{"id":47,"date":"2026-05-18T12:37:26","date_gmt":"2026-05-18T12:37:26","guid":{"rendered":"https:\/\/convly.ai\/overfitting-how-to-prevent-it\/"},"modified":"2026-06-15T18:18:18","modified_gmt":"2026-06-15T18:18:18","slug":"overfitting-how-to-prevent-it","status":"publish","type":"post","link":"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/","title":{"rendered":"Overfitting nell'apprendimento automatico: cos'\u00e8 e come prevenirlo"},"content":{"rendered":"<p>A machine learning model can score 99% accuracy in testing and then fail badly in the real world. The usual culprit has a name: <strong>overfitting<\/strong>. It is the single most common mistake in applied machine learning, and understanding it is essential to building models that actually work. This guide explains overfitting clearly and gives you the proven ways to prevent it.<\/p>\n<div class=\"convly-tldr\">\n<h3>Punti chiave<\/h3>\n<ul>\n<li><strong>Overfitting<\/strong> is when a model memorizes its training data instead of learning the general pattern.<\/li>\n<li><strong>The sign:<\/strong> excellent performance on training data, poor performance on new data.<\/li>\n<li><strong>The opposite problem<\/strong> is underfitting \u2014 a model too simple to learn the pattern at all.<\/li>\n<li><strong>Prevent it with:<\/strong> more data, a simpler model, regularization, cross-validation, and early stopping.<\/li>\n<li><strong>Always test on data the model never saw<\/strong> \u2014 that&#8217;s the only honest measure of quality.<\/li>\n<\/ul>\n<\/div>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_84 counter-flat ez-toc-counter ez-toc-container-direction\">\n<label for=\"ez-toc-cssicon-toggle-item-6a38a8e4a9988\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Attiva\/Disattiva<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #000000;color:#000000\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #000000;color:#000000\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewbox=\"0 0 24 24\" version=\"1.2\" baseprofile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6a38a8e4a9988\"  aria-label=\"Attiva\/Disattiva\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1' ><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#What_is_overfitting\" >What is overfitting?<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#A_simple_analogy\" >A simple analogy<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#How_to_spot_overfitting\" >How to spot overfitting<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#The_opposite_problem_underfitting\" >The opposite problem: underfitting<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#Why_overfitting_happens\" >Why overfitting happens<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#How_to_prevent_overfitting\" >How to prevent overfitting<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#Data_leakage_the_hidden_cause_of_fake_good_results\" >Data leakage: the hidden cause of fake good results<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#FAQ\" >Domande frequenti<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#Bottom_line\" >Conclusione<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/convly.ai\/it\/overfitting-how-to-prevent-it\/#Related_articles\" >Articoli correlati<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"What_is_overfitting\"><\/span>What is overfitting?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Overfitting happens when a model learns its training data <em>too well<\/em> \u2014 including the noise, quirks, and random accidents that don&#8217;t represent the real pattern. Instead of learning the general rule, it memorizes the specific examples.<\/p>\n<p>The goal of machine learning is <strong>generalization<\/strong>: performing well on new, unseen data. An overfit model fails at exactly that. It has essentially memorized the answers to the practice exam, so it aces the practice exam \u2014 and then collapses on the real one, because the questions are different.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"A_simple_analogy\"><\/span>A simple analogy<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Picture two students preparing for a math test.<\/p>\n<p>The first <strong>understands the concepts<\/strong> \u2014 the methods, the reasoning. Give them any problem, even one they&#8217;ve never seen, and they can solve it.<\/p>\n<p>The second <strong>memorizes<\/strong> the exact practice problems and their answers, word for word. On the practice test, they score perfectly. On the real test, with new numbers, they&#8217;re lost \u2014 they never learned the method, only the specific answers.<\/p>\n<p>The second student is an overfit model: flawless on training data, helpless on anything new.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"How_to_spot_overfitting\"><\/span>How to spot overfitting<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Overfitting has one classic, unmistakable signature: <strong>a large gap between training performance and test performance.<\/strong><\/p>\n<p>This is why you always split your data. You train the model on one portion (the training set) and evaluate it on a separate portion it never saw (the test set). Then:<\/p>\n<ul>\n<li><strong>Small gap, both scores good<\/strong> \u2192 the model generalizes well. Healthy.<\/li>\n<li><strong>Training score high, test score much lower<\/strong> \u2192 overfitting. The model memorized.<\/li>\n<li><strong>Both scores poor<\/strong> \u2192 underfitting. The model is too simple (more on this below).<\/li>\n<\/ul>\n<p>If your model is brilliant on training data and mediocre on test data, you have overfitting \u2014 full stop.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"The_opposite_problem_underfitting\"><\/span>The opposite problem: underfitting<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Overfitting has a mirror image. <strong>Underfitting<\/strong> is when a model is too simple to capture the real pattern, so it performs poorly on <em>both<\/em> training and test data. It hasn&#8217;t memorized \u2014 it hasn&#8217;t learned at all.<\/p>\n<p>The two define a balance every ML practitioner manages:<\/p>\n<table class=\"convly-vs\">\n<thead>\n<tr>\n<th>Problem<\/th>\n<th>Training score<\/th>\n<th>Test score<\/th>\n<th>Cause<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Underfitting<\/td>\n<td>Poor<\/td>\n<td>Poor<\/td>\n<td>Model too simple<\/td>\n<\/tr>\n<tr>\n<td>Good fit<\/td>\n<td>Buono<\/td>\n<td>Buono<\/td>\n<td>Right complexity<\/td>\n<\/tr>\n<tr>\n<td>Overfitting<\/td>\n<td>Eccellente<\/td>\n<td>Poor<\/td>\n<td>Model too complex \/ too little data<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>The aim is the middle row: a model complex enough to learn the pattern, but not so complex it memorizes the noise.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Why_overfitting_happens\"><\/span>Why overfitting happens<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The common causes:<\/p>\n<ul>\n<li><strong>Too little training data<\/strong> \u2014 with few examples, the model can memorize them all instead of generalizing.<\/li>\n<li><strong>A model that&#8217;s too complex<\/strong> \u2014 a very flexible model has enough capacity to fit every quirk in the data.<\/li>\n<li><strong>Training for too long<\/strong> \u2014 past a point, extra training just fits noise more tightly.<\/li>\n<li><strong>Noisy or low-quality data<\/strong> \u2014 the more random junk in the data, the more there is to wrongly &#8220;learn.&#8221;<\/li>\n<li><strong>Too many features<\/strong> \u2014 irrelevant inputs give the model spurious patterns to latch onto.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"How_to_prevent_overfitting\"><\/span>How to prevent overfitting<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>There&#8217;s no single fix \u2014 practitioners combine several techniques.<\/p>\n<h3>1. Get more training data<\/h3>\n<p>The most effective cure. With more examples, memorizing becomes impossible and the model is forced to learn the genuine pattern. When you can&#8217;t collect more, <strong>data augmentation<\/strong> \u2014 creating realistic variations of what you have (rotating or cropping images, for instance) \u2014 helps.<\/p>\n<h3>2. Simplify the model<\/h3>\n<p>If the model is too complex, reduce its capacity: fewer parameters, a shallower structure, fewer features. Always try a simpler model first \u2014 it&#8217;s less prone to overfitting and easier to understand.<\/p>\n<h3>3. Use regularization<\/h3>\n<p>Regularization adds a penalty for complexity during training, discouraging the model from relying too heavily on any one feature or fitting extreme values. It&#8217;s a standard, built-in option in most ML algorithms and one of the most effective tools available.<\/p>\n<h3>4. Use cross-validation<\/h3>\n<p>Cross-validation tests the model on several different splits of the data rather than one. It gives a more honest, stable estimate of real-world performance and quickly reveals a model that only looks good on a lucky split.<\/p>\n<h3>5. Stop training early<\/h3>\n<p>Monitor performance on a validation set during training. When validation performance stops improving and starts to slip, stop \u2014 continuing past that point only fits noise. This is <strong>early stopping<\/strong>.<\/p>\n<h3>6. Use dropout (for neural networks)<\/h3>\n<p>Per <a href=\"\/it\/neural-networks-explained\/\">neural networks<\/a>, <strong>dropout<\/strong> randomly switches off some neurons during each training step. This stops the network from over-relying on any single path and forces it to learn more robust, general patterns.<\/p>\n<h3>7. Always hold out a real test set<\/h3>\n<p>Non-negotiable: keep a portion of data the model never sees during training or tuning, and judge the model only on that. It&#8217;s the only honest measure of how the model will perform in the real world.<\/p>\n<p><!--ai-enriched--><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Data_leakage_the_hidden_cause_of_fake_good_results\"><\/span>Data leakage: the hidden cause of fake good results<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Most of this guide treats overfitting as a modeling problem \u2014 a model too complex for too little data. But there is a quieter cause that produces the same symptom and fools far more practitioners: <strong>data leakage<\/strong>. Leakage is when information that would not be available at prediction time sneaks into training. The model looks brilliant in testing, then collapses in production. If your validation scores seem too good to be true, suspect leakage before you suspect luck.<\/p>\n<p>There are two families to watch for:<\/p>\n<ul>\n<li><strong>Train-test contamination.<\/strong> Test data bleeds into the training process. The classic mistake is preprocessing <em>before<\/em> splitting: if you scale, normalize, or impute missing values using statistics from the whole dataset, your training set has already &#8220;seen&#8221; the mean and range of the test set. Always split first, then fit any transformer on the training data alone and apply it to the test set.<\/li>\n<li><strong>Target leakage.<\/strong> A feature secretly encodes the answer. A model predicting whether a patient has an illness will look near-perfect if one of its inputs is &#8220;medication prescribed for that illness&#8221; \u2014 information that only exists <em>after<\/em> the diagnosis. The feature is not available when you actually need a prediction, so the score is fiction.<\/li>\n<\/ul>\n<p>Time-ordered data adds a third trap. Randomly shuffling a time series before splitting lets the model train on the future to predict the past, which violates causality and inflates accuracy. For anything with a timestamp, split chronologically: train on earlier periods, test on later ones.<\/p>\n<p>Leakage is dangerous precisely because none of the fixes elsewhere in this article catch it. More data, regularization, and early stopping all assume your evaluation is honest. If the test set is contaminated, every signal you rely on to detect overfitting is itself corrupted \u2014 so the model passes every check and still fails for real users.<\/p>\n<p>Three habits prevent most of it. First, wrap preprocessing and the model in a single pipeline (scikit-learn&#8217;s <strong>Pipeline<\/strong> does this) so transforms are only ever fit on training folds. Second, audit suspiciously strong features by asking: <em>would I genuinely know this value at the moment of prediction?<\/em> If not, drop it. Third, when results look spectacular, treat that as a red flag to investigate rather than a victory to celebrate. Genuine generalization rarely looks effortless.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"FAQ\"><\/span>Domande frequenti<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3>What is overfitting in machine learning?<\/h3>\n<p>Overfitting is when a model learns its training data too well \u2014 memorizing the noise and quirks instead of the general pattern. It performs excellently on training data but poorly on new, unseen data, because it never learned to generalize.<\/p>\n<h3>How do I know if my model is overfitting?<\/h3>\n<p>Compare its performance on training data versus test data (data it never saw). If it scores much higher on training than on testing, it&#8217;s overfitting. A healthy model performs similarly well on both.<\/p>\n<h3>What is the difference between overfitting and underfitting?<\/h3>\n<p>Overfitting is a model too complex that memorizes the training data and fails on new data. Underfitting is a model too simple to learn the pattern at all, so it performs poorly on both training and new data. The goal is the balanced middle.<\/p>\n<h3>How do you prevent overfitting?<\/h3>\n<p>Use more training data, choose a simpler model, apply regularization, use cross-validation, and stop training early when validation performance stops improving. For neural networks, dropout also helps. Most practitioners combine several of these techniques.<\/p>\n<h3>Does more data always fix overfitting?<\/h3>\n<p>More high-quality data is the most reliable cure, because it makes memorization impossible and forces genuine learning. But it isn&#8217;t always available \u2014 which is why simplifying the model, regularization, and early stopping matter as practical alternatives.<\/p>\n<h3>What is data leakage, and how is it different from overfitting?<\/h3>\n<p>Overfitting is a model memorizing noise in legitimately available training data. Data leakage is information that should not be available \u2014 such as test-set statistics or a feature that encodes the answer \u2014 contaminating training. They produce the same symptom (great test scores, poor real-world results), but leakage is more insidious: it makes your evaluation itself untrustworthy, so the usual overfitting checks fail to catch it. The fix is data hygiene \u2014 split before preprocessing and audit any feature that looks too predictive.<\/p>\n<h3>Why does my model overfit when I fine-tune an LLM on a small dataset?<\/h3>\n<p>Small fine-tuning sets are a textbook overfitting risk: with few examples, the model memorizes them instead of learning the pattern. The tell-tale sign is training loss falling while validation loss climbs. The standard remedies are running fewer epochs (often just a handful) with early stopping, and using a parameter-efficient method like LoRA, which constrains updates to a small subset of weights and acts as built-in regularization that resists memorization.<\/p>\n<h3>Is a small gap between training and test accuracy acceptable?<\/h3>\n<p>Yes. A small gap is normal and healthy \u2014 no model performs identically on data it has seen versus data it has not. Overfitting is signaled by a <em>large<\/em> or <em>widening<\/em> gap, where training accuracy keeps climbing while test accuracy stalls or falls. Chasing a zero gap usually means underfitting instead. Judge a model by its test-set performance, and treat the gap as a direction-of-travel warning light rather than a number to eliminate.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Bottom_line\"><\/span>Conclusione<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Overfitting is the gap between looking good and being good. A model that memorizes its training data will dazzle you in testing and disappoint you in production \u2014 it learned the answers, not the method.<\/p>\n<p>The defense is straightforward: always evaluate on data the model never saw, watch for the train-versus-test gap, and prevent overfitting with more data, simpler models, regularization, cross-validation, and early stopping. Master this balance and you&#8217;ll build models that work not just on your desk, but in the real world. For the bigger picture, see our <a href=\"\/it\/what-is-machine-learning-beginners-guide\/\">guide to machine learning<\/a>.<\/p>\n<p><!--related-block--><\/p>\n<div class=\"convly-related\">\n<h2><span class=\"ez-toc-section\" id=\"Related_articles\"><\/span>Articoli correlati<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/convly.ai\/it\/what-is-a-vector-database-2026\/\">Che cos\u2019\u00e8 un database vettoriale? (Guida 2026)<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/it\/best-free-datasets-machine-learning\/\">15 Best Free Datasets for Machine Learning Projects (2026)<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/it\/neural-networks-explained\/\">Reti neurali spiegate a non ingegneri (Guida 2026)<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/it\/deep-learning-vs-machine-learning\/\">Deep learning vs apprendimento automatico: le differenze fondamentali (2026)<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/it\/top-10-machine-learning-algorithms\/\">Top 10 Machine Learning Algorithms Every Beginner Should Know<\/a><\/li>\n<\/ul>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Overfitting is the most common reason a machine learning model fails in the real world. This guide explains what it is, how to spot it, and how to prevent it.<\/p>","protected":false},"author":0,"featured_media":48,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[2],"tags":[496,460,494,493,495],"class_list":["post-47","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning","tag-cross-validation","tag-machine-learning","tag-model-training","tag-overfitting","tag-regularization"],"_links":{"self":[{"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/posts\/47","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/comments?post=47"}],"version-history":[{"count":4,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/posts\/47\/revisions"}],"predecessor-version":[{"id":1152,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/posts\/47\/revisions\/1152"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/media\/48"}],"wp:attachment":[{"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/media?parent=47"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/categories?post=47"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/tags?post=47"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}