{"id":"https://openalex.org/W4413908777","doi":"https://doi.org/10.1145/3736229.3736264","title":"Compression for High-Performance Lineage","display_name":"Compression for High-Performance Lineage","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4413908777","doi":"https://doi.org/10.1145/3736229.3736264"},"language":"en","primary_location":{"id":"doi:10.1145/3736229.3736264","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3736229.3736264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ProvenanceWeek 2025","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":null,"display_name":"Xiaoyu Han","orcid":"https://orcid.org/0009-0001-6658-8287"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Han","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-6658-8287","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020730215","display_name":"Haneen Mohammed","orcid":"https://orcid.org/0000-0002-4535-1926"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haneen Mohammed","raw_affiliation_strings":["Columbia University, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-4535-1926","affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035315306","display_name":"Charlie Summers","orcid":"https://orcid.org/0009-0002-6301-9430"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charlie Summers","raw_affiliation_strings":["Columbia University, New York, USA"],"raw_orcid":"https://orcid.org/0009-0002-6301-9430","affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University, New York, USA"],"raw_orcid":"https://orcid.org/0000-0003-4254-6688","affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11001324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9969000220298767,"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":0.994700014591217,"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":0.5509079694747925},{"id":"https://openalex.org/keywords/lineage","display_name":"Lineage (genetic)","score":0.5507203936576843},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5222212076187134},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11756962537765503},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10878941416740417},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06722980737686157},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.06714856624603271},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.057085901498794556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5509079694747925},{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.5507203936576843},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5222212076187134},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11756962537765503},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10878941416740417},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06722980737686157},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.06714856624603271},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.057085901498794556}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3736229.3736264","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3736229.3736264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ProvenanceWeek 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-171862","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-171862","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G582452355","display_name":null,"funder_award_id":"1845638, 1740305, 2008295, 2106197, 2103794","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":32,"referenced_works":["https://openalex.org/W1974374149","https://openalex.org/W1983178058","https://openalex.org/W2024171325","https://openalex.org/W2039548475","https://openalex.org/W2044547639","https://openalex.org/W2047182010","https://openalex.org/W2107745473","https://openalex.org/W2119325664","https://openalex.org/W2123686039","https://openalex.org/W2161768947","https://openalex.org/W2288788587","https://openalex.org/W2600741786","https://openalex.org/W2614037574","https://openalex.org/W2801126065","https://openalex.org/W2889523940","https://openalex.org/W2949054050","https://openalex.org/W2953222880","https://openalex.org/W2958080619","https://openalex.org/W2963123635","https://openalex.org/W3011197833","https://openalex.org/W3015276915","https://openalex.org/W3016996288","https://openalex.org/W3028867501","https://openalex.org/W3103264664","https://openalex.org/W4230804723","https://openalex.org/W4249285655","https://openalex.org/W4312460160","https://openalex.org/W4379383205","https://openalex.org/W4387951978","https://openalex.org/W4400909668","https://openalex.org/W4410539002","https://openalex.org/W4412719245"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2506149209","https://openalex.org/W4396701345","https://openalex.org/W2352153050","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Data":[0,15],"lineage":[1,24,46,55,63,67,112,117,124,132],"tracks":[2],"precise":[3],"input-output":[4],"relationships":[5],"of":[6,75,103],"SQL":[7],"queries":[8],"and":[9,30,77,134],"has":[10],"proven":[11],"instrumental":[12],"for":[13,66,110],"Interactive":[14],"Exploration":[16],"(IDE)":[17],"applications.":[18],"However,":[19],"existing":[20],"approaches":[21],"overlook":[22],"prohibitive":[23],"storage":[25,125],"costs":[26],"in":[27,96],"IDE":[28,97],"workloads":[29],"rely":[31],"on":[32],"low-throughput":[33],"query":[34,93,135],"engines":[35],"that":[36,57,82],"bottleneck":[37],"performance.":[38],"To":[39],"address":[40],"this,":[41],"we":[42,70,99],"present":[43],"two":[44],"novel":[45],"compression":[47,80],"strategies":[48],"built":[49],"upon":[50],"SmokedDuck":[51],"\u2014":[52],"a":[53,101],"high-performance":[54],"system":[56],"captures":[58],"data":[59,85],"movement":[60],"patterns":[61],"as":[62],"artifacts":[64],"(LAs)":[65],"reconstruction.":[68],"First,":[69],"identify":[71],"key":[72],"compressibility":[73],"determinants":[74],"LAs":[76,109],"design":[78],"effective":[79],"schemes":[81],"achieve":[83],"compact":[84],"representation":[86],"through":[87],"redundancy":[88],"elimination.":[89],"Second,":[90],"by":[91],"analyzing":[92],"pattern":[94],"similarities":[95],"workloads,":[98],"establish":[100],"set":[102],"rules":[104],"to":[105,122],"reuse":[106],"the":[107],"captured":[108],"new":[111],"derivation,":[113],"thereby":[114],"obviating":[115],"redundant":[116],"capture.":[118],"Experiments":[119],"demonstrate":[120],"up":[121],"10x":[123],"reduction":[126],"versus":[127],"naive":[128],"SmokedDuck,":[129],"with":[130],"minimal":[131],"capture":[133],"time":[136],"overhead.":[137]},"counts_by_year":[],"updated_date":"2026-05-25T08:39:21.599409","created_date":"2025-10-10T00:00:00"}
