{"id":"https://openalex.org/W4289655174","doi":"https://doi.org/10.1109/isit50566.2022.9834465","title":"Generalized Longest Repeated Substring Min-Entropy Estimator","display_name":"Generalized Longest Repeated Substring Min-Entropy Estimator","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4289655174","doi":"https://doi.org/10.1109/isit50566.2022.9834465"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834465","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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/A5061899832","display_name":"Jiheon Woo","orcid":"https://orcid.org/0000-0001-9122-5691"},"institutions":[{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jiheon Woo","raw_affiliation_strings":["DGIST,Department of Electrical Engineering and Computer Science,Daegu,South Korea","Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea"],"affiliations":[{"raw_affiliation_string":"DGIST,Department of Electrical Engineering and Computer Science,Daegu,South Korea","institution_ids":["https://openalex.org/I193352282"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea","institution_ids":["https://openalex.org/I193352282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004472994","display_name":"Chanhee Yoo","orcid":null},"institutions":[{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanhee Yoo","raw_affiliation_strings":["DGIST,Department of Electrical Engineering and Computer Science,Daegu,South Korea","Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea"],"affiliations":[{"raw_affiliation_string":"DGIST,Department of Electrical Engineering and Computer Science,Daegu,South Korea","institution_ids":["https://openalex.org/I193352282"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea","institution_ids":["https://openalex.org/I193352282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774710","display_name":"Young Sik Kim","orcid":"https://orcid.org/0000-0003-4114-4935"},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]},{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Sik Kim","raw_affiliation_strings":["Chosun University,Department of Information and Communication Engineering,Gwangju,South Korea","DGIST,Department of Electrical Engineering and Computer Science,Daegu,South Korea","Department of Information and Communication Engineering, Chosun University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chosun University,Department of Information and Communication Engineering,Gwangju,South Korea","institution_ids":["https://openalex.org/I152238500"]},{"raw_affiliation_string":"DGIST,Department of Electrical Engineering and Computer Science,Daegu,South Korea","institution_ids":["https://openalex.org/I193352282"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Chosun University, Gwangju, South Korea","institution_ids":["https://openalex.org/I152238500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063057008","display_name":"Yuval Cassuto","orcid":"https://orcid.org/0000-0001-6369-6699"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yuval Cassuto","raw_affiliation_strings":["Technion - Israel Institute of Technology,Viterbi Department of Electrical and Computer Engineering,Haifa,Israel","Viterbi Department of Electrical and Computer Engineering, Technion - Israel Institute of Technology, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion - Israel Institute of Technology,Viterbi Department of Electrical and Computer Engineering,Haifa,Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Viterbi Department of Electrical and Computer Engineering, Technion - Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025186204","display_name":"Yongjune Kim","orcid":"https://orcid.org/0000-0003-0120-3750"},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]},{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjune Kim","raw_affiliation_strings":["Chosun University,Department of Information and Communication Engineering,Gwangju,South Korea","DGIST,Department of Electrical Engineering and Computer Science,Daegu,South Korea","Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea"],"affiliations":[{"raw_affiliation_string":"Chosun University,Department of Information and Communication Engineering,Gwangju,South Korea","institution_ids":["https://openalex.org/I152238500"]},{"raw_affiliation_string":"DGIST,Department of Electrical Engineering and Computer Science,Daegu,South Korea","institution_ids":["https://openalex.org/I193352282"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea","institution_ids":["https://openalex.org/I193352282"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061899832"],"corresponding_institution_ids":["https://openalex.org/I193352282"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27052359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"342","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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":0.9997000098228455,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9972000122070312,"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/T11017","display_name":"Chaos-based Image/Signal Encryption","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/estimator","display_name":"Estimator","score":0.7601704001426697},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.6346480846405029},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6288230419158936},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6053279638290405},{"id":"https://openalex.org/keywords/entropy-estimation","display_name":"Entropy estimation","score":0.5736004710197449},{"id":"https://openalex.org/keywords/min-entropy","display_name":"Min entropy","score":0.4993729591369629},{"id":"https://openalex.org/keywords/maximum-entropy-probability-distribution","display_name":"Maximum entropy probability distribution","score":0.49683812260627747},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.49468252062797546},{"id":"https://openalex.org/keywords/bias-of-an-estimator","display_name":"Bias of an estimator","score":0.43732500076293945},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.42845407128334045},{"id":"https://openalex.org/keywords/entropy-rate","display_name":"Entropy rate","score":0.42017364501953125},{"id":"https://openalex.org/keywords/joint-entropy","display_name":"Joint entropy","score":0.4189673662185669},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.411583811044693},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.40411147475242615},{"id":"https://openalex.org/keywords/binary-entropy-function","display_name":"Binary entropy function","score":0.38866108655929565},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3706935942173004},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.3189579248428345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2920411229133606},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09561681747436523},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.08790040016174316}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7601704001426697},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.6346480846405029},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6288230419158936},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6053279638290405},{"id":"https://openalex.org/C95546049","wikidata":"https://www.wikidata.org/wiki/Q1345207","display_name":"Entropy estimation","level":3,"score":0.5736004710197449},{"id":"https://openalex.org/C196083917","wikidata":"https://www.wikidata.org/wiki/Q17103874","display_name":"Min entropy","level":5,"score":0.4993729591369629},{"id":"https://openalex.org/C60507348","wikidata":"https://www.wikidata.org/wiki/Q6795892","display_name":"Maximum entropy probability distribution","level":3,"score":0.49683812260627747},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.49468252062797546},{"id":"https://openalex.org/C191393472","wikidata":"https://www.wikidata.org/wiki/Q15222032","display_name":"Bias of an estimator","level":4,"score":0.43732500076293945},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.42845407128334045},{"id":"https://openalex.org/C125252325","wikidata":"https://www.wikidata.org/wiki/Q1345213","display_name":"Entropy rate","level":4,"score":0.42017364501953125},{"id":"https://openalex.org/C106752470","wikidata":"https://www.wikidata.org/wiki/Q1364826","display_name":"Joint entropy","level":3,"score":0.4189673662185669},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.411583811044693},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.40411147475242615},{"id":"https://openalex.org/C44415725","wikidata":"https://www.wikidata.org/wiki/Q4913893","display_name":"Binary entropy function","level":3,"score":0.38866108655929565},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3706935942173004},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.3189579248428345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2920411229133606},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09561681747436523},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.08790040016174316},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit50566.2022.9834465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834465","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1517403092","https://openalex.org/W1988624553","https://openalex.org/W2006624419","https://openalex.org/W2093566764","https://openalex.org/W2219499198","https://openalex.org/W2784781042","https://openalex.org/W2950286539","https://openalex.org/W3087034880","https://openalex.org/W3091642928","https://openalex.org/W4226216636","https://openalex.org/W6810967250"],"related_works":["https://openalex.org/W2330170324","https://openalex.org/W1994292739","https://openalex.org/W2045693826","https://openalex.org/W2898188192","https://openalex.org/W2159862004","https://openalex.org/W2889528597","https://openalex.org/W4390944229","https://openalex.org/W4387596451","https://openalex.org/W2765692396","https://openalex.org/W2041435955"],"abstract_inverted_index":{"The":[0,121],"min-entropy":[1,32,50,61,79,115,171,192],"is":[2,26,91],"a":[3,34,117,163,179],"widely":[4],"used":[5],"metric":[6],"to":[7,28,112,217],"quantify":[8],"the":[9,17,21,31,56,66,73,78,82,88,96,98,114,125,130,134,139,144,150,168,186,201,207,218],"randomness":[10],"of":[11,19,33,77,84,116,149,156,170],"generated":[12],"random":[13],"numbers,":[14],"which":[15,211],"measures":[16],"difficulty":[18],"guessing":[20],"most":[22],"likely":[23],"output.":[24],"It":[25],"difficult":[27],"accurately":[29],"estimate":[30,113],"non-independent":[35],"and":[36,52,189,196],"identically":[37],"distributed":[38],"(non-IID)":[39],"source.":[40],"Hence,":[41],"NIST":[42],"Special":[43],"Publication":[44],"(SP)":[45],"800-90B":[46],"adopts":[47],"ten":[48,60],"different":[49],"estimators":[51],"then":[53],"conservatively":[54],"selects":[55],"minimum":[57],"value":[58],"among":[59],"estimates.":[62,172,193],"Among":[63],"these":[64,175],"estimators,":[65],"longest":[67],"repeated":[68,85],"substring":[69],"(LRS)":[70],"estimator":[71,100,141,182,205],"estimates":[72],"collision":[74,89,131,151],"entropy":[75,90,132,147,152,155],"instead":[76,148],"by":[80,128,142],"counting":[81],"number":[83],"substrings.":[86],"Since":[87],"an":[92,214],"upper":[93],"bound":[94],"on":[95],"min-entropy,":[97],"LRS":[99,140,181,204,220],"inherently":[101],"provides":[102,190],"overestimated":[103],"outputs.":[104],"In":[105],"this":[106],"paper,":[107],"we":[108,137,177],"propose":[109,178],"two":[110],"techniques":[111],"non-IID":[118],"source":[119],"accurately.":[120],"first":[122],"technique":[123],"resolves":[124,185],"overestimation":[126,187],"problem":[127,188],"translating":[129],"into":[133],"min-entropy.":[135],"Next,":[136],"generalize":[138],"adopting":[143,162],"general":[145],"R\u00e9nyi":[146,154],"(i.e.,":[153],"order":[157,165],"two).":[158],"We":[159],"show":[160],"that":[161,183,200],"higher":[164],"can":[166],"reduce":[167],"variance":[169],"By":[173],"integrating":[174],"techniques,":[176],"generalized":[180,203],"effectively":[184],"stable":[191],"Theoretical":[194],"analysis":[195],"empirical":[197],"results":[198],"support":[199],"proposed":[202],"improves":[206],"estimation":[208],"accuracy":[209],"significantly,":[210],"makes":[212],"it":[213],"appealing":[215],"alternative":[216],"current-standard":[219],"estimator.":[221]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}