{"id":"https://openalex.org/W4287026417","doi":"https://doi.org/10.1137/25m1736657","title":"Pointwise Distance Distributions for Detecting Near-Duplicates in Large Materials Databases","display_name":"Pointwise Distance Distributions for Detecting Near-Duplicates in Large Materials Databases","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W4287026417","doi":"https://doi.org/10.1137/25m1736657"},"language":"en","primary_location":{"id":"doi:10.1137/25m1736657","is_oa":false,"landing_page_url":"https://doi.org/10.1137/25m1736657","pdf_url":null,"source":{"id":"https://openalex.org/S77200987","display_name":"SIAM Journal on Applied Mathematics","issn_l":"0036-1399","issn":["0036-1399","1095-712X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Applied Mathematics","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.04798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065160818","display_name":"Daniel Widdowson","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel E. Widdowson","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067536683","display_name":"Vitaliy Kurlin","orcid":"https://orcid.org/0000-0001-5328-5351"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vitaliy A. Kurlin","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, UK"],"raw_orcid":"https://orcid.org/0000-0001-5328-5351","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":2.996e-05,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"86","issue":"3","first_page":"898","last_page":"918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12613","display_name":"X-ray Diffraction in Crystallography","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12613","display_name":"X-ray Diffraction in Crystallography","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.8208283185958862},{"id":"https://openalex.org/keywords/euclidean-geometry","display_name":"Euclidean geometry","score":0.6228442788124084},{"id":"https://openalex.org/keywords/euclidean-space","display_name":"Euclidean space","score":0.5563819408416748},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.5148257613182068},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.49887704849243164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4892423152923584},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.4885745942592621},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4736536741256714},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.45950552821159363},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.4561367332935333},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.43945109844207764},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.3419038653373718},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.31676584482192993},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.25770488381385803},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09313204884529114}],"concepts":[{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.8208283185958862},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.6228442788124084},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.5563819408416748},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.5148257613182068},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.49887704849243164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4892423152923584},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.4885745942592621},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4736536741256714},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.45950552821159363},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.4561367332935333},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.43945109844207764},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.3419038653373718},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.31676584482192993},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.25770488381385803},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09313204884529114},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/25m1736657","is_oa":false,"landing_page_url":"https://doi.org/10.1137/25m1736657","pdf_url":null,"source":{"id":"https://openalex.org/S77200987","display_name":"SIAM Journal on Applied Mathematics","issn_l":"0036-1399","issn":["0036-1399","1095-712X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Applied Mathematics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2108.04798","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.04798","pdf_url":"https://arxiv.org/pdf/2108.04798","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2108.04798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.04798","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.04798","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.04798","pdf_url":"https://arxiv.org/pdf/2108.04798","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G6663847162","display_name":null,"funder_award_id":"EP/X018474/1","funder_id":"https://openalex.org/F4320307035","funder_display_name":"New Horizons Foundation"}],"funders":[{"id":"https://openalex.org/F4320307035","display_name":"New Horizons Foundation","ror":"https://ror.org/02jxgq335"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W143502885","https://openalex.org/W42113618","https://openalex.org/W2103468410","https://openalex.org/W2480115405","https://openalex.org/W3197542402","https://openalex.org/W1856228368","https://openalex.org/W2971527398","https://openalex.org/W82829784","https://openalex.org/W2069165070","https://openalex.org/W2105228010"],"abstract_inverted_index":{"Many":[0],"real":[1],"objects":[2],"are":[3,103],"modeled":[4],"as":[5,11,195],"discrete":[6,40,132],"sets":[7,44,149],"of":[8,38,45,89,119,144,199],"points,":[9],"such":[10,69],"corners":[12],"or":[13,30],"other":[14],"salient":[15],"features.":[16],"For":[17],"our":[18],"main":[19],"applications":[20],"in":[21,27,56,78,91,115,136,150,181],"chemistry,":[22],"points":[23,47,102],"represent":[24],"atomic":[25],"centers":[26],"a":[28,31,57,86,92,116,171,192,196,200],"molecule":[29],"solid":[32],"material.":[33],"We":[34,123],"study":[35],"the":[36,63,82,100,105,120,125,139,142,162,184],"problem":[37],"classifying":[39],"(finite":[41],"and":[42,113,134],"periodic)":[43],"unordered":[46],"under":[48],"isometry,":[49],"which":[50],"is":[51,108,177],"any":[52,131],"transformation":[53],"preserving":[54],"distances":[55],"metric":[58,97],"space.":[59],"Experimental":[60],"noise":[61],"motivates":[62],"new":[64],"practical":[65],"requirement":[66],"to":[67,85,109,138,190],"make":[68],"invariants":[70,112],"Lipschitz":[71],"continuous":[72],"so":[73],"that":[74],"perturbing":[75],"every":[76],"point":[77],"its":[79],"epsilon-neighborhood":[80],"changes":[81],"invariant":[83],"up":[84],"constant":[87],"multiple":[88],"epsilon":[90],"suitable":[93],"distance":[94],"satisfying":[95],"all":[96,111,147],"axioms.":[98],"Since":[99],"given":[101],"unordered,":[104],"key":[106],"challenge":[107],"compute":[110],"metrics":[114],"near-linear":[117],"time":[118],"input":[121],"size.":[122],"define":[124],"Pointwise":[126],"Distance":[127],"Distribution":[128],"(PDD)":[129],"for":[130,146],"set":[133],"prove,":[135],"addition":[137],"properties":[140],"above,":[141],"completeness":[143],"PDD":[145,154,185],"periodic":[148],"general":[151],"position.":[152],"The":[153,175],"can":[155],"compare":[156],"nearly":[157],"2":[158,168],"million":[159],"crystals":[160],"from":[161],"world's":[163],"five":[164],"largest":[165],"databases":[166],"within":[167],"hours":[169],"on":[170],"modest":[172],"desktop":[173],"computer.":[174],"impact":[176],"upholding":[178],"data":[179],"integrity":[180],"crystallography":[182],"because":[183],"will":[186],"not":[187],"allow":[188],"anyone":[189],"claim":[191],"`new'":[193],"material":[194],"noisy":[197],"disguise":[198],"known":[201],"crystal.":[202]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2022-07-25T00:00:00"}
