{"id":"https://openalex.org/W7133301959","doi":"https://doi.org/10.5281/zenodo.18850283","title":"Citation Matrix and Metadata Derived from the PKG24S4 Database","display_name":"Citation Matrix and Metadata Derived from the PKG24S4 Database","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133301959","doi":"https://doi.org/10.5281/zenodo.18850283"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.18850283","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18850283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18850283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103043214","display_name":"Laura Menotti","orcid":"https://orcid.org/0000-0002-0676-682X"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Menotti, Laura","raw_affiliation_strings":["University of Padua"],"raw_orcid":"https://orcid.org/0000-0002-0676-682X","affiliations":[{"raw_affiliation_string":"University of Padua","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098947055","display_name":"Mirco Cazzaro","orcid":"https://orcid.org/0009-0006-3856-7207"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cazzaro, Mirco","raw_affiliation_strings":["University of Padua"],"raw_orcid":"https://orcid.org/0009-0006-3856-7207","affiliations":[{"raw_affiliation_string":"University of Padua","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078254809","display_name":"Gianmaria Silvello","orcid":"https://orcid.org/0000-0003-4970-4554"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvello, Gianmaria","raw_affiliation_strings":["University of Padua"],"raw_orcid":"https://orcid.org/0000-0003-4970-4554","affiliations":[{"raw_affiliation_string":"University of Padua","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084898176","display_name":"Matteo Lissandrini","orcid":"https://orcid.org/0000-0001-7922-5998"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lissandrini, Matteo","raw_affiliation_strings":["University of Verona"],"raw_orcid":"https://orcid.org/0000-0001-7922-5998","affiliations":[{"raw_affiliation_string":"University of Verona","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087078518","display_name":"Peter Buneman","orcid":"https://orcid.org/0009-0004-9056-8587"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Buneman, Peter","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":"https://orcid.org/0009-0004-9056-8587","affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7759000062942505},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7160999774932861},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6712999939918518},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5530999898910522},{"id":"https://openalex.org/keywords/flat-file-database","display_name":"Flat file database","score":0.45399999618530273},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.4284999966621399},{"id":"https://openalex.org/keywords/b-tree","display_name":"B-tree","score":0.4189000129699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853999733924866},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7759000062942505},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7160999774932861},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6712999939918518},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6381000280380249},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C201743585","wikidata":"https://www.wikidata.org/wiki/Q1373925","display_name":"Flat file database","level":5,"score":0.45399999618530273},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4456000030040741},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.4316999912261963},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.4284999966621399},{"id":"https://openalex.org/C78669399","wikidata":"https://www.wikidata.org/wiki/Q677051","display_name":"B-tree","level":3,"score":0.4189000129699707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C105345328","wikidata":"https://www.wikidata.org/wiki/Q206276","display_name":"Citation analysis","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C40350719","wikidata":"https://www.wikidata.org/wiki/Q2451637","display_name":"Torrent file","level":4,"score":0.3019999861717224},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C178315738","wikidata":"https://www.wikidata.org/wiki/Q603441","display_name":"Bibliometrics","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C70000936","wikidata":"https://www.wikidata.org/wiki/Q4672467","display_name":"Access method","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.18850283","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18850283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"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":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18850283","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18850283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Version":[0],"Upadate:":[1],"we":[2,327,421,636,653,902],"provide":[3],"zipped":[4],"files":[5,80,473,944],"for":[6,82,168,205,249,382,389,396,447,696,737,785,805,832,948,955],"faster":[7],"download.":[8],"This":[9,926],"repository":[10],"contains":[11,647,734],"sparse":[12],"matrices":[13,77],"and":[14,19,27,46,66,69,72,78,87,92,102,116,153,189,220,264,301,320,394,464,494,599,617,640,699,713,727,752,772,789,835,861,896,910,953],"auxiliary":[15],"tables":[16,125,625,726],"describing":[17],"citation":[18,49,68,124,158,195,368,416,892],"authorship":[20,70],"relations":[21],"among":[22],"biomedical":[23],"papers,":[24,100,112],"clinical":[25,63,103,114,173,210,254,307,554,563,568,574,807],"trials,":[26,64,115],"patents":[28,321,577,584],"derived":[29],"from":[30,556,560,578,583,611],"the":[31,59,157,178,183,190,194,215,221,226,231,236,238,259,265,270,279,286,293,312,323,344,360,400,407,415,424,441,444,455,467,479,484,488,498,520,621,657,664,685,724,728,738,872,914,935,939,959,966],"PKG24S4":[32,499,512],"version":[33],"of":[34,108,156,185,223,225,267,269,289,402,431,487,511,536,603,704,851,891,917,930,961],"PubMedKG":[35],"(PKG).":[36],"The":[37,353,367,470,509,667,775,841,942],"source":[38,345,361,686,873,940],"database":[39,346,362,501],"integrates":[40],"PubMed,":[41],"ClinicalTrials.gov,":[42],"USPTO":[43,579],"(via":[44],"PatentsView),":[45],"additional":[47],"open":[48],"resources":[50],"into":[51,75],"a":[52,786,879],"unified":[53],"relational":[54,500],"schema.":[55],"We":[56,97,144,435,496,517,605,690,710,877],"focus":[57,518],"on":[58,459,519,923],"core":[60],"entities":[61],"(papers,":[62],"patents)":[65],"their":[67],"links,":[71],"reorganize":[73],"them":[74,701,791,837],"machine\u2011readable":[76],"TSV":[79,147,163,200,244,438,452,472,669,843],"suitable":[81],"large\u2011scale":[83],"network":[84],"analysis,":[85],"scientometrics,":[86],"method":[88],"development":[89],"in":[90,105,123,193,235,343,359,372,406,414,466,551,684,723,871,938,965],"bibliometrics":[91],"science\u2011of\u2011science":[93],"research.":[94],"Data":[95,490,493],"Statistics":[96],"consider":[98],"all":[99,412,783,830,885,931],"patents,":[101],"trials":[104,555,810],"PKG24S4,":[106],"consisting":[107,155],"40,363,572":[109,886],"nodes:":[110],"38,217,186":[111],"530,522":[113],"1,615,864":[117],"patents.":[118,594],"Nodes":[119],"that":[120,285,623,638,855],"appear":[121],"only":[122,656,715],"(C04,":[126],"C12,":[127],"C16)":[128],"but":[129],"lack":[130],"metadata":[131,151,525],"(in":[132],"C01,":[133],"C11,":[134],"or":[135,678,693,864],"C15)":[136],"are":[137,356,720,869,945],"retained":[138],"with":[139,165,202,246,322,333,443,457,573,593,650,801,811,854],"missing":[140],"metadata.":[141],"Files":[142,161],"Outline":[143],"share":[145],"five":[146],"files,":[148],"three":[149,379,889],"comprising":[150],"information":[152,276,458,689,736],"two":[154,471,748],"matrix.":[159],"Metadata":[160],"node_id_type.zip:":[162],"file":[164,201,245,291,439,453],"one":[166,203,247,381,388,395,627,757,947,954],"row":[167,176,191,204,213,248,257,288,397,462,481,628,659,956],"each":[169,206,250,290,403,448,461,530,697,806,833,899,962],"node":[170,179,186,207,216,227,251,260,271,329,698],"(paper,":[171,208,252],"patent,":[172,209,253],"trial).":[174,211,255,569],"Each":[175,212,256],"reports":[177,214,258],"identifier":[180,217,261],"(first":[181,218,262],"column),":[182,188],"type":[184],"(second":[187,228,272],"id":[192],"matrix":[196,369,417,883],"(third":[197],"column).":[198,229,273],"node_year.zip:":[199],"column)":[219,263],"year":[222,232,665,681],"publication":[224,604,607],"If":[230,274],"is":[233,241,277,282,292,370,433,513,682,765,773,817,824],"unavailable":[234,683,870],"database,":[237],"second":[239,280],"column":[240,281,391,445,793,823,839,950],"empty.":[242,283],"node_authors.zip:":[243],"list":[266,535,542,850,866,916],"authors":[268,537,598,692,725,744,784,868],"author":[275,354,548,708,718,730],"unavailable,":[278],"Note":[284],"first":[287,480,485,658],"header":[294],"information.":[295],"Node":[296],"Identifiers":[297],"PKG":[298],"stores":[299],"PMIDs":[300,649],"patent":[302,834],"identifiers":[303,309,330,355,549],"as":[304,331,342,358,702,767],"integers,":[305],"while":[306,933],"trial":[308,564],"already":[310],"carry":[311],"prefix":[313],"\u201cNCT\u201d.":[314],"To":[315],"avoid":[316],"collisions":[317],"between":[318,597],"papers":[319,561,586],"same":[324,739],"numeric":[325],"ID,":[326],"normalize":[328],"strings":[332],"explicit":[334,821],"prefixes:":[335],"Papers:":[336,779],"PMID":[337,661,788],"(e.g.,":[338,347,351],"\u201cPMID245\u201d).":[339],"Clinical":[340,795],"trials:":[341,796],"\u201cNCT00887523\u201d).":[348],"Patents:":[349,826],"PTID":[350],"\u201cPTID123\u201d).":[352],"kept":[357],"(i.e.,":[363],"integers).":[364],"Citation":[365,875],"Matrix":[366,876],"shared":[371],"Compressed":[373],"Sparse":[374],"Row":[375],"(CSR)":[376],"format,":[377],"using":[378],"arrays:":[380],"non-zero":[383,449],"values":[384],"(called":[385],"*data":[386],"array*),":[387],"corresponding":[390,949],"indices":[392,468,951],"(`indices.tsv`),":[393],"pointers":[398,957],"indicating":[399,958],"start":[401,960],"row's":[404,963],"data":[405,426,964],"other":[408,967],"arrays":[409,968],"(`indptr.tsv`).":[410],"Since":[411],"edges":[413],"have":[418,745],"unit":[419],"weight,":[420],"can":[422,504],"omit":[423],"separate":[425],"array.":[427,469,489],"A":[428],"single":[429],"array":[430,456],"ones":[432],"sufficient.":[434],"share:":[436],"indices.zip:":[437],"representing":[440,454],"arry":[442],"index":[446],"value":[450],"indptr.zip:":[451],"where":[460],"starts":[463],"ends":[465],"do":[474],"not":[475,721],"contain":[476,626,642],"an":[477,768],"header,":[478],"corresponds":[482],"to":[483,532,562,585,912],"element":[486],"Construction":[491],"Source":[492],"Tables":[495],"use":[497],"(https://doi.org/10.1038/s41597-025-05343-8),":[502],"which":[503],"be":[505],"downloaded":[506],"at:":[507,515],"https://www.scidb.cn/en/detail?dataSetId=4.":[508],"documentation":[510],"available":[514],"https://github.com/PubMedKG/PubMedKG.github.io/.":[516],"following":[521],"tables:":[522],"C01Papers:":[523],"paper":[524,531],"(PubMed":[526],"articles).":[527],"C02LinkPapersAuthors:":[528],"links":[529],"its":[533],"ordered":[534],"(AIDs).":[538,601],"C04ReferenceListPapers:":[539],"paper\u2011to\u2011paper":[540],"reference":[541],"(paper":[543,566],"citing":[544,567,588,900],"papers).":[545],"C07Authors:":[546],"disambiguated":[547,707],"(AID)":[550],"PKG.":[552],"C11ClinicalTrials:":[553],"ClinicalTrials.gov.":[557],"C12LinkPapersClinicaltrials:":[558],"citations":[559,582],"records":[565],"C14Investigators:":[570],"investigators":[571,800],"associated":[572,592,853],"trials.":[575],"C15Patents:":[576],"(PatentsView).":[580],"C16LinkPatentsPapers:":[581],"(patent":[587],"paper).":[589],"C19Inventors:":[590],"inventors":[591,600,831],"C20LinkAuthorsInventors:":[595],"mapping":[596],"Year":[602],"extract":[606,691],"(or":[608],"registration)":[609],"years":[610],"C01":[612,646],"(papers),":[613],"C11":[614,639],"(clinical":[615],"trials),":[616],"C15":[618,641],"(patents),":[619],"under":[620],"assumption":[622],"these":[624],"per":[629,660],"entity":[630],"after":[631,857],"deduplication.":[632],"During":[633],"quality":[634],"checks":[635],"observed":[637],"no":[643,820],"duplicates,":[644],"whereas":[645],"3,159":[648],"multiple":[651,812],"rows;":[652],"therefore":[654],"keep":[655,714],"when":[662],"creating":[663],"table.":[666],"resulting":[668,842,943],"node_year.tsv":[670],"has:":[671,845],"node_id:":[672,846],"normalized":[673,847],"identifier.":[674,848],"year:":[675],"four\u2011digit":[676],"year,":[677],"empty":[679,865],"if":[680,867],"tables.":[687,874,941],"Authors":[688],"analogous":[694],"contributors":[695],"store":[700],"lists":[703],"AIDs":[705,852],"(PKG\u2019s":[706],"IDs).":[709],"discard":[711],"names":[712,719],"AIDs,":[716],"since":[717,819],"stored":[722],"master":[729],"table":[731],"A02AuthorList":[732],"often":[733],"inconsistent":[735],"AID":[740,753,763,859],"(over":[741],"5":[742],"million":[743,758],"at":[746],"least":[747],"different":[749],"name":[750],"variants,":[751],"0":[754,764,860],"aggregates":[755],"over":[756,884],"distinct":[759],"names).":[760],"In":[761],"addition,":[762],"treated":[766],"invalid":[769],"\u201cunknown":[770],"author\u201d":[771],"discarded.":[774],"extraction":[776],"logic":[777],"is:":[778],"Use":[780,797,827],"`C02LinkPapersAuthors`,":[781],"selecting":[782,799,829],"given":[787],"ordering":[790,822,836],"by":[792,838],"AuthorOrder.":[794],"`C14Investigators`,":[798],"role":[802],"PRINCIPAL_INVESTIGATOR":[803],"(PI)":[804],"trial.":[808],"For":[809,898],"PIs":[813],"(37,791":[814],"cases),":[815],"order":[816],"arbitrary":[818],"provided.":[825],"`C19Inventors`,":[828],"InventorSequence.":[840],"node_authors.tsv":[844],"list_auth:":[849],"node,":[856,901],"removing":[858],"null":[862],"values,":[863],"construct":[878],"sparse,":[880],"directed":[881],"adjacency":[882],"nodes":[887],"capturing":[888],"types":[890],"edges:":[893],"paper\u2192paper,":[894],"paper\u2192clinical_trial,":[895],"patent\u2192paper.":[897],"ran":[903],"dedicated":[904],"SQL":[905],"queries":[906],"against":[907],"C04ReferenceListPapers,":[908],"C12LinkPapersClinicaltrials,":[909],"C16LinkPatentsPapers":[911],"retrieve":[913],"complete":[915],"cited":[918],"entities,":[919],"rather":[920],"than":[921],"relying":[922],"pre\u2011aggregated":[924],"views.":[925],"strategy":[927],"ensures":[928],"coverage":[929],"references":[932],"respecting":[934],"directional":[936],"semantics":[937],"two:":[946],"(indices.tsv),":[952],"(indptr.tsv).":[969]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-02-27T00:00:00"}
