1% references_part03.bib — Part III (Data and Systematic Review Protocol). Every entry verified by a single2% Crossref or arXiv API lookup on 2026-11-03; see references_verification_part03.csv.3@article{page2021prisma,4 author = {Page, Matthew J. and McKenzie, Joanne E. and Bossuyt, Patrick M. and Boutron, Isabelle and Hoffmann, Tammy C. and Mulrow, Cynthia D. and Shamseer, Larissa and Tetzlaff, Jennifer M. and Akl, Elie A. and Brennan, Sue E. and Chou, Roger and Glanville, Julie and Grimshaw, Jeremy M. and Hr{\'o}bjartsson, Asbj{\o}rn and Lalu, Manoj M. and Li, Tianjing and Loder, Elizabeth W. and Mayo-Wilson, Evan and McDonald, Steve and McGuinness, Luke A. and Stewart, Lesley A. and Thomas, James and Tricco, Andrea C. and Welch, Vivian A. and Whiting, Penny and Moher, David},5 title = {The {PRISMA} 2020 statement: an updated guideline for reporting systematic reviews},6 journal = {BMJ},7 year = {2021},8 volume = {372},9 pages = {n71},10 doi = {10.1136/bmj.n71},11 note = {verified: crossref 2026-11-03}12}13@article{page2021prismaee,14 author = {Page, Matthew J. and Moher, David and Bossuyt, Patrick M. and Boutron, Isabelle and Hoffmann, Tammy C. and Mulrow, Cynthia D. and Shamseer, Larissa and Tetzlaff, Jennifer M. and Akl, Elie A. and Brennan, Sue E. and Chou, Roger and Glanville, Julie and Grimshaw, Jeremy M. and Hr{\'o}bjartsson, Asbj{\o}rn and Lalu, Manoj M. and Li, Tianjing and Loder, Elizabeth W. and Mayo-Wilson, Evan and McDonald, Steve and McGuinness, Luke A. and Stewart, Lesley A. and Thomas, James and Tricco, Andrea C. and Welch, Vivian A. and Whiting, Penny and McKenzie, Joanne E.},15 title = {{PRISMA} 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews},16 journal = {BMJ},17 year = {2021},18 volume = {372},19 pages = {n160},20 doi = {10.1136/bmj.n160},21 note = {verified: crossref 2026-11-03}22}23@inproceedings{petersen2008mapping,24 author = {Petersen, Kai and Feldt, Robert and Mujtaba, Shahid and Mattsson, Michael},25 title = {Systematic mapping studies in software engineering},26 booktitle = {Proceedings of the 12th International Conference on Evaluation and Assessment in Software Engineering (EASE)},27 series = {Electronic Workshops in Computing},28 publisher = {BCS Learning and Development},29 year = {2008},30 doi = {10.14236/ewic/EASE2008.8},31 note = {verified: crossref 2026-11-03}32}33@article{petersen2015mapping,34 author = {Petersen, Kai and Vakkalanka, Sairam and Kuzniarz, Ludwik},35 title = {Guidelines for conducting systematic mapping studies in software engineering: An update},36 journal = {Information and Software Technology},37 year = {2015},38 volume = {64},39 pages = {1--18},40 doi = {10.1016/j.infsof.2015.03.007},41 note = {verified: crossref 2026-11-03}42}43@article{tricco2018prismascr,44 author = {Tricco, Andrea C. and Lillie, Erin and Zarin, Wasifa and O'Brien, Kelly K. and Colquhoun, Heather and Levac, Danielle and Moher, David and Peters, Micah D. J. and Horsley, Tanya and Weeks, Laura and Hempel, Susanne and Akl, Elie A. and Chang, Christine and McGowan, Jessie and Stewart, Lesley and Hartling, Lisa and Aldcroft, Adrian and Wilson, Michael G. and Garritty, Chantelle and Lewin, Simon and Godfrey, Christina M. and Macdonald, Marilyn T. and Langlois, Etienne V. and Soares-Weiser, Karla and Moriarty, Jo and Clifford, Tammy and Tun{\c{c}}alp, {\"O}zge and Straus, Sharon E.},45 title = {{PRISMA} extension for scoping reviews ({PRISMA-ScR}): Checklist and explanation},46 journal = {Annals of Internal Medicine},47 year = {2018},48 volume = {169},49 number = {7},50 pages = {467--473},51 doi = {10.7326/M18-0850},52 note = {verified: crossref 2026-11-03}53}54@article{rethlefsen2021prismas,55 author = {Rethlefsen, Melissa L. and Kirtley, Shona and Waffenschmidt, Siw and Ayala, Ana Patricia and Moher, David and Page, Matthew J. and Koffel, Jonathan B.},56 title = {{PRISMA-S}: an extension to the {PRISMA} Statement for Reporting Literature Searches in Systematic Reviews},57 journal = {Systematic Reviews},58 year = {2021},59 volume = {10},60 pages = {39},61 doi = {10.1186/s13643-020-01542-z},62 note = {verified: crossref 2026-11-03}63}64@article{haddaway2022prismaflow,65 author = {Haddaway, Neal R. and Page, Matthew J. and Pritchard, Chris C. and McGuinness, Luke A.},66 title = {{PRISMA2020}: An {R} package and {Shiny} app for producing {PRISMA} 2020-compliant flow diagrams, with interactivity for optimised digital transparency and Open Synthesis},67 journal = {Campbell Systematic Reviews},68 year = {2022},69 volume = {18},70 number = {2},71 pages = {e1230},72 doi = {10.1002/cl2.1230},73 note = {verified: crossref 2026-11-03}74}75@article{gusenbauer2020search,76 author = {Gusenbauer, Michael and Haddaway, Neal R.},77 title = {Which academic search systems are suitable for systematic reviews or meta-analyses? {Evaluating} retrieval qualities of {Google Scholar}, {PubMed}, and 26 other resources},78 journal = {Research Synthesis Methods},79 year = {2020},80 volume = {11},81 number = {2},82 pages = {181--217},83 doi = {10.1002/jrsm.1378},84 note = {verified: crossref 2026-11-03}85}86@incollection{ley2002dblp,87 author = {Ley, Michael},88 title = {The {DBLP} computer science bibliography: Evolution, research issues, perspectives},89 booktitle = {String Processing and Information Retrieval (SPIRE 2002)},90 series = {Lecture Notes in Computer Science},91 volume = {2476},92 publisher = {Springer},93 year = {2002},94 pages = {1--10},95 doi = {10.1007/3-540-45735-6_1},96 note = {verified: crossref 2026-11-03}97}98@article{ley2009dblp,99 author = {Ley, Michael},100 title = {{DBLP}: some lessons learned},101 journal = {Proceedings of the VLDB Endowment},102 year = {2009},103 volume = {2},104 number = {2},105 pages = {1493--1500},106 doi = {10.14778/1687553.1687577},107 note = {verified: crossref 2026-11-03}108}109@article{ginsparg2011arxiv,110 author = {Ginsparg, Paul},111 title = {{ArXiv} at 20},112 journal = {Nature},113 year = {2011},114 volume = {476},115 pages = {145--147},116 doi = {10.1038/476145a},117 note = {verified: crossref 2026-11-03}118}119@misc{clement2019arxiv,120 author = {Clement, Colin B. and Bierbaum, Matthew and O'Keeffe, Kevin P. and Alemi, Alexander A.},121 title = {On the use of {arXiv} as a dataset},122 year = {2019},123 eprint = {1905.00075},124 archiveprefix = {arXiv},125 howpublished = {arXiv preprint arXiv:1905.00075},126 note = {verified: arxiv 2026-11-03}127}128@misc{priem2022openalex,129 author = {Priem, Jason and Piwowar, Heather and Orr, Richard},130 title = {{OpenAlex}: A fully-open index of scholarly works, authors, venues, institutions, and concepts},131 year = {2022},132 eprint = {2205.01833},133 archiveprefix = {arXiv},134 howpublished = {arXiv preprint arXiv:2205.01833},135 note = {verified: arxiv 2026-11-03}136}137@misc{kinney2023s2,138 author = {Kinney, Rodney and Anastasiades, Chloe and Authur, Russell and Beltagy, Iz and Bragg, Jonathan and Buraczynski, Alexandra and Cachola, Isabel and Candra, Stefan and Chandrasekhar, Yoganand and Cohan, Arman and others},139 title = {The {Semantic Scholar} Open Data Platform},140 year = {2023},141 eprint = {2301.10140},142 archiveprefix = {arXiv},143 howpublished = {arXiv preprint arXiv:2301.10140},144 note = {verified: arxiv 2026-11-03}145}146@misc{alperin2024openalex,147 author = {Alperin, Juan Pablo and Portenoy, Jason and Demes, Kyle and Larivi{\`e}re, Vincent and Haustein, Stefanie},148 title = {An analysis of the suitability of {OpenAlex} for bibliometric analyses},149 year = {2024},150 eprint = {2404.17663},151 archiveprefix = {arXiv},152 howpublished = {arXiv preprint arXiv:2404.17663},153 note = {verified: arxiv 2026-11-03}154}155@article{culbert2025openalex,156 author = {Culbert, Jack H. and Hobert, Anne and Jahn, Najko and Haupka, Nick and Schmidt, Marion and Donner, Paul and Mayr, Philipp},157 title = {Reference coverage analysis of {OpenAlex} compared to {Web of Science} and {Scopus}},158 journal = {Scientometrics},159 year = {2025},160 volume = {130},161 pages = {2475--2492},162 doi = {10.1007/s11192-025-05293-3},163 note = {verified: crossref 2026-11-03}164}165@article{scheidsteger2023openalex,166 author = {Scheidsteger, Thomas and Haunschild, Robin},167 title = {Which of the metadata with relevance for bibliometrics are the same and which are different when switching from {Microsoft Academic Graph} to {OpenAlex}?},168 journal = {Profesional de la informaci{\'o}n},169 year = {2023},170 doi = {10.3145/epi.2023.mar.09},171 note = {verified: crossref 2026-11-03}172}173@article{delgadoquiros2024completeness,174 author = {Delgado-Quir{\'o}s, Lorena and Ortega, Jos{\'e} Luis},175 title = {Completeness degree of publication metadata in eight free-access scholarly databases},176 journal = {Quantitative Science Studies},177 year = {2024},178 volume = {5},179 number = {1},180 pages = {31--49},181 doi = {10.1162/qss_a_00286},182 note = {verified: crossref 2026-11-03}183}184@article{visser2021comparison,185 author = {Visser, Martijn and van Eck, Nees Jan and Waltman, Ludo},186 title = {Large-scale comparison of bibliographic data sources: {Scopus}, {Web of Science}, {Dimensions}, {Crossref}, and {Microsoft Academic}},187 journal = {Quantitative Science Studies},188 year = {2021},189 volume = {2},190 number = {1},191 pages = {20--41},192 doi = {10.1162/qss_a_00112},193 note = {verified: crossref 2026-11-03}194}195@article{martinmartin2021comparison,196 author = {Mart{\'i}n-Mart{\'i}n, Alberto and Thelwall, Mike and Orduna-Malea, Enrique and Delgado L{\'o}pez-C{\'o}zar, Emilio},197 title = {{Google Scholar}, {Microsoft Academic}, {Scopus}, {Dimensions}, {Web of Science}, and {OpenCitations}' {COCI}: a multidisciplinary comparison of coverage via citations},198 journal = {Scientometrics},199 year = {2021},200 volume = {126},201 pages = {871--906},202 doi = {10.1007/s11192-020-03690-4},203 note = {verified: crossref 2026-11-03}204}205@article{mongeon2016coverage,206 author = {Mongeon, Philippe and Paul-Hus, Ad{\`e}le},207 title = {The journal coverage of {Web of Science} and {Scopus}: a comparative analysis},208 journal = {Scientometrics},209 year = {2016},210 volume = {106},211 pages = {213--228},212 doi = {10.1007/s11192-015-1765-5},213 note = {verified: crossref 2026-11-03}214}215@article{hendricks2020crossref,216 author = {Hendricks, Ginny and Tkaczyk, Dominika and Lin, Jennifer and Feeney, Patricia},217 title = {{Crossref}: The sustainable source of community-owned scholarly metadata},218 journal = {Quantitative Science Studies},219 year = {2020},220 volume = {1},221 number = {1},222 pages = {414--427},223 doi = {10.1162/qss_a_00022},224 note = {verified: crossref 2026-11-03}225}226@article{wang2020mag,227 author = {Wang, Kuansan and Shen, Zhihong and Huang, Chiyuan and Wu, Chieh-Han and Dong, Yuxiao and Kanakia, Anshul},228 title = {{Microsoft Academic Graph}: When experts are not enough},229 journal = {Quantitative Science Studies},230 year = {2020},231 volume = {1},232 number = {1},233 pages = {396--413},234 doi = {10.1162/qss_a_00021},235 note = {verified: crossref 2026-11-03}236}237@article{radev2013acl,238 author = {Radev, Dragomir R. and Muthukrishnan, Pradeep and Qazvinian, Vahed and Abu-Jbara, Amjad},239 title = {The {ACL} anthology network corpus},240 journal = {Language Resources and Evaluation},241 year = {2013},242 volume = {47},243 pages = {919--944},244 doi = {10.1007/s10579-012-9211-2},245 note = {verified: crossref 2026-11-03}246}247@article{fellegi1969linkage,248 author = {Fellegi, Ivan P. and Sunter, Alan B.},249 title = {A theory for record linkage},250 journal = {Journal of the American Statistical Association},251 year = {1969},252 volume = {64},253 number = {328},254 pages = {1183--1210},255 doi = {10.1080/01621459.1969.10501049},256 note = {verified: crossref 2026-11-03}257}258@book{christen2012matching,259 author = {Christen, Peter},260 title = {Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection},261 publisher = {Springer},262 address = {Berlin, Heidelberg},263 year = {2012},264 doi = {10.1007/978-3-642-31164-2},265 note = {verified: crossref 2026-11-03}266}267@article{lin2020preprints,268 author = {Lin, Jialiang and Yu, Yao and Zhou, Yu and Zhou, Zhiyang and Shi, Xiaodong},269 title = {How many preprints have actually been printed and why: a case study of computer science preprints on {arXiv}},270 journal = {Scientometrics},271 year = {2020},272 volume = {124},273 pages = {555--574},274 doi = {10.1007/s11192-020-03430-8},275 note = {verified: crossref 2026-11-03}276}277@article{cabanac2021preprint,278 author = {Cabanac, Guillaume and Oikonomidi, Theodora and Boutron, Isabelle},279 title = {Day-to-day discovery of preprint--publication links},280 journal = {Scientometrics},281 year = {2021},282 volume = {126},283 pages = {5285--5304},284 doi = {10.1007/s11192-021-03900-7},285 note = {verified: crossref 2026-11-03}286}287@article{wang2013window,288 author = {Wang, Jian},289 title = {Citation time window choice for research impact evaluation},290 journal = {Scientometrics},291 year = {2013},292 volume = {94},293 pages = {851--872},294 doi = {10.1007/s11192-012-0775-9},295 note = {verified: crossref 2026-11-03 (online 2012, volume 94 = 2013)}296}297@article{waltman2016review,298 author = {Waltman, Ludo},299 title = {A review of the literature on citation impact indicators},300 journal = {Journal of Informetrics},301 year = {2016},302 volume = {10},303 number = {2},304 pages = {365--391},305 doi = {10.1016/j.joi.2016.02.007},306 note = {verified: crossref 2026-11-03}307}308@article{fortunato2018science,309 author = {Fortunato, Santo and Bergstrom, Carl T. and B{\"o}rner, Katy and Evans, James A. and Helbing, Dirk and Milojevi{\'c}, Sta{\v{s}}a and Petersen, Alexander M. and Radicchi, Filippo and Sinatra, Roberta and Uzzi, Brian and Vespignani, Alessandro and Waltman, Ludo and Wang, Dashun and Barab{\'a}si, Albert-L{\'a}szl{\'o}},310 title = {Science of science},311 journal = {Science},312 year = {2018},313 volume = {359},314 number = {6379},315 pages = {eaao0185},316 doi = {10.1126/science.aao0185},317 note = {verified: crossref 2026-11-03}318}319@article{nosek2018preregistration,320 author = {Nosek, Brian A. and Ebersole, Charles R. and DeHaven, Alexander C. and Mellor, David T.},321 title = {The preregistration revolution},322 journal = {Proceedings of the National Academy of Sciences},323 year = {2018},324 volume = {115},325 number = {11},326 pages = {2600--2606},327 doi = {10.1073/pnas.1708274114},328 note = {verified: crossref 2026-11-03}329}330@article{vannoorden2023retractions,331 author = {Van Noorden, Richard},332 title = {More than 10,000 research papers were retracted in 2023 --- a new record},333 journal = {Nature},334 year = {2023},335 volume = {624},336 pages = {479--481},337 doi = {10.1038/d41586-023-03974-8},338 note = {verified: crossref 2026-11-03}339}340