diff --git a/paper/paper.pdf b/paper/paper.pdf
index cf068eb20ffbfd2478615fc7baf464313de22f43..54bbf81cb790d48a7b64cd276f1356f2804d8c57 100644
Binary files a/paper/paper.pdf and b/paper/paper.pdf differ
diff --git a/paper/paper.tex b/paper/paper.tex
index 32ef0222971c1399a02cb5a67d9236c1f8ecfe62..74bee8501cff1d4a84b782f5fbee2a115daac91f 100644
--- a/paper/paper.tex
+++ b/paper/paper.tex
@@ -99,88 +99,79 @@
 
 
 \begin{abstract}
-  Counterfactual Explanations offer an intuitive and straightforward way to explain Black Box Models but they are not unique. To address the need for plausible explanations, existing work has primarily relied on surrogate models to learn how the input data is distributed. This effectively reallocates the task of learning realistic representations of the data from the model itself to the surrogate. Consequently, the generated explanations may look plausible to humans but not necessarily conform with the behaviour of the Black Box Model. We formalise this notion of model conformity through the introduction of tailored evaluation measures and propose a novel algorithmic framework for generating \textbf{E}nergy-\textbf{C}onstrained \textbf{C}onformal \textbf{Co}unterfactuals that are only as plausible as the model permits. To do so, \textbf{ECCCo} leverages recent advances in energy-based modelling and predictive uncertainty quantification through conformal inference. Through illustrative examples and extensive empirical studies, we demonstrate that ECCCos reconcile the need for plausibility and model conformity. 
+  Counterfactual Explanations offer an intuitive and straightforward way to explain black-box models but they are not unique. To address the need for plausible explanations, existing work has primarily relied on surrogate models to learn how the input data is distributed. This effectively reallocates the task of learning realistic representations of the data from the model itself to the surrogate. Consequently, the generated explanations may look plausible to humans but not necessarily conform with the behaviour of the black-box model. We formalise this notion of model conformity through the introduction of tailored evaluation measures and propose a novel algorithmic framework for generating \textbf{E}nergy-\textbf{C}onstrained \textbf{C}onformal \textbf{Co}unterfactuals that are only as plausible as the model permits. To do so, \textbf{ECCCo} leverages recent advances in energy-based modelling and predictive uncertainty quantification through conformal inference. Through illustrative examples and extensive empirical studies, we demonstrate that ECCCos reconcile the need for plausibility and model conformity. 
 \end{abstract}
 
 \section{Introduction}\label{intro}
 
-Counterfactual Explanations provide a powerful, flexible and intuitive way to not only explain Black Box Models but also enable affected individuals to challenge them through the means of Algorithmic Recourse. Instead of opening the black box, Counterfactual Explanations work under the premise of strategically perturbing model inputs to understand model behaviour \citep{wachter2017counterfactual}. Intuitively speaking, we generate explanations in this context by asking simple what-if questions of the following nature: `Our credit risk model currently predicts that this individual's credit profile is too risky to offer them a loan. What if they reduced their monthly expenditures by 10\%? Will our model then predict that the individual is credit-worthy'? 
+Counterfactual Explanations provide a powerful, flexible and intuitive way to not only explain black-box models but also enable affected individuals to challenge them through the means of Algorithmic Recourse. Instead of opening the black box, Counterfactual Explanations work under the premise of strategically perturbing model inputs to understand model behaviour~\citep{wachter2017counterfactual}. Intuitively speaking, we generate explanations in this context by asking simple what-if questions of the following nature: `Our credit risk model currently predicts that this individual's credit profile is too risky to offer them a loan. What if they reduced their monthly expenditures by 10\%? Will our model then predict that the individual is credit-worthy'? 
 
-This is typically implemented by defining a target outcome $\mathbf{y}^* \in \mathcal{Y}$ for some individual $\mathbf{x} \in \mathcal{X}=\mathbb{R}^D$ described by $D$ attributes, for which the model $M_{\theta}:\mathcal{X}\mapsto\mathcal{Y}$ initially predicts a different outcome: $M_{\theta}(\mathbf{x})\ne \mathbf{y}^*$. Counterfactuals are then searched by minimizing a loss function that compares the predicted model output to the target outcome: $\text{yloss}(M_{\theta}(\mathbf{x}),\mathbf{y}^*)$. Since Counterfactual Explanations (CE) work directly with the Black Box Model, valid counterfactuals always have full local fidelity by construction \citep{mothilal2020explaining}. Fidelity is defined as the degree to which explanations approximate the predictions of the Black Box Model. This is arguably one of the most important evaluation metrics for model explanations, since any explanation that explains a prediction not actually made by the model is useless \citep{molnar2020interpretable}. 
+This is typically implemented by defining a target outcome $\mathbf{y}^* \in \mathcal{Y}$ for some individual $\mathbf{x} \in \mathcal{X}=\mathbb{R}^D$ described by $D$ attributes, for which the model $M_{\theta}:\mathcal{X}\mapsto\mathcal{Y}$ initially predicts a different outcome: $M_{\theta}(\mathbf{x})\ne \mathbf{y}^*$. Counterfactuals are then searched by minimizing a loss function that compares the predicted model output to the target outcome: $\text{yloss}(M_{\theta}(\mathbf{x}),\mathbf{y}^*)$. Since Counterfactual Explanations (CE) work directly with the black-box model, valid counterfactuals always have full local fidelity by construction~\citep{mothilal2020explaining}. Fidelity is defined as the degree to which explanations approximate the predictions of the black-box model. This is arguably one of the most important evaluation metrics for model explanations, since any explanation that explains a prediction not actually made by the model is useless~\citep{molnar2020interpretable}. 
 
-In situations where full fidelity is a requirement, CE therefore offers a more appropriate solution to Explainable Artificial Intelligence (XAI) than other popular approaches like LIME \citep{ribeiro2016why} and SHAP \citep{lundberg2017unified}, which involve local surrogate models. But even full fidelity is not a sufficient condition for ensuring that an explanation adequately describes the behaviour of a model. That is because two very distinct explanations can both lead to the same model prediction, especially when dealing with heavily parameterized models:
+In situations where full fidelity is a requirement, CE therefore offers a more appropriate solution to Explainable Artificial Intelligence (XAI) than other popular approaches like LIME~\citep{ribeiro2016why} and SHAP~\citep{lundberg2017unified}, which involve local surrogate models. But even full fidelity is not a sufficient condition for ensuring that an explanation faithfully describes the behaviour of a model. That is because multiple very distinct explanations can all lead to the same model prediction, especially when dealing with heavily parameterized models like deep neural networks which are typically underspecified by the available data~\citep{wilson2020case}.
 
-\begin{quotation}
-  […] deep neural networks are typically very underspecified by the available data, and […] parameters [therefore] correspond to a diverse variety of compelling explanations for the data.
-  --- \citet{wilson2020case}
-\end{quotation}
-
-When people talk about Black Box Models, this is usually the type of model they have in mind. 
-
-In the context of CE, the idea that no two explanations are the same arises almost naturally. Even the baseline approach proposed by \citet{wachter2017counterfactual} can yield a diverse set of explanations if counterfactuals are initialised randomly. This multiplicity of explanations has not only been acknowledged in the literature but positively embraced: since individuals seeking Algorithmic Recourse (AR) have unique preferences,~\citet{mothilal2020explaining}, for example, have prescribed \textit{diversity} as an explicit goal for counterfactuals. More generally, the literature on CE and AR has brought forward a myriad of desiderata for explanations, which we will discuss in more detail in the following section.
+In the context of CE, the idea that no two explanations are the same arises almost naturally. A key focus in the literature has therefore been to identify those explanations and algorithmic recourses that are deemed most appropriate based on a myriad of desiderata such as sparsity, actionability and plausibility. In this work, we draw closer attention to the insufficiency of model fidelity as an evaluation metric for the faithfulness of counterfactual explanations. Our key contributions are as follows: firstly, we introduce a new notion of faithfulness that is suitable for counterfactuals and propose a novel evaluation measure that draws inspiration from recent advances in Energy-Based Modelling (EBM); secondly, we a novel algorithmic approach for generating Energy-Constrained Conformal Counterfactuals (ECCCo) that explicitly address the need for faithfulness; finally, we provide illustrative examples and extensive empirical evidence demonstrating that ECCCos faithfully explain model behaviour without sacrificing existing desidarata like plausibility and sparsity. 
 
 \section{Background and Related Work}\label{background}
 
-In this section, we provide some background on Counterfactual Explanations and our motivation for this work. To start off, we briefly introduce the methodology uncerlying most state-of-the-art (SOTA) counterfactual generators.
+In this section, we provide some background on Counterfactual Explanations and our motivation for this work. To start, we briefly introduce the methodology underlying most state-of-the-art (SOTA) counterfactual generators.
 
 \subsection{Gradient-Based Counterfactual Search}\label{gradient}
 
-While Counterfactual Explanations can be generated for arbitrary regression models \citep{spooner2021counterfactual}, existing work has primarily focused on classification problems. Let $\mathcal{Y}=(0,1)^K$ denote the one-hot-encoded output domain with $K$ classes. Then most SOTA counterfactual generators rely on gradient descent to optimize different flavours of the following counterfactual search objective:
+While Counterfactual Explanations can be generated for arbitrary regression models~\citep{spooner2021counterfactual}, existing work has primarily focused on classification problems. Let $\mathcal{Y}=(0,1)^K$ denote the one-hot-encoded output domain with $K$ classes. Then most SOTA counterfactual generators rely on gradient descent to optimize different flavours of the following counterfactual search objective:
 
 \begin{equation} \label{eq:general}
 \begin{aligned}
-\mathbf{Z}^\prime &= \arg \min_{\mathbf{Z}^\prime \in \mathcal{Z}^M} \left\{  {\text{yloss}(M_{\theta}(f(\mathbf{Z}^\prime)),\mathbf{y}^*)}+ \lambda {\text{cost}(f(\mathbf{Z}^\prime)) }  \right\} 
+\mathbf{Z}^\prime &= \arg \min_{\mathbf{Z}^\prime \in \mathcal{Z}^L} \left\{  {\text{yloss}(M_{\theta}(f(\mathbf{Z}^\prime)),\mathbf{y}^*)}+ \lambda {\text{cost}(f(\mathbf{Z}^\prime)) }  \right\} 
 \end{aligned} 
 \end{equation}
 
-Here $\text{yloss}$ denotes the primary loss function already introduced above and $\text{cost}$ is either a single penalty or a collection of penalties that are used to impose constraints through regularization. Following the convention in \citet{altmeyer2023endogenous} we use $\mathbf{Z}^\prime=\{ \mathbf{z}_m\}_M$ to denote the $M$-dimensional array of counterfactual states. This is to explicitly account for the fact that we can generate multiple counterfactuals $M$, as with DiCE \citep{mothilal2020explaining}, and may choose to traverse a latent encoding $\mathcal{Z}$ of the feature space $\mathcal{X}$ where we denote $f^{-1}: \mathcal{X} \mapsto \mathcal{Z}$. Encodings may involve simple feature transformations or more advanced techniques involving generative models, as we will discuss further below. 
+Here $\text{yloss}$ denotes the primary loss function already introduced above and $\text{cost}$ is either a single penalty or a collection of penalties that are used to impose constraints through regularization. Equation~\ref{eq:general} restates the baseline approach to gradient-based counterfactual search proposed by~\citet{wachter2017counterfactual} in general form where $\mathbf{Z}^\prime=\{ \mathbf{z}_l\}_L$ denotes an $L$-dimensional array of counterfactual states~\citep{altmeyer2023endogenous}. This is to explicitly account for the multiplicity of explanations and the fact that we may choose to generate multiple counterfactuals and traverse a latent encoding $\mathcal{Z}$ of the feature space $\mathcal{X}$ where we denote $f^{-1}: \mathcal{X} \mapsto \mathcal{Z}$. Encodings may involve simple feature transformations or more advanced techniques involving generative models, as we will discuss further below. The baseline approach, which we will simply refer to as \textbf{Wachter}~\citep{wachter2017counterfactual}, searches a single counterfactual directly in the feature space and penalises its distance between the original factual. 
 
-Solutions to Equation~\ref{eq:general} are considered valid as soon as the predicted label matches the target label. A stripped-down counterfactual explanation is therefore little different from an adversarial example. In Figure~\ref{fig:adv}, for example, we have the baseline approach proposed in \citet{wachter2017counterfactual} to MNIST data (centre panel). This approach solves Equation~\ref{eq:general} through gradient-descent in the feature space with a penalty for the distance between the factual $\mathbf{x}$ and the counterfactual $\mathbf{x}^{\prime}$. The underlying classifier $M_{\theta}$ is a simple Multi-Layer Perceptron (MLP) with good test accuracy. For the generated counterfactual $\mathbf{x}^{\prime}$ the model predicts the target label with high confidence (centre panel in Figure~\ref{fig:adv}). The explanation is valid by definition, even though it looks a lot like an Adversarial Example \citep{goodfellow2014explaining}. \citet{schut2021generating} make the connection between Adversarial Examples and Counterfactual Explanations explicit and propose using a Jacobian-Based Saliency Map Attack (JSMA) to solve Equation~\ref{eq:general}. They demonstrate that this approach yields realistic and sparse counterfactuals for Bayesian, adversarially robust classifiers. Applying their approach to our simple MNIST classifier does not yield a realistic counterfactual but this one, too, is valid (right panel in Figure~\ref{fig:adv}). 
+Solutions to Equation~\ref{eq:general} are considered valid as soon as the predicted label matches the target label. A stripped-down counterfactual explanation is therefore little different from an adversarial example. In Figure~\ref{fig:adv}, for example, we have applied Wachter to MNIST data (centre panel) where the underlying classifier $M_{\theta}$ is a simple Multi-Layer Perceptron (MLP) with above 90 percent test accuracy. For the generated counterfactual $\mathbf{x}^{\prime}$ the model predicts the target label with high confidence (centre panel in Figure~\ref{fig:adv}). The explanation is valid by definition, even though it looks a lot like an Adversarial Example~\citep{goodfellow2014explaining}. \citet{schut2021generating} make the connection between Adversarial Examples and Counterfactual Explanations explicit and propose using a Jacobian-Based Saliency Map Attack (JSMA) to solve Equation~\ref{eq:general}. They demonstrate that this approach yields realistic and sparse counterfactuals for Bayesian, adversarially robust classifiers. Applying their approach to our simple MNIST classifier does not yield a realistic counterfactual but this one, too, is valid (right panel in Figure~\ref{fig:adv}). 
 
 \subsection{From Adversial Examples to Plausible Explanations}
 
-The crucial difference between Adversarial Examples (AE) and Counterfactual Explanations is one of intent. While an AE is intended to go unnoticed, a CE should have certain desirable properties. The literature has made this explicit by introducing various so-called \textit{desiderata}. To properly serve both AI practitioners and individuals affected by AI decision-making systems, counterfactuals should be sparse, proximate~\citep{wachter2017counterfactual}, actionable~\citep{ustun2019actionable}, diverse~\citep{mothilal2020explaining}, plausible~\citep{joshi2019realistic,poyiadzi2020face,schut2021generating}, robust~\citep{upadhyay2021robust,pawelczyk2022probabilistically,altmeyer2023endogenous} and causal~\citep{karimi2021algorithmic} among other things. 
+The crucial difference between Adversarial Examples (AE) and Counterfactual Explanations is one of intent. While an AE is intended to go unnoticed, a CE should have certain desirable properties. The literature has made this explicit by introducing various so-called \textit{desiderata} that counterfactuals should meet in order to properly serve both AI practitioners and individuals affected by AI decision-making systems. The list of desiderate includes but is not limited to the following: sparsity, proximity~\citep{wachter2017counterfactual}, actionability~\citep{ustun2019actionable}, diversity~\citep{mothilal2020explaining}, plausibility~\citep{joshi2019realistic,poyiadzi2020face,schut2021generating}, robustness~\citep{upadhyay2021robust,pawelczyk2022probabilistically,altmeyer2023endogenous} and causality~\citep{karimi2021algorithmic}.
 
-Researchers have come up with various ways to meet these desiderata, which have been extensively surveyed and evaluated in various studies~\citep{verma2020counterfactual,karimi2020survey,pawelczyk2021carla,artelt2021evaluating,guidotti2022counterfactual}. Perhaps unsurprisingly, the different desiderata are often positively correlated. For example, \citet{artelt2021evaluating} find that plausibility typically also leads to improved robustness. Similarly, plausibility has also been connected to causality in the sense that plausible counterfactuals respect causal relationships \citep{mahajan2020preserving}. 
+Researchers have come up with various ways to meet these desiderata, which have been extensively surveyed and evaluated in various studies~\citep{verma2020counterfactual,karimi2020survey,pawelczyk2021carla,artelt2021evaluating,guidotti2022counterfactual}. Perhaps unsurprisingly, the different desiderata are often positively correlated. For example, \citet{artelt2021evaluating} find that plausibility typically also leads to improved robustness. Similarly, plausibility has also been connected to causality in the sense that plausible counterfactuals respect causal relationships~\citep{mahajan2020preserving}. 
 
 \subsubsection{Plausibility through Surrogates}
 
-Arguably, the plausibility of counterfactuals has been among the primary concerns and some have focused explicitly on this goal. \citet{joshi2019realistic}, for example, were among the first to suggest that instead of searching counterfactuals in the feature space $\mathcal{X}$, we can instead traverse a latent embedding $\mathcal{Z}$ that implicitly codifies the data generating process (DGP) of $\mathbf{x}\sim\mathcal{X}$. To learn the latent embedding, they introduce a surrogate model. In particular, they propose to use the latent embedding of a Variational Autoencoder (VAE) trained to generate samples $\mathbf{x}^* \leftarrow \mathcal{G}(\mathbf{z})$ where $\mathcal{G}$ denotes the decoder part of the VAE. Provided the surrogate model is well-trained, their proposed approach ---REVISE--- can yield compelling counterfactual explanations like the one in the centre panel of Figure~\ref{fig:vae}. 
+Arguably, the plausibility of counterfactuals has been among the primary concerns and some have focused explicitly on this goal. \citet{joshi2019realistic}, for example, were among the first to suggest that instead of searching counterfactuals in the feature space $\mathcal{X}$, we can instead traverse a latent embedding $\mathcal{Z}$ (Equation~\ref{eq:general}) that implicitly codifies the data generating process (DGP) of $\mathbf{x}\sim\mathcal{X}$. To learn the latent embedding, they introduce a surrogate model. In particular, they propose to use the latent embedding of a Variational Autoencoder (VAE) trained to generate samples $\mathbf{x}^* \leftarrow \mathcal{G}(\mathbf{z})$ where $\mathcal{G}$ denotes the decoder part of the VAE. Provided the surrogate model is well-trained, their proposed approach ---REVISE--- can yield compelling counterfactual explanations like the one in the centre panel of Figure~\ref{fig:vae}. 
 
-Others have proposed similar approaches. \citet{dombrowski2021diffeomorphic} traverse the base space of a normalizing flow to solve Equation~\ref{eq:general}, essentially relying on a different surrogate model for the generative task. \citet{poyiadzi2020face} use density estimators ($\hat{p}: \mathcal{X} \mapsto [0,1]$) to constrain the counterfactual paths. \citet{karimi2021algorithmic} argue that counterfactuals should comply with the causal model that generates the data. All of these different approaches share a common goal: ensuring that the generated counterfactuals comply with the true and unobserved DGP. To summarize this broad objective, we propose the following definition:
+Others have proposed similar approaches. \citet{dombrowski2021diffeomorphic} traverse the base space of a normalizing flow to solve Equation~\ref{eq:general}, essentially relying on a different surrogate model for the generative task. \citet{poyiadzi2020face} use density estimators ($\hat{p}: \mathcal{X} \mapsto [0,1]$) to constrain the counterfactuals to dense regions in the feature space. \citet{karimi2021algorithmic} argue that counterfactuals should comply with the causal model that generates the data. All of these different approaches share a common goal: ensuring that the generated counterfactuals comply with the true and unobserved DGP. To summarize this broad objective, we propose the following definition:
 
 \begin{definition}[Plausible Counterfactuals]
   \label{def:plausible}
   Let $\mathcal{X}|\mathbf{y}^*$ denote the true conditional distribution of samples in the target class $\mathbf{y}^*$. Then for $\mathbf{x}^{\prime}$ to be considered a plausible counterfactual, we need: $\mathbf{x}^{\prime} \sim \mathcal{X}|\mathbf{y}^*$.
 \end{definition}
 
-Note that Definition~\ref{def:plausible} is consistent with the notion of plausible counterfactual paths, since we can simply apply it to each counterfactual state along the path.
-
-Surrogate models offer an obvious solution to achieve this objective. Unfortunately, surrogates also introduce a dependency: the generated explanations no longer depend exclusively on the Black Box Model itself, but also on the surrogate model. This is not necessarily problematic if the primary objective is not to explain the behaviour of the model but to offer recourse to individuals affected by it. It may become problematic even in this context if the dependency turns into a vulnerability. To illustrate this point, we have used REVISE \citep{joshi2019realistic} with an underfitted VAE to generate the counterfactual in the right panel of Figure~\ref{fig:vae}: in this case, the decoder step of the VAE fails to yield plausible values ($\{\mathbf{x}^{\prime} \leftarrow \mathcal{G}(\mathbf{z})\} \not\sim \mathcal{X}|\mathbf{y}^*$) and hence the counterfactual search in the learned latent space is doomed.
+Surrogate models offer an obvious solution to achieve this objective. Unfortunately, surrogates also introduce a dependency: the generated explanations no longer depend exclusively on the black-box model itself, but also on the surrogate model. This is not necessarily problematic if the primary objective is not to explain the behaviour of the model but to offer recourse to individuals affected by it. It may become problematic even in this context if the dependency turns into a vulnerability. To illustrate this point, we have used REVISE~\citep{joshi2019realistic} with an underfitted VAE to generate the counterfactual in the right panel of Figure~\ref{fig:vae}: in this case, the decoder step of the VAE fails to yield plausible values ($\{\mathbf{x}^{\prime} \leftarrow \mathcal{G}(\mathbf{z})\} \not\sim \mathcal{X}|\mathbf{y}^*$) and hence the counterfactual search in the learned latent space is doomed.
 
 \begin{figure}
   \centering
   \begin{minipage}[t]{0.45\textwidth}
     \centering
     \includegraphics[width=\textwidth]{../artifacts/results/images/you_may_not_like_it.png}
-    \caption{You may not like it, but this is what stripped-down counterfactuals look like. Counterfactuals for turning an 8 (eight) into a 3 (three): original image (left); counterfactual produced using \citet{wachter2017counterfactual} (centre); and a counterfactual produced using JSMA-based approach introduced by \citep{schut2021generating}.}\label{fig:adv}
+    \caption{Explanations or Adversarial Examples? Counterfactuals for turning an 8 (eight) into a 3 (three): original image (left); counterfactual produced using~\citet{wachter2017counterfactual} (centre); and a counterfactual produced using the approach introduced by~\citep{schut2021generating} that uses Jacobian-Based Saliency Map Attacks to solve Equation~\ref{eq:general}.}\label{fig:adv}
   \end{minipage}\hfill
   \begin{minipage}[t]{0.45\textwidth}
     \centering
     \includegraphics[width=\textwidth]{../artifacts/results/images/surrogate_gone_wrong.png}
-    \caption{Using surrogates can improve plausibility, but also increases vulnerability. Counterfactuals for turning an 8 (eight) into a 3 (three): original image (left); counterfactual produced using REVISE \citep{joshi2019realistic} with a well-specified surrogate (centre); and a counterfactual produced using REVISE \citep{joshi2019realistic} with a poorly specified surrogate (right).}\label{fig:vae}
+    \caption{Using surrogates can improve plausibility, but also increases vulnerability. Counterfactuals for turning an 8 (eight) into a 3 (three): original image (left); counterfactual produced using REVISE~\citep{joshi2019realistic} with a well-specified surrogate (centre); and a counterfactual produced using REVISE~\citep{joshi2019realistic} with a poorly specified surrogate (right).}\label{fig:vae}
   \end{minipage}
 \end{figure}
 
 \subsubsection{Plausibility through Minimal Predictive Uncertainty}
 
-\citet{schut2021generating} show that to meet the plausibility objective we need not explicitly model the input distribution. Pointing to the undesirable engineering overhead induced by surrogate models, they propose that we rely on the implicit minimisation of predictive uncertainty instead. Their proposed methodology solves Equation~\ref{eq:general} by greedily applying JSMA in the feature space with standard cross-entropy loss and no penalty at all. They demonstrate theoretically and empirically that their approach yields counterfactuals for which the model $M_{\theta}$ predicts the target label $\mathbf{y}^*$ with high confidence. Provided the model is well-specified, these counterfactuals are plausible. Unfortunately, this idea hinges on the assumption that the Black Box Model provides well-calibrated predictive uncertainty estimates.
+\citet{schut2021generating} show that to meet the plausibility objective we need not explicitly model the input distribution. Pointing to the undesirable engineering overhead induced by surrogate models, they propose that we rely on the implicit minimisation of predictive uncertainty instead. Their proposed methodology solves Equation~\ref{eq:general} by greedily applying JSMA in the feature space with standard cross-entropy loss and no penalty at all. They demonstrate theoretically and empirically that their approach yields counterfactuals for which the model $M_{\theta}$ predicts the target label $\mathbf{y}^*$ with high confidence. Provided the model is well-specified, these counterfactuals are plausible. Unfortunately, this idea hinges on the assumption that the black-box model provides well-calibrated predictive uncertainty estimates.
 
 \subsection{From Fidelity to Model Conformity}
 
-Above we explained that since Counterfactual Explanations work directly with the Black Box model, the fidelity of explanations as we defined it earlier is not a concern. This may explain why research has primarily focused on other desiderata, most notably plausibility (Definition~\ref{def:plausible}). Enquiring about the plausibility of a counterfactual essentially boils down to the following question: `Is this counterfactual consistent with the underlying data'? To introduce this section, we posit a related, slightly more nuanced question: `Is this counterfactual consistent with what the model has learned about the underlying data'? We will argue that fidelity is not a sufficient evaluation measure to answer this question and propose a novel way to assess if Counterfactual Explanations conform with model behaviour. 
+Above we explained that since Counterfactual Explanations work directly with the Black Box model, the fidelity of explanations as we defined it earlier is not a concern. This may explain why research has primarily focused on other desiderata, most notably plausibility (Definition~\ref{def:plausible}). Enquiring about the plausibility of a counterfactual essentially boils down to the following question: `Is this counterfactual consistent with the underlying data'? We posit a related, slightly more nuanced question: `Is this counterfactual consistent with what the model has learned about the underlying data'? We will argue that fidelity is not a sufficient evaluation measure to answer this question and propose a novel way to assess if Counterfactual Explanations conform with model behaviour. 
 
-The word \textit{fidelity} stems from the Latin word `fidelis', which means `faithful, loyal, trustworthy' \citep{mw2023fidelity}. As we explained in Section~\ref{background}, model explanations are generally considered faithful if their corresponding predictions coincide with the predictions made by the model itself. Since this definition of faithfulness is not useful in the context of Counterfactual Explanations, we propose an adapted version: 
+The word \textit{fidelity} stems from the Latin word `fidelis', which means `faithful, loyal, trustworthy'~\citep{mw2023fidelity}. As we explained in Section~\ref{background}, model explanations are generally considered faithful if their corresponding predictions coincide with the predictions made by the model itself. Since this definition of faithfulness is not useful in the context of Counterfactual Explanations, we propose an adapted version: 
 
 \begin{definition}[Conformal Counterfactuals]
   \label{def:conformal}
@@ -195,7 +186,7 @@ The primary objective of this work has been to develop a methodology for generat
 
 \subsection{Quantifying the Model's Generative Property}
 
-Recent work by \citet{grathwohl2020your} on Energy Based Models (EBM) has pointed out that there is a `generative model hidden within every standard discriminative model'. The authors show that we can draw samples from the posterior conditional distribution $p_{\theta}(\mathbf{x}|\mathbf{y})$ using Stochastic Gradient Langevin Dynamics (SGLD). The authors use this insight to train classifiers jointly for the discriminative task using standard cross-entropy and the generative task using SGLD. They demonstrate empirically that among other things this improves predictive uncertainty quantification for discriminative models. Our findings in this work suggest that Joint Energy Models (JEM) also tend to yield more plausible Counterfactual Explanations. Based on the definition of plausible counterfactuals (Definition~\ref{def:plausible}) this is not surprising. 
+Recent work by~\citet{grathwohl2020your} on Energy Based Models (EBM) has pointed out that there is a `generative model hidden within every standard discriminative model'. The authors show that we can draw samples from the posterior conditional distribution $p_{\theta}(\mathbf{x}|\mathbf{y})$ using Stochastic Gradient Langevin Dynamics (SGLD). The authors use this insight to train classifiers jointly for the discriminative task using standard cross-entropy and the generative task using SGLD. They demonstrate empirically that among other things this improves predictive uncertainty quantification for discriminative models. Our findings in this work suggest that Joint Energy Models (JEM) also tend to yield more plausible Counterfactual Explanations. Based on the definition of plausible counterfactuals (Definition~\ref{def:plausible}) this is not surprising. 
 
 Crucially for our purpose, one can apply their proposed sampling strategy during inference to essentially any standard discriminative model. Even models that are not explicitly trained for the joint objective learn about the distribution of inputs $X$ by learning to make conditional predictions about the output $y$. We can leverage this observation to quantify the generative property of the Black Box model itself. In particular, note that if we fix $\mathbf{y}$ to our target value $\mathbf{y}^*$, we can sample from $p_{\theta}(\mathbf{x}|\mathbf{y}^*)$ using SGLD as follows, 
 
@@ -209,9 +200,9 @@ where $\mathbf{r}_j \sim \mathcal{N}(\mathbf{0},\mathbf{I})$ is the stochastic t
 
 \subsection{Quantifying the Model's Predictive Uncertainty}
 
-To quantify the model's predictive uncertainty we use Conformal Prediction (CP), an approach that has recently gained popularity in the Machine Learning community \citep{angelopoulos2021gentle,manokhin2022awesome}. Crucially for our intended application, CP is model-agnostic and can be applied during inference without placing any restrictions on model training. Intuitively, CP works under the premise of turning heuristic notions of uncertainty into rigorous uncertainty estimates by repeatedly sifting through the training data or a dedicated calibration dataset. Conformal classifiers produce prediction sets for individual inputs that include all output labels that can be reasonably attributed to the input. These sets tend to be larger for inputs that do not conform with the training data and are therefore characterized by high predictive uncertainty. 
+To quantify the model's predictive uncertainty we use Conformal Prediction (CP), an approach that has recently gained popularity in the Machine Learning community~\citep{angelopoulos2021gentle,manokhin2022awesome}. Crucially for our intended application, CP is model-agnostic and can be applied during inference without placing any restrictions on model training. Intuitively, CP works under the premise of turning heuristic notions of uncertainty into rigorous uncertainty estimates by repeatedly sifting through the training data or a dedicated calibration dataset. Conformal classifiers produce prediction sets for individual inputs that include all output labels that can be reasonably attributed to the input. These sets tend to be larger for inputs that do not conform with the training data and are therefore characterized by high predictive uncertainty. 
 
-In order to generate counterfactuals that are associated with low predictive uncertainty, we use a smooth set size penalty introduced by \citet{stutz2022learning} in the context of conformal training:
+In order to generate counterfactuals that are associated with low predictive uncertainty, we use a smooth set size penalty introduced by~\citet{stutz2022learning} in the context of conformal training:
 
 \begin{equation}\label{eq:setsize}
   \begin{aligned}
@@ -221,7 +212,7 @@ In order to generate counterfactuals that are associated with low predictive unc
 
 Here, $\kappa \in \{0,1\}$ is a hyper-parameter and $C_{\theta,\mathbf{y}}(\mathbf{x}_i;\alpha)$ can be interpreted as the probability of label $\mathbf{y}$ being included in the prediction set. 
 
-In order to compute this penalty for any Black Box Model we merely need to perform a single calibration pass through a holdout set $\mathcal{D}_{\text{cal}}$. Arguably, data is typically abundant and in most applications, practitioners tend to hold out a test data set anyway. Consequently, CP removes the restriction on the family of predictive models, at the small cost of reserving a subset of the available data for calibration. This particular case of conformal prediction is referred to as Split Conformal Prediction (SCP) as it involves splitting the training data into a proper training dataset and a calibration dataset. Details concerning our implementation of Conformal Prediction can be found in Appendix~\ref{app-cp}.
+In order to compute this penalty for any black-box model we merely need to perform a single calibration pass through a holdout set $\mathcal{D}_{\text{cal}}$. Arguably, data is typically abundant and in most applications, practitioners tend to hold out a test data set anyway. Consequently, CP removes the restriction on the family of predictive models, at the small cost of reserving a subset of the available data for calibration. This particular case of conformal prediction is referred to as Split Conformal Prediction (SCP) as it involves splitting the training data into a proper training dataset and a calibration dataset. Details concerning our implementation of Conformal Prediction can be found in Appendix~\ref{app-cp}.
 
 \subsection{Energy-Constrained Conformal Counterfactuals (ECCCo)}
 
@@ -234,7 +225,7 @@ Our framework for generating ECCCos combines the ideas introduced in the previou
   \end{aligned} 
 \end{equation}
 
-where $\hat{\mathbf{x}}_{\theta}$ denotes samples generated using SGLD (Equation~\ref{eq:sgld}) and $\text{dist}(\cdot)$ is a generic term for a distance metric. Our default choice for $\text{dist}(\cdot)$ is the Manhatten Distance since it enforces sparsity.
+where $\hat{\mathbf{x}}_{\theta}$ denotes samples generated using SGLD (Equation~\ref{eq:sgld}) and $\text{dist}(\cdot)$ is a generic term for a distance metric. Our default choice for $\text{dist}(\cdot)$ is the L1 Norm, or Manhattan distance, since it induces sparsity.
 
 The first two terms in Equation~\ref{eq:eccco} correspond to the counterfactual search objective defined in~\citet{wachter2017counterfactual} which merely penalises the distance of counterfactuals from their factual values. The additional two penalties in ECCCo ensure that counterfactuals conform with the model's generative property and lead to minimally uncertain predictions, respectively. The hyperparameters $\lambda_1, ..., \lambda_3$ can be used to balance the different objectives: for example, we may choose to incur larger deviations from the factual in favour of conformity with the model's generative property by choosing lower values of $\lambda_1$ and relatively higher values of $\lambda_2$. Figure~\ref{fig:eccco} illustrates this balancing act for an example involving synthetic data: vector fields indicate the direction of gradients with respect to the different components our proposed objective function (Equation~\ref{eq:eccco}).
 
@@ -260,7 +251,7 @@ The first two terms in Equation~\ref{eq:eccco} correspond to the counterfactual
   \State Initialize $t \gets 0$
   \While{\textit{not converged} or $t < T$}
   \State $\hat{\mathbf{x}}_{\theta, t} \gets \text{rand}(\mathcal{B},n_{\mathcal{B}})$
-  \State $\mathbf{z}^\prime \gets \mathbf{z}^\prime - \eta \nabla_{\mathbf{z}^\prime} \mathcal{L}(\mathbf{z}^\prime,\mathbf{y}^*,\hat{\mathbf{x}}_{\theta, t})$
+  \State $\mathbf{z}^\prime \gets \mathbf{z}^\prime - \eta \nabla_{\mathbf{z}^\prime} \mathcal{L}(\mathbf{z}^\prime,\mathbf{y}^*,\hat{\mathbf{x}}_{\theta, t}; \Lambda, \alpha)$
   \State $t \gets t+1$
   \EndWhile
   \State $\mathbf{x}^\prime \gets f(\mathbf{z}^\prime)$
@@ -278,9 +269,9 @@ The first two terms in Equation~\ref{eq:eccco} correspond to the counterfactual
 
 The entire procedure for generating ECCCos is described in Algorithm~\ref{alg:eccco}. For the sake of simplicity and without loss of generality, we limit our attention to generating a single counterfactual $\mathbf{x}^\prime=f(\mathbf{z}^\prime)$ where in contrast to Equation~\ref{eq:eccco} $\mathbf{z}^\prime$ denotes a $1$-dimensional array containing a single counterfactual state. That state is initialized by passing the factual $\mathbf{x}$ through the encoder $f^{-1}$ which in our case corresponds to a simple feature transformer, rather than the encoder part of VAE as in REVISE~\citep{joshi2019realistic}. Next, we generate a buffer of $N_{\mathcal{B}}$ conditional samples $\hat{\mathbf{x}}_{\theta}|\mathbf{y}^*$ using SGLD (Equation~\ref{eq:sgld}) and conformalise the model $M_{\theta}$ through Split Conformal Prediction on training data $\mathcal{D}$.
 
-Finally, we search counterfactuals through gradient descent. Let $\mathcal{L}(\mathbf{z}^\prime,\mathbf{y}^*,\hat{\mathbf{x}}_{\theta, t})$ denote our loss function defined in Equation~\ref{eq:eccco}. Then in each iteration, we first randomly draw $n_{\mathcal{B}}$ samples from the buffer $\mathcal{B}$ before updating the counterfactual state $\mathbf{z}^\prime$ by moving in the negative direction of that loss function. The search terminates once the convergence criterium is met or the maximum number of iterations $T$ has been exhausted. Note that the choice of convergence criterium has important implications on the final counterfactual. For more detail on this see Appendix~\ref{app:eccco}).
+Finally, we search counterfactuals through gradient descent. Let $\mathcal{L}(\mathbf{z}^\prime,\mathbf{y}^*,\hat{\mathbf{x}}_{\theta, t})$ denote our loss function defined in Equation~\ref{eq:eccco}. Then in each iteration, we first randomly draw $n_{\mathcal{B}}$ samples from the buffer $\mathcal{B}$ before updating the counterfactual state $\mathbf{z}^\prime$ by moving in the negative direction of that loss function. The search terminates once the convergence criterium is met or the maximum number of iterations $T$ has been exhausted. Note that the choice of convergence criterium has important implications on the final counterfactual (for more detail on this see Appendix~\ref{app:eccco}).
 
-Figure~\ref{fig:eccco-mnist} presents ECCCos for the MNIST example from Section~\ref{background} for various Black Box models of increasing complexity from left to right: a simple Multi-Layer Perceptron (MLP); an Ensemble of MLPs, each of the same architecture as the single MLP; a Joint Energy Model (JEM) based on the same MLP architecture; and finally, an Ensemble of these JEMs. Since Deep Ensembles have an improved capacity for predictive uncertainty quantification and JEMs are explicitly trained to learn plausible representations of the input data, it is intuitive to see that the plausibility of counterfactuals visibly improves from left to right. This provides some first anecdotal evidence that ECCCos achieve plausibility while maintaining faithfulness to the Black Box. 
+Figure~\ref{fig:eccco-mnist} presents ECCCos for the MNIST example from Section~\ref{background} for various black-box models of increasing complexity from left to right: a simple Multi-Layer Perceptron (MLP); an Ensemble of MLPs, each of the same architecture as the single MLP; a Joint Energy Model (JEM) based on the same MLP architecture; and finally, an Ensemble of these JEMs. Since Deep Ensembles have an improved capacity for predictive uncertainty quantification and JEMs are explicitly trained to learn plausible representations of the input data, it is intuitive to see that the plausibility of counterfactuals visibly improves from left to right. This provides some first anecdotal evidence that ECCCos achieve plausibility while maintaining faithfulness to the Black Box. 
 
 \section{Empirical Analysis}\label{emp}
 
@@ -288,9 +279,9 @@ In this section, we bolster our anecdotal findings from the previous section thr
 
 \subsection{Evaluation Measures}\label{evaluation}
 
-Above we have defined plausibility (\ref{def:plausible}) and conformity (\ref{def:conformal}) for Counterfactual Explanations. In this subsection, we introduce evaluation measures that facilitate a quantitative evaluation of counterfactuals for these objectives. 
+Above we have defined plausibility (Definition~\ref{def:plausible}) and conformity (Definition~\ref{def:conformal}) for Counterfactual Explanations. In this subsection, we introduce evaluation measures that facilitate a quantitative evaluation of counterfactuals for these objectives. 
 
-Firstly, in order to assess the plausibility of counterfactuals we adapt the implausibility metric proposed in \citet{guidotti2022counterfactual}. The authors propose to evaluate plausibility in terms of the distance of the counterfactual $\mathbf{x}^{\prime}$ from its nearest neighbour in the target class $\mathbf{y}^*$: the smaller this distance, the more plausible the counterfactual. Instead of focusing only on the nearest neighbour of $\mathbf{x}^{\prime}$, we suggest computing the average over distances from multiple (possibly all) observed instances in the target class. Formally, for a single counterfactual, we have:
+Firstly, in order to assess the plausibility of counterfactuals we adapt the implausibility metric proposed in~\citet{guidotti2022counterfactual}. The authors propose to evaluate plausibility in terms of the distance of the counterfactual $\mathbf{x}^{\prime}$ from its nearest neighbour in the target class $\mathbf{y}^*$: the smaller this distance, the more plausible the counterfactual. Instead of focusing only on the nearest neighbour of $\mathbf{x}^{\prime}$, we suggest computing the average over distances from multiple (possibly all) observed instances in the target class. Formally, for a single counterfactual, we have:
 
 \begin{equation}\label{eq:impl}
   \begin{aligned}
@@ -306,7 +297,7 @@ This measure is straightforward to compute and should be less sensitive to outli
   \end{aligned}
 \end{equation}
 
-As noted by \citet{guidotti2022counterfactual}, these distance-based measures are simplistic and more complex alternative measures may ultimately be more appropriate for the task. For example, we considered using statistical divergence measures instead. This would involve generating not one but many counterfactuals and comparing the generated empirical distribution to the target distributions in Definitions~\ref{def:plausible} and~\ref{def:conformal}. While this approach is potentially more rigorous, generating enough counterfactuals is not always practical. 
+As noted by~\citet{guidotti2022counterfactual}, these distance-based measures are simplistic and more complex alternative measures may ultimately be more appropriate for the task. For example, we considered using statistical divergence measures instead. This would involve generating not one but many counterfactuals and comparing the generated empirical distribution to the target distributions in Definitions~\ref{def:plausible} and~\ref{def:conformal}. While this approach is potentially more rigorous, generating enough counterfactuals is not always practical. 
 
 \subsection{Data}
 
@@ -321,7 +312,7 @@ As noted by \citet{guidotti2022counterfactual}, these distance-based measures ar
 
 \subsection{Key Insights}
 
-Consistent with the findings in \citet{schut2021generating}, we have demonstrated that predictive uncertainty estimates can be leveraged to generate plausible counterfactuals. Interestingly, \citet{schut2021generating} point out that this finding --- as intuitive as it is --- may be linked to a positive connection between the generative task and predictive uncertainty quantification. In particular, \citet{grathwohl2020your} demonstrate that their proposed method for integrating the generative objective in training yields models that have improved predictive uncertainty quantification. Since neither \citet{schut2021generating} nor we have employed any surrogate generative models, our findings seem to indicate that the positive connection found in \citet{grathwohl2020your} is bidirectional.
+Consistent with the findings in~\citet{schut2021generating}, we have demonstrated that predictive uncertainty estimates can be leveraged to generate plausible counterfactuals. Interestingly, \citet{schut2021generating} point out that this finding --- as intuitive as it is --- may be linked to a positive connection between the generative task and predictive uncertainty quantification. In particular, \citet{grathwohl2020your} demonstrate that their proposed method for integrating the generative objective in training yields models that have improved predictive uncertainty quantification. Since neither~\citet{schut2021generating} nor we have employed any surrogate generative models, our findings seem to indicate that the positive connection found in~\citet{grathwohl2020your} is bidirectional.
 
 \subsection{Limitations}
 
@@ -348,17 +339,17 @@ Consistent with the findings in \citet{schut2021generating}, we have demonstrate
 
 \subsection{JEM}\label{app-jem}
 
-While $\mathbf{x}_J$ is only guaranteed to distribute as $p_{\theta}(\mathbf{x}|\mathbf{y}^*)$ if $\epsilon \rightarrow 0$ and $J \rightarrow \infty$, the bias introduced for a small finite $\epsilon$ is negligible in practice \citep{murphy2023probabilistic,grathwohl2020your}. While \citet{grathwohl2020your} use Equation~\ref{eq:sgld} during training, we are interested in applying the conditional sampling procedure in a post hoc fashion to any standard discriminative model. 
+While $\mathbf{x}_J$ is only guaranteed to distribute as $p_{\theta}(\mathbf{x}|\mathbf{y}^*)$ if $\epsilon \rightarrow 0$ and $J \rightarrow \infty$, the bias introduced for a small finite $\epsilon$ is negligible in practice~\citep{murphy2023probabilistic,grathwohl2020your}. While~\citet{grathwohl2020your} use Equation~\ref{eq:sgld} during training, we are interested in applying the conditional sampling procedure in a post-hoc fashion to any standard discriminative model. 
 
 \subsection{Conformal Prediction}\label{app-cp}
 
-The fact that conformal classifiers produce set-valued predictions introduces a challenge: it is not immediately obvious how to use such classifiers in the context of gradient-based counterfactual search. Put differently, it is not clear how to use prediction sets in Equation~\ref{eq:general}. Fortunately, \citet{stutz2022learning} have recently proposed a framework for Conformal Training that also hinges on differentiability. Specifically, they show how Stochastic Gradient Descent can be used to train classifiers not only for the discriminative task but also for additional objectives related to Conformal Prediction. One such objective is \textit{efficiency}: for a given target error rate $alpha$, the efficiency of a conformal classifier improves as its average prediction set size decreases. To this end, the authors introduce a smooth set size penalty defined in Equation~\ref{eq:setsize}
+The fact that conformal classifiers produce set-valued predictions introduces a challenge: it is not immediately obvious how to use such classifiers in the context of gradient-based counterfactual search. Put differently, it is not clear how to use prediction sets in Equation~\ref{eq:general}. Fortunately, \citet{stutz2022learning} have recently proposed a framework for Conformal Training that also hinges on differentiability. Specifically, they show how Stochastic Gradient Descent can be used to train classifiers not only for the discriminative task but also for additional objectives related to Conformal Prediction. One such objective is \textit{efficiency}: for a given target error rate $\alpha$, the efficiency of a conformal classifier improves as its average prediction set size decreases. To this end, the authors introduce a smooth set size penalty defined in Equation~\ref{eq:setsize} in the body of this paper
 
-Formally, it is defined as $C_{\theta,\mathbf{y}}(\mathbf{x}_i;\alpha):=\sigma\left((s(\mathbf{x}_i,\mathbf{y})-\alpha) T^{-1}\right)$ for $\mathbf{y}\in\mathcal{Y}$ where $\sigma$ is the sigmoid function and $T$ is a hyper-parameter used for temperature scaling \citep{stutz2022learning}.
+Formally, it is defined as $C_{\theta,\mathbf{y}}(\mathbf{x}_i;\alpha):=\sigma\left((s(\mathbf{x}_i,\mathbf{y})-\alpha) T^{-1}\right)$ for $\mathbf{y}\in\mathcal{Y}$, where $\sigma$ is the sigmoid function and $T$ is a hyper-parameter used for temperature scaling~\citep{stutz2022learning}.
 
-Intuitively, CP works under the premise of turning heuristic notions of uncertainty into rigorous uncertainty estimates by repeatedly sifting through the data. It can be used to generate prediction intervals for regression models and prediction sets for classification models \citep{altmeyer2022conformal}. Since the literature on CE and AR is typically concerned with classification problems, we focus on the latter. A particular variant of CP called Split Conformal Prediction (SCP) is well-suited for our purposes because it imposes only minimal restrictions on model training. 
+Intuitively, CP works under the premise of turning heuristic notions of uncertainty into rigorous uncertainty estimates by repeatedly sifting through the data. It can be used to generate prediction intervals for regression models and prediction sets for classification models~\citep{altmeyer2022conformal}. Since the literature on CE and AR is typically concerned with classification problems, we focus on the latter. A particular variant of CP called Split Conformal Prediction (SCP) is well-suited for our purposes, because it imposes only minimal restrictions on model training. 
 
-Specifically, SCP involves splitting the data $\mathcal{D}_n=\{(\mathbf{x}_i,\mathbf{y}_i)\}_{i=1,...,n}$ into a proper training set $\mathcal{D}_{\text{train}}$ and a calibration set $\mathcal{D}_{\text{cal}}$. The former is used to train the classifier in any conventional fashion. The latter is then used to compute so-called nonconformity scores: $\mathcal{S}=\{s(\mathbf{x}_i,\mathbf{y}_i)\}_{i \in \mathcal{D}_{\text{cal}}}$ where $s: (\mathcal{X},\mathcal{Y}) \mapsto \mathbb{R}$ is referred to as \textit{score function}. In the context of classification, a common choice for the score function is just $s_i=1-M_{\theta}(\mathbf{x}_i)[\mathbf{y}_i]$, that is one minus the softmax output corresponding to the observed label $\mathbf{y}_i$ \citep{angelopoulos2021gentle}. 
+Specifically, SCP involves splitting the data $\mathcal{D}_n=\{(\mathbf{x}_i,\mathbf{y}_i)\}_{i=1,...,n}$ into a proper training set $\mathcal{D}_{\text{train}}$ and a calibration set $\mathcal{D}_{\text{cal}}$. The former is used to train the classifier in any conventional fashion. The latter is then used to compute so-called nonconformity scores: $\mathcal{S}=\{s(\mathbf{x}_i,\mathbf{y}_i)\}_{i \in \mathcal{D}_{\text{cal}}}$ where $s: (\mathcal{X},\mathcal{Y}) \mapsto \mathbb{R}$ is referred to as \textit{score function}. In the context of classification, a common choice for the score function is just $s_i=1-M_{\theta}(\mathbf{x}_i)[\mathbf{y}_i]$, that is one minus the softmax output corresponding to the observed label $\mathbf{y}_i$~\citep{angelopoulos2021gentle}. 
 
 Finally, classification sets are formed as follows,
 
@@ -368,9 +359,9 @@ Finally, classification sets are formed as follows,
   \end{aligned}
 \end{equation}
 
-where $\hat{q}$ denotes the $(1-\alpha)$-quantile of $\mathcal{S}$ and $\alpha$ is a predetermined error rate. As the size of the calibration set increases, the probability that the classification set $C(\mathbf{x}_{\text{test}})$ for a newly arrived sample $\mathbf{x}_{\text{test}}$ does not cover the true test label $\mathbf{y}_{\text{test}}$ approaches $\alpha$ \citep{angelopoulos2021gentle}. 
+where $\hat{q}$ denotes the $(1-\alpha)$-quantile of $\mathcal{S}$ and $\alpha$ is a predetermined error rate. As the size of the calibration set increases, the probability that the classification set $C(\mathbf{x}_{\text{test}})$ for a newly arrived sample $\mathbf{x}_{\text{test}}$ does not cover the true test label $\mathbf{y}_{\text{test}}$ approaches $\alpha$~\citep{angelopoulos2021gentle}. 
 
-Observe from Equation~\ref{eq:scp} that Conformal Prediction works on an instance-level basis, much like Counterfactual Explanations are local. The prediction set for an individual instance $\mathbf{x}_i$ depends only on the characteristics of that sample and the specified error rate. Intuitively, the set is more likely to include multiple labels for samples that are difficult to classify, so the set size is indicative of predictive uncertainty. To see why this effect is exacerbated by small choices for $\alpha$ consider the case of $\alpha=0$, which requires that the true label is covered by the prediction set with probability equal to one.
+Observe from Equation~\ref{eq:scp} that Conformal Prediction works on an instance-level basis, much like Counterfactual Explanations are local. The prediction set for an individual instance $\mathbf{x}_i$ depends only on the characteristics of that sample and the specified error rate. Intuitively, the set is more likely to include multiple labels for samples that are difficult to classify, so the set size is indicative of predictive uncertainty. To see why this effect is exacerbated by small choices for $\alpha$ consider the case of $\alpha=0$, which requires that the true label is covered by the prediction set with probability equal to 1.
 
 \subsection{Conformal Prediction}\label{app:eccco}