{"id":"https://openalex.org/W6891773809","doi":"https://doi.org/10.4230/lipics.sea.2025.12","title":"Bit Packed Encodings for Grammar-Compressed Strings Supporting Fast Random Access","display_name":"Bit Packed Encodings for Grammar-Compressed Strings Supporting Fast Random Access","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6891773809","doi":"https://doi.org/10.4230/lipics.sea.2025.12"},"language":"en","primary_location":{"id":"pmh:oai:drops-oai.dagstuhl.de:23250","is_oa":true,"landing_page_url":"https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.SEA.2025.12","pdf_url":"https://drops.dagstuhl.de/storage/00lipics/lipics-vol338-sea2025/LIPIcs.SEA.2025.12/LIPIcs.SEA.2025.12.pdf","source":{"id":"https://openalex.org/S4377196569","display_name":"DROPS (Schloss Dagstuhl \u2013 Leibniz Center for Informatics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799853480","host_organization_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","host_organization_lineage":["https://openalex.org/I2799853480"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"InProceedings"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://drops.dagstuhl.de/storage/00lipics/lipics-vol338-sea2025/LIPIcs.SEA.2025.12/LIPIcs.SEA.2025.12.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cleary, Alan M.","orcid":"https://orcid.org/0000-0002-6567-5346"},"institutions":[{"id":"https://openalex.org/I1310183320","display_name":"National Center for Genome Resources","ror":"https://ror.org/01p4cne93","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1310183320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cleary, Alan M.","raw_affiliation_strings":["National Center for Genome Resources, Santa Fe, NM, USA"],"raw_orcid":"https://orcid.org/0000-0002-6567-5346","affiliations":[{"raw_affiliation_string":"National Center for Genome Resources, Santa Fe, NM, USA","institution_ids":["https://openalex.org/I1310183320"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Winjum, Joseph","orcid":"https://orcid.org/0009-0001-4592-3891"},"institutions":[{"id":"https://openalex.org/I23732399","display_name":"Montana State University","ror":"https://ror.org/02w0trx84","country_code":"US","type":"education","lineage":["https://openalex.org/I23732399","https://openalex.org/I4210126032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Winjum, Joseph","raw_affiliation_strings":["Montana State University, Bozeman, MT, USA"],"raw_orcid":"https://orcid.org/0009-0001-4592-3891","affiliations":[{"raw_affiliation_string":"Montana State University, Bozeman, MT, USA","institution_ids":["https://openalex.org/I23732399"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dood, Jordan","orcid":"https://orcid.org/0009-0001-8043-3919"},"institutions":[{"id":"https://openalex.org/I1308906816","display_name":"NortonLifeLock (United States)","ror":"https://ror.org/0449t3a80","country_code":"US","type":"company","lineage":["https://openalex.org/I1308906816"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dood, Jordan","raw_affiliation_strings":["Hyalite Technologies LLC, Bozeman, MT, USA"],"raw_orcid":"https://orcid.org/0009-0001-8043-3919","affiliations":[{"raw_affiliation_string":"Hyalite Technologies LLC, Bozeman, MT, USA","institution_ids":["https://openalex.org/I1308906816"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shibata, Hiroki","orcid":"https://orcid.org/0009-0006-6502-7476"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shibata, Hiroki","raw_affiliation_strings":["Joint Graduate School of Mathematics for Innovation, Kyushu University, Fukuoka, Japan"],"raw_orcid":"https://orcid.org/0009-0006-6502-7476","affiliations":[{"raw_affiliation_string":"Joint Graduate School of Mathematics for Innovation, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":null,"display_name":"Inenaga, Shunsuke","orcid":"https://orcid.org/0000-0002-1833-010X"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Inenaga, Shunsuke","raw_affiliation_strings":["Department of Informatics, Kyushu University, Fukuoka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1833-010X","affiliations":[{"raw_affiliation_string":"Department of Informatics, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15121807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9768999814987183,"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":0.9768999814987183,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.003800000064074993,"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/T12029","display_name":"DNA and Biological Computing","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7498000264167786},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6438000202178955},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.625},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5670999884605408},{"id":"https://openalex.org/keywords/bit-array","display_name":"Bit array","score":0.5465999841690063},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5440000295639038},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4433000087738037}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7498000264167786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614999771118164},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6438000202178955},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.625},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C150807984","wikidata":"https://www.wikidata.org/wiki/Q1992074","display_name":"Bit array","level":3,"score":0.5465999841690063},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5012000203132629},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4742000102996826},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46650001406669617},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.3709000051021576},{"id":"https://openalex.org/C117011727","wikidata":"https://www.wikidata.org/wiki/Q1278488","display_name":"Bit (key)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:drops-oai.dagstuhl.de:23250","is_oa":true,"landing_page_url":"https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.SEA.2025.12","pdf_url":"https://drops.dagstuhl.de/storage/00lipics/lipics-vol338-sea2025/LIPIcs.SEA.2025.12/LIPIcs.SEA.2025.12.pdf","source":{"id":"https://openalex.org/S4377196569","display_name":"DROPS (Schloss Dagstuhl \u2013 Leibniz Center for Informatics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799853480","host_organization_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","host_organization_lineage":["https://openalex.org/I2799853480"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"InProceedings"},{"id":"doi:10.4230/lipics.sea.2025.12","is_oa":true,"landing_page_url":"https://doi.org/10.4230/lipics.sea.2025.12","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:drops-oai.dagstuhl.de:23250","is_oa":true,"landing_page_url":"https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.SEA.2025.12","pdf_url":"https://drops.dagstuhl.de/storage/00lipics/lipics-vol338-sea2025/LIPIcs.SEA.2025.12/LIPIcs.SEA.2025.12.pdf","source":{"id":"https://openalex.org/S4377196569","display_name":"DROPS (Schloss Dagstuhl \u2013 Leibniz Center for Informatics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799853480","host_organization_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","host_organization_lineage":["https://openalex.org/I2799853480"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"InProceedings"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6909785270690918,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6576069084","display_name":"CRII: III: Toward the Compression of Pangenomic DNA Sequence Data Using Context-Free Grammars","funder_award_id":"2105391","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7436239820","display_name":null,"funder_award_id":"JP23K18466","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6891773809.pdf","grobid_xml":"https://content.openalex.org/works/W6891773809.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Grammar-based":[0],"compression":[1,5],"is":[2,115],"a":[3,48],"powerful":[4],"technique":[6,83],"that":[7,102,124,131,142],"allows":[8],"for":[9,53],"computation":[10],"over":[11],"the":[12,41,94,97,110,116,121,133],"compressed":[13],"data.":[14],"While":[15],"there":[16,27],"has":[17,28],"been":[18,29],"extensive":[19],"theoretical":[20],"work":[21,31],"on":[22,32,68],"grammar":[23,34,44,155],"and":[24,46,74,123,158],"encoding":[25,156],"size,":[26],"little":[30],"practical":[33],"encodings.":[35],"In":[36],"this":[37,69],"work,":[38],"we":[39,148],"consider":[40],"canonical":[42],"array-of-arrays":[43,98],"representation":[45],"present":[47,62],"general":[49],"bit":[50,64,145],"packing":[51,65],"approach":[52,70],"reducing":[54],"its":[55],"space":[56],"requirements":[57],"in":[58,120,136,154],"practice.":[59,137],"We":[60,100],"then":[61],"three":[63],"strategies":[66],"based":[67],"-":[71,77],"one":[72],"online":[73],"two":[75],"offline":[76],"with":[78],"different":[79],"space-time":[80],"trade-offs.":[81],"This":[82],"can":[84,149],"be":[85],"used":[86],"to":[87],"encode":[88],"any":[89],"grammar-compressed":[90],"string":[91],"while":[92],"preserving":[93],"virtues":[95],"of":[96,118,161],"representation.":[99],"show":[101,141],"our":[103,139],"encodings":[104,147],"are":[105,126],"Nlog\u2082":[106],"N":[107,114],"away":[108],"from":[109],"information-theoretic":[111,134],"bound,":[112],"where":[113],"number":[117],"symbols":[119],"grammar,":[122],"they":[125],"much":[127],"smaller":[128],"than":[129],"methods":[130],"meet":[132],"bound":[135],"Moreover,":[138],"experiments":[140],"by":[143],"using":[144],"packed":[146],"achieve":[150],"state-of-the-art":[151],"performance":[152,160],"both":[153],"size":[157],"run-time":[159],"random-access":[162],"queries.":[163]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}