Considerate approaches to constructing summary statistics for ABC model selection
The DOI matches its Crossref record; 52 of the 55 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The limitations that have been highlighted in the literature are pertinent for cases where inferences are based on summary statistics of the data instead of the data themselves, an approach conventionally adopted in population genetics applications. In these cases model selection is notoriously dependent on arbitrary choices made in the set-up of the ABC inference, and can swing in favor of any Pl”
From A framework for parameter estimation and model selection from experimental data in systems biology using approximate Bayesian computation (2014) · cites this paper as [33]
Citations
Cites
Model selection and multimodel inference: a practical information-theoretic approach.
Guthery, F. S., Burnham, K. P., & Anderson, D. R. (2003) · The Journal of Wildlife Management · doi:10.2307/3802723 · Cited by 41,495
Elements of Information Theory
Cover, T. M., & Thomas, J. A. (2001) · Wiley eBooks · doi:10.1002/0471200611 · Cited by 36,808
Gelman, A., Carlin, J. B., Stern, H. S., & Rubin, D. B. (2003) · doi:10.1201/9780429258480 · Cited by 27,276
Elements of Information Theory
Cover, T. M., & Thomas, J. A. (2005) · doi:10.1002/047174882x · Cited by 13,791
Information theory, inference, and learning algorithms
(2004) · Choice Reviews Online · doi:10.5860/choice.41-5949 · Cited by 6,362
Information Theory, Inference, and Learning Algorithms
(2004) · Kybernetes · doi:10.1108/03684920410534506 · Cited by 4,937
Ziegel, E. R., Lehmann, E. L., & Casella, G. (1999) · Technometrics · doi:10.2307/1270597 · Cited by 4,203
ASH, R. B. (1966) · Cited by 3,990
Cox, D. R., & Hinkley, D. V. (1974) · doi:10.1007/978-1-4899-2887-0 · Cited by 3,089
Approximate Bayesian computation in population genetics
Beaumont, M. A., Zhang, W., & Balding, D. J. (2002) · Genetics · doi:10.1093/genetics/162.4.2025 · Cited by 2,932
Research works printed but not linked: 3
- Dean, T.A., Singh, S.S., Jasra, A., Peters, G.W.: Parameter estimation for hidden Markov models with intractable likelihoods (2011). arXiv: 1103.5399 · arXiv
- Hein, J., Schierup, M., Wiuf, C.: Gene Genealogies, Variation and Evolution. Oxford University Press, London (2005)
- Rudnick, J., Gaspari, G.: Elements of the Random Walk. Cambridge University Press, Cambridge (2010)
Cited by
Fearnhead, P., & Prangle, D. (2012) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2011.01010.x · Cited by 567
Reliable ABC model choice via random forests
Pudlo, P., Marin, J.-M., Estoup, A., Cornuet, J.-M., Gautier, M., & Robert, C. P. (2016) · Bioinformatics · doi:10.1093/bioinformatics/btv684 · Cited by 384
“Barnes et al. (2012) developed an interesting methodology to select the summary statistics but with the requirement to aggregate estimation and model pseudo-sufficient statistics for all models. This induces a deeply inefficient dimension inflation and can be very time consuming. It may seem tempting to collect the la…”
BackgroundMethodInfluentialA Comparative Review of Dimension Reduction Methods in Approximate Bayesian Computation
Blum, M. G. B., Nunes, M. A., Prangle, D., & Sisson, S. A. (2013) · Statistical Science · doi:10.1214/12-sts406 · Cited by 353
“s, evaluation of such a performance diagnostic is entirely practicable, as no further model simulations are required. This idea is also relevant to methods of dimension reduction for model selection (Barnes et al. (2012); Estoup et al. (2012)) where a misclassification rate based on a leave-one-out procedure can serve…”
BackgroundMethodQuantification of subclonal selection in cancer from bulk sequencing data
Williams, M. J., Werner, B., Heide, T., Curtis, C., Barnes, C. P., Sottoriva, A., & Graham, T. A. (2018) · Nature Genetics · doi:10.1038/s41588-018-0128-6 · Cited by 261
“In contrast to many applications of ABC that use summary statistics, we use the full data distribution, thus avoiding issues of inconsistent Bayes factors due to loss of information54,55.”
Self-citationApproximate Bayesian computation (ABC) gives exact results under the assumption of model error
Wilkinson, R. D. (2013) · Statistical Applications in Genetics and Molecular Biology · doi:10.1515/sagmb-2013-0010 · Cited by 247
Liepe, J., Kirk, P., Filippi, S., Toni, T., Barnes, C. P., & Stumpf, M. P. H. (2014) · Nature Protocols · doi:10.1038/nprot.2014.025 · Cited by 217
“However, this approach will usually result in some loss of information (which can have negative theoretical and practical consequences), and hence considerable care must be taken to choose appropriate, informative summaries of the data 29–33 .”
BackgroundSelf-citationModel selection in systems and synthetic biology
Kirk, P., Thorne, T., & Stumpf, M. P. (2013) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2013.03.012 · Cited by 118
Self-citationApproximate Bayesian Computation for infectious disease modelling
Minter, A., & Retkutė, R. (2019) · Epidemics · doi:10.1016/j.epidem.2019.100368 · Cited by 147
“Proposed solutions to choosing optimal summary statistics for ABC include a sequential scheme to assess the information content of a list of summary statistics (Joyce and Marjoram, 2008), minimisation of the estimated entropy of the posterior approximation (Nunes and Balding, 2010), finding statistical summaries of th…”
Cameron, E., & Pettitt, A. N. (2012) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2012.21371.x · Cited by 132
McKinley, T. J., Vernon, I., Andrianakis, I., McCreesh, N., Oakley, J. E., Nsubuga, R. N., Goldstein, M., & White, R. G. (2018) · Statistical Science · doi:10.1214/17-sts618 · Cited by 102
“Increasing research effort has been placed into deriving approximately sufficient summary measures [e.g. Joyce and Marjoram, 2008, Nunes and Balding, 2010, Barnes et al., 2012, Fearnhead and Prangle, 2012, Ratmann et al., 2014].”
BackgroundBridging the gap between GLUE and formal statistical approaches: approximate Bayesian computation
Sadegh, M., & Vrugt, J. A. (2013) · Hydrology and earth system sciences · doi:10.5194/hess-17-4831-2013 · Cited by 98
Semi-automatic selection of summary statistics for ABC model choice
Prangle, D., Fearnhead, P., Cox, M. P., Biggs, P. J., & French, N. P. (2013) · Statistical Applications in Genetics and Molecular Biology · doi:10.1515/sagmb-2013-0012 · Cited by 77
“Examples are Joyce and Marjoram (2008); Nunes and Balding (2010); Barnes et al. (2012b), the last of which has methods specifically for model choice.”
BackgroundMethodInfluentialShared behavioral mechanisms underlie C. elegans aggregation and swarming
Ding, S. S., Schumacher, L. J., Javer, A., Endres, R. G., & Brown, A. E. (2019) · eLife · doi:10.7554/elife.43318 · Cited by 51
Silk, D., Filippi, S., & Stumpf, M. P. H. (2013) · Statistical Applications in Genetics and Molecular Biology · doi:10.1515/sagmb-2012-0043 · Cited by 51
Self-citationQuantification of subclonal selection in cancer from bulk sequencing data
Williams, M. J., Werner, B., Curtis, C., Barnes, C. P., Sottoriva, A., & Graham, T. A. (2016) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/096305 · Cited by 36
Self-citationRoss, R. J. H., Baker, R. E., Parker, A. J., Ford, M. J., Mort, R. L., & Yates, C. A. (2017) · npj Systems Biology and Applications · doi:10.1038/s41540-017-0010-7 · Cited by 36
Modeling Tuberculosis Dynamics, Detection and Control in Cattle Herds
Bekara, M. E. A., Courcoul, A., Bénet, J., & Durand, B. (2014) · PLoS ONE · doi:10.1371/journal.pone.0108584 · Cited by 38
“[45] to choose a set of summary statistics from all possible summary statistics.”
BackgroundMethodLenive, O., Kirk, P., & Stumpf, M. P. H. (2016) · BMC Systems Biology · doi:10.1186/s12918-016-0324-x · Cited by 29
“The inference procedure is similar to that employed by [24, 41, 42], as described in Algorithm 2.”
MethodSelf-citationOpen problems in mathematical biology
Vittadello, S. T., & Stumpf, M. P. H. (2022) · Mathematical Biosciences · doi:10.1016/j.mbs.2022.108926 · Cited by 30
“Perhaps not so obvious is that many computational schemes that apply straightforwardly in the context of parameter estimation — such as Markov Chain Monte Carlo sampling [25], or approximate Bayesian computation (ABC) [26, 27] — require significant modification and adaptation for model selection.”
BackgroundSelf-citationParametric analysis of time-censored aggregate lifetime data
Chen, P., Ye, Z., & Zhai, Q. (2019) · IISE Transactions · doi:10.1080/24725854.2019.1628374 · Cited by 25
“In the literature, the ABC algorithm brings a straightforward solution to approximate PðMjDÞ (e.g., Toni et al. (2009) and Barnes et al. (2012)).”
BackgroundMethodSummary Statistics in Approximate Bayesian ComputationPreprint
Prangle, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.05633 · Cited by 53
“The entropy minimisation method of Nunes and Balding (2010) and the approach of Barnes et al. (2012) are successively more sophisticated information theoretic approaches.”
BackgroundMethodInfluentialApproximate Bayesian Computation: A Survey on Recent Results
Robert, C. P. (2016) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-319-33507-0_7 · Cited by 32
The impact of temporal sampling resolution on parameter inference for biological transport models
Harrison, J. U., & Baker, R. E. (2018) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1006235 · Cited by 17
“To obtain potentially improved results for inference with ABC for this type of data (time series observations of angle changes), we could consider a more systematic choice of summary statistics [3, 9, 15] or a more efficient version of the ABC algorithm, such as ABC-SMC [45, 48], which applies sequential Monte Carlo m…”
MethodRapid Bayesian Inference for Expensive Stochastic Models
Warne, D. J., Baker, R. E., & Simpson, M. J. (2021) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2021.2000419 · Cited by 21
“Summary statistics can reduce the data dimensionality, however, they will often incur information loss (Barnes et al. 2012; Blum et al. 2013; Fearnhead and Prangle 2012).”
BackgroundMarin, J., Pudlo, P., Estoup, A., & Robert, C. P. (2018) · Chapman & Hall/CRC eBooks · doi:10.1201/9781315117195-6 · Cited by 26
“en dicult in practice to design a summary statistic that is informative about the model. Let us signal here that a summary selection approach purposely geared towards model selection can be found in [2]. Let us stress in and for this section that the said method similarly suers from the above curse of dimensionality.…”
MethodApproximation Bayesian computation
Marjoram, P. (2013) · OA Genetics · doi:10.13172/2054-197x-1-1-853 · Cited by 18
Approximate Bayesian inference for complex ecosystems
Stumpf, M. P. H. (2016) · Cited by 13
Self-citationExact Inference with Approximate Computation for Differentially Private Data via Perturbations
Gong, R. (2022) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.797 · Cited by 35
“…projection and regression (Beaumont et al., 2002; Wegmann et al., 2009), optimization of information and distance criteria (Nunes & Balding, 2010; Barnes et al., 2012; Bernton et al., 2019), and auxiliary likelihoods (Drovandi et al., 2011; Gleim & Pigorsch, 2013); see Blum et al. (2013) and…”
BackgroundApproximate Bayesian computation with functional statistics
Soubeyrand, S., Carpentier, F., Guiton, F., & Klein, E. K. (2013) · Statistical Applications in Genetics and Molecular Biology · doi:10.1515/sagmb-2012-0014 · Cited by 12
“…may be selected based on Kullback-Leibler divergence, relative ε-sufficiency or minimum entropy (Joyce and Marjoram, 2008; Nunes and Balding, 2010; Barnes et al., 2012), the statistics may be transformed into axes of a PLS regression (Wegmann et al., 2009) or into point estimates of the model…”
BackgroundMethodApproximate Bayesian Computation by Modelling Summary Statistics in a Quasi-likelihood Framework
Cabras, S., Castellanos, M. E., & Ruli, E. (2015) · Bayesian Analysis · doi:10.1214/14-ba921 · Cited by 11
“They require a choice of and for this purpose several authors (Bortot et al., 2007; Faisal et al., 2013; Ratmann et al., 2014; Barnes et al., 2012; Aeschbacher et al., 2012) suggest approaches where is estimated as part of an extended model with respect to π(y | θ), while a recent approach based on diagnostic tools fo…”
BackgroundMethodAn automatic adaptive method to combine summary statistics in approximate Bayesian computation
Harrison, J. U., & Baker, R. E. (2020) · PLoS ONE · doi:10.1371/journal.pone.0236954 · Cited by 10
“[35] based on an approximate sufficiency criterion.”
MethodBayesian and Algebraic Strategies to Design in Synthetic Biology
Araujo, R. P., Vittadello, S. T., & Stumpf, M. P. H. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3129527 · Cited by 10
Self-citationInferring ASF transmission in domestic pigs and wild boars using a paired model iterative approach
Beaunée, G., Deslandes, F., & Vergu, E. (2023) · Epidemics · doi:10.1016/j.epidem.2023.100665 · Cited by 11
Ancestral inference in tumors: How much can we know?
Zhao, J., Siegmund, K. D., Shibata, D. K., & Marjoram, P. (2014) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2014.05.027 · Cited by 9
“Development of rigorous procedures for choice of statistics, as a function of analysis question at hand, is an area of active research (Barnes et al., 2012; Fearnhead and Prangle, 2012; Hong et al., 2010; Joyce and Marjoram, 2008; Jung and Marjoram, 2011).”
BackgroundOn selection of statistics for approximate Bayesian computing (or the method of simulated moments)
Creel, M., & Kristensen, D. (2015) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2015.05.005 · Cited by 10
“This version of our selection procedure chooses the set of summary statistics that maximizes the information content over the whole distribution and so is similar in spirit to the one of Barnes et al. (2012).”
BackgroundMethodInfluentialSoubeyrand, S., & Haon-Lasportes, E. (2015) · Statistics & Probability Letters · doi:10.1016/j.spl.2015.08.003 · Cited by 9
Rimella, L., Alderton, S., Sammarro, M., Rowlingson, B., Cocker, D., Feasey, N., Fearnhead, P., & Jewell, C. (2023) · Journal of the Royal Statistical Society Series C (Applied Statistics) · doi:10.1093/jrsssc/qlad055 · Cited by 8
“and these can be difficult to construct (Barnes et al., 2012; Prangle et al., 2014).”
BackgroundSmith, R. L., & Grohn, Y. T. (2015) · PLoS ONE · doi:10.1371/journal.pone.0129535 · Cited by 11
Discrimination between accelerated life models via Approximate Bayesian Computation
Rabhi, M., Abdessalem, A. B., Saintis, L., Castanier, B., & Sohoin, R. (2023) · Quality and Reliability Engineering International · doi:10.1002/qre.3283 · Cited by 6
A new method for dimensionality reduction of multi-dimensional data using Copulas
Houari, R., Bounceur, A., & Kechadi, T. (2013) · International Symposium on Programming and Systems (ISPS) · doi:10.1109/isps.2013.6581491 · Cited by 4
Model updating and model selection for structural structures via Approximate Bayesian Computation
Abdessalem, A. B., Dervilis, N., Wagg, D., & Keith Worden, B. (2026) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.113836 · Cited by 3
Unifying Summary Statistic Selection for Approximate Bayesian Computation
Hoffmann, T., & Onnela, J.-P. “. (2026) · Statistics and Computing · doi:10.1007/s11222-025-10808-2 · Cited by 16
“…include methods to select informative summaries from a pool of candidates (Blum and François 2010; Joyce and Mar-joram 2008; Nunes and Balding 2010; Barnes et al. 2012; Blum et al. 2013) and parameterized transformations that can be optimized to learn summaries (Aeschbacher et al. 2012; Fearnhead…”
InfluentialThe impact of experimental design choices on parameter inference for models of growing cell colonies
Parker, A. J., Simpson, M. J., & Baker, R. E. (2018) · Royal Society Open Science · doi:10.1098/rsos.180384 · Cited by 4
Rapid Bayesian Inference for Expensive Stochastic Models
Warne, D. J., Baker, R. E., & Simpson, M. J. (2021) · QUT ePrints (Queensland University of Technology) · doi:10.6084/m9.figshare.16934424 · Cited by 3
Goodness of fit for models with intractable likelihood
Cabras, S., Castellanos, M. E., & Ratmann, O. (2021) · Test · doi:10.1007/s11749-020-00747-7 · Cited by 3
Asymptotically exact inference in differentiable generative models
Graham, M. M., & Storkey, A. (2017) · Electronic Journal of Statistics · doi:10.1214/17-ejs1340si · Cited by 24
“By a data processing inequality argument we know that the mutual information between z and s(x) will be less than or equal to the mutual information between z and x therefore we would expect for the posterior distribution on z given s(x) to be less informative about z than the posterior distribution given x [5].”
BackgroundInformed Choices: How to Calibrate ABC with Hypothesis Testing
Ratmann, O., Camacho, A., Hu, S. Z., & Colijn, C. (2018) · Chapman & Hall/CRC eBooks · doi:10.1201/9781315117195-11 · Cited by 2
Simulation-based Bayesian Analysis of Complex Data.
Marjoram, P., Hamblin, S., & Foley, B. R. (2015) · PubMed · Cited by 3
Reliable ABC model choice via random forestsPreprint
Pudlo, P., Marin, J., Estoup, A., Cornuet, J., Gautier, M., & Robert, C. P. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.6288 · Cited by 2
Hierarchical surrogate-based Approximate Bayesian Computation for an electric motor test benchPreprint
John, D., Stohrer, L., Schillings, C., Schick, M., & Heuveline, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.09597 · Cited by 2
Early mutation bursts in colorectal tumors
Zhao, J., Salomon, M. P., Shibata, D. K., Curtis, C. N., Siegmund, K. D., & Marjoram, P. (2017) · PLoS ONE · doi:10.1371/journal.pone.0172516 · Cited by 1
“Some summary statistics s might be more informative for a particular parameter θ than others, therefore, a higher weight on s will help infer the posterior distribution of θ [25,30].”
BackgroundMisspecification-robust likelihood-free inference in high dimensions
Thomas, O., Sá‐Leão, R., de LENCASTRE, H., Samuel Kaski, A., Corander, J., & Pesonen, H. (2025) · Computational Statistics · doi:10.1007/s00180-025-01607-4 · Cited by 1
“This was followed by articles in a similar spirit introducing stricter information-theoretic principles to filtering a large initial pool of summaries (Nunes and Balding 2010; Barnes et al. 2012).”
Computational inference in mathematical biology: Methodological developments and applications
Warne, D. J. (2020) · Queensland University of Technology · doi:10.5204/thesis.eprints.202835 · Cited by 1
Buckwar, E., Tamborrino, M., & Tubikanec, I. (2019) · Statistics and Computing · doi:10.1007/s11222-019-09909-6 · Cited by 45
“Since then, it has been successfully applied in a wide range of fields; see, e.g. Barnes et al. (2012), Blum (2010a), Boys et al. (2008), McKinley et al. (2017), Moores et al. (2015) and Toni et al. (2009).”
BackgroundOn Model Selection with Summary StatisticsPreprint
Ruli, E. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.10749
“see also Marin et al., 2014). Finding cross-model sufficient statistics in practice is impossible, and some efforts have been spent on constructing summary statistics for ABC model selection (see, e.g., Barnes et al., 2012). However, at the best of our knowledge, the choice of summary statistics for ABC model selection i…”
MethodA Note on Simulation-Based Inference by Matching Random FeaturesPreprint
Shalizi, C. R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.09220
(2019) · Wiley eBooks · doi:10.1002/9781118768853.refs
Liu, S., She, D., Zhang, L., & Xia, J. (2022) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-022-02282-3
“Although the construction of a set of approximately sufficient statistics when using ABC has been intensively investigated in statistical sciences (Wegmann et al. 2009; Barnes et al. 2012; Fearnhead and Prangle 2012; Beaumont 2019), research into sufficient signatures for complex hydrological models is so far limited.”
BackgroundApproximate Bayesian Computation with Statistical Distances for Model Selection
Grazian, C. (2025) · Bayesian Analysis · doi:10.1214/26-ba1586 · Cited by 2
“Given that sufficient statistics for model selection must be sufficient within each model and across models, Barnes et al. (2012) provide a two stage subset selection method to achieve approximate sufficiency.”
Bayesian statistical inference for intractable likelihood models
Raynal, L. (2019) · theses.fr (ABES) · doi:10.70675/1c0e35f2z5d68z463dzad94za955d0642195 · Cited by 3
“An approach based on the Kullback-Leibler divergence is proposed by Barnes et al. (2012) and Filippi et al. (2012) to assess of the sufficiency of statistics.”
Method
Metadata
- Authors
- Barnes, C. P., Filippi, S., Stumpf, M. P. H., & Thorne, T.
- Affiliations
- Imperial College London (GB)
- Corresponding author
- Stumpf, Michael P. H.
- Venue
- Statistics and Computing
- Published
- 2012-06-09
- Volume
- 22
- Issue
- 6
- Pages
- 1181-1197
- ISSN
- 0960-3174 (ISSN-L)
- 1573-1375
- OpenAlex
- W2066999504
- Cited by
- 61
- References
- 55
- Citations by year
- 2026: 3 · 2025: 2 · 2023: 3 · 2022: 3 · 2021: 6 · 2020: 2 · 2019: 6 · 2018: 7 · 2017: 3 · 2016: 3 · 2015: 7 · 2014: 5 · 2013: 9 · 2012: 2
- FWCI
- 6.70
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Statistics and Computing (publishedVersion)
- UCL Discovery (University College London) (submittedVersion)
- Spiral (Imperial College London) (submittedVersion)
- Funders
- Biotechnology and Biological Sciences Research Council (BB/G007934/1)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Markov Chains and Monte Carlo Methods
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic diversity and population structure
- Keywords
- approximate Bayesian computation, model selection, summary statistics, sufficient statistics, information-theoretic approach, information loss, parameter estimation, simulation-based inference
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.