Use PDF-derived method diagram SVGs

Author: luis-marques

content/_index.md

@@ -51,11 +51,11 @@ $$
 ```
 The resulting prediction region `$\hat{\mathcal C} = \bigcup_{S_m \in \mathcal S} \hat{\mathcal C}_{S_m}(s_t,u_t,S_m) \subseteq C$` is a union of regions built over the robot's configuration strata.
 
-{% figure(alt=["Offline calibration diagram"] src=["./paper_figures/offline_calibration_dark.svg?v=20260608-svg-diagrams"] dark_src=["./paper_figures/offline_calibration_dark.svg?v=20260608-svg-diagrams"]) %}
+{% figure(alt=["Offline calibration diagram"] src=["./paper_figures/offline_calibration_dark.svg?v=20260608-svg-diagrams-v3"] dark_src=["./paper_figures/offline_calibration_dark.svg?v=20260608-svg-diagrams-v3"]) %}
 **Offline calibration of CaPTURe.** For each transition in `$D_{\mathrm{cal}}$`, `$\hat f$` receives the current full-system state `$s_t := (\mathfrak{c}_t,\dot{\mathfrak{c}}_t)$` and action `$u_t$` to sample `$L$` predictive particles (black) of the future target configuration `$c_{t+1}$` which we use to compute the nonconformity score `$R_i$` (blue). A subset of transition-scores `$D_{\mathrm{cal}}^{part}$` is used to fit a regression decision-tree that separates the input space -- state, velocity and future strata `$S(c_{t+1})$` -- into groups with approximately group-constant prediction score. The holdout subset `$D_{\mathrm{cal}}^{cp}$` is then passed through the `DTree` with each example landing in a leaf node and hence corresponding group `$k$`. SplitCP is performed independently for each group, resulting in a per-partition conformal threshold `$\hat q_k$`.
 {% end %}
 
-{% figure(alt=["Prediction region construction diagram"] src=["./paper_figures/diagram_region_construction_dark.svg?v=20260608-svg-diagrams"] dark_src=["./paper_figures/diagram_region_construction_dark.svg?v=20260608-svg-diagrams"]) %}
+{% figure(alt=["Prediction region construction diagram"] src=["./paper_figures/diagram_region_construction_dark.svg?v=20260608-svg-diagrams-v3"] dark_src=["./paper_figures/diagram_region_construction_dark.svg?v=20260608-svg-diagrams-v3"]) %}
 **Construction of stratified prediction region `$\hat{\mathcal C}$`.** Given an action `$u_t$` and current full-system state `$s_t := (\mathfrak{c}_t,\dot{\mathfrak{c}}_t)$` the predictive model `$\hat f$` returns predictive particles (black) representing possible future target configurations. For each candidate future stratum `$(S_m)$` in C-space, we query the pre-fit `DTree` with `$(s_t,u_t,S_m)$` to get a contact-aware uncertainty threshold `$\hat q_k$`. For each stratum, we evaluate which configurations in `$S_m$` have score `$\le \hat q_k$`, where the score is the `$k$`-th distance between a candidate configuration in `$S_m$` and the particles. Finally, we compose the full prediction region `$\hat{\mathcal C}(s_t,u_t,\mathcal S)$` as the union of the per-stratum regions over candidate future strata `$S_m \in \mathcal S$`.
 {% end %}