% references_part04.bib — Part IV (Computational Methodology), WP44.
% Every entry verified on 2026-11-03 by a Crossref / OpenAlex / arXiv lookup; see references_verification_part04.csv.

@article{waltman2016review,
  author  = {Waltman, Ludo},
  title   = {A review of the literature on citation impact indicators},
  journal = {Journal of Informetrics},
  year    = {2016},
  volume  = {10},
  number  = {2},
  pages   = {365--391},
  doi     = {10.1016/j.joi.2016.02.007}
}

@misc{openalex2026fwci,
  author       = {{OpenAlex}},
  title        = {Works: attributes ({F}ield-{W}eighted {C}itation {I}mpact, \texttt{fwci})},
  howpublished = {OpenAlex documentation, \url{https://help.openalex.org/data/works/attributes/}},
  year         = {2026},
  note         = {Accessed 3 November 2026}
}

@article{ceriani2012gini,
  author  = {Ceriani, Lidia and Verme, Paolo},
  title   = {The origins of the {G}ini index: extracts from {V}ariabilit{\`a} e {M}utabilit{\`a} (1912) by {C}orrado {G}ini},
  journal = {The Journal of Economic Inequality},
  year    = {2012},
  volume  = {10},
  number  = {3},
  pages   = {421--443},
  doi     = {10.1007/s10888-011-9188-x}
}

@article{hirschman1964paternity,
  author  = {Hirschman, Albert O.},
  title   = {The paternity of an index},
  journal = {American Economic Review},
  year    = {1964},
  volume  = {54},
  number  = {5},
  pages   = {761--762},
  note    = {OpenAlex W2163989766}
}

@article{rao1982diversity,
  author  = {Rao, C. Radhakrishna},
  title   = {Diversity and dissimilarity coefficients: a unified approach},
  journal = {Theoretical Population Biology},
  year    = {1982},
  volume  = {21},
  number  = {1},
  pages   = {24--43},
  doi     = {10.1016/0040-5809(82)90004-1}
}

@article{stirling2007diversity,
  author  = {Stirling, Andy},
  title   = {A general framework for analysing diversity in science, technology and society},
  journal = {Journal of The Royal Society Interface},
  year    = {2007},
  volume  = {4},
  number  = {15},
  pages   = {707--719},
  doi     = {10.1098/rsif.2007.0213}
}

@article{leinster2012diversity,
  author  = {Leinster, Tom and Cobbold, Christina A.},
  title   = {Measuring diversity: the importance of species similarity},
  journal = {Ecology},
  year    = {2012},
  volume  = {93},
  number  = {3},
  pages   = {477--489},
  doi     = {10.1890/10-2402.1}
}

@article{rafols2010diversity,
  author  = {Rafols, Ismael and Meyer, Martin},
  title   = {Diversity and network coherence as indicators of interdisciplinarity: case studies in bionanoscience},
  journal = {Scientometrics},
  year    = {2010},
  volume  = {82},
  number  = {2},
  pages   = {263--287},
  doi     = {10.1007/s11192-009-0041-y}
}

@article{zhang2016diversity,
  author  = {Zhang, Lin and Rousseau, Ronald and Gl{\"a}nzel, Wolfgang},
  title   = {Diversity of references as an indicator of the interdisciplinarity of journals: taking similarity between subject fields into account},
  journal = {Journal of the Association for Information Science and Technology},
  year    = {2016},
  volume  = {67},
  number  = {5},
  pages   = {1257--1265},
  doi     = {10.1002/asi.23487}
}

@article{newman2004community,
  author  = {Newman, M. E. J. and Girvan, M.},
  title   = {Finding and evaluating community structure in networks},
  journal = {Physical Review E},
  year    = {2004},
  volume  = {69},
  number  = {2},
  pages   = {026113},
  doi     = {10.1103/PhysRevE.69.026113}
}

@article{leicht2008directed,
  author  = {Leicht, E. A. and Newman, M. E. J.},
  title   = {Community structure in directed networks},
  journal = {Physical Review Letters},
  year    = {2008},
  volume  = {100},
  number  = {11},
  pages   = {118703},
  doi     = {10.1103/PhysRevLett.100.118703}
}

@article{fortunato2007resolution,
  author  = {Fortunato, Santo and Barth{\'e}lemy, Marc},
  title   = {Resolution limit in community detection},
  journal = {Proceedings of the National Academy of Sciences},
  year    = {2007},
  volume  = {104},
  number  = {1},
  pages   = {36--41},
  doi     = {10.1073/pnas.0605965104}
}

@article{fortunato2010community,
  author  = {Fortunato, Santo},
  title   = {Community detection in graphs},
  journal = {Physics Reports},
  year    = {2010},
  volume  = {486},
  number  = {3--5},
  pages   = {75--174},
  doi     = {10.1016/j.physrep.2009.11.002}
}

@inproceedings{cohan2020specter,
  author    = {Cohan, Arman and Feldman, Sergey and Beltagy, Iz and Downey, Doug and Weld, Daniel S.},
  title     = {{SPECTER}: Document-level representation learning using citation-informed transformers},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  year      = {2020},
  pages     = {2270--2282},
  doi       = {10.18653/v1/2020.acl-main.207}
}

@inproceedings{singh2023scirepeval,
  author    = {Singh, Amanpreet and D'Arcy, Mike and Cohan, Arman and Downey, Doug and Feldman, Sergey},
  title     = {{SciRepEval}: A multi-format benchmark for scientific document representations},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
  year      = {2023},
  pages     = {5548--5566},
  doi       = {10.18653/v1/2023.emnlp-main.338}
}

@inproceedings{ostendorff2022scincl,
  author    = {Ostendorff, Malte and Rethmeier, Nils and Augenstein, Isabelle and Gipp, Bela and Rehm, Georg},
  title     = {Neighborhood contrastive learning for scientific document representations with citation embeddings},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  year      = {2022},
  doi       = {10.18653/v1/2022.emnlp-main.802}
}

@inproceedings{reimers2019sbert,
  author    = {Reimers, Nils and Gurevych, Iryna},
  title     = {{Sentence-BERT}: Sentence embeddings using {S}iamese {BERT}-networks},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing},
  year      = {2019},
  pages     = {3980--3990},
  doi       = {10.18653/v1/D19-1410}
}

@misc{mcinnes2018umap,
  author        = {McInnes, Leland and Healy, John and Melville, James},
  title         = {{UMAP}: Uniform manifold approximation and projection for dimension reduction},
  year          = {2018},
  howpublished  = {arXiv preprint arXiv:1802.03426},
  note          = {Preprint}
}

@article{mcinnes2017hdbscan,
  author  = {McInnes, Leland and Healy, John and Astels, Steve},
  title   = {hdbscan: Hierarchical density based clustering},
  journal = {The Journal of Open Source Software},
  year    = {2017},
  volume  = {2},
  number  = {11},
  pages   = {205},
  doi     = {10.21105/joss.00205}
}

@inproceedings{campello2013hdbscan,
  author    = {Campello, Ricardo J. G. B. and Moulavi, Davoud and Sander, Joerg},
  title     = {Density-based clustering based on hierarchical density estimates},
  booktitle = {Advances in Knowledge Discovery and Data Mining (PAKDD 2013), Lecture Notes in Computer Science},
  publisher = {Springer},
  year      = {2013},
  pages     = {160--172},
  doi       = {10.1007/978-3-642-37456-2_14}
}

@article{hubert1985comparing,
  author  = {Hubert, Lawrence and Arabie, Phipps},
  title   = {Comparing partitions},
  journal = {Journal of Classification},
  year    = {1985},
  volume  = {2},
  number  = {1},
  pages   = {193--218},
  doi     = {10.1007/BF01908075}
}

@article{wang2017novelty,
  author  = {Wang, Jian and Veugelers, Reinhilde and Stephan, Paula},
  title   = {Bias against novelty in science: A cautionary tale for users of bibliometric indicators},
  journal = {Research Policy},
  year    = {2017},
  volume  = {46},
  number  = {8},
  pages   = {1416--1436},
  doi     = {10.1016/j.respol.2017.06.006}
}

@article{bernal2017its,
  author  = {Bernal, James Lopez and Cummins, Steven and Gasparrini, Antonio},
  title   = {Interrupted time series regression for the evaluation of public health interventions: a tutorial},
  journal = {International Journal of Epidemiology},
  year    = {2017},
  volume  = {46},
  number  = {1},
  pages   = {348--355},
  doi     = {10.1093/ije/dyw098}
}

@article{newey1987hac,
  author  = {Newey, Whitney K. and West, Kenneth D.},
  title   = {A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix},
  journal = {Econometrica},
  year    = {1987},
  volume  = {55},
  number  = {3},
  pages   = {703--708},
  doi     = {10.2307/1913610}
}

@article{andrews1991hac,
  author  = {Andrews, Donald W. K.},
  title   = {Heteroskedasticity and autocorrelation consistent covariance matrix estimation},
  journal = {Econometrica},
  year    = {1991},
  volume  = {59},
  number  = {3},
  pages   = {817--858},
  doi     = {10.2307/2938229}
}

@article{bai1998breaks,
  author  = {Bai, Jushan and Perron, Pierre},
  title   = {Estimating and testing linear models with multiple structural changes},
  journal = {Econometrica},
  year    = {1998},
  volume  = {66},
  number  = {1},
  pages   = {47--78},
  doi     = {10.2307/2998540}
}

@article{liu1997segmented,
  author  = {Liu, Jian and Wu, Shiying and Zidek, James V.},
  title   = {On segmented multivariate regression},
  journal = {Statistica Sinica},
  year    = {1997},
  volume  = {7},
  number  = {2},
  pages   = {497--525},
  note    = {OpenAlex W2142183678}
}

@article{schwarz1978bic,
  author  = {Schwarz, Gideon},
  title   = {Estimating the dimension of a model},
  journal = {The Annals of Statistics},
  year    = {1978},
  volume  = {6},
  number  = {2},
  pages   = {461--464},
  doi     = {10.1214/aos/1176344136}
}

@article{killick2012pelt,
  author  = {Killick, R. and Fearnhead, P. and Eckley, I. A.},
  title   = {Optimal detection of changepoints with a linear computational cost},
  journal = {Journal of the American Statistical Association},
  year    = {2012},
  volume  = {107},
  number  = {500},
  pages   = {1590--1598},
  doi     = {10.1080/01621459.2012.737745}
}

@article{truong2020ruptures,
  author  = {Truong, Charles and Oudre, Laurent and Vayatis, Nicolas},
  title   = {Selective review of offline change point detection methods},
  journal = {Signal Processing},
  year    = {2020},
  volume  = {167},
  pages   = {107299},
  doi     = {10.1016/j.sigpro.2019.107299}
}

@article{yao1988schwarz,
  author  = {Yao, Yi-Ching},
  title   = {Estimating the number of change-points via {S}chwarz' criterion},
  journal = {Statistics \& Probability Letters},
  year    = {1988},
  volume  = {6},
  number  = {3},
  pages   = {181--189},
  doi     = {10.1016/0167-7152(88)90118-6}
}

@misc{adams2007bocpd,
  author        = {Adams, Ryan Prescott and MacKay, David J. C.},
  title         = {Bayesian online changepoint detection},
  year          = {2007},
  howpublished  = {arXiv preprint arXiv:0710.3742},
  note          = {Preprint}
}

@article{fearnhead2006exact,
  author  = {Fearnhead, Paul},
  title   = {Exact and efficient {B}ayesian inference for multiple changepoint problems},
  journal = {Statistics and Computing},
  year    = {2006},
  volume  = {16},
  number  = {2},
  pages   = {203--213},
  doi     = {10.1007/s11222-006-8450-8}
}

@article{bergmeir2012crossval,
  author  = {Bergmeir, Christoph and Ben{\'i}tez, Jos{\'e} M.},
  title   = {On the use of cross-validation for time series predictor evaluation},
  journal = {Information Sciences},
  year    = {2012},
  volume  = {191},
  pages   = {192--213},
  doi     = {10.1016/j.ins.2011.12.028}
}

@article{friedman2001gbm,
  author  = {Friedman, Jerome H.},
  title   = {Greedy function approximation: A gradient boosting machine},
  journal = {The Annals of Statistics},
  year    = {2001},
  volume  = {29},
  number  = {5},
  pages   = {1189--1232},
  doi     = {10.1214/aos/1013203451}
}

@misc{pedregosa2011sklearn,
  author        = {Pedregosa, Fabian and Varoquaux, Ga{\"e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and Vanderplas, Jake and Passos, Alexandre and Cournapeau, David and Brucher, Matthieu and Perrot, Matthieu and Duchesnay, {\'E}douard},
  title         = {Scikit-learn: Machine learning in {P}ython},
  year          = {2011},
  howpublished  = {Journal of Machine Learning Research 12, 2825--2830; arXiv:1201.0490},
  note          = {Verified through the arXiv record}
}

@article{hanley1982auc,
  author  = {Hanley, James A. and McNeil, Barbara J.},
  title   = {The meaning and use of the area under a receiver operating characteristic ({ROC}) curve},
  journal = {Radiology},
  year    = {1982},
  volume  = {143},
  number  = {1},
  pages   = {29--36},
  doi     = {10.1148/radiology.143.1.7063747}
}

@article{zhang2014multilabel,
  author  = {Zhang, Min-Ling and Zhou, Zhi-Hua},
  title   = {A review on multi-label learning algorithms},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year    = {2014},
  volume  = {26},
  number  = {8},
  pages   = {1819--1837},
  doi     = {10.1109/TKDE.2013.39}
}

@article{cohen1960kappa,
  author  = {Cohen, Jacob},
  title   = {A coefficient of agreement for nominal scales},
  journal = {Educational and Psychological Measurement},
  year    = {1960},
  volume  = {20},
  number  = {1},
  pages   = {37--46},
  doi     = {10.1177/001316446002000104}
}

@article{fellegi1969linkage,
  author  = {Fellegi, Ivan P. and Sunter, Alan B.},
  title   = {A theory for record linkage},
  journal = {Journal of the American Statistical Association},
  year    = {1969},
  volume  = {64},
  number  = {328},
  pages   = {1183--1210},
  doi     = {10.1080/01621459.1969.10501049}
}

@article{efron1979bootstrap,
  author  = {Efron, B.},
  title   = {Bootstrap methods: Another look at the jackknife},
  journal = {The Annals of Statistics},
  year    = {1979},
  volume  = {7},
  number  = {1},
  pages   = {1--26},
  doi     = {10.1214/aos/1176344552}
}

@inproceedings{raasveldt2019duckdb,
  author    = {Raasveldt, Mark and M{\"u}hleisen, Hannes},
  title     = {{DuckDB}: an embeddable analytical database},
  booktitle = {Proceedings of the 2019 International Conference on Management of Data (SIGMOD '19)},
  year      = {2019},
  pages     = {1981--1984},
  doi       = {10.1145/3299869.3320212}
}