{"id":"https://openalex.org/W4395020705","doi":"https://doi.org/10.1145/3620665.3640353","title":"Palantir: Hierarchical Similarity Detection for Post-Deduplication Delta Compression","display_name":"Palantir: Hierarchical Similarity Detection for Post-Deduplication Delta Compression","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4395020705","doi":"https://doi.org/10.1145/3620665.3640353"},"language":"en","primary_location":{"id":"doi:10.1145/3620665.3640353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620665.3640353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","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/A5021811009","display_name":"Hongming Huang","orcid":"https://orcid.org/0000-0002-5531-474X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Hongming Huang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong","Huawei Technologies, Hong Kong, Hong Kong","City University of Hong Kong, Hong Kong, Hong Kong Huawei Technologies, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-5531-474X","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Huawei Technologies, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong Huawei Technologies, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396027","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-4008-1963"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Huawei Technologies, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-4008-1963","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041553391","display_name":"Qiang Su","orcid":"https://orcid.org/0000-0002-4482-6248"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Su","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-4482-6248","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022420830","display_name":"Hong Xu","orcid":"https://orcid.org/0000-0002-9359-9571"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hong Xu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9359-9571","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101441768","display_name":"Chun Jason Xue","orcid":"https://orcid.org/0000-0002-6431-9868"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","HK"],"is_corresponding":false,"raw_author_name":"Chun Jason Xue","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong","Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, United Arab Emirates","Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, United Arab Emirates City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-6431-9868","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, United Arab Emirates City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011466225","display_name":"Andr\u00e9 Brinkmann","orcid":"https://orcid.org/0000-0003-3083-2775"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Brinkmann","raw_affiliation_strings":["Johannes Gutenberg University Mainz, Mainz, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3083-2775","affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5021811009"],"corresponding_institution_ids":["https://openalex.org/I168719708","https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":1.9868,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87764642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"830","last_page":"845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9800999760627747,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9675999879837036,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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-deduplication","display_name":"Data deduplication","score":0.9018462896347046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6355999708175659},{"id":"https://openalex.org/keywords/delta","display_name":"Delta","score":0.5176306366920471},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.46538296341896057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41412559151649475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39003491401672363},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36239123344421387},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2203611433506012},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09137749671936035},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08998170495033264}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9018462896347046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6355999708175659},{"id":"https://openalex.org/C5072461","wikidata":"https://www.wikidata.org/wiki/Q49506","display_name":"Delta","level":2,"score":0.5176306366920471},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.46538296341896057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41412559151649475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39003491401672363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36239123344421387},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2203611433506012},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09137749671936035},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08998170495033264},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620665.3640353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620665.3640353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G313215489","display_name":null,"funder_award_id":"GRF 11209520","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"},{"id":"https://openalex.org/G7612465753","display_name":null,"funder_award_id":"CRF C7004-22G","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W22807665","https://openalex.org/W69510097","https://openalex.org/W89823361","https://openalex.org/W1445823765","https://openalex.org/W1474119323","https://openalex.org/W1901266868","https://openalex.org/W1995875735","https://openalex.org/W1998817683","https://openalex.org/W2056980397","https://openalex.org/W2073053905","https://openalex.org/W2073370301","https://openalex.org/W2122962290","https://openalex.org/W2133893097","https://openalex.org/W2134792144","https://openalex.org/W2138630447","https://openalex.org/W2148885851","https://openalex.org/W2161488606","https://openalex.org/W2346147088","https://openalex.org/W2351279544","https://openalex.org/W2923621035","https://openalex.org/W2982637157","https://openalex.org/W3174127842","https://openalex.org/W4221145440","https://openalex.org/W6601060166"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W4296125805","https://openalex.org/W1982579475"],"abstract_inverted_index":{"Deduplication":[0],"compresses":[1],"backup":[2],"data":[3,26],"by":[4,37,41],"identifying":[5],"and":[6,46],"removing":[7],"duplicate":[8],"blocks.":[9],"However,":[10],"deduplication":[11],"cannot":[12],"detect":[13],"when":[14],"two":[15,54],"blocks":[16,36,49,55],"are":[17],"very":[18],"similar,":[19],"which":[20],"opens":[21],"up":[22],"opportunities":[23],"for":[24,67],"further":[25],"reduction":[27],"using":[28,50],"delta":[29,59,66],"compression.":[30],"Most":[31],"existing":[32],"works":[33],"find":[34],"similar":[35,48],"characterizing":[38],"each":[39],"block":[40],"a":[42,57],"set":[43],"of":[44],"features":[45],"matching":[47],"coarse-grained":[51],"super-features.":[52],"If":[53],"share":[56],"super-feature,":[58],"compression":[60],"only":[61],"needs":[62],"to":[63],"store":[64],"their":[65],"the":[68],"new":[69],"block.":[70]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
