{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T19:08:15Z","timestamp":1777662495970,"version":"3.51.4"},"reference-count":60,"publisher":"MIT Press","issue":"3","license":[{"start":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T00:00:00Z","timestamp":1683072000000},"content-version":"vor","delay-in-days":122,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-19-1-0354"],"award-info":[{"award-number":["FA9550-19-1-0354"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000925","name":"Templeton Foundation","doi-asserted-by":"publisher","award":["62452"],"award-info":[{"award-number":["62452"]}],"id":[{"id":"10.13039\/100000925","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union\u2019s Horizon","award":["No 810115 \u2013 DYNASNET"],"award-info":[{"award-number":["No 810115 \u2013 DYNASNET"]}]},{"name":"The Eric and Wendy Schmidt Fund for Strategic\n                                Innovation","award":["G-22-63228"],"award-info":[{"award-number":["G-22-63228"]}]},{"name":"NSF","award":["SES-2219575"],"award-info":[{"award-number":["SES-2219575"]}]}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Science of science (SciSci) is a growing field encompassing diverse interdisciplinary research programs that study the processes underlying science. The field has benefited greatly from access to massive digital databases containing the products of scientific discourse\u2014including publications, journals, patents, books, conference proceedings, and grants. The subsequent proliferation of mathematical models and computational techniques for quantifying the dynamics of innovation and success in science has made it difficult to disentangle universal scientific processes from those dependent on specific databases, data-processing decisions, field practices, etc. Here we present pySciSci, a freely available and easily adaptable package for the analysis of large-scale bibliometric data. The pySciSci package standardizes access to many of the most common data sets in SciSci and provides efficient implementations of common and advanced analytical techniques.<\/jats:p>","DOI":"10.1162\/qss_a_00260","type":"journal-article","created":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T09:55:46Z","timestamp":1683107746000},"page":"700-710","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":16,"title":["Reproducible science of science at scale:\n                    <i>pySciSci<\/i>"],"prefix":"10.1162","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0099-7480","authenticated-orcid":true,"given":"Alexander J.","family":"Gates","sequence":"first","affiliation":[{"name":"School of Data Science, University of Virginia, Charlottesville, VA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4028-3522","authenticated-orcid":true,"given":"Albert-L\u00e1szl\u00f3","family":"Barab\u00e1si","sequence":"additional","affiliation":[{"name":"Network Science Institute, Northeastern University, Boston, MA"},{"name":"Channing Division of Network Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, MA"}]}],"member":"281","published-online":{"date-parts":[[2023,12,8]]},"reference":[{"issue":"4","key":"2024032016303499600_bib1","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1016\/j.joi.2017.08.007","article-title":"Bibliometrix: An R-tool\n                        for comprehensive science mapping analysis","volume":"11","author":"Aria","year":"2017","journal-title":"Journal\n                        of Informetrics"},{"key":"2024032016303499600_bib2","volume-title":"Network science","author":"Barab\u00e1si","year":"2016"},{"issue":"3\u20134","key":"2024032016303499600_bib3","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1016\/S0378-4371(02)00736-7","article-title":"Evolution of the social network of\n                        scientific collaborations","volume":"311","author":"Barab\u00e1si","year":"2002","journal-title":"Physica A: Statistical\n                        Mechanics and its Applications"},{"issue":"10","key":"2024032016303499600_bib4","doi-asserted-by":"publisher","first-page":"P10008","DOI":"10.1088\/1742-5468\/2008\/10\/P10008","article-title":"Fast unfolding of communities in large\n                        networks","volume":"2008","author":"Blondel","year":"2008","journal-title":"Journal of Statistical Mechanics: Theory\n                        and Experiment"},{"issue":"6","key":"2024032016303499600_bib5","doi-asserted-by":"publisher","first-page":"e6022","DOI":"10.1371\/journal.pone.0006022","article-title":"A principal component analysis of 39\n                        scientific impact measures","volume":"4","author":"Bollen","year":"2009","journal-title":"PLOS ONE"},{"issue":"2","key":"2024032016303499600_bib6","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1023\/A:1014800407876","article-title":"Advantages and limitations in the use of\n                        impact factor measures for the assessment of research\n                        performance","volume":"53","author":"Bordons","year":"2002","journal-title":"Scientometrics"},{"issue":"12","key":"2024032016303499600_bib7","doi-asserted-by":"publisher","first-page":"2389","DOI":"10.1002\/asi.21419","article-title":"Co-citation analysis, bibliographic\n                        coupling, and direct citation: Which citation approach represents the\n                        research front most accurately?","volume":"61","author":"Boyack","year":"2010","journal-title":"Journal of the American Society for Information Science and\n                        Technology"},{"issue":"3","key":"2024032016303499600_bib8","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1002\/asi.20317","article-title":"Citespace II: Detecting and visualizing\n                        emerging trends and transient patterns in scientific\n                        literature","volume":"57","author":"Chen","year":"2006","journal-title":"Journal of the American Society for\n                        Information Science and Technology"},{"issue":"7679","key":"2024032016303499600_bib9","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1038\/551163a","article-title":"The catalogue that made metrics, and\n                        changed science","volume":"551","author":"Csiszar","year":"2017","journal-title":"Nature"},{"key":"2024032016303499600_bib10","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1038\/s41593-020-0658-y","article-title":"The extent and drivers of gender imbalance in neuroscience\n                        reference lists","volume":"23","author":"Dworkin","year":"2020","journal-title":"Nature Neuroscience"},{"issue":"6379","key":"2024032016303499600_bib11","doi-asserted-by":"publisher","first-page":"eaao0185","DOI":"10.1126\/science.aao0185","article-title":"Science of science","volume":"359","author":"Fortunato","year":"2018","journal-title":"Science"},{"issue":"3","key":"2024032016303499600_bib12","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1287\/mnsc.2015.2366","article-title":"A dynamic network measure of\n                        technological change","volume":"63","author":"Funk","year":"2017","journal-title":"Management Science"},{"issue":"4","key":"2024032016303499600_bib13","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1016\/j.joi.2011.06.006","article-title":"Bibliometric impact assessment with R\n                        and the CITAN package","volume":"5","author":"Gagolewski","year":"2011","journal-title":"Journal of\n                        Informetrics"},{"issue":"35","key":"2024032016303499600_bib14","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.21105\/joss.01264","article-title":"CluSim: A Python package for calculating\n                        clustering similarity","volume":"4","author":"Gates","year":"2019","journal-title":"Journal of Open Source\n                        Software"},{"issue":"7845","key":"2024032016303499600_bib15","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1038\/d41586-021-00314-6","article-title":"A wealth of discovery built on the Human\n                        Genome Project\u2014By the numbers","volume":"590","author":"Gates","year":"2021","journal-title":"Nature"},{"key":"2024032016303499600_bib16","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1038\/d41586-019-03308-7","article-title":"Nature\u2019s reach: Narrow work has\n                        broad impact","volume":"575","author":"Gates","year":"2019","journal-title":"Nature"},{"issue":"1","key":"2024032016303499600_bib17","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1038\/s41598-019-44892-y","article-title":"Element-centric clustering comparison\n                        unifies overlaps and hierarchy","volume":"9","author":"Gates","year":"2019","journal-title":"Scientific\n                        Reports"},{"issue":"1","key":"2024032016303499600_bib18","doi-asserted-by":"publisher","DOI":"10.5399\/osu\/ADVJRNL.3.1.3","article-title":"The NSF ADVANCE Network of\n                        Organizations","volume":"3","author":"Gold","year":"2022","journal-title":"ADVANCE Journal"},{"key":"2024032016303499600_bib19","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.knosys.2018.03.022","article-title":"Graph embedding techniques,\n                        applications, and performance: A survey","volume":"151","author":"Goyal","year":"2018","journal-title":"Knowledge-Based Systems"},{"issue":"3","key":"2024032016303499600_bib20","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1007\/s11192-011-0482-y","article-title":"Mapping scientific\n                        institutions","volume":"89","author":"Grauwin","year":"2011","journal-title":"Scientometrics"},{"key":"2024032016303499600_bib21","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1145\/2939672.2939754","article-title":"node2vec: Scalable feature learning for\n                        networks","volume-title":"Proceedings of the 22nd ACM SIGKDD\n                        International Conference on Knowledge Discovery and Data Mining","author":"Grover","year":"2016"},{"issue":"46","key":"2024032016303499600_bib22","doi-asserted-by":"publisher","first-page":"16569","DOI":"10.1073\/pnas.0507655102","article-title":"An index to quantify an individual\u2019s scientific\n                        research output","volume":"102","author":"Hirsch","year":"2005","journal-title":"Proceedings of the National Academy\n                        of Sciences"},{"issue":"9","key":"2024032016303499600_bib23","doi-asserted-by":"publisher","first-page":"4609","DOI":"10.1073\/pnas.1914221117","article-title":"Historical comparison of gender\n                        inequality in scientific careers across countries and\n                        disciplines","volume":"117","author":"Huang","year":"2020","journal-title":"Proceedings of the National Academy of\n                        Sciences"},{"issue":"24","key":"2024032016303499600_bib24","doi-asserted-by":"publisher","first-page":"7426","DOI":"10.1073\/pnas.1424329112","article-title":"Defining and identifying sleeping\n                        beauties in science","volume":"112","author":"Ke","year":"2015","journal-title":"Proceedings of the National\n                        Academy of Sciences"},{"key":"2024032016303499600_bib25","doi-asserted-by":"publisher","DOI":"10.1177\/2378023117738903","article-title":"Men set their own cites high: Gender and self-citation across\n                        fields and over time","volume":"3","author":"King","year":"2017","journal-title":"Socius"},{"key":"2024032016303499600_bib26","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/504211a","article-title":"Bibliometrics: Global gender disparities in\n                        science","volume":"504","author":"Larivi\u00e8re","year":"2013","journal-title":"Nature"},{"issue":"2","key":"2024032016303499600_bib27","doi-asserted-by":"publisher","first-page":"1535","DOI":"10.1007\/s11192-014-1238-2","article-title":"Open data and open code for big science\n                        of science studies","volume":"101","author":"Light","year":"2014","journal-title":"Scientometrics"},{"issue":"7714","key":"2024032016303499600_bib28","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1038\/s41586-018-0315-8","article-title":"Hot streaks in artistic, cultural, and\n                        scientific careers","volume":"559","author":"Liu","year":"2018","journal-title":"Nature"},{"key":"2024032016303499600_bib29","doi-asserted-by":"publisher","first-page":"556282","DOI":"10.3389\/fdata.2020.556282","article-title":"CADRE: A collaborative, cloud-based solution for big\n                        bibliographic data research in academic libraries","volume":"3","author":"Mabry","year":"2020","journal-title":"Frontiers in Big Data"},{"issue":"4","key":"2024032016303499600_bib30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3012704","article-title":"A survey of link prediction in complex\n                        networks","volume":"49","author":"Martinez","year":"2016","journal-title":"ACM Computing Surveys"},{"issue":"4","key":"2024032016303499600_bib31","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1002\/asi.23089","article-title":"Detecting the historical roots of\n                        research fields by reference publication year spectroscopy\n                        (RPYS)","volume":"65","author":"Marx","year":"2014","journal-title":"Journal of the Association for Information\n                        Science and Technology"},{"key":"2024032016303499600_bib32","doi-asserted-by":"publisher","first-page":"56","DOI":"10.25080\/Majora-92bf1922-00a","article-title":"Data structures for statistical\n                        computing in Python","volume-title":"Proceedings of the 9th Python in Science Conference","author":"McKinney","year":"2010"},{"issue":"1","key":"2024032016303499600_bib33","doi-asserted-by":"publisher","DOI":"10.3145\/epi.2020.ene.03","article-title":"Software tools for conducting bibliometric analysis in\n                        science: An up-to-date review","volume":"29","author":"Moral-Mu\u00f1oz","year":"2020","journal-title":"Profesional de la\n                        Informaci\u00f3n"},{"key":"2024032016303499600_bib34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.02785","article-title":"Unsupervised embedding of trajectories\n                        captures the latent structure of mobility","author":"Murray","year":"2020","journal-title":"arXiv\n                        preprint"},{"issue":"Suppl. 1","key":"2024032016303499600_bib35","doi-asserted-by":"publisher","first-page":"5200","DOI":"10.1073\/pnas.0307545100","article-title":"Coauthorship networks and patterns of scientific\n                        collaboration","volume":"101","author":"Newman","year":"2004","journal-title":"Proceedings of the National Academy\n                        of Sciences"},{"issue":"23","key":"2024032016303499600_bib36","doi-asserted-by":"publisher","first-page":"8577","DOI":"10.1073\/pnas.0601602103","article-title":"Modularity and community structure in\n                        networks","volume":"103","author":"Newman","year":"2006","journal-title":"Proceedings of the National Academy of\n                        Sciences"},{"issue":"7942","key":"2024032016303499600_bib37","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1038\/s41586-022-05543-x","article-title":"Papers and patents are becoming less disruptive over\n                        time","volume":"613","author":"Park","year":"2023","journal-title":"Nature"},{"key":"2024032016303499600_bib38","doi-asserted-by":"publisher","first-page":"eabb9004","DOI":"10.1126\/sciadv.abb9004","article-title":"Neural embeddings of scholarly\n                        periodicals reveal complex disciplinary organizations","volume":"7","author":"Peng","year":"2021","journal-title":"Science Advances"},{"issue":"3","key":"2024032016303499600_bib39","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1007\/s11192-008-2197-2","article-title":"Is science becoming more\n                        interdisciplinary? Measuring and mapping six research fields over\n                        time","volume":"81","author":"Porter","year":"2009","journal-title":"Scientometrics"},{"key":"2024032016303499600_bib40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.01833","article-title":"OpenAlex: A fully-open index of\n                        scholarly works, authors, venues, institutions, and\n                    concepts","author":"Priem","year":"2022","journal-title":"arXiv preprint"},{"issue":"45","key":"2024032016303499600_bib41","doi-asserted-by":"publisher","first-page":"17268","DOI":"10.1073\/pnas.0806977105","article-title":"Universality of citation distributions:\n                        Toward an objective measure of scientific impact","volume":"105","author":"Radicchi","year":"2008","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2024032016303499600_bib42","doi-asserted-by":"publisher","first-page":"130","DOI":"10.25080\/Majora-7b98e3ed-013","article-title":"Dask: Parallel computation with blocked\n                        algorithms and task scheduling","volume-title":"Proceedings of\n                        the 14th Python in Science Conference","author":"Rocklin","year":"2015"},{"issue":"2","key":"2024032016303499600_bib43","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1007\/s11192-019-03213-w","article-title":"Software survey: Scientopy, a\n                        scientometric tool for topics trend analysis in scientific\n                        publications","volume":"121","author":"Ruiz-Rosero","year":"2019","journal-title":"Scientometrics"},{"key":"2024032016303499600_bib44","volume-title":"Superior: The return of race science","author":"Saini","year":"2019"},{"issue":"16","key":"2024032016303499600_bib45","doi-asserted-by":"publisher","first-page":"6483","DOI":"10.1073\/pnas.0808904106","article-title":"Extracting the multiscale backbone of\n                        complex weighted networks","volume":"106","author":"Serrano","year":"2009","journal-title":"Proceedings of the\n                        National Academy of Sciences"},{"issue":"34","key":"2024032016303499600_bib46","doi-asserted-by":"publisher","first-page":"12325","DOI":"10.1073\/pnas.1401992111","article-title":"Collective credit allocation in\n                        science","volume":"111","author":"Shen","year":"2014","journal-title":"Proceedings of the National Academy of\n                        Sciences"},{"issue":"6312","key":"2024032016303499600_bib47","doi-asserted-by":"publisher","first-page":"aaf5239","DOI":"10.1126\/science.aaf5239","article-title":"Quantifying the evolution of individual\n                        scientific impact","volume":"354","author":"Sinatra","year":"2016","journal-title":"Science"},{"issue":"15","key":"2024032016303499600_bib48","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1098\/rsif.2007.0213","article-title":"A general framework for analysing\n                        diversity in science, technology and society","volume":"4","author":"Stirling","year":"2007","journal-title":"Journal of the Royal Society Interface"},{"issue":"6157","key":"2024032016303499600_bib49","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1126\/science.1240474","article-title":"Atypical combinations and scientific\n                        impact","volume":"342","author":"Uzzi","year":"2013","journal-title":"Science"},{"issue":"2","key":"2024032016303499600_bib50","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s11192-009-0146-3","article-title":"Software survey: VOSviewer, a computer\n                        program for bibliometric mapping","volume":"84","author":"van Eck","year":"2010","journal-title":"Scientometrics"},{"key":"2024032016303499600_bib51","doi-asserted-by":"publisher","DOI":"10.1017\/9781108610834","volume-title":"The science of science","author":"Wang","year":"2021"},{"issue":"6154","key":"2024032016303499600_bib52","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1126\/science.1237825","article-title":"Quantifying long-term scientific\n                        impact","volume":"342","author":"Wang","year":"2013","journal-title":"Science"},{"issue":"3","key":"2024032016303499600_bib53","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/s11192-012-0775-9","article-title":"Citation time window choice for research\n                        impact evaluation","volume":"94","author":"Wang","year":"2013","journal-title":"Scientometrics"},{"issue":"44","key":"2024032016303499600_bib54","doi-asserted-by":"publisher","first-page":"E9216","DOI":"10.1073\/pnas.1702121114","article-title":"The misleading narrative of the canonical faculty\n                        productivity trajectory","volume":"114","author":"Way","year":"2017","journal-title":"Proceedings of the National\n                        Academy of Sciences"},{"issue":"2","key":"2024032016303499600_bib55","doi-asserted-by":"publisher","first-page":"101290","DOI":"10.1016\/j.joi.2022.101290","article-title":"Metrics and mechanisms: Measuring the\n                        unmeasurable in the science of science","volume":"16","author":"Wu","year":"2022","journal-title":"Journal of\n                        Informetrics"},{"issue":"7744","key":"2024032016303499600_bib56","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1038\/s41586-019-0941-9","article-title":"Large teams develop and small teams disrupt science and\n                        technology","volume":"566","author":"Wu","year":"2019","journal-title":"Nature"},{"issue":"5827","key":"2024032016303499600_bib57","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1126\/science.1136099","article-title":"The increasing dominance of teams in\n                        production of knowledge","volume":"316","author":"Wuchty","year":"2007","journal-title":"Science"},{"key":"2024032016303499600_bib58","doi-asserted-by":"publisher","first-page":"847","DOI":"10.2307\/2657505","article-title":"Sex differences in research productivity: New evidence about\n                        an old puzzle","volume":"63","author":"Xie","year":"1998","journal-title":"American Sociological\n                    Review"},{"key":"2024032016303499600_bib59","doi-asserted-by":"publisher","first-page":"e439","DOI":"10.7717\/peerj-cs.439","article-title":"Persona2vec: A flexible multirole\n                        representations learning framework for graphs","volume":"7","author":"Yoon","year":"2021","journal-title":"PeerJ\n                        Computer Science"},{"issue":"1","key":"2024032016303499600_bib60","doi-asserted-by":"publisher","first-page":"3439","DOI":"10.1038\/s41467-019-11401-8","article-title":"Increasing trend of scientists to switch\n                        between topics","volume":"10","author":"Zeng","year":"2019","journal-title":"Nature Communications"}],"container-title":["Quantitative Science Studies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/qss\/article-pdf\/4\/3\/700\/2351847\/qss_a_00260.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/qss\/article-pdf\/4\/3\/700\/2351847\/qss_a_00260.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T12:31:02Z","timestamp":1710937862000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/qss\/article\/4\/3\/700\/115875\/Reproducible-science-of-science-at-scale-pySciSci"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,8,12]]}},"URL":"https:\/\/doi.org\/10.1162\/qss_a_00260","relation":{"has-review":[{"id-type":"doi","id":"10.1162\/QSS_A_00260\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00260\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00260\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00260\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00260\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00260\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00260\/v1\/review1","asserted-by":"object"}]},"ISSN":["2641-3337"],"issn-type":[{"value":"2641-3337","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}