of":[9,109,139],"distributed":[10],"machine":[11],"learning":[12],"(ML)":[13],"pipelines":[14],"by":[15],"leveraging":[16],"fine-grained":[17,34],"data":[18,35,39,80],"lineage.":[19],"exposes":[21],"a":[22,128],"concise":[23],"yet":[24],"powerful":[25],"API,":[26],"derived":[27],"from":[28],"primitive":[29],"lineage":[30,36,103,116,125],"types,":[31],"capture":[33],"for":[37],"each":[38],"transformation.":[40],"It":[41,55],"records":[42],"input":[44],"datasets,":[45],"output":[47],"datasets":[48],"and":[49,83,91],"cell-level":[51],"mapping":[52,111],"between":[53],"them.":[54],"also":[56],"collects":[57],"sufficient":[58],"information":[59],"that":[60],"is":[61,132],"needed":[62],"reproduce":[64],"computation.":[66],"efficiently":[68],"enables":[69],"common":[70],"ML":[71,140],"operations":[73],"such":[74],"as":[75],"code":[76],"debugging,":[77],"result":[78],"analysis,":[79],"anomaly":[81],"removal,":[82],"computation":[84],"replay.":[85],"By":[86],"exploiting":[87],"metadata":[89],"separation":[90],"high-order":[92],"function":[93],"encoding":[94],"strategies,":[95],"we":[96],"observe":[97],"an":[98],"O(10^3)x":[99],"total":[100],"improvement":[101],"in":[102],"storage":[104],"efficiency":[105],"vs.":[106],"baseline":[108],"cell-wise":[110],"recording":[112],"while":[113],"maintaining":[114],"integrity.":[117],"can":[119],"answer":[120],"real":[122],"use":[123],"case":[124],"queries":[126],"within":[127],"few":[129],"seconds,":[130],"which":[131],"low":[133],"enough":[134],"interactive":[137],"pipelines.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}