{"id":6257,"date":"2026-04-16T11:38:52","date_gmt":"2026-04-16T16:38:52","guid":{"rendered":"https:\/\/ykim.synology.me\/wordpress\/?p=6257"},"modified":"2026-04-16T15:31:01","modified_gmt":"2026-04-16T20:31:01","slug":"balancing-model-sensitivity-and-explainability-r%c2%b2","status":"publish","type":"post","link":"https:\/\/ykim.synology.me\/wordpress\/balancing-model-sensitivity-and-explainability-r%c2%b2-6257\/","title":{"rendered":"Balancing Model Sensitivity and Explainability (R\u00b2)"},"content":{"rendered":"<style>.kadence-column6257_4de40a-71 > .kt-inside-inner-col{display:flex;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col,.kadence-column6257_4de40a-71 > .kt-inside-inner-col:before{border-top-left-radius:0px;border-top-right-radius:0px;border-bottom-right-radius:0px;border-bottom-left-radius:0px;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm, 1rem);}.kadence-column6257_4de40a-71 > .kt-inside-inner-col{flex-direction:row;flex-wrap:wrap;align-items:flex-end;justify-content:flex-start;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col > *, .kadence-column6257_4de40a-71 > .kt-inside-inner-col > figure.wp-block-image, .kadence-column6257_4de40a-71 > .kt-inside-inner-col > figure.wp-block-kadence-image{margin-top:0px;margin-bottom:0px;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col > .kb-image-is-ratio-size{flex-grow:1;}.kt-row-column-wrap > .kadence-column6257_4de40a-71{align-self:flex-end;}.kt-inner-column-height-full:not(.kt-has-1-columns) > .wp-block-kadence-column.kadence-column6257_4de40a-71{align-self:auto;}.kt-inner-column-height-full:not(.kt-has-1-columns) > .wp-block-kadence-column.kadence-column6257_4de40a-71 > .kt-inside-inner-col{align-items:flex-end;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col:before{opacity:0.3;}.kadence-column6257_4de40a-71{position:relative;}@media all and (max-width: 1024px){.kt-row-column-wrap > .kadence-column6257_4de40a-71{align-self:flex-end;}}@media all and (max-width: 1024px){.kt-inner-column-height-full:not(.kt-has-1-columns) > .wp-block-kadence-column.kadence-column6257_4de40a-71{align-self:auto;}}@media all and (max-width: 1024px){.kt-inner-column-height-full:not(.kt-has-1-columns) > .wp-block-kadence-column.kadence-column6257_4de40a-71 > .kt-inside-inner-col{align-items:flex-end;}}@media all and (max-width: 1024px){.kadence-column6257_4de40a-71 > .kt-inside-inner-col{flex-direction:row;flex-wrap:wrap;align-items:flex-end;justify-content:flex-start;}}@media all and (min-width: 768px) and (max-width: 1024px){.kadence-column6257_4de40a-71 > .kt-inside-inner-col > *, .kadence-column6257_4de40a-71 > .kt-inside-inner-col > figure.wp-block-image, .kadence-column6257_4de40a-71 > .kt-inside-inner-col > figure.wp-block-kadence-image{margin-top:0px;margin-bottom:0px;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col > .kb-image-is-ratio-size{flex-grow:1;}}@media all and (max-width: 767px){.kt-row-column-wrap > .kadence-column6257_4de40a-71{align-self:flex-end;}.kt-inner-column-height-full:not(.kt-has-1-columns) > .wp-block-kadence-column.kadence-column6257_4de40a-71{align-self:auto;}.kt-inner-column-height-full:not(.kt-has-1-columns) > .wp-block-kadence-column.kadence-column6257_4de40a-71 > .kt-inside-inner-col{align-items:flex-end;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col{flex-direction:row;flex-wrap:wrap;justify-content:flex-start;justify-content:flex-start;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col > *, .kadence-column6257_4de40a-71 > .kt-inside-inner-col > figure.wp-block-image, .kadence-column6257_4de40a-71 > .kt-inside-inner-col > figure.wp-block-kadence-image{margin-top:0px;margin-bottom:0px;}.kadence-column6257_4de40a-71 > .kt-inside-inner-col > .kb-image-is-ratio-size{flex-grow:1;}}<\/style>\n<div class=\"wp-block-kadence-column kadence-column6257_4de40a-71 kb-section-dir-horizontal\"><div class=\"kt-inside-inner-col\">\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"683\" src=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Aerial-view-of-the-Great-Blue-Hole-in-Belize-1024x683.jpg\" alt=\"\" class=\"wp-image-6258\" style=\"width:800px\" srcset=\"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Aerial-view-of-the-Great-Blue-Hole-in-Belize-1024x683.jpg 1024w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Aerial-view-of-the-Great-Blue-Hole-in-Belize-300x200.jpg 300w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Aerial-view-of-the-Great-Blue-Hole-in-Belize-768x512.jpg 768w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Aerial-view-of-the-Great-Blue-Hole-in-Belize-1280x855.jpg 1280w, https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Aerial-view-of-the-Great-Blue-Hole-in-Belize.jpg 1536w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p class=\"has-theme-palette-6-color has-text-color has-link-color wp-elements-3e4c6214bb02b5855aad68aba4904935 wp-block-paragraph\" style=\"font-size:8px\">Aerial view of the Great Blue Hole in Belize<\/p>\n<\/div><\/div>\n\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n<style>.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col{padding-right:var(--global-kb-spacing-xxl, 5rem);padding-left:var(--global-kb-spacing-sm, 1.5rem);}.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col,.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col:before{border-top-left-radius:0px;border-top-right-radius:0px;border-bottom-right-radius:0px;border-bottom-left-radius:0px;}.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm, 1rem);}.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col{flex-direction:column;}.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col > .aligncenter{width:100%;}.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col:before{opacity:0.3;}.kadence-column6257_e0aa5d-43{position:relative;}@media all and (max-width: 1024px){.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}@media all and (max-width: 767px){.kadence-column6257_e0aa5d-43 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}<\/style>\n<div class=\"wp-block-kadence-column kadence-column6257_e0aa5d-43\"><div class=\"kt-inside-inner-col\">\n<p class=\"wp-block-paragraph\">In the model training process, the responsiveness (sensitivity) of $Y$ to variations in $X$ is a core factor that determines the balance between generalization performance and explainability ($R^2$).<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">$$R^2 = 1 &#8211; \\frac{SS{res}}{SS_{tot}} = 1- \\frac{\\sum_{i=1}^{n}{(y_{i} &#8211; \\hat{y}_{i})^2}}{\\sum_{i=1}^{n}{(y_{i} &#8211; \\bar{y})^2}}$$<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Where:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>$y_i$: Actual observed value<\/li>\n\n\n\n<li>$\\hat{y}_i$: Model predicted value<\/li>\n\n\n\n<li>$\\bar{y}$: Mean of observed values<\/li>\n\n\n\n<li>$SS_{res}$: Residual Sum of Squares<\/li>\n\n\n\n<li>$SS_{tot}$: Total Sum of Squares<\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<h3 class=\"wp-block-heading\">1. Root Causes of Sensitivity Variance<\/h3>\n\n\n<style>.kadence-column6257_486a5f-92 > .kt-inside-inner-col{padding-right:var(--global-kb-spacing-xxl, 5rem);padding-left:var(--global-kb-spacing-sm, 1.5rem);}.kadence-column6257_486a5f-92 > .kt-inside-inner-col,.kadence-column6257_486a5f-92 > .kt-inside-inner-col:before{border-top-left-radius:0px;border-top-right-radius:0px;border-bottom-right-radius:0px;border-bottom-left-radius:0px;}.kadence-column6257_486a5f-92 > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm, 1rem);}.kadence-column6257_486a5f-92 > .kt-inside-inner-col{flex-direction:column;}.kadence-column6257_486a5f-92 > .kt-inside-inner-col > .aligncenter{width:100%;}.kadence-column6257_486a5f-92 > .kt-inside-inner-col:before{opacity:0.3;}.kadence-column6257_486a5f-92{position:relative;}@media all and (max-width: 1024px){.kadence-column6257_486a5f-92 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}@media all and (max-width: 767px){.kadence-column6257_486a5f-92 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}<\/style>\n<div class=\"wp-block-kadence-column kadence-column6257_486a5f-92\"><div class=\"kt-inside-inner-col\">\n<p class=\"wp-block-paragraph\">A model&#8217;s tendency to react sensitively or insensitively to changes in input values typically arises from the following factors:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Signal-to-Noise Ratio (SNR):<\/strong> If the data contains high levels of noise, the model may fail to identify the true signal and instead converge toward an average value, resulting in <strong>insensitivity<\/strong>.<\/li>\n\n\n\n<li><strong>Model Capacity:<\/strong> Simple models like Linear Regression tend to be <strong>insensitive<\/strong> as they capture relationships only as straight lines. Conversely, complex models like Deep Learning or Tree-based ensembles are highly <strong>sensitive<\/strong>, attempting to learn even minute fluctuations in the data.<\/li>\n\n\n\n<li><strong>Regularization Strength:<\/strong> Applying strong L1 (Lasso) or L2 (Ridge) regularization reduces weight ($W$) values, making the model <strong>insensitive<\/strong>. Without regularization, the model becomes highly <strong>sensitive<\/strong>, with $Y$ fluctuating wildly in response to small changes in $X$.<\/li>\n\n\n\n<li><strong>Scaling Issues:<\/strong> As previously discussed, if the range of $Y$ is too narrow (e.g., $0$ to $0.2$), the gradients become small, potentially causing the model to ignore variations in $X$, leading to an <strong>insensitive<\/strong> state.<\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<h3 class=\"wp-block-heading\">2. Data Slope Vs Model Sensitivity in True vs Prediction Chart (1:1 Chart)<\/h3>\n\n\n<style>.kadence-column6257_fdde2e-33 > .kt-inside-inner-col{padding-right:var(--global-kb-spacing-xxl, 5rem);padding-left:var(--global-kb-spacing-sm, 1.5rem);}.kadence-column6257_fdde2e-33 > .kt-inside-inner-col,.kadence-column6257_fdde2e-33 > .kt-inside-inner-col:before{border-top-left-radius:0px;border-top-right-radius:0px;border-bottom-right-radius:0px;border-bottom-left-radius:0px;}.kadence-column6257_fdde2e-33 > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm, 1rem);}.kadence-column6257_fdde2e-33 > .kt-inside-inner-col{flex-direction:column;}.kadence-column6257_fdde2e-33 > .kt-inside-inner-col > .aligncenter{width:100%;}.kadence-column6257_fdde2e-33 > .kt-inside-inner-col:before{opacity:0.3;}.kadence-column6257_fdde2e-33{position:relative;}@media all and (max-width: 1024px){.kadence-column6257_fdde2e-33 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}@media all and (max-width: 767px){.kadence-column6257_fdde2e-33 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}<\/style>\n<div class=\"wp-block-kadence-column kadence-column6257_fdde2e-33\"><div class=\"kt-inside-inner-col\">\n<p class=\"wp-block-paragraph\">In an ideal predictive model, all data points should lie perfectly along the <strong>$y = x$ line<\/strong>, where the regression slope is exactly <strong>1<\/strong>. Deviations from this slope provide critical insights into the model&#8217;s behavior:<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">1) Slope > 1 (Sensitive \/ Over-reacting)<\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Phenomenon:<\/strong> The predicted values ($y$) exhibit greater variance than the actual values ($x$). Even a minor change in the input results in a disproportionately large swing in the output.<\/li>\n\n\n\n<li><strong>Interpretation:<\/strong> The model is <strong>over-responding<\/strong> to the underlying data fluctuations.<\/li>\n\n\n\n<li><strong>Associated State:<\/strong> This is typically a symptom of <strong>Overfitting<\/strong>. The model has internalized high-frequency noise from the training set, causing it to produce extreme outputs even for subtle shifts in input features.<\/li>\n<\/ul>\n\n\n\n<h4 class=\"wp-block-heading\">2) Slope &lt; 1 (Insensitive \/ Under-reacting)<\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Phenomenon:<\/strong> Despite significant changes in the actual values ($x$), the predictions ($y$) remain relatively stagnant, often clustering around the global mean.<\/li>\n\n\n\n<li><strong>Interpretation:<\/strong> The model is behaving <strong>conservatively<\/strong> or is <strong>insensitive<\/strong> to the data&#8217;s variance.<\/li>\n\n\n\n<li><strong>Associated State:<\/strong> This often indicates <strong>Underfitting<\/strong>. When a model fails to capture complex patterns, it tends to hedge its bets by predicting values closer to the average\u2014a phenomenon known as <strong>regression to the mean<\/strong>. This results in a flattened slope significantly below 1.<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\"><\/ul>\n<\/div><\/div>\n\n\n\n<h3 class=\"wp-block-heading\">3. Impact on R\u00b2 Improvement<\/h3>\n\n\n<style>.kadence-column6257_9df667-b0 > .kt-inside-inner-col{padding-right:var(--global-kb-spacing-xxl, 5rem);padding-left:var(--global-kb-spacing-sm, 1.5rem);}.kadence-column6257_9df667-b0 > .kt-inside-inner-col,.kadence-column6257_9df667-b0 > .kt-inside-inner-col:before{border-top-left-radius:0px;border-top-right-radius:0px;border-bottom-right-radius:0px;border-bottom-left-radius:0px;}.kadence-column6257_9df667-b0 > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm, 1rem);}.kadence-column6257_9df667-b0 > .kt-inside-inner-col{flex-direction:column;}.kadence-column6257_9df667-b0 > .kt-inside-inner-col > .aligncenter{width:100%;}.kadence-column6257_9df667-b0 > .kt-inside-inner-col:before{opacity:0.3;}.kadence-column6257_9df667-b0{position:relative;}@media all and (max-width: 1024px){.kadence-column6257_9df667-b0 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}@media all and (max-width: 767px){.kadence-column6257_9df667-b0 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}<\/style>\n<div class=\"wp-block-kadence-column kadence-column6257_9df667-b0\"><div class=\"kt-inside-inner-col\">\n<p class=\"wp-block-paragraph\">In conclusion, an <strong>&#8220;Appropriately Sensitive Model&#8221;<\/strong> is most advantageous for improving $R^2$.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Why Sensitivity Favors R\u00b2:<\/strong> The Coefficient of Determination ($R^2$) measures how well the model explains the variance in the data. As the model more precisely follows the patterns of $Y$ changing with $X$ (higher sensitivity), the residuals decrease, and $R^2$ approaches 1.<\/li>\n\n\n\n<li><strong>Caveat (Overfitting):<\/strong> If a model is excessively sensitive and learns underlying noise, it may show a high $R^2$ on training data but suffer from <strong>overfitting<\/strong>, causing $R^2$ to plummet on new (test) data.<\/li>\n\n\n\n<li><strong>Limitations of Insensitivity:<\/strong> If a model is too insensitive, it misses the actual trends in the data (<strong>underfitting<\/strong>), resulting in a consistently low $R^2$.<\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<h3 class=\"wp-block-heading\">4. Strategies for Enhancing R\u00b2<\/h3>\n\n\n<style>.kadence-column6257_59f67a-a5 > .kt-inside-inner-col{padding-right:var(--global-kb-spacing-xl, 4rem);padding-left:var(--global-kb-spacing-sm, 1.5rem);}.kadence-column6257_59f67a-a5 > .kt-inside-inner-col,.kadence-column6257_59f67a-a5 > .kt-inside-inner-col:before{border-top-left-radius:0px;border-top-right-radius:0px;border-bottom-right-radius:0px;border-bottom-left-radius:0px;}.kadence-column6257_59f67a-a5 > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm, 1rem);}.kadence-column6257_59f67a-a5 > .kt-inside-inner-col{flex-direction:column;}.kadence-column6257_59f67a-a5 > .kt-inside-inner-col > .aligncenter{width:100%;}.kadence-column6257_59f67a-a5 > .kt-inside-inner-col:before{opacity:0.3;}.kadence-column6257_59f67a-a5{position:relative;}@media all and (max-width: 1024px){.kadence-column6257_59f67a-a5 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}@media all and (max-width: 767px){.kadence-column6257_59f67a-a5 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}<\/style>\n<div class=\"wp-block-kadence-column kadence-column6257_59f67a-a5\"><div class=\"kt-inside-inner-col\">\n<p class=\"wp-block-paragraph\">To improve $R^2$ by adjusting the sensitivity of the data currently under analysis, consider the following approaches:<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">A. Increasing Sensitivity (Resolving Underfitting)<\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Feature Engineering:<\/strong> If the relationship between $X$ and $Y$ is non-linear, add terms like $X^2$, $log(X)$, or interaction terms between features.<\/li>\n\n\n\n<li><strong>Complex Model Selection:<\/strong> Utilize Random Forest, XGBoost, or Artificial Neural Networks (ANN) instead of simple Linear Regression to capture complex patterns.<\/li>\n\n\n\n<li><strong>Reducing Regularization:<\/strong> Decrease the penalty terms (Alpha or Lambda values) to allow the model more freedom to learn from the data.<\/li>\n<\/ul>\n\n\n\n<h4 class=\"wp-block-heading\">B. Suppressing Noise for Stable R\u00b2 (Resolving Overfitting)<\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Target Scaling:<\/strong> Expand the $Y$ range to $[0, 1]$ to improve learning efficiency and gradient flow.<\/li>\n\n\n\n<li><strong>Data Cleaning:<\/strong> Remove outliers to prevent the model from becoming overly sensitive to erroneous fluctuations.<\/li>\n\n\n\n<li><strong>Cross-Validation:<\/strong> Ensure the $R^2$ is reliable by verifying that the model is not reacting sensitively only to a specific subset of the data.<\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<h3 class=\"wp-block-heading\">Summary<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">To practically enhance $R^2$, the model must first be designed to sensitively capture meaningful variations in $X$. The subsequent risk of overfitting to noise should be managed through appropriate regularization and systematic data scaling.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<div style='text-align:center' class='yasr-auto-insert-overall'><\/div><div style='text-align:center' class='yasr-auto-insert-visitor'><\/div>","protected":false},"excerpt":{"rendered":"<p>Aerial view of the Great Blue Hole in Belize In the model training process, the responsiveness (sensitivity) of $Y$ to variations in $X$ is a core factor that determines the balance between generalization performance and explainability ($R^2$). $$R^2 = 1 &#8211; \\frac{SS{res}}{SS_{tot}} = 1- \\frac{\\sum_{i=1}^{n}{(y_{i} &#8211; \\hat{y}_{i})^2}}{\\sum_{i=1}^{n}{(y_{i} &#8211; \\bar{y})^2}}$$ Where: 1. Root Causes of Sensitivity&#8230;<\/p>\n","protected":false},"author":4,"featured_media":6258,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"_kadence_starter_templates_imported_post":false,"_kad_post_transparent":"","_kad_post_title":"","_kad_post_layout":"","_kad_post_sidebar_id":"","_kad_post_content_style":"","_kad_post_vertical_padding":"","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"_kad_post_classname":"","yasr_overall_rating":0,"yasr_post_is_review":"","yasr_auto_insert_disabled":"","yasr_review_type":"","fifu_image_url":"","fifu_image_alt":"","iawp_total_views":0,"footnotes":""},"categories":[56,371],"tags":[],"class_list":["post-6257","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-science-slug","category-training-slug"],"yasr_visitor_votes":{"stars_attributes":{"read_only":false,"span_bottom":false},"number_of_votes":0,"sum_votes":0},"jetpack_featured_media_url":"https:\/\/ykim.synology.me\/wordpress\/wp-content\/uploads\/2026\/04\/Aerial-view-of-the-Great-Blue-Hole-in-Belize.jpg","_links":{"self":[{"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/posts\/6257","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/comments?post=6257"}],"version-history":[{"count":20,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/posts\/6257\/revisions"}],"predecessor-version":[{"id":6291,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/posts\/6257\/revisions\/6291"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/media\/6258"}],"wp:attachment":[{"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/media?parent=6257"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/categories?post=6257"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ykim.synology.me\/wordpress\/wp-json\/wp\/v2\/tags?post=6257"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}