diff --git a/.gitignore b/.gitignore index 75555507..04032bfc 100644 --- a/.gitignore +++ b/.gitignore @@ -2,6 +2,8 @@ /.quarto/ *.html !_site/**/*.html +# redirect pages for renamed article repositories (declared in _quarto.yml resources) +!/published-*/index.html /**/.DS_Store */.DS_Store /_freeze/ diff --git a/_quarto.yml b/_quarto.yml index c24c4e9a..0649aa1f 100644 --- a/_quarto.yml +++ b/_quarto.yml @@ -5,6 +5,9 @@ project: - "*.qmd" - "site/**/*.qmd" - "blog/**/*.qmd" + resources: + # redirect pages for renamed article repositories (old URL -> new URL) + - published-202306-sanou-multiscale_glasso/index.html post-render: - scripts/fix-sitemap.lua website: @@ -17,7 +20,7 @@ website: locale: en_US twitter-card: card-style: summary_large_image - favicon: assets/favicon.ico + favicon: assets/img/logo_notext.png navbar: background: primary logo-alt: Computo’s Logo diff --git a/blog/2023-07-04-what-reproducibility/index.qmd b/blog/2023-07-04-what-reproducibility/index.qmd index 8e906b99..971b2373 100644 --- a/blog/2023-07-04-what-reproducibility/index.qmd +++ b/blog/2023-07-04-what-reproducibility/index.qmd @@ -39,7 +39,7 @@ When applicable, the switch from external to editorial reproducibility is done w ## Examples of data transfer solutions ### Intermediate results storage -- in python environment: the [`joblib.Memory`](https://joblib.readthedocs.io/en/latest/memory.html) class which provides a caching mechanism for python functions, and can be used to save the results of a function call to disk, and load it back later. +- in python environment: the [`joblib.Memory`](https://joblib.readthedocs.io/en/stable/generated/joblib.Memory.html) class which provides a caching mechanism for python functions, and can be used to save the results of a function call to disk, and load it back later. - in R environment: the `.RData` file format, which can be loaded back in R with the `load()` function. ### Transfer of the results to the notebook environment diff --git a/blog/2026-07-26-google-scholar/index.qmd b/blog/2026-07-26-google-scholar/index.qmd index c7faa5f4..22138e83 100644 --- a/blog/2026-07-26-google-scholar/index.qmd +++ b/blog/2026-07-26-google-scholar/index.qmd @@ -1,6 +1,7 @@ --- title: Google Scholar Indexing date: '2026-07-26' +date-modified: '2026-09-16' description: How Computo ensures Google Scholar indexing and understanding URL selection categories: - indexing @@ -29,43 +30,50 @@ Computo articles also include the following recommended tags for richer indexing - `citation_journal_title` -- "Computo" - `citation_issn` -- "2824-7795" -- `citation_pdf_url` -- link to the article PDF -- `citation_abstract_html_url` -- link to the article landing page +- `citation_pdf_url` -- link to the article PDF (`main.pdf`) +- `citation_fulltext_html_url` -- link to the article landing page - `citation_doi` -- the article DOI ### The `google-scholar` flag -All Computo article repositories include `google-scholar: true` in their `_quarto.yml` configuration. When this flag is set, the [Computo Quarto extension](https://github.com/computorg/computo-quarto-extension) automatically generates the complete set of Highwire Press meta tags from the article's frontmatter and `citation:` block. This happens at render time -- no manual intervention is needed. +All Computo article repositories include `google-scholar: true` in their `_quarto.yml` configuration. When this flag is set, [Quarto](https://quarto.org/docs/authoring/create-citeable-articles.html#google-scholar) itself generates the complete set of Highwire Press meta tags at render time, from the document metadata (`title`, `author`, `date`) and from the `citation:` block. No manual intervention is needed. -Here is what the configuration looks like in a published article's `_quarto.yml`: +Here is what the configuration looks like in a published article's `_quarto.yml` (for a repository named `published-YYYYMM-name`): ```yaml +title: "Article Title" +author: + - name: "Author Name" + orcid: 0000-0000-0000-0000 + affiliations: + - name: "Institution" +date: 2024-01-01 google-scholar: true citation: - title: "Article Title" - author: - - id: author1 - name: "Author Name" - affiliation: "Institution" - date: 2024-01-01 - doi: "10.57750/xxxxx" - journal: "Computo" + type: article-journal + container-title: "Computo" publisher: "French Statistical Society" - ISSN: "2824-7795" - url: "https://computo-journal.org/article-slug/" - pdf: "article-slug.pdf" - abstract: "..." + issn: "2824-7795" + doi: "10.57750/xxxxx" + url: "https://computo-journal.org/published-YYYYMM-name/" + pdf-url: "https://computo-journal.org/published-YYYYMM-name/main.pdf" ``` +::: {.callout-warning} +### Keep all metadata in `_quarto.yml` +Do not repeat metadata in the front matter of `main.qmd`. A `citation:` block there **replaces** the one in `_quarto.yml` entirely (dropping `url` and `pdf-url`), and an `author:` list that differs from the one in `_quarto.yml` leads to duplicated authors in the generated citation. +::: + From this, Quarto generates HTML meta tags like: ```html - + - + + ``` @@ -73,7 +81,7 @@ From this, Quarto generates HTML meta tags like: Beyond meta tags, Computo articles benefit from several features that help Google Scholar's crawlers: -- **Sitemap**: Quarto auto-generates a `sitemap.xml` (thanks to `site-url` being configured in the main site's `_quarto.yml`), which helps search engines discover all article URLs. +- **Sitemap**: Quarto auto-generates a `sitemap.xml` for the journal website (thanks to `site-url` being configured in the main site's `_quarto.yml`), and a post-render script adds the URL of every published article, which helps search engines discover them. - **Open access**: All articles are freely accessible without login walls or paywalls, meeting Google Scholar's requirement for crawlable full text. - **Stable URLs**: Each article has a permanent URL on `computo-journal.org` and a DOI, ensuring persistent access. - **Abstract visibility**: The full author-written abstract is clearly visible on each article's landing page. @@ -115,6 +123,17 @@ For the full official documentation, see Google Scholar's [Inclusion Guidelines ## Indexing status report +::: {.callout-important} +### Update: September 2026 +A September 2026 audit found that, contrary to what this post initially stated, the `citation_pdf_url` tag was **missing from all Computo articles** until September 15, 2026, as well as from two landing pages that were redirect-only. All articles have since been fixed: + +- every article now declares `pdf-url` in its `citation:` block, and the tag is present on all article pages; +- article metadata was moved from `main.qmd` to `_quarto.yml`, which also removed duplicated authors from the generated citation of three articles; +- re-indexing of all article pages has been requested through Google Search Console. + +The report below reflects the July 2026 situation, before these fixes. +::: + ::: {.callout-note} ### Report date: July 2026 The following status was verified by searching Google Scholar for each published article. @@ -139,7 +158,7 @@ The following status was verified by searching Google Scholar for each published ### Not yet indexed in Google Scholar -The following 18 published articles were **not found** in Google Scholar as of July 2026: +The following 16 published articles were **not found** in Google Scholar as of July 2026: | # | Article | Authors | Year | |---|---------|---------|------| diff --git a/news.yml b/news.yml index 2936ef45..2cb3c6b9 100644 --- a/news.yml +++ b/news.yml @@ -12,7 +12,7 @@ Computo has been presented at the [2nd Toronto Workshop on reproducibility](https://canssiontario.utoronto.ca/toronto_workshop_on_reproducibility_2022/) ! - 🤩 [slides are online here](http://computo.sfds.asso.fr/comm/) + 🤩 [slides are online here](https://computo-journal.org/comm/) - date: 2022-06-14 07:59:00-0400 description: >2+ @@ -34,20 +34,20 @@ [François-David](https://fradav.github.io/) and - [Ghislain](https://gdurif.perso.math.cnrs.fr/) [in the team](board) 👨‍💻 ! + [Ghislain](https://gdurif.perso.math.cnrs.fr/) [in the team](site/board.html) 👨‍💻 ! Thanks for their support. - date: 2023-02-08 07:59:00-0400 description: >2 - We have [updated our templates for submitting to Computo](https://computo.sfds.asso.fr/submit/): all based on Quarto, but now with more specific and hoefully friendly set-ups for R, Python or Julia users. + We have [updated our templates for submitting to Computo](https://computo-journal.org/site/guidelines-authors.html): all based on Quarto, but now with more specific and hoefully friendly set-ups for R, Python or Julia users. - date: 2023-06-21 07:59:00-0400 description: >2+ Delighted to welcome - [Marie-Pierre](httpshttps://marieetienne.github.io/) [in the team](board) 👨‍💻 ! + [Marie-Pierre](https://marieetienne.github.io/) [in the team](site/board.html) 👨‍💻 ! - date: 2023-06-21 07:59:00-0400 description: >2+ @@ -64,7 +64,7 @@ Delighted to welcome - [Aymeric Stamm](https://astamm.github.io/) [in the team](board) 👨‍💻 ! + [Aymeric Stamm](https://astamm.github.io/) [in the team](site/board.html) 👨‍💻 ! - date: 2025-09-16 07:59:00-0400 description: >2+ @@ -83,9 +83,9 @@ Happy to welcome - [Mathieu Carrière](https://www-sop.inria.fr/members/Mathieu.Carriere/) [in the team](board) 👨‍💻 ! + [Mathieu Carrière](https://www-sop.inria.fr/members/Mathieu.Carriere/) [in the team](site/board.html) 👨‍💻 ! -- date: 2026-12-16 07:59:00-0400 +- date: 2026-06-16 07:59:00-0400 description: >2+ The next [2026 French Statistics Days](https://jds2026.sciencesconf.org/) is fast approaching and will take place in Clermont-Ferrand. To mark the occasion, [François-David Collin](https://fradav.perso.math.cnrs.fr/) is running a [workshop](https://computo-journal.org/jds-workshop/) on how to use Computo templates to help you prepare your submission with ease. diff --git a/publications/in_production.bib b/publications/in_production.bib deleted file mode 100644 index 8b137891..00000000 --- a/publications/in_production.bib +++ /dev/null @@ -1 +0,0 @@ - diff --git a/publications/mock_papers.bib b/publications/mock_papers.bib deleted file mode 100644 index 63bfa931..00000000 --- a/publications/mock_papers.bib +++ /dev/null @@ -1,39 +0,0 @@ -@Article {mock_tsne, - bibtex_show = {true}, - author = {van der Maaten, Laurens and Hinton, Geoffrey}, - title = {{Visualizing Data using t-SNE: practical Computo example}}, - journal = {Computo}, - year = {2021}, - volume = {0}, - repository = {published-paper-tsne}, - type = {Template}, - language = {R, Python}, - domain = {Template}, - abstract = {We present a new technique called “t-SNE” that - visualizes high-dimensional data by giving each - datapoint a location in a two or three-dimensional - map. The technique is a variation of Stochastic - Neighbor Embedding hinton:stochastic that is much - easier to optimize, and produces significantly - better visualizations by reducing the tendency to - crowd points together in the center of the - map. t-SNE is better than existing techniques at - creating a single map that reveals structure at many - different scales. This is particularly important for - high-dimensional data that lie on several different, - but related, low-dimensional manifolds, such as - images of objects from multiple classes seen from - multiple viewpoints. For visualizing the structure - of very large data sets, we show how t-SNE can use - random walks on neighborhood graphs to allow the - implicit structure of all the data to influence the - way in which a subset of the data is displayed. We - illustrate the performance of t-SNE on a wide - variety of data sets and compare it with many other - non-parametric visualization techniques, including - Sammon mapping, Isomap, and Locally Linear - Embedding. The visualization produced by t-SNE are - significantly better than those produced by other - techniques on almost all of the data sets.}, - keywords = {template, documentation, quarto, R, python} -} diff --git a/publications/publications.qmdold b/publications/publications.qmdold deleted file mode 100644 index 8521509b..00000000 --- a/publications/publications.qmdold +++ /dev/null @@ -1,32 +0,0 @@ ---- -title: "Articles" -description: "Publications by years in reversed chronological order" -bibliography: - published: published.bib - pipeline: in_production.bib - examples: mock_papers.bib -nocite: | - @* -filters: - - multibib -validate-yaml: false ---- - -## Published Articles - -::: {#refs-published} -::: - -## In the Pipeline - -Manuscripts conditionally accepted, whose editorial and scientific reproducibility are being validated. - -::: {#refs-pipeline} -::: - -## Examples and Mock Contributions - -These are examples that help authors submitting to the journal by demonstrating formatting features. - -::: {#refs-examples} -::: diff --git a/publications/published.bib b/publications/published.bib deleted file mode 100644 index afe572d2..00000000 --- a/publications/published.bib +++ /dev/null @@ -1,380 +0,0 @@ -@article{giorgi2024, - bibtex_show = {true}, - author = {Giorgi, Daphn\'e and Kaakai, Sarah and Lemaire, Vincent}, - publisher = {French Statistical Society}, - title = {Efficient simulation of individual-based population models}, - journal = {Computo}, - year = 2025, - url = {https://computo.sfds.asso.fr/published-202412-giorgi-efficient/}, - doi = {10.57750/sfxn-1t05}, - issn = {2824-7795}, - type = {{Research article}}, - domain = {Statistics}, - language = {R}, - repository = {published-202412-giorgi-efficient}, - langid = {en}, - abstract = { -The `R` Package `IBMPopSim` facilitates the simulation of the random evolution of heterogeneous populations using stochastic Individual-Based Models (IBMs). The package enables users to simulate population evolution, in which individuals are characterized by their age and some characteristics, and the population is modified by different types of events, including births/arrivals, death/exit events, or changes of characteristics. The frequency at which an event can occur to an individual can depend on their age and characteristics, but also on the characteristics of other individuals (interactions). Such models have a wide range of applications in fields including actuarial science, biology, ecology or epidemiology. `IBMPopSim` overcomes the limitations of time-consuming IBMs simulations by implementing new efficient algorithms based on thinning methods, which are compiled using the `Rcpp` package while providing a user-friendly interface. -} -} - -@article{ambroise2024, - bibtex_show = {true}, - author = {Laplante, Félix and Ambroise, Christophe}, - publisher = {French Statistical Society}, - title = {Spectral Bridges: Scalable Spectral Clustering Based on Vector Quantization}, - journal = {Computo}, - year = 2025, - url = {https://computo.sfds.asso.fr/published-202412-ambroise-spectral/}, - doi = {10.57750/1gr8-bk61}, - issn = {2824-7795}, - type = {{Research article}}, - domain = {Machine Learning}, - language = {R}, - repository = {published-202412-ambroise-spectral}, - langid = {en}, - abstract = {In this paper, Spectral Bridges, a novel clustering algorithm, is introduced. This algorithm builds upon the traditional k-means and spectral clustering frameworks by subdividing data into small Voronoï regions, which are subsequently merged according to a connectivity measure. Drawing inspiration from Support Vector Machine’s margin concept, a non-parametric clustering approach is proposed, building an affinity margin between each pair of Voronoï regions. This approach delineates intricate, non-convex cluster structures and is robust to hyperparameter choice. The numerical experiments underscore Spectral Bridges as a fast, robust, and versatile tool for clustering tasks spanning diverse domains. Its efficacy extends to large-scale scenarios encompassing both real-world and synthetic datasets. The Spectral Bridge algorithm is implemented both in Python (https://pypi.org/project/spectral-bridges) and R (https://github.com/cambroise/spectral-bridges-Rpackage). -} -} - -@article{legrand2024, - bibtex_show = {true}, - author = {Legrand, Juliette and Pimont, François and Dupuy, Jean-Luc - and Opitz, Thomas}, - publisher = {French Statistical Society}, - title = {Bayesian Spatiotemporal Modelling of Wildfire Occurrences and - Sizes for Projections Under Climate Change}, - journal = {Computo}, - year = 2024, - url = {https://computo.sfds.asso.fr/published-202407-legrand-wildfires/}, - doi = {10.57750/4y84-4t68}, - issn = {2824-7795}, - type = {{Research article}}, - domain = {Statistics}, - language = {R}, - repository = {published-202407-legrand-wildfires}, - langid = {en}, - abstract = {Appropriate spatiotemporal modelling of wildfire activity - is crucial for its prediction and risk management. Here, we focus on - wildfire risk in the Aquitaine region in the Southwest of France and - its projection under climate change. We study whether wildfire risk - could further increase under climate change in this specific region, - which does not lie in the historical core area of wildfires in - Southeastern France, corresponding to the Southwest. For this - purpose, we consider a marked spatiotemporal point process, a - flexible model for occurrences and magnitudes of such environmental - risks, where the magnitudes are defined as the burnt areas. The - model is first calibrated using 14 years of past observation data of - wildfire occurrences and weather variables, and then applied for - projection of climate-change impacts using simulations of numerical - climate models until 2100 as new inputs. We work within the - framework of a spatiotemporal Bayesian hierarchical model, and we - present the workflow of its implementation for a large dataset at - daily resolution for 8km-pixels using the INLA-SPDE approach. The - assessment of the posterior distributions shows a satisfactory fit - of the model for the observation period. We stochastically simulate - projections of future wildfire activity by combining climate model - output with posterior simulations of model parameters. Depending on - climate models, spline-smoothed projections indicate low to moderate - increase of wildfire activity under climate change. The increase is - weaker than in the historical core area, which we attribute to - different weather conditions (oceanic versus Mediterranean). Besides - providing a relevant case study of environmental risk modelling, - this paper is also intended to provide a full workflow for - implementing the Bayesian estimation of marked log-Gaussian Cox - processes using the R-INLA package of the R statistical software.} -} - -@article{pishchagina2024, - bibtex_show = {true}, - author = {Pishchagina, Liudmila and Rigaill, Guillem and Runge, - Vincent}, - publisher = {French Statistical Society}, - title = {Geometric-Based {Pruning} {Rules} for {Change} {Point} - {Detection} in {Multiple} {Independent} {Time} {Series}}, - journal = {Computo}, - year = 2024, - url = {https://computo.sfds.asso.fr/published-202406-pishchagina-change-point/}, - doi = {10.57750/9vvx-eq57}, - issn = {2824-7795}, - type = {{Research article}}, - domain = {Statistics}, - language = {R}, - repository = {published-202406-pishchagina-change-point}, - langid = {en}, - abstract = {We address the challenge of identifying multiple change - points in a group of independent time series, assuming these change - points occur simultaneously in all series and their number is - unknown. The search for the best segmentation can be expressed as a - minimization problem over a given cost function. We focus on dynamic - programming algorithms that solve this problem exactly. When the - number of changes is proportional to data length, an - inequality-based pruning rule encoded in the PELT algorithm leads to - a linear time complexity. Another type of pruning, called functional - pruning, gives a close-to-linear time complexity whatever the number - of changes, but only for the analysis of univariate time series. We - propose a few extensions of functional pruning for multiple - independent time series based on the use of simple geometric shapes - (balls and hyperrectangles). We focus on the Gaussian case, but some - of our rules can be easily extended to the exponential family. In a - simulation study we compare the computational efficiency of - different geometric-based pruning rules. We show that for a small - number of time series some of them ran significantly faster than - inequality-based approaches in particular when the underlying number - of changes is small compared to the data length.} -} - -@article{susmann_adaptive, - bibtex_show = {true}, - author = {Susmann, Herbert and and Chambaz, Antoine and Josse, Julie}, - publisher = {French Statistical Society}, - title = {{AdaptiveConformal: An R Package for Adaptive Conformal Inference}}, - journal = {Computo}, - year = 2024, - url = {https://computo.sfds.asso.fr/published-202407-susmann-adaptive-conformal}, - doi = {10.57750/edan-5f53}, - type = {{Research article}}, - domain = {Statistics}, - language = {R}, - repository = {published-202407-susmann-adaptive-conformal}, - langid = {en}, - abstract = {Conformal Inference (CI) is a popular approach for generating finite sample prediction intervals based on the output of any point prediction method when data are exchangeable. Adaptive Conformal Inference (ACI) algorithms extend CI to the case of sequentially observed data, such as time series, and exhibit strong theoretical guarantees without having to assume exchangeability of the observed data. The common thread that unites algorithms in the ACI family is that they adaptively adjust the width of the generated prediction intervals in response to the observed data. We provide a detailed description of five ACI algorithms and their theoretical guarantees, and test their performance in simulation studies. We then present a case study of producing prediction intervals for influenza incidence in the United States based on black-box point forecasts. Implementations of all the algorithms are released as an open-source R package, AdaptiveConformal, which also includes tools for visualizing and summarizing conformal prediction intervals.} -} - -@article{lefort_peerannot, - bibtex_show = {true}, - author = {Lefort, Tanguy and Charlier, Benjamin and Joly, Alexis and Salmon, Joseph}, - title = {{Peerannot: classification for crowdsourced image datasets with Python}}, - journal = {Computo}, - year = 2024, - abstract = {Crowdsourcing is a quick and easy way to collect labels for large datasets, involving many workers. However, workers often disagree with each other. Sources of error can arise from the workers’ skills, but also from the intrinsic difficulty of the task. We present peerannot: a Python library for managing and learning from crowdsourced labels for classification. Our library allows users to aggregate labels from common noise models or train a deep learning-based classifier directly from crowdsourced labels. In addition, we provide an identification module to easily explore the task difficulty of datasets and worker capabilities.}, - doi = {10.57750/qmaz-gr91}, - repository = {published-202402-lefort-peerannot}, - type = {{Research article}}, - language = {Python}, - domain = {Machine Learning}, - keywords = {crowdsourcing, label noise, task difficulty, worker ability, classification}, - issn = {2824-7795} -} - -@article{elmasri-optimal, - bibtex_show = {true}, - author = {El Masri, Maxime and Morio, Jérôme and Simatos, Florian}, - title = {{Optimal projection for parametric importance sampling in high dimensions}}, - journal = {Computo}, - year = 2024, - abstract = {In this paper we propose a dimension-reduction strategy in order to improve the performance of importance sampling in high dimension. The idea is to estimate variance terms in a small number of suitably chosen directions. We first prove that the optimal directions, i.e., the ones that minimize the Kullback--Leibler divergence with the optimal auxiliary density, are the eigenvectors associated to extreme (small or large) eigenvalues of the optimal covariance matrix. We then perform extensive numerical experiments that show that as dimension increases, these directions give estimations which are very close to optimal. Moreover, we show that the estimation remains accurate even when a simple empirical estimator of the covariance matrix is used to estimate these directions. These theoretical and numerical results open the way for different generalizations, in particular the incorporation of such ideas in adaptive importance sampling schemes}, - doi = {doi.org/10.57750/jjza-6j82}, - repository = {published-202402-elmasri-optimal}, - type = {{Research article}}, - language = {Python}, - domain = {Statistics}, - keywords = {Rare event simulation, Parameter estimation, Importance sampling, Dimension reduction, Kullback--Leibler divergence, Projection}, - issn = {2824-7795} -} - -@article{adrat_repulsion, - bibtex_show = {true}, - author = {Adrat, Hamza and Decreusefond, Laurent}, - title = {{Point Process Discrimination According to Repulsion}}, - journal = {Computo}, - year = 2024, - abstract = {In numerous applications, cloud of points do seem to exhibit repulsion in the intuitive sense that there is no local cluster as in a Poisson process. Motivated by data coming from cellular networks, we devise a classification algorithm based on the form of the Voronoi cells. We show that, in the particular set of data we are given, we can retrieve some repulsiveness between antennas, which was expected for engineering reasons.}, - doi = {10.57750/3r07-aw28}, - repository = {published_202401_adrat_repulsion}, - type = {{Research article}}, - language = {Python}, - domain = {Statistics}, - keywords = {classification, point process, repulsion}, - issn = {2824-7795} -} - - -@article{favrot_hierarchical, - bibtex_show = {true}, - author = {Favrot, Armand and Makoswki, David}, - title = {{A hierarchical model to evaluate pest treatments from prevalence and intensity data}}, - journal = {Computo}, - year = 2024, - abstract = {In plant epidemiology, pest abundance is measured in field trials using metrics assessing either pest prevalence (fraction of the plant population infected) or pest intensity (average number of pest individuals present in infected plants). Some of these trials rely on prevalence, while others rely on intensity, depending on the protocols. In this paper, we present a hierarchical Bayesian model able to handle both types of data. In this model, the intensity and prevalence variables are derived from a latent variable representing the number of pest individuals on each host individual, assumed to follow a Poisson distribution. Effects of pest treaments, time trend, and between-trial variability are described using fixed and random effects. We apply the model to a real dataset in the context of aphid control in sugar beet fields. In this dataset, prevalence and intensity were derived from aphid counts observed on either factorial trials testing different types of pesticides treatments or field surveys monitoring aphid abundance. Next, we perform simulations to assess the impacts of using either prevalence or intensity data, or both types of data simultaneously, on the accuracy of the model parameter estimates and on the ranking of pesticide treatment efficacy. Our results show that, when pest prevalence and pest intensity data are collected separately in different trials, the model parameters are more accurately estimated using both types of trials than using one type of trials only. When prevalence data are collected in all trials and intensity data are collected in a subset of trials, estimations and pest treatment ranking are more accurate using both types of data than using prevalence data only. When only one type of observation can be collected in a pest survey or in an experimental trial, our analysis indicates that it is better to collect intensity data than prevalence data when all or most of the plants are expected to be infested, but that both types of data lead to similar results when the level of infestation is low to moderate. Finally, our simulations show that it is unlikely to obtain accurate results with fewer than 40 trials when assessing the efficacy of pest control treatments based on prevalence and intensity data. Because of its flexibility, our model can be used to evaluate and rank the efficacy of pest treatments using either prevalence or intensity data, or both types of data simultaneously. As it can be easily implemented using standard Bayesian packages, we hope that it will be useful to agronomists, plant pathologists, and applied statisticians to analyze pest surveys and field experiments conducted to assess the efficacy of pest treatments.}, - doi = {10.57750/6cgk-g727}, - repository = {published-202312-favrot-hierarchical}, - type = {{Research article}}, - language = {R}, - domain = {Statistics}, - keywords = {bayesian model, epidemiology, hierarchical model, pest control, trial, survey}, - issn = {2824-7795} -} - -@article{cleynen_local, - bibtex_show = {true}, - author = {Cleynen, Alice and Raynal, Louis and Marin, Jean-Michel}, - title = {{Local tree methods for classification: a review and some dead ends}}, - journal = {Computo}, - year = 2023, - abstract = {Random Forests (RF) [@breiman:2001] are very popular machine learning methods. They perform well even with little or no tuning, and have some theoretical guarantees, especially for sparse problems [@biau:2012;@scornet:etal:2015]. These learning strategies have been used in several contexts, also outside the field of classification and regression. To perform Bayesian model selection in the case of intractable likelihoods, the ABC Random Forests (ABC-RF) strategy of @pudlo:etal:2016 consists in applying Random Forests on training sets composed of simulations coming from the Bayesian generative models. The ABC-RF technique is based on an underlying RF for which the training and prediction phases are separated. The training phase does not take into account the data to be predicted. This seems to be suboptimal as in the ABC framework only one observation is of interest for the prediction. In this paper, we study tree-based methods that are built to predict a specific instance in a classification setting. This type of methods falls within the scope of local (lazy/instance-based/case specific) classification learning. We review some existing strategies and propose two new ones. The first consists in modifying the tree splitting rule by using kernels, the second in using a first RF to compute some local variable importance that is used to train a second, more local, RF. Unfortunately, these approaches, although interesting, do not provide conclusive results.}, - doi = {10.57750/3j8m-8d57}, - repository = {published-202312-cleynen-local}, - type = {{Research article}}, - language = {R}, - domain = {Statistics}, - keywords = {classification, Random Forests, local methods}, - issn = {2824-7795} -} - -@article{delattre_fim, - bibtex_show = {true}, - author = {Delattre, Maud and Kuhn, Estelle}, - title = {{Computing an empirical Fisher information matrix estimate in latent variable models through stochastic approximation}}, - journal = {Computo}, - year = 2023, - abstract = {The Fisher information matrix (FIM) is a key quantity in statistics. However its exact computation is often not trivial. In particular in many latent variable models, it is intricated due to the presence of unobserved variables. Several methods have been proposed to approximate the FIM when it can not be evaluated analytically. Different estimates have been considered, in particular moment estimates. However some of them require to compute second derivatives of the complete data log-likelihood which leads to some disadvantages. In this paper, we focus on the empirical Fisher information matrix defined as an empirical estimate of the covariance matrix of the score, which only requires to compute the first derivatives of the log-likelihood. Our contribution consists in presenting a new numerical method to evaluate this empirical Fisher information matrix in latent variable model when the proposed estimate can not be directly analytically evaluated. We propose a stochastic approximation estimation algorithm to compute this estimate as a by-product of the parameter estimate. We evaluate the finite sample size properties of the proposed estimate and the convergence properties of the estimation algorithm through simulation studies.}, - doi = {10.57750/r5gx-jk62}, - repository = {published-202311-delattre-fim}, - type = {{Research article}}, - language = {R}, - domain = {Statistics}, - keywords = {Model-based standard error, moment estimate, Fisher identity, stochastic approximation algorithm}, - issn = {2824-7795} -} - -@article{sanou_multiscale, - bibtex_show = {true}, - author = {Sanou, Edmond and Ambroise, Christophe and Robin, Geneviève}, - title = {{Inference of Multiscale Gaussian Graphical Model}}, - journal = {Computo}, - year = 2023, - abstract = {Gaussian Graphical Models (GGMs) are widely used in high-dimensional data analysis to synthesize the interaction between variables. In many applications, such as genomics or image analysis, graphical models rely on sparsity and clustering to reduce dimensionality and improve performances. This paper explores a slightly different paradigm where clustering is not knowledge-driven but performed simultaneously with the graph inference task. We introduce a novel Multiscale Graphical Lasso (MGLasso) to improve networks interpretability by proposing graphs at different granularity levels. The method estimates clusters through a convex clustering approach — a relaxation of k-means, and hierarchical clustering. The conditional independence graph is simultaneously inferred through a neighborhood selection scheme for undirected graphical models. MGLasso extends and generalizes the sparse group fused lasso problem to undirected graphical models. We use continuation with Nesterov smoothing in a shrinkage-thresholding algorithm (CONESTA) to propose a regularization path of solutions along the group fused Lasso penalty, while the Lasso penalty is kept constant. Extensive experiments on synthetic data compare the performances of our model to state-of-the-art clustering methods and network inference models. Applications to gut microbiome data and poplar's methylation mixed with transcriptomic data are presented.}, - doi = {10.57750/1f4p-7955}, - repository = {published-202306-sanou-multiscale_glasso}, - type = {{Research article}}, - language = {R and Python}, - domain = {Statistics}, - keywords = {Neighborhood selection, Convex hierarchical clustering, Gaussian graphical models}, - issn = {2824-7795} -} - - -@article{chagneux_macrolitter, - bibtex_show = {true}, - author = {Chagneux, Mathis and Le Corff, Sylvain and - Gloaguen, Pierre and Ollion, Charles and Lepâtre, Océane and - Bruge, Antoine}, - title = {Macrolitter Video Counting on Riverbanks Using State - Space Models and Moving Cameras}, - journal = {Computo}, - year = {2023}, - repository = {published-202301-chagneux-macrolitter}, - doi = {10.57750/845m-f805}, - language = {Python}, - issn = {2824-7795}, - langid = {en}, - type = {{Research article}}, - abstract = {Litter is a known cause of degradation in marine - environments and most of it travels in rivers before - reaching the oceans. In this paper, we present a - novel algorithm to assist waste monitoring along - watercourses. While several attempts have been made - to quantify litter using neural object detection in - photographs of floating items, we tackle the more - challenging task of counting directly in videos - using boat-embedded cameras. We rely on multi-object - tracking (MOT) but focus on the key pitfalls of - false and redundant counts which arise in typical - scenarios of poor detection performance. Our system - only requires supervision at the image level and - performs Bayesian filtering via a state space model - based on optical flow. We present a new open image - dataset gathered through a crowdsourced campaign and - used to train a center-based anchor-free object - detector. Realistic video footage assembled by water - monitoring experts is annotated and provided for - evaluation. Improvements in count quality are - demonstrated against systems built from - state-of-the-art multi-object trackers sharing the - same detection capabilities. A precise error - decomposition allows clear analysis and highlights - the remaining challenges.} -} - -@article{boulin_clayton, - bibtex_show = {true}, - author = {Boulin, Alexis}, - title = {{A Python Package for Sampling from Copulae: - clayton}}, - journal = {Computo}, - year = 2023, - abstract = {The package clayton is designed to be intuitive, - user-friendly, and efficient. It offers a wide range - of copula models, including Archimedean, Elliptical, - and Extreme. The package is implemented in pure - Python, making it easy to install and use. In - addition, we provide detailed documentation and - examples to help users get started quickly. We also - conduct a performance comparison with existing R - packages, demonstrating the efficiency of our - implementation. The clayton package is a valuable - tool for researchers and practitioners working with - copulae in Python}, - doi = {10.57750/4szh-t752}, - repository = {published-202301-boulin-clayton}, - type = {{Software paper}}, - language = {Python}, - domain = {Statistics}, - keywords = {Copulae, Random number generation}, - issn = {2824-7795} -} - -@article{gimenez_lynx, - bibtex_show = {true}, - author = {Gimenez, Olivier and Kervellec, Maelis and Fanjul, - Jean-Baptiste and Chaine, Anna and Marescot, Lucile - and Bollet, Yoann and Duchamp, Christophe}, - title = {{Trade-off between deep learning for species - identification and inference about predator-prey - co-occurrence: Reproducible R workflow integrating - models in computer vision and ecological - statistics}}, - journal = {Computo}, - year = 2022, - abstract = {Deep learning is used in computer vision problems - with important applications in several scientific - fields. In ecology for example, there is a growing - interest in deep learning for automatizing - repetitive analyses on large amounts of images, such - as animal species identification. However, there - are challenging issues toward the wide adoption of - deep learning by the community of ecologists. First, - there is a programming barrier as most algorithms - are written in Python while most ecologists are - versed in R. Second, recent applications of deep - learning in ecology have focused on computational - aspects and simple tasks without addressing the - underlying ecological questions or carrying out the - statistical data analysis to answer these questions. - Here, we showcase a reproducible R workflow - integrating both deep learning and statistical - models using predator-prey relationships as a case - study. We illustrate deep learning for the - identification of animal species on images collected - with camera traps, and quantify spatial - co-occurrence using multispecies occupancy models. - Despite average model classification performances, - ecological inference was similar whether we analysed - the ground truth dataset or the classified - dataset. This result calls for further work on the - trade-offs between time and resources allocated to - train models with deep learning and our ability to - properly address key ecological questions with - biodiversity monitoring. We hope that our - reproducible workflow will be useful to ecologists - and applied statisticians.}, - doi = {10.57750/yfm2-5f45}, - repository = {published-202204-deeplearning-occupancy-lynx}, - type = {{Research article}}, - language = {R}, - domain = {Statistical Ecology}, - keywords = {computer vision, deep-learning, species distribution - modeling, ecological statistics}, - issn = {2824-7795} -} diff --git a/publications/templates.bib b/publications/templates.bib deleted file mode 100644 index 0a89e3e2..00000000 --- a/publications/templates.bib +++ /dev/null @@ -1,59 +0,0 @@ -@Article {template_r, - author = {{Computo editorial board}}, - title = {{Computo Template for R users}}, - journal = {Computo}, - year = {2022}, - volume = {0}, - repository = {template-computo-R}, - type = {Template}, - language = {R}, - domain = {Template}, - abstract = {Documentation and sample of a simple R-based - submission for the Computo journal, using our - Quarto-based template and renv for handling - dependencies. Shows how to automatically setup and - build the HTML and PDF outputs, ready to submit to - our peer-review platform.}, - keywords = {template, documentation, R, quarto, renv} -} - -@Article {template_python, - author = {{Computo editorial board}}, - title = {{Computo Template for Python users}}, - journal = {Computo}, - year = {2022}, - volume = {0}, - repository = {template-computo-python}, - type = {Template}, - language = {Python}, - domain = {Template}, - abstract = {Documentation and sample of a simple Python-based - submission for the Computo journal, using our - Quarto-based template and pip/venv for handling - dependencies. Shows how to automatically setup and - build the HTML and PDF outputs, ready to submit to - our peer-review platform.}, - keywords = {template, documentation, Python, quarto, venv} -} - -@Article {template_python, - author = {{Computo editorial board}}, - title = {{Computo Template for Julia users}}, - journal = {Computo}, - year = {2022}, - volume = {0}, - repository = {template-computo-julia}, - type = {Template}, - language = {Julia}, - domain = {Template}, - abstract = {Documentation and sample of a simple Julia-based - submission for the Computo journal, using our - Quarto-based template and the built-in Julia Pkg manager. - Shows how to automatically setup and - build the HTML and PDF outputs, ready to submit to - our peer-review platform.}, - keywords = {template, documentation, Julia, quarto, Pkg} -} - - - diff --git a/publications/templates_obsolete.bib b/publications/templates_obsolete.bib deleted file mode 100644 index dc57ecfd..00000000 --- a/publications/templates_obsolete.bib +++ /dev/null @@ -1,22 +0,0 @@ ---- ---- - -@Article {template_myst, - author = {{Computo editorial board}}, - title = {{Template for writing a contribution for Computo based on Myst/Jupyter book}}, - journal = {Computo}, - year = {2021}, - volume = {0}, - repository = {template-computo-myst}, - type = {Template}, - language = {R, Python}, - domain = {Template}, - abstract = {This document provides a Myst/Jupyter book template - for contributions to the Computo Journal. It also - serves as a documentation for configuring the github - repository which will host the notebook source of - your manuscript and prove us the reproducibility of - your work.}, - keywords = {template, documentation, Rmarkdown, binder} -} - diff --git a/published-202306-sanou-multiscale_glasso/index.html b/published-202306-sanou-multiscale_glasso/index.html new file mode 100644 index 00000000..ba8d9283 --- /dev/null +++ b/published-202306-sanou-multiscale_glasso/index.html @@ -0,0 +1,15 @@ + + + + + Moved: Inference of Multiscale Gaussian Graphical Models + + + + + + +

This article has moved to + https://computo-journal.org/published-202306-sanou-multiscale-glasso/.

+ + diff --git a/site/guidelines-reviewers.qmd b/site/guidelines-reviewers.qmd index 128ab36f..3169695b 100644 --- a/site/guidelines-reviewers.qmd +++ b/site/guidelines-reviewers.qmd @@ -1,6 +1,8 @@ --- title: Reviewing for Computo description: Guidelines for reviewers +aliases: + - /guidelines-reviewers format: html: {} page-layout: article diff --git a/site/mock-papers.yml b/site/mock-papers.yml index 0c3c299b..3c2ad2b4 100644 --- a/site/mock-papers.yml +++ b/site/mock-papers.yml @@ -63,7 +63,7 @@ } pdf: '' - url: http://computo-journal.org/published-paper-tsne/ + url: https://computo-journal.org/published-paper-tsne/ status: published - title: Visualizing Data using t-SNE (mock contribution) name: published-paper-tsne-R @@ -103,7 +103,7 @@ title = {Visualizing {Data} Using {t-SNE} (Mock Contribution)}, journal = {Computo}, date = {2008-08-11}, - url = {https://computo-journal.org/published-paper-tsne/}, + url = {https://computo-journal.org/published-paper-tsne-R/}, doi = {10.57750/xxx-xxx}, issn = {2824-7795}, langid = {en}, @@ -130,5 +130,5 @@ } pdf: '' - url: http://computo-journal.org/published-paper-tsne-R/ + url: https://computo-journal.org/published-paper-tsne-R/ status: published diff --git a/site/published.xml b/site/published.xml index e7b0e845..12ec4bc3 100644 --- a/site/published.xml +++ b/site/published.xml @@ -182,8 +182,8 @@ Reservoir Computing in R: a Tutorial for Using reservoirnet to Predict Complex Time-Series - Thomas Ferté, Kalidou Ba, Dan Dutartre, Pierrick Legrand, Vianney Jouhet, Rodolphe Thiébaut, Xavier Hinaut and Boris P Hejblum - http://computo-journal.org/published-202505-ferte-reservoirnet/ - http://computo-journal.org/published-202505-ferte-reservoirnet/ + https://computo-journal.org/published-202505-ferte-reservoirnet/ + https://computo-journal.org/published-202505-ferte-reservoirnet/ Fri, 27 Jun 2025 00:00:00 GMT Reservoir Computing (RC) is a machine learning method based on neural networks that efficiently process information @@ -208,8 +208,8 @@ Efficient simulation of individual-based population models - Daphné Giorgi, Sarah Kaakai and Vincent Lemaire - http://computo-journal.org/published-202412-giorgi-efficient/ - http://computo-journal.org/published-202412-giorgi-efficient/ + https://computo-journal.org/published-202412-giorgi-efficient/ + https://computo-journal.org/published-202412-giorgi-efficient/ Mon, 27 Jan 2025 00:00:00 GMT The `R` Package `IBMPopSim` facilitates the simulation of the random evolution of heterogeneous populations using stochastic diff --git a/site/published.yml b/site/published.yml index 733e0a72..d3f4847a 100644 --- a/site/published.yml +++ b/site/published.yml @@ -541,7 +541,7 @@ } pdf: '' - url: http://computo-journal.org/published-202505-ferte-reservoirnet/ + url: https://computo-journal.org/published-202505-ferte-reservoirnet/ status: published - title: Efficient simulation of individual-based population models name: published-202412-giorgi-efficient @@ -550,7 +550,8 @@ doi: 10.57750/sfxn-1t05 year: 2025 date: 2025-01-27 - description: '' + description: > + This document provides a full description of the Stochastic Individual-Based Models (IBMs) that can be implemented in the IBMPopSim package. A unified mathematical and simulation framework is given, with a detailed description of the simulation algorithm. Examples of applications for the package are also provided, showing the performance and flexibility of IBMPopSim. abstract: >- The `R` Package `IBMPopSim` facilitates the simulation of the random evolution of heterogeneous populations using stochastic @@ -597,7 +598,7 @@ } pdf: '' - url: http://computo-journal.org/published-202412-giorgi-efficient/ + url: https://computo-journal.org/published-202412-giorgi-efficient/ status: published - title: Spectral Bridges name: published-202412-ambroise-spectral @@ -657,7 +658,7 @@ } pdf: '' - url: http://computo-journal.org/published-202412-ambroise-spectral/ + url: https://computo-journal.org/published-202412-ambroise-spectral/ status: published - title: 'AdaptiveConformal: An `R` Package for Adaptive Conformal Inference' name: published-202407-susmann-adaptive-conformal @@ -718,7 +719,7 @@ } pdf: '' - url: http://computo-journal.org/published-202407-susmann-adaptive-conformal/ + url: https://computo-journal.org/published-202407-susmann-adaptive-conformal/ status: published - title: Bayesian spatiotemporal modelling of wildfire occurrences and sizes for projections under climate change name: published-202407-legrand-wildfires @@ -762,8 +763,7 @@ bibtex: >+ @article{legrand2024, author = {Legrand, Juliette and Pimont, François and Dupuy, Jean-Luc - and Opitz, Thomas and Pimont, François and Dupuy, Jean-Luc and - Opitz, Thomas}, + and Opitz, Thomas}, publisher = {French Statistical Society}, title = {Bayesian Spatiotemporal Modelling of Wildfire Occurrences and Sizes for Projections Under Climate Change}, @@ -805,7 +805,7 @@ } pdf: '' - url: http://computo-journal.org/published-202407-legrand-wildfires/ + url: https://computo-journal.org/published-202407-legrand-wildfires/ status: published - title: Geometric-Based Pruning Rules for Change Point Detection in Multiple Independent Time Series name: published-202406-pishchagina-change-point @@ -873,7 +873,7 @@ } pdf: '' - url: http://computo-journal.org/published-202406-pishchagina-change-point/ + url: https://computo-journal.org/published-202406-pishchagina-change-point/ status: published - title: 'Peerannot: classification for crowdsourced image datasets with Python' name: published-202402-lefort-peerannot @@ -882,7 +882,14 @@ doi: 10.57750/qmaz-gr91 year: 2024 date: 2024-05-07 - description: '' + description: > + Crowdsourcing is a quick and easy way to collect labels for large datasets, involving many workers. + + However, it is common for workers to disagree with each other. + + Sources of error can arise from the workers' skills, but also from the intrinsic difficulty of the task. + + We introduce `peerannot`, a Python library for managing and learning from crowdsourced labels of image classification tasks. abstract: >- Crowdsourcing is a quick and easy way to collect labels for large datasets, involving many workers. However, workers often @@ -921,7 +928,7 @@ } pdf: '' - url: http://computo-journal.org/published-202402-lefort-peerannot/ + url: https://computo-journal.org/published-202402-lefort-peerannot/ status: published - title: Optimal projection for parametric importance sampling in high dimensions name: published-202402-elmasri-optimal @@ -979,7 +986,7 @@ } pdf: '' - url: http://computo-journal.org/published-202402-elmasri-optimal/ + url: https://computo-journal.org/published-202402-elmasri-optimal/ status: published - title: Point Process Discrimination According to Repulsion name: published-202401-adrat-repulsion @@ -1075,7 +1082,7 @@ repo: published-202312-favrot-hierarchical bibtex: >+ @article{favrot2024, - author = {Favrot, Armand and Makowski, David and Makowski, David}, + author = {Favrot, Armand and Makowski, David}, publisher = {French Statistical Society}, title = {A Hierarchical Model to Evaluate Pest Treatments from Prevalence and Intensity Data}, @@ -1203,7 +1210,7 @@ } pdf: '' - url: http://computo-journal.org/published-202312-cleynen-local/ + url: https://computo-journal.org/published-202312-cleynen-local/ status: published - title: Computing an empirical Fisher information matrix estimate in latent variable models through stochastic approximation name: published-202311-delattre-fim @@ -1270,10 +1277,10 @@ } pdf: '' - url: http://computo-journal.org/published-202311-delattre-fim/ + url: https://computo-journal.org/published-202311-delattre-fim/ status: published - title: Inference of Multiscale Gaussian Graphical Models - name: published-202306-sanou-multiscale_glasso + name: published-202306-sanou-multiscale-glasso authors: Edmond Sanou, Christophe Ambroise and Geneviève Robin journal: Computo doi: 10.57750/1f4p-7955 @@ -1303,7 +1310,7 @@ performances of our model to state-of-the-art clustering methods and network inference models. Applications to gut microbiome data and poplar’s methylation mixed with transcriptomic data are presented. - repo: published-202306-sanou-multiscale_glasso + repo: published-202306-sanou-multiscale-glasso bibtex: >+ @article{sanou2023, author = {Sanou, Edmond and Ambroise, Christophe and Robin, Geneviève}, @@ -1311,7 +1318,7 @@ title = {Inference of {Multiscale} {Gaussian} {Graphical} {Models}}, journal = {Computo}, date = {2023-06-28}, - url = {https://computo-journal.org/published-202306-sanou-multiscale_glasso/}, + url = {https://computo-journal.org/published-202306-sanou-multiscale-glasso/}, doi = {10.57750/1f4p-7955}, issn = {2824-7795}, langid = {en}, @@ -1340,7 +1347,7 @@ } pdf: '' - url: http://computo-journal.org/published-202306-sanou-multiscale_glasso/ + url: https://computo-journal.org/published-202306-sanou-multiscale-glasso/ status: published - title: 'Macrolitter video counting on riverbanks using state space models and moving cameras ' name: published-202301-chagneux-macrolitter @@ -1406,7 +1413,7 @@ } pdf: '' - url: http://computo-journal.org/published-202301-chagneux-macrolitter/ + url: https://computo-journal.org/published-202301-chagneux-macrolitter/ status: published - title: 'A Python Package for Sampling from Copulae: clayton' name: published-202301-boulin-clayton @@ -1457,7 +1464,7 @@ } pdf: '' - url: http://computo-journal.org/published-202301-boulin-clayton/ + url: https://computo-journal.org/published-202301-boulin-clayton/ status: published - title: Trade-off between deep learning for species identification and inference about predator-prey co-occurrence name: published-202204-deeplearning-occupancy-lynx @@ -1498,8 +1505,7 @@ @article{gimenez2022, author = {Gimenez, Olivier and Kervellec, Maëlis and Fanjul, Jean-Baptiste and Chaine, Anna and Marescot, Lucile and Bollet, - Yoann and Duchamp, Christophe and Gimenez, Olivier and Kervellec, - Maëlis and Marescot, Lucile}, + Yoann and Duchamp, Christophe}, publisher = {French Statistical Society}, title = {Trade-Off Between Deep Learning for Species Identification and Inference about Predator-Prey Co-Occurrence},