From 3a0b50d99047d39081bf27980fd69753bb8603cb Mon Sep 17 00:00:00 2001 From: Jan Kowalczyk Date: Fri, 2 May 2025 14:56:10 +0200 Subject: [PATCH] some more work on background --- thesis/Main.tex | 46 +++++++++--------- thesis/bib/bibliography.bib | 29 +++++++++++ .../ml_unsupervised_learning_placeholder.png | Bin 0 -> 160786 bytes 3 files changed, 51 insertions(+), 24 deletions(-) create mode 100644 thesis/figures/ml_unsupervised_learning_placeholder.png diff --git a/thesis/Main.tex b/thesis/Main.tex index 5298f5d..6f462ab 100755 --- a/thesis/Main.tex +++ b/thesis/Main.tex @@ -303,7 +303,7 @@ By their very nature anomalies are rare occurences and oftentimes unpredictable \begin{enumerate} \item \textbf{Classification Based} - A classification technique such as an SVM or a fitting neural network is used to classify samples as either normal or anomalous based on labeled training data. Alternatively, if not enough labeled training data is available a one-class classification algorithm can be employed. In that case, the algorithm assumes all training samples to be normal and then learns a boundary around the normal samples to differentiate them from anomalous samples which lie outside the learnt boundary. \item \textbf{Clustering Based} - Clustering techniques such as K-Means clustering or DBSCAN aim to group similar data together into clusters, differentiating it from dissimilar data which may belong to another or no cluster at all. Anomaly detection methods from this category employ such a technique, with the assumption that normal data will assemble into one or more clusters due to their similar properties, while anomalies may create their own smaller clusters, not belong to any cluster at all or at least be an appreciable distance from the closest normal cluster's center. - \item \textbf{Nearest Neighbor Based} - Similar to the clustering based category, these techniques assume normal data is more closely clustered than anomalies and therefore utilize either a sample's distance to their $k^{th}$ nearest neighbor or the density of their local neighborhood, to judge wether a sample is anomalous. + \item \textbf{Nearest Neighbor Based} - Similar to the clustering based category, these techniques assume normal data is more closely clustered than anomalies and therefore utilize either a sample's distance to their $k^{th}$ nearest neighbor or the density of their local neighborhood, to judge wether a sample is anomalous. \item \textbf{Statistical} - These methods try to fit a statistical model of the normal behaviour to the data. After the distribution from which normal data originates is defined, samples can be found to be normal or anomalous based on their likelihood to arise from said distribution. \item \textbf{Information Theoretic} - The main assumption for information theoretic anomaly detection methods, is that anomalies differ somehow in their information content from anomalous data. An information theoretic measure is therefore used to determine iregularities in the data's information content, enabling the detection of anomalous samples. \item \textbf{Spectral} - Spectral approaches assume the possibility to map data into a lower-dimensional space, where normal data appears significantly different from anomalous data. To this end a dimensionality reduction technique such as PCA is used to embed the data into a lower dimensional subspace. Although it may be easier to differentiate normal and anomalous data in that subspace, it is still necessary to employ a technique capable of this feat, so spectral methods are oftentimes used as a pre-processing step followed by an anomaly detection method operating on the data's subspace. @@ -314,7 +314,9 @@ In this thesis we used an anomaly detection method, namely Deep Semi-Supervised Chapter~\ref{chp:deepsad} describes DeepSAD in more detail, which shows that it is a clustering based approach with a spectral pre-processing component, in that it uses a neural network to reduce the inputs dimensionality while simultaneously clustering normal data closely around a given centroid. It then produces an anomaly score by calculating the geometric distance between a data sample and the aforementioned cluster centroid, assuming the distance is shorter for normal than for anomalous data. Since our data is high dimensional it makes sense to use a spectral method to reduce the datas dimensionality and an approach which results in an analog value rather than a binary classification is useful for our use-case since we want to quantify not only classify the data degradation. -%\todo[inline, color=green!40]{data availability leading into semi-supervised learning algorithms} +%\todo[inline, color=green!40]{data availability leading into semi-supervised learning algorithms} + +There is a wide array of problems in domains similar to the one we research in this paper, for which modeling them as anomaly detection problems has been proven successful. The degradation of pointclouds, produced by an industrial 3D sensor, has been modeled as an anomaly detection task in~\cite{bg_ad_pointclouds_scans}. \citeauthor{bg_ad_pointclouds_scans} propose a student-teacher model capable of infering a pointwise anomaly score for degradation in point clouds. The teacher network is trained on an anomaly-free dataset to extract dense features of the point clouds' local geometries, after which an identical student network is trained to emulate the teacher networks' outputs. For degraded pointclouds the regression between the teacher's and student's outputs is calculated and interpreted as the anomaly score, with the rationalization that the student network has not observed features produced by anomalous geometries during training, leaving it incapable of producing a similar output as the teacher for those regions. Another example would be~\cite{bg_ad_pointclouds_poles}, which proposes a method to detect and classify pole-like objects in urban point cloud data, to differentiate between natural and man-made objects such as street signs, for autonomous driving purposes. An anomaly detection method was used to identify the vertical pole-like objects in the point clouds and then using a clustering algorithm to group similar objects and classify them as either trees or poles. As already shortly mentioned at the beginning of this section, anomaly detection methods and their usage are oftentimes challenged by the limited availability of anomalous data, owing to the very nature of anomalies which are rare occurences. Oftentimes the intended use-case is to even find unknown anomalies in a given dataset which have not yet been identified. In addition, it can be challenging to classify anomalies correctly for complex data, since the very definition of an anomaly is dependent on many factors such as the type of data, the intended use-case or even how the data evolves over time. For these reasons most types of anomaly detection approaches limit their reliance on anomalous data during training and many of them do not differentiate between normal and anomalous data at all. DeepSAD is a semi-supervised method which is characterized by using a mixture of labeled and unlabeled data. @@ -349,7 +351,11 @@ As already shortly mentioned at the beginning of this section, anomaly detection {explain what ML is, how the different approaches work, why to use semi-supervised} {autoencoder special case (un-/self-supervised) used in DeepSAD $\rightarrow$ explain autoencoder} -Machine learning defines types of algorithms capable of learning from existing data to perform tasks on previously unseen data without being explicitely programmed to do so~\cite{machine_learning_first_definition}. They are oftentimes categorized by the underlying technique employed, by the type of task they are trained to achieve or by the feedback provided to the algorithm during training. For the latter, the most prominent categories are supervised learning, unsupervised learning and reinforcement learning. +Machine learning defines types of algorithms capable of learning from existing data to perform tasks on previously unseen data without being explicitely programmed to do so~\cite{machine_learning_first_definition}. Many kinds of machine learning methods exist, but neural networks are one of the most commonly used and researched of them, due to their versatility and domain independent success over the last decades. They are comprised of connected artifical neurons, modeled roughly after neurons and synapses in the brain. +\todo[inline, color=green!40]{talk about neural networks, deep learning, backwards propagation, optimization goals, iterative process, then transition to the categories} +One way to categorize machine learning algorithms is by the nature of the feedback provided for the algorithm to learn. The most prominent of those categories are supervised learning, unsupervised learning and reinforcement learning. + +\todo[inline, color=green!40]{rewrite last paragraph to be more generally about ML first, talk about neural networks, deep learning, backwards propagation, optimization goals, iterative process, then transition to the categories} For supervised learning each data sample is augmented by including a label depicting the ideal output the algorithm can produce for the given input. During the learning step these algorithms can compare their generated output with the one provided by an expert and calculate the error between them, minimizing the error to improve performance. Such labels are typically either a categorical or continuous target which are most commonly used for classification and regression tasks respectively. @@ -357,7 +363,7 @@ For supervised learning each data sample is augmented by including a label depic Unsupervised learning algorithms use raw data without a target label that can be used during the learning process. These types of algorithms are often utilized to identify underlying patterns in data which may be hard to discover using classical data analysis due to for example large data size or high data complexity. Cluster analysis depicts one common use case, in which data is grouped into clusters such that data from one cluster resembles other data from the same cluster more closely than data from other clusters, according to some predesignated criteria. Another important use case are dimensionality reduction tasks which transform high-dimensional data into a lower-dimensional subspace while retaining meaningful information of the original data. -\todo[inline, color=green!40]{illustration unsupervised learning} +\fig{ml_unsupervised_learning}{figures/ml_unsupervised_learning_placeholder.png}{PLACEHOLDER - An illustration of unsupervised learning-the training data does not contain any additional information like a label. The algorithm learns to group similar input data together.} A more interactive approach to learning is taken by reinforcement learning, which provides the algorithm with an environment and an interpreter of the environment's state. During training the algorithm explores new possible actions and their impact on the provided environment. The interpreter can then reward or punish the algorithm based on the outcome of its actions. To improve the algorithms capability it will try to maximize the rewards received from the interpreter, retaining some randomness as to enable the exploration of different actions and their outcomes. Reinforcement learning is usually used for cases where an algorithm has to make sequences of decisions in complex environments e.g., autonomous driving tasks. @@ -366,7 +372,6 @@ A more interactive approach to learning is taken by reinforcement learning, whic Semi-Supervised learning algorithms are an inbetween category of supervised and unsupervised algorithms, in that they use a mixture of labeled and unlabeled data. Typically vastly more unlabeled data is used during training of such algorithms than labeled data, due to the effort and expertise required to label large quantities of data correctly. Semi-supervised methods are oftentimes an effort to improve a machine learning algorithm belonging to either the supervised or unsupervised category. Supervised methods such as classification tasks are enhanced by using large amounts of unlabeled data to augment the supervised training without additional need of labeling work. Alternatively, unsupervised methods like clustering algorithms may not only use unlabeled data but improve their performance by considering some hand-labeled data during training. %Semi-Supervised learning algorithms are an inbetween category of supervised and unsupervised algorithms, in that they use a mixture of labeled and unlabeled data. Typically vastly more unlabeled data is used during training of such algorithms than labeled data, due to the effort and expertise required to label large quantities of data correctly. The type of task performed by semi-supervised methods can originate from either supervised learningor unsupervised learning domain. For classification tasks which are oftentimes achieved using supervised learning the additional unsupervised data is added during training with the hope to achieve a better outcome than when training only with the supervised portion of the data. In contrast for unsupervised learning use cases such as clustering algorithms, the addition of labeled samples can help guide the learning algorithm to improve performance over fully unsupervised training. -\todo[inline, color=green!40]{Talk about deep learning, backwards propagation, optimization goals, iterative process?} For anomaly detection methods, the underlying techniques can belong to any of these or other categories of machine learning algorithms. As described in section~\ref{sec:anomaly_detection}, they may not even use any machine learning at all. While supervised anomaly detection methods exist, their suitability depends mostly on the availability of labeled training data and on a reasonable proportionality between normal and anomalous data. Both requirements can be challenging due to labeling often being labour intesive and the anomalies' intrinsic property to occur rarely when compared to normal data. DeepSAD is a semi-supervised method which extends its unsupervised predecessor Deep SVDD by including some labeled samples during training with the intention to improve the algorithm's performance. Both, DeepSAD and Deep SVDD include the training of an autoencoder as a pre-training step, a machine learning architecture, frequently grouped with unsupervised algorithms, even though that definition can be contested when scrutinizing it in more detail, which we will look at next. @@ -382,19 +387,12 @@ Autoencoders are a type of neural network architecture, whose main goal is learn \fig{autoencoder_general}{figures/autoencoder_principle_placeholder.png}{PLACEHOLDER - An illustration of autoencoders' general architecture and reconstruction task.} -One key use case of autoencoders is to employ them as a dimensionality reduction technique. In that case, the latent space inbetween the encoder and decoder is of a lower dimensionality than the input data itself. Due to the aforementioned reconstruction goal, the shared information between the input data and its latent space representation is maximized, which is known as following the infomax principle. After training such an autoencoder, it may be used to generate lower-dimensional representations of the given datatype, enabling more performant computations which may have been infeasible to achieve on the original data. DeepSAD which we employ in this paper, uses an autoencoder in a pre-training step to achieve this goal among others. - - -\todo[inline, color=green!40]{VAEs?} -%Another way to employ autoencoders is to use them as a generative technique. The decoder in autoencoders is trained to reproduce the input state from its encoded representation, which can also be interpreted as the decoder being able to generate data of the input type, from an encoded representation. A classic autoencoder trains the encoder to map its input to a single point in the latent space-a distriminative modeling approach, which can succesfully learn a predictor given enough data. In generative modeling on the other hand, the goal is to learn the distribution the data originates from, which is the idea behind variational autoencoders (VAE). VAEs have the encoder produce an distribution instead of a point representation, samples from which are then fed to the decoder to reconstruct the original input. The result is the encoder learning to model the generative distribution of the input data, which enables new usecases, due to the latent representation - - - -\todo[inline]{autoencoder explanation} -\todo[inline, color=green!40]{autoencoders are a neural network architecture archetype (words) whose training target is to reproduce the input data itself - hence the name. the architecture is most commonly a mirrored one consisting of an encoder which transforms input data into a hyperspace represantation in a latent space and a decoder which transforms the latent space into the same data format as the input data (phrasing), this method typically results in the encoder learning to extract the most robust and critical information of the data and the (todo maybe something about the decoder + citation for both). it is used in many domains translations, LLMs, something with images (search example + citations)} -\todo[inline, color=green!40]{typical encoder decoder mirrored figure} \todo[inline, color=green!40]{explain figure} -\todo[inline, color=green!40]{our chosen method Deep SAD uses an autoencoder to translate input data into a latent space, in which it can more easily differentiate between normal and anomalous data} +\todo[inline, color=green!40]{Paragraph about Variational Autoencoders? generative models vs discriminative models, enables other common use cases such as generating new data by changing parameterized generative distribution in latent space - VAES are not really relevant, maybe leave them out and just mention them shortly, with the hint that they are important but too much to explain since they are not key knowledge for this thesis} + +One key use case of autoencoders is to employ them as a dimensionality reduction technique. In that case, the latent space inbetween the encoder and decoder is of a lower dimensionality than the input data itself. Due to the aforementioned reconstruction goal, the shared information between the input data and its latent space representation is maximized, which is known as following the infomax principle. After training such an autoencoder, it may be used to generate lower-dimensional representations of the given datatype, enabling more performant computations which may have been infeasible to achieve on the original data. DeepSAD uses an autoencoder in a pre-training step to achieve this goal among others. This is especially useful for our usecase since point clouds produced by lidar sensors such as the one used in robotics are usually very high-dimensional, owed to the difficulty in mapping the whole scene with enough detail to navigate it. + +%Another way to employ autoencoders is to use them as a generative technique. The decoder in autoencoders is trained to reproduce the input state from its encoded representation, which can also be interpreted as the decoder being able to generate data of the input type, from an encoded representation. A classic autoencoder trains the encoder to map its input to a single point in the latent space-a distriminative modeling approach, which can succesfully learn a predictor given enough data. In generative modeling on the other hand, the goal is to learn the distribution the data originates from, which is the idea behind variational autoencoders (VAE). VAEs have the encoder produce an distribution instead of a point representation, samples from which are then fed to the decoder to reconstruct the original input. The result is the encoder learning to model the generative distribution of the input data, which enables new usecases, due to the latent representation \newsection{lidar_related_work}{Lidar - Light Detection and Ranging} @@ -445,7 +443,7 @@ In this chapter, we explore the method \emph{Deep Semi-Supervised Anomaly Detect {how clustering AD generally works, how it does in DeepSAD} {since the reader knows the general idea $\rightarrow$ what is the step-by-step?} -Deep SAD's overall mechanics are similar to clustering-based anomaly detection methods, which according to~\cite{anomaly_detection_survey} typically follow a two-step approach. First, a clustering algorithm groups data points around a centroid; then, the distances of individual data points from this centroid are calculated and used as an anomaly score. In Deep SAD, these concepts are implemented by employing a neural network, which is jointly trained to map input data onto a latent space and to minimize the volume of an data-encompassing hypersphere, whose center is the aforementioned centroid. The data's geometric distance in the latent space to the hypersphere center is used as the anomaly score, where a larger distance between data and centroid corresponds to a higher probability of a sample being anomalous. This is achieved by shrinking the data-encompassing hypersphere during training, proportionally to all training data, of which is required that there is significantly more normal than anomalous data present. The outcome of this approach is that normal data gets clustered more closely around the centroid, while anomalies appear further away from it as can be seen in the toy example depicted in figure~\ref{fig:deep_svdd_transformation}. +Deep SAD's overall mechanics are similar to clustering-based anomaly detection methods, which according to~\cite{anomaly_detection_survey} typically follow a two-step approach. First, a clustering algorithm groups data points around a centroid; then, the distances of individual data points from this centroid are calculated and used as an anomaly score. In Deep SAD, these concepts are implemented by employing a neural network, which is jointly trained to map input data onto a latent space and to minimize the volume of an data-encompassing hypersphere, whose center is the aforementioned centroid. The data's geometric distance in the latent space to the hypersphere center is used as the anomaly score, where a larger distance between data and centroid corresponds to a higher probability of a sample being anomalous. This is achieved by shrinking the data-encompassing hypersphere during training, proportionally to all training data, of which is required that there is significantly more normal than anomalous data present. The outcome of this approach is that normal data gets clustered more closely around the centroid, while anomalies appear further away from it as can be seen in the toy example depicted in figure~\ref{fig:deep_svdd_transformation}. %Deep SAD is an anomaly detection algorithm that belongs to the category of clustering-based methods, which according to~\cite{anomaly_detection_survey} typically follow a two-step approach. First, a clustering algorithm groups data points around a centroid; then, the distances of individual data points from this centroid are calculated and used as an anomaly score. In addition to that, DeepSAD also utilizes a spectral component by mapping the input data onto a lower-dimensional space, which enables it to detect anomalies in high-dimensional complex data types. In Deep SAD, these concepts are implemented by employing a neural network, which is jointly trained to map data into a latent space and to minimize the volume of an data-encompassing hypersphere whose center is the aforementioned centroid. The geometric distance in the latent space to the hypersphere center is used as the anomaly score, where a larger distance between data and centroid corresponds to a higher probability of a sample being anomalous. This is achieved by shrinking the data-encompassing hypersphere during training, proportionally to all training data, of which is required that there is significantly more normal than anomalous data present. The outcome of this approach is that normal data gets clustered more closely around the centroid, while anomalies appear further away from it as can be seen in the toy example depicted in figure~\ref{fig:deep_svdd_transformation}. @@ -457,7 +455,7 @@ Deep SAD's overall mechanics are similar to clustering-based anomaly detection m {pre-training is autoencoder, self-supervised, dimensionality reduction} {pre-training done $\rightarrow$ how are the pre-training results used?} -Before DeepSAD's training can begin, a pre-training step is required, during which an autoencoder is trained on all available input data. One of DeepSAD's goals is to map input data onto a lower dimensional latent space, in which the separation between normal and anomalous data can be achieved. To this end DeepSAD and its predecessor Deep SVDD make use of the autoencoder's reconstruction goal, whose successful training ensures confidence in the encoder architecture's suitability for extracting the input datas' most prominent information to the latent space inbetween the encoder and decoder. DeepSAD goes on to use just the encoder as its main network architecture, discarding the decoder at this step, since reconstruction of the input is unnecessary. +Before DeepSAD's training can begin, a pre-training step is required, during which an autoencoder is trained on all available input data. One of DeepSAD's goals is to map input data onto a lower dimensional latent space, in which the separation between normal and anomalous data can be achieved. To this end DeepSAD and its predecessor Deep SVDD make use of the autoencoder's reconstruction goal, whose successful training ensures confidence in the encoder architecture's suitability for extracting the input datas' most prominent information to the latent space inbetween the encoder and decoder. DeepSAD goes on to use just the encoder as its main network architecture, discarding the decoder at this step, since reconstruction of the input is unnecessary. %The results of the pre-training are used twofold. Firstly the encoders' weights at the end of pre-training can be used to initialize Deep SAD's weights for the main training step which aligns with the aforementioned Infomax principle, since we can assume the autoencoder maximized the shared information between the input and the latent space represenation. Secondly an initial forward-pass is run on the encoder network for all available training data samples and the results' mean position in the latent space is used to define the hypersphere center $\mathbf{c}$ which according to~\cite{deepsad} allows for faster convergence during the main training step than randomly chosen centroids. An alternative method of initializing the hypersphere center could be to use only labeled normal examples for the forward-pass, so not to pollute $\mathbf{c}$'s position with anomalous samples, which would only be possible if sufficient labeled normal samples are available. From this point on, the hypersphere center $\mathbf{c}$ stays fixed and does not change, which is necessary since it being a free optimization variable could lead to a trivial hypersphere collapse solution if the network was trained fully unsupervised. @@ -543,7 +541,7 @@ The neural network architecture of DeepSAD is not fixed but rather dependent on %Fortunately situations like earthquakes, structural failures and other circumstances where rescue robots need to be employed are uncommon occurences. When such an operation is conducted, the main focus lies on the fast and safe rescue of any survivors from the hazardous environment, therefore it makes sense that data collection is not a priority. Paired with the rare occurences this leads to a lack of publicly available data of such situations. To improve any method, a large enough, diversified and high quality dataset is always necessary to provide a comprehensive evaluation. Additionally, in this work we evaluate a training based method, which increases the requirements on the data manifold, which makes it all the more complex to find a suitable dataset. In this chapter we will state the requirements we defined for the data, talk about the dataset that was chosen for this task, including some statistics and points of interest, as well as how it was preprocessed for the training and evaluation of the methods. -Situations such as earthquakes, structural failures, and other emergencies that require rescue robots are fortunately rare. When these operations do occur, the primary focus is on the rapid and safe rescue of survivors rather than on data collection. Consequently, there is a scarcity of publicly available data from such scenarios. To improve any method, however, a large, diverse, and high-quality dataset is essential for comprehensive evaluation. This challenge is further compounded in our work, as we evaluate a training-based approach that imposes even higher requirements on the data to enable training, making it difficult to find a suitable dataset. +Situations such as earthquakes, structural failures, and other emergencies that require rescue robots are fortunately rare. When these operations do occur, the primary focus is on the rapid and safe rescue of survivors rather than on data collection. Consequently, there is a scarcity of publicly available data from such scenarios. To improve any method, however, a large, diverse, and high-quality dataset is essential for comprehensive evaluation. This challenge is further compounded in our work, as we evaluate a training-based approach that imposes even higher demands on the data to enable training, making it difficult to find a suitable dataset. In this chapter, we outline the specific requirements we established for the data, describe the dataset selected for this task—including key statistics and notable features—and explain the preprocessing steps applied for training and evaluating the methods. @@ -576,9 +574,9 @@ Additionally, the dataset must be sufficiently large for training learning-based To evaluate how effectively a method can quantify LiDAR data degradation, we require a degradation label for each scan. Ideally, each scan would be assigned an analog value that correlates with the degree of degradation, but even a binary label—indicating whether a scan is degraded or not—would be useful. -Before identifying available options for labeling, it is essential to define what “degradation” means in the context of LiDAR scans and the resulting point clouds. LiDAR sensors combine multiple range measurements, taken nearly simultaneously, into a single point cloud with the sensor’s location as the reference point. In an ideal scenario, each measurement produces one point; however, in practice, various factors cause some measurements to be incomplete, resulting in missing points even under good conditions. Additionally, some measurements may return incorrect ranges. For example, when a measurement ray strikes an aerosol particle, it may register a shorter range than the distance to the next solid object. The combined effect of missing and erroneous measurements constitutes degradation. One could also argue that degradation includes the type or structure of errors and missing points, which in turn affects how the point cloud can be further processed. For instance, if aerosol particles are densely concentrated in a small region, they might be interpreted as a solid object which could indicate a high level of degradation, even if the overall number of erroneous measurements is lower when compared to a scan where aerosol particles are evenly distributed. In the latter case, outlier detection algorithms might easily remove the erroneous points, minimizing their impact on subsequent processing. Thus, defining data degradation for LiDAR scans is not straightforward. +Before identifying available options for labeling, it is essential to define what “degradation” means in the context of LiDAR scans and the resulting point clouds. LiDAR sensors combine multiple range measurements, taken nearly simultaneously, into a single point cloud with the sensor’s location as the reference point. In an ideal scenario, each measurement produces one point; however, in practice, various factors cause some measurements to be incomplete, resulting in missing points even under good conditions. Additionally, some measurements may return incorrect ranges. For example, when a measurement ray strikes an aerosol particle, it may register a shorter range than the distance to the next solid object. The combined effect of missing and erroneous measurements can be argued to constitute the scan's degradation. On the other hand, degradation could also include the type or structure of errors and missing points, which in turn affects how the point cloud can be processed further. For instance, if aerosol particles are densely concentrated in a small region, they might be interpreted as a solid object which could indicate a high level of degradation, even if the overall number of erroneous measurements is lower when compared to a scan where aerosol particles are evenly distributed. In the latter case, outlier detection algorithms might easily remove the erroneous points, minimizing their impact on subsequent processing. Thus, defining data degradation for LiDAR scans is not straightforward. -An alternative approach would be to establish an objective measurement of degradation. Since the degradation in our use case primarily arises from airborne particles, one might assume that directly measuring their concentration would allow us to assign an analog score that correlates with degradation. However, this approach is challenging to implement in practice. Sensors that measure airborne particle concentration and size typically do so only at the sensor’s immediate location, whereas the LiDAR emits measurement rays that traverse a wide field of view. This localized measurement might be sufficient if the aerosol distribution is uniform, but it does not capture variations in degradation across the entire point cloud. To our knowledge, no public dataset exists that meets our requirements while also including detailed data on aerosol particle density and size. +An alternative approach would be to establish an objective measurement of degradation. Since the degradation in our use case primarily arises from airborne particles, one might assume that directly measuring their concentration would allow us to assign an analog score that correlates with degradation. However, this approach is challenging to implement in practice. Sensors that measure airborne particle concentration and size typically do so only at the sensor’s immediate location, whereas lidar sensors emit measurement rays that traverse a wide field of view and distance. This localized measurement might be sufficient if the aerosol distribution is uniform, but it does not capture variations in degradation across the entire point cloud. To our knowledge, no public dataset exists that meets our requirements while also including detailed data on aerosol particle density and size. %For training purposes we generally do not require labels since the semi-supervised method may fall back to a unsupervised one if no labels are provided. To improve the method's performance it is possible to provide binary labels i.e., normal and anomalous-correlating to non-degraded and degraded respectively-but the amount of the provided training labels does not have to be large and can be handlabelled as is typical for semi-supervised methods, since they often work on mostly unlabeled data which is difficult or even impossible to fully label. @@ -619,7 +617,7 @@ We use data from the \emph{Ouster OS1-32} LiDAR sensor, which was configured to %During the measurement campaign 14 experiments were conducted, of which 10 did not contain the utilization of the artifical smoke machine and 4 which did contain the artifical degradation, henceforth refered to as normal and anomalous experiments respectively. During 13 of the experiments the sensor platform was in near constant movement (sometimes translation - sometimes rotation) with only 1 anomalous experiment having the sensor platform stationary. This means we do not have 2 stationary experiments to directly compare the data from a normal and an anomalous experiment, where the sensor platform was not moved, nonetheless the genereal experiments are similar enough for direct comparisons. During anomalous experiments the artifical smoke machine appears to have been running for some time before data collection, since in camera images and lidar data alike, the water vapor appears to be distributed quite evenly throughout the closer perimeter of the smoke machine. The stationary experiment is also unique in that the smoke machine is quite close to the sensor platform and actively produces new smoke, which is dense enough for the lidar data to see the surface of the newly produced water vapor as a solid object. -During the measurement campaign, 14 experiments were conducted—10 without the artificial smoke machine (hereafter referred to as normal experiments) and 4 with it (anomalous experiments). In 13 of these experiments, the sensor platform was in near-constant motion (either translating or rotating), with only one anomalous experiment conducted while the platform remained stationary. Although this means we do not have two stationary experiments for a direct comparison between normal and anomalous conditions, the overall experiments are similar enough to allow for meaningful comparisons. +During the measurement campaign, 14 experiments were conducted—10 without the artificial smoke machine (hereafter referred to as normal experiments) and 4 with it (anomalous experiments). In 13 of these experiments, the sensor platform was in near-constant motion (either translating or rotating), with only one anomalous experiment conducted while the platform remained stationary. Although this means we do not have two stationary experiments from the same exact position for a direct comparison between normal and anomalous conditions, the overall experiments are similar enough to allow for meaningful comparisons. In the anomalous experiments, the artificial smoke machine appears to have been running for some time before data collection began, as evidenced by both camera images and LiDAR data showing an even distribution of water vapor around the machine. The stationary experiment is particularly unique: the smoke machine was positioned very close to the sensor platform and was actively generating new, dense smoke, to the extent that the LiDAR registered the surface of the fresh water vapor as if it were a solid object. @@ -653,7 +651,7 @@ As we can see in figure~\ref{fig:data_missing_points}, the artifical smoke intro % In experiments with artifical smoke present, we observe many points in the point cloud very close to the sensor where there are no solid objects and therefore the points have to be produced by airborne particles from the artifical smoke. The phenomenon can be explained, in that the closer to the sensor an airborne particle is hit, the higher the chance of it reflecting the ray in a way the lidar can measure. In \ref{fig:particles_near_sensor} we see a box diagram depicting how significantly more measurements of the anomaly expirements produce a range smaller than 50 centimeters. Due to the sensor platform's setup and its paths taken during experiments we can conclude that any measurement with a range smaller than 50 centimeters has to be erroneous. While the amount of these returns near the sensor could most likely be used to estimate the sensor data quality while the sensor itself is located inside an environment containing airborne particles, this method would not allow to anticipate sensor data degradation before the sensor itself enters the affected area. Since lidar is used to sense the visible geometry from a distance, it would be desireable to quantify the data degradation of an area before the sensor itself enters it. Due to these reasons we did not use this phenomenon in our work. -In experiments with artificial smoke, we observe numerous points in the point cloud very close to the sensor, even though no solid objects exist at that range. These points are therefore generated by airborne particles in the artificial smoke. This phenomenon occurs because the closer an airborne particle is to the sensor, the higher the probability it reflects the laser beam in a measurable way. As shown in Figure~\ref{fig:particles_near_sensor}, a box diagram illustrates that significantly more measurements during these experiments report ranges shorter than 50 centimeters. Given the sensor platform's setup and its experimental trajectory, we conclude that any measurement with a range under 50 centimeters is erroneous. +In experiments with artificial smoke, we observe numerous points in the point cloud very close to the sensor, even though no solid objects exist at that range. These points are therefore generated by airborne particles in the artificial smoke. This phenomenon likely occurs because the closer an airborne particle is to the sensor, the higher the probability it reflects the laser beam in a measurable way. As shown in Figure~\ref{fig:particles_near_sensor}, a box diagram illustrates that significantly more measurements during these experiments report ranges shorter than 50 centimeters. Given the sensor platform's setup and its experimental trajectory, we conclude that any measurement with a range under 50 centimeters is erroneous. While the density of these near-sensor returns might be used to estimate data quality when the sensor is already in an environment with airborne particles, this method cannot anticipate data degradation before the sensor enters such an area. Since LiDAR is intended to capture visible geometry from a distance, it is preferable to quantify potential degradation of an area in advance. For these reasons, we did not incorporate this phenomenon into our subsequent analysis. diff --git a/thesis/bib/bibliography.bib b/thesis/bib/bibliography.bib index 9151d29..8961ecb 100755 --- a/thesis/bib/bibliography.bib +++ b/thesis/bib/bibliography.bib @@ -339,5 +339,34 @@ year = {1959}, month = jul, pages = {210–229}, +}, +@inproceedings{bg_ad_pointclouds_scans, + title = {Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors + }, + url = {http://dx.doi.org/10.1109/WACV56688.2023.00264}, + DOI = {10.1109/wacv56688.2023.00264}, + booktitle = {2023 IEEE/CVF Winter Conference on Applications of Computer + Vision (WACV)}, + publisher = {IEEE}, + author = {Bergmann, Paul and Sattlegger, David}, + year = {2023}, + month = jan, + pages = {2612–2622}, +}, + @article{bg_ad_pointclouds_poles, + title = {Automatic Detection and Classification of Pole-Like Objects in Urban + Point Cloud Data Using an Anomaly Detection Algorithm}, + volume = {7}, + ISSN = {2072-4292}, + url = {http://dx.doi.org/10.3390/rs71012680}, + DOI = {10.3390/rs71012680}, + number = {10}, + journal = {Remote Sensing}, + publisher = {MDPI AG}, + author = {Rodríguez-Cuenca, Borja and García-Cortés, Silverio and Ordóñez, + Celestino and Alonso, Maria}, + year = {2015}, + month = sep, + pages = {12680–12703}, } diff --git a/thesis/figures/ml_unsupervised_learning_placeholder.png b/thesis/figures/ml_unsupervised_learning_placeholder.png new file mode 100644 index 0000000000000000000000000000000000000000..075cfc05e515c3d1d842888d704c71e44b156257 GIT binary patch literal 160786 zcmeAS@N?(olHy`uVBq!ia0y~yV6I?bVD#Z&V_;yIDJ6G@fq{V~+0!|Ik(YsSPNuaH z0|NtNage(c!@6@aFBupV7(87ZLn`LH*;~FR)phEN|FNN4zgs@PcY9(FNAD80Su(sF zN?MsBqN2sKB;D)#j6YYN+jDVdrC(8+%<+r!e+95JcciGSZea1;)^x$6?^160Ws|vi z_X`f)+r8?ZJjkTBJgE%E+rK{D{Ic`;n}FSqqE?5k6?(r{U8vJVX`+V;h}!>sg}5~% zlmnt}+PJXlgJeLQPM2*0i<-m{%A+{~4|c;fPtk)Wj2FP9Y!QJdYG^MXd^m zDImd3tpcKZAeMpzZ#s2w#etmw;&tXI(#+a~xHl{=|1K0x{?}*L4s*bhokB}r!Z<2I z6uZWZf8Y1QqL?!tDc(m7ckc85s|E_g^K);kc2hb(Z-=i_%IAlSE7!24mcQ|qZrbrL zf91KVH11~Z^iZxPU-sSI@>+SK__R&O{8EDc{ym(Sv7jlIn#jUkYX? zKdF3}a7p1&!8(TLhaSpy==*P~;Ic{)`LXHK$tBGNw(IsB`!1)zz*>3H>4V6QjH}&y zUTFAl-}UU;;(!~Q&WTNZd2?R}XU)ZeyZ@UE_#T|p+_k?d|KQI!xzee-3+5etwD-N7 z@Q0RvM|bCmU$i|Qxq&r8{9Sge#j3nxw+dq4IL2K{am}!}=4`i+cWSEo1k>mTI`_ox zzL#~CQM8#5dE)b@{tNRSd|!DjJlAB3dPULn#`(7vawTwk-#hnvA8*m|7VBNS*SmC1 zpZHwEyx%BL<>Termmfk+Q$AHrJi*=lLvwMO%BGhV_tRA;6mj*-yl6OG&{Ix6jq|5RC+e zPcrLYSFm<@MRFT87xOI@xt6xH=AtoI1HbX1qyw6}{x)CQ>+bWSk88pzJ+Y_ZOp_X} zKU}@#UjFVrm$-mMDKeFDU&`0tYo09QD;>eRO4e`17dw*)N>>EiJXU`FFY#`<$hBt~ za~U2Vuv*}|Vin&Kj%k%slTy?S+9P_E^|dBH>6xWrAl6lSr|j#@n97^2OT^0N@7Gt~ z|M>8kx!dhK3o3HH8&=kPm@ts3#3TxB>iG}|)RE?t>B%Ai|88K98XtYn9E+gjO z=A7)g@xir^pXb-j?>=YEoomZ2CUYd(|F_2GGD`ss0b3ToQ;Mml^TKDlNk<%>YaV}O zs(3uZwuJkC`5!zn-`{_1-Fl{Q{&%Bg5#q}FLWOMlpZ?6;z<2C&p6|DQRh9M(4QTDXUWU&qsv?OD;O-F7D)9^cb^ zK{Hz|`odwId5`*9?H}GT{@1!o-hKC_g_kR$TpQ(PoLp}A*D`L~?Z5*UxW6u&c;d^H zT!qcku5gHCTmJ2y|M2ATyv56mYTmsRQD~0-e9-?7Z?#N;jlqvaYCp^UpDwx^JwJ)t z@wC;xZ#Tai{rZycp}M0W+D6Rzn8N>xW0eZl&KDVUg+=zPG_EMoeZqHOXTsL-$2G4G z=P%V;oDt=r`9yQ_g}lsXZ>t36|9K<6z)YPhK|fH2&r#skgtZT6$N#gpsk-lbCT~jK zg)qZ3=|4Z?{|oEi|1R;N+0lYMKsti^H~Ue8`@hcHr{7dAPuyhI>ykWo(Ob43AJqTN ztYnwtefi*hXXD~Iy+;Z^_n&*}KK&2B=GlZZj9jV_^B>hT^Vj`2ANgTc@W*osvERGw ze6OV~n0;sShpcl}kG&-_AF1APH^>OuH0`16`=7#n7BBZ6IKXzvY4MGxcMM2~Wb zklZDk=N(CZ5M2@eb1UcHOHl%kY&fT}c++M=ufe`7 z&Qf!?v%QmVsU7Q`e4{WcZ^|s$w3GRDyz5*yu!g=9U6}WS>4IF$WOe!d?T)7B7GxQ# z%q>_UR%(B2LEfgSqsn_<@0p*LJ8$W`*$)+DOwCU%$V%=iHCYn5tH4c3pRc~7HX)_h zFm+?0VvGtE&PyWKa&XxTE*HWi%d~%U}A&v7mR7S(}V*-!AU)y)VcBlS7?`}FRZt?B- zcjJ2|moW2zvgLD3EVi$9Ey~inz&9k>Z+vlR}RF=AW3s2h<2hlCQe#b3} zcw0YNJS{lY6tQXnYm@W5gB`}9JC$vkd0hJ*1fEm&6Ii}$-90~!+H2kGp7;uLs0qz5 zU=Eh@w9!z{ST3NRA=9=<|At@bkv}Z~=eZl592J{H4{9A;=fybAsnRz;yXNt;MfnD=+FIs+dGp+&CGTHj`J{lK zIiHel8C*R7`R94X`gtEuoqRcGN|^cGO6l55SDu$O|ML)JId$q(j_&REJEZ-BwCoRW zU=!tul&=^ z<<;#@8-5I3wygY7z3{us-}{8WE5F{}ljreZrd!LM8JA4%=3kx{y;SANah9b!-p^IH zsSL9FDqgzd*4Mgkll^9d@J;?)a_HyN{SOU=cON@>Uc10&?Nh#s4eN~GKQK4^-;k^z zK7~1-=kYy*7@iN?zW=j4p|c@XxJ#N8y3A^R=eHde-Ez)^9;o@%NG^jEFWy$Q8M8SvsliulV{BKyk1=ItuNp< zQ*Zr>ZP!*-S;yDDdbj!16cK+Lvp;8#te%rB^ZEe1e zE93T?{$Jp1`DR110GmgTWA}n17dCOK&-=DK#i-+}<~`v)BUj;5i=)d}6LW3{_~j=3 zzqoY&yZjfrt8;x;tqn=IyJ@M4+vAcCT>(M6!mAAYGBTRAxaL*7@N;6hn|bX3FW<+_ z^JASSZeLcrtvK|gMVQS;j!WUy%c|QIrcaqCb;*1RhhnnwMDflQ4_xP2U;S71w=l?S zPK#uBx_f=;oOPGy>*)H3h^Q@DU7!24CF_AKzS|CVM&dioTD9+K#1PcS`ulPFU@q^=Rk$$rCQUEMLyWG+}ncslVsv zs9eZaW7&Am;4beL^?R#-=f_L>-`CvrsdAmouk(7n(tZlsrv&#O`)&7A(y!+B?+jy? z%e# zKJ=G)fz5KovZmATul&CJee=sYzNdB@?_6=qo-+H{zS%zJ{}0U#`TnB(*K6lf?^o?I z(tNMBY*qQZ)3rCA?paZI>;L!2KKrL8$NnlL*LCdWx9Qsd=XU+#eP7ot4X~^H^Fm%e zren#g-?uxoFWbf5%)QgPOKVXa&x?H9(?8ctC9^X6r(&WljUyn>Y(d~Q3L1$Ct#|2xQTt1x3 z|E62E=X-4S;_r4lj(_D}GMPa^E!Ni>g%2=u8FVplJw2*yp{J~_B&>;cjqUcs{Qj4!fM~mbN8406p***?W!d{Rm~IR zr!L6X^jdgm!SA~HI(5GD<)tf@cX2-d&dE{xa<$#mW0fzo0-xRvla8ETU)IV#QzNG2 zeKc1`r1{^j2P;JWO{-&#`?`E_Rq}0V4Q*Oh*vdxm$ zuYSE1xwOLP&%WnE7Lgy;*6E+0_i0|J@2mW?5AS*fA`+aEb zb^R0E!lE3@%>vdv?U`;-HT(Q!^X~Au#w-7p-akL}?^~Bttpv3x!J*Zw^KJM76Wz2< z-(IqeFORQ%?vLX#WtZF!r+qy&Wz&Agl`~VDPH7f~?pwHiv5myaTkEv$FTbNPSF5(R z(q`$u6)W>^cxOnc@A@hKOE>mwxKXCs)Okr9tJcdLnp+zFll%B*p$kVE)^EQ5`rgqx z^*R-s9dp~)3SQxP^|boOE87Jzr^2Qr&pPO7>9k|tCh=2c_qHE2&y?_1>z_aQ*gCn{ zX+bZ(6{p5V|9g^uvGW0!_wL{c*FsjNus&TodAEY{3pM^bg~GpO_8RZKdDlSr`;Wul zALY31o;*=%??F$qgT{8-*o6AaB_s7zwnn`$e|#k7$@hj84_xDR<#a8$Cb~g^BOzJC z>dT#fTIT&N8w9hwI?h?LmHayAdGK|?I{j7#9*(;}pN!s!?14wdN6 zyZWAMh2Wv1)16#P@2}f%g(W^xT6_QAPgX$%TfLHBFLt=7a-@!L#XF7|{`YT0I;I?| zVKX`ST;rv9B+sm$8I0BU#)nS3 zs^j37zs+&#b(M-!Ts(ZD6z zcQi%#f_EkCDl*dznUcQk%l;WVJpX^2%$WP(s@m}>w<7l+TITh1#jEyJKNqg_I&vgE z?Cpl4#q$;gPA}bY=dk~+jF$^mTRrxT)IV+4>-OVK?alvNoqpw-US8@HyH><zMG)X_zFqZtt6tb^Bi_ZF!sEH94tKF}U>K zv-kgdbDzt0o@Ni|oRY1o^YcXh&olA+rnkv!Ulu-eHhtf@gYNSV?Ed#9{~+%aFSlb` z?QJGYulr?Zddz{9^=P%fvH#EY@Bc|m&Ew_S{9>DS@8Wg{%sE`GC~Wc7cDZ5t z@9+(u>)ac28|I0gN;%XM^K(6SaEh$aocxOd{3R7n`m!VT{ZL%D?-5rT?=p?olDTC9 zwg-0K`_8!SUZ#K9jo$`S&NSIDXH{IZh<)WDx8U&N{l5(F|9(~hH|Ie57 zn|bTa7Z@y+o~q5dor&xCT=TetN5$v%eR?bs>6SD}VEx52DfbWiJ!-E1!x?6`Yl8m& z=l02;3XhZ)=pEN?UCF!Q{K554x7h!5Hz?k?uKAMG!3o==RgN{uCcaGGzB%pc<2m); zB4?~qlG(DNc_K8@uuMkgJp7AjoJq1zI=T*_mjlK#@p*sk6v=$ z`D~T;Ov4#L#%*cF%X3ZN*Zp^&vH7s}jmr7X4(ClmsSV)&;1 zLg1dy$^QeS9yrC9zvrD^aB${*rBcVr&9^3cAG#y^?cwGB-%L+TTJWOB_F(dN-6xN{ z^%qRu`l7@r=i$u#znS_ft{T26{_#2?fv(mK%X#O_hkLK(9&X%Sf2{KPywf$%A z@14l2mSxyn)^e=OBK_3X#@hFn%ujzmvm-$#Xx7rx(-lrJIt5xxxoGiGW3d4HIc_d* zt-jx4ch5=tMf0EJY1%Z;IbF8jro`M>n)7CaHcv29ubbCy+rqu`j%`l)s64^^;2D>i zrCrmFFX~tQ7wOEIv*LlPnLN|^yugjOGTiS+bE}64eyjPp_kCPM{i#36 z_dAP9=WvG|sM^bCVRh4D>y?Xf{|u(b6tI22_qjO4@LU3KkW44P;>x31aywp!$;JHe zw%V!W{PCUrKZ|PFGNY}HQ9GLy+)rz)?3pxS;xsOIH7Qj~&BqUZvCq%?X0ZI6MCq|z zdbO<$6DD6`*>vgBx`W~pR#zkzAGCPHy{E<0dMlg4;S}%bpZ3bvOik^Ucj{fgylwF^ zlh(~wUU5$U_rO|Y*TF`2nX@b3|FpQGvt;VkIqL%EZMW7~dqHcVn{ak`;nS(&g?~e* zU;f~mrL}ya)sAZ#`wGs4v>kdLQ~I!6GB>;IR;m8Izx(=)($_m5Q00))yl%zfs-T>@ zrRKX>RE)%b!yPg{8>LeC_V4<3Jmy35dgILx7oL#3&}3e4#;|?zcA4#W%h-809uz&t zE#_)0{rsQn_Dy%^t!I^dQ!K8ld*E2%^Fyx#=5FP=qI=I`&FcoCqSuzcRwz6D3Tew; z@A#9?v`|9##-(P>g`5!uPOI1tKVRb+6x_4EqJjJTPqFWJKYL4go@@A$7Co0)wTu1z zFH8P=TPO5|KKb{0&*xhC3;4U2Ejy{M(Sxb;)zOSWr=Qcv&vb*g*kyROqKR-2Vh zHC}P+#WjgVqH5)5e57Nl-kD3j%_yrpT66FBKl`-RKih@UY|I+ijTao~{dD1w_K$z% z`;V=0bT>3R7V~&xW%rrtNh%Ky8Sih*JM(nO_L`P(`R`Fhw-;&Xc*X~G+^bqPol7{D z&w2Cd05`{K(e3|UFsM| z%ev2R7EeHmuZr&dTii}^X{-Kl*zf+9q__V?&NHp{+A$BEMySTd`f$xNV}-`JO@SX^WHOk>wi4R;HcX^PPj0^RbGNSM02VrI8K>KV-Jl zN`29Jx8qyZIm_SKJZh4>ng)DXr#76;xm;Rkvc)5{XO_JB(aHUNMj^8s&mC8gXPy3e zb@uuv?c(*b7gn`j+3FF~$R@=#uj-B6xwf0qVm3AmCU&rgO_s`Tm=99qlx%GVSe_c2p@!^&E!%(Rh@ui zBJO|sx3&vpOM01Zn;LwXvvTvrFmWOey;iGXX}yW~|r<_aw^wmP-u7tfSf z{xVsWuG{rBhSTR)TRD5q-ZE#aKkFK?Fx|cV@-^SgPr zWAL39_ebGT)D4@%DpId)&K+Jev$@3T_3mh;DXpi2wWqNi72uRx|K(Y^+-|Yau)R6{XW4-VF&AZ*WMwu#yZpWQ zSp8qwv!UKIvSl(HV>);;POpesw_%50_pa?cSq`E8|8O*iukNq)sqY+)@>_yy zvtN33@8f?x_1E<)7FCU|hwKuBVxAs4b!39}A}{fsr+8O<*)&I_&GEWPrTXFj&-DI1 z{v3aBwc4pNkDfzfOvfgyXenFXYS^VD{d8UQ`qYz$`9H1v|Mk3zzIDfgZKCgKkvnrFo7c4pwu?-2i)|Lyk$bIsOCu+J3R~A!Z?VE(`~QmO*MD!H zQGcd-!9HcK{yFsF<+Y6}i){*D?~JK?$e*E-JL@c8=QWdJgI&k& zye&(cZ_EFr?e;s?t6b;8_1KeOq2|V<>!Esw7ZvVwSCw*+h^~^q|L52J&EHlY zJ!9B4D~N?(rByusTtZcj+@18`WQV6QB@ee-M5cW>^|*}9#%<?}XrKFj`B%4F zHm%(gsI9`hy{~n8ZGZOqzlz8DFH4@DIWeQ=_~W?~OiWsfb7H+ERwSN-$~ z^+XF%{iW=imNqJHmpm>1pY{LGpYE1lW96SVEWXdydT2&t!RbqrMdKT^cKn$A-+q70 z58*U*%Waq4j!d3mwJrDJfddIn>e&zPSWKVuKlIhFOqXLP=DI3MTwJ<1`9@n)(Xqw$ zm)8_Mxi#6c|6@Q0)A|ed94|fmcw6turtWiT-zF@#y?2a9ZA&z(pK8wTzkLgWs`A>z zH0P&_h(z{z3SG!u_jkVjr|#(dqze&OcDQD;KPqJF(MT~#KDS`mOSc_=n(~u`4mX9* zZ&F+6y#A2ofvSGBFPVOoYbspCBj&RE-_Ww06cDgDVAiw}rvMf4DK8qUxON>?z5gTp z-JhqrXXfS>&gCmjF1Tj6d16pRcd_oC*8!g;#cRH=F4^;V!u5TU;@ht9377k^mWNuO zYK{MCEf-V5efyg2+A=@(e)kp2xuR1f3~wx2kj5iEznE=#S(xGSc^jR$)-=4mt>seL ze?qObZ&uqs!K6- zd~f1!rHaa~30aEgqj;`liyY+;pZ8zaPx4md-+l|jJu|P{vgS`t{~)r^urh3Y1Yc6& zxrL_;H{R9CxWaZLf4}q3x0_y{{H*52y8PCegZc9-ro8=LXF8!-f5+eH=8Ef@#oLSI z7K?guvdbCFmyh2(Vac2OG7S~Sj$NC)KHk-+e7fh(JMV*}JNKAWW=i@fNAq0n%(+`? ze)ntqI_cW1OEYVa8wai}4qOnk^3G3#=tVZ3cLV%QkEP%FfBE#zm&>vPjr=BYO;RaY zGhv~?+KW*VQXUhO+l;ulSl83w&hs{Z3#3xKBZ1N z%p`Yd#$pGdODab-+^3le&YswBelz>}-4}WRP76=*&QNzN`Yzm*I;DE&x3w>4yt<`U z7qs{tf4ZJxM92GXwHaHvHMsVDJ-dF8g1&;p~JYNiUhj z{{N@FpYxA3V?FQdovV&_svDXLU0wF`%Hu!h>;GzN%kAmkl^=LLQ90XiR;lm#Uww%; zmOk0)I7`lhb+PWFs3mzlr}b?nA1#mNo~zDTc(GdFI`L?brU{2!S5M7Rp>w~!NiNx9 zc+Y5xRKc{UvkGp(^LO&T*FA@~s2+d5U++Jo^6F_u z3%Fk;DV}%Q;wf+TvMlc5R=4Gvahk_&<$hYzy4jcSM!md^ShuR8<7=kLUBf-(sAWi)6HXCGxnEE4}9NTwK=YFI>aq`N(6bb93RkT|ac>;!2eFZRYzRBE04{ zU&f~cy3;>S);@PI^{|PM_bc6X8X4P+Cq?o4I6Yi&_ne_u!ObeYy)T&D!q)5dD&~kS z`=&U%KQ1==@GkWqx5EE5n)=&yWb+#r8(h&`o&6-Mq0s)ojO+^~rbW`PoRkHnmMwU8 zt@z~5|A+UQ$FW`F+dgH1#KYo(+`6xei+4W%CY^a<**dOmvt|YbC(Px2*AR6%NBoME zX0x-Vnf%i|oA)0-@jSe1)905;#5cZMxA$wJ*k#k5 z&u4L07F=Abk~e3KrQ0Hfi%!cYKiG`=jn5;EU=%VP1!ON+Nmc;J~knSI^v9&53<(+xvA)n zi?)lSZs3!(Vy@PQ%Z}}MvgiE;x!6dlrSn!hsVGPuejWC3t#i!Q?{n2XdHK#Bcq4nG z_I$0!>r$7dYW;N&{>9(toSV4nl>GZHDI;Pt%Ws+Cs&hNeuFzD> z?=_ymaY`)Y^{Gu|j)7~^ZYGy+e9m~AiSw3M>XXBb!80WybYtAeI@fPVh?C}d~ z3LJwRlA0CP<(O`;cCmS6doS8Xtni>|u;P^o3krIB0yJJ&v`(60Sa`!GeVy5kJ4PYb zw;V4D%KdO{q0sqF>he$b&Hq1zb-lG{%7nBqg9+C-82PRheS7)eabuOK@zg~b&qbm> zcs8B6(bd22x&DpXgMt&TWv-1qC9j$SFryW^HNr&hOXvD;!-Mc<^%M)Z1(w z6Dpn8vAk!^=e}gZYaHrzBlY`T$s1+X4vSao?cLe*zV`3^OuN4#&K#9_f@>u*quHM2 z9i3nEXZ_8e2d+EZTWI-5WqRD7T)7>;r}JdCm*?ipOYRmtXZ_gzXS@Dewv%!hwwuM@ z9ecjxVd|XnZ~s+2549bDNTRc^lv+?AoepvX=Bw`q7>1=~s!!-|mOieg=Tho$>X zIiIl2y&|!h)$IIA^{zcvmrX5q;!z82tGOiCeK@@Ew%{KA>?tM>ty2}hO8H*Ao4@7m z$)7jBnlC84;peDp_$1(*(aH^Mx@(z!n|N{=v~q2p#`H+{mdKW4(+e-Era#P@XX6`b zeNWAlcZ=kqEdR~6Jr@t&W)!{EmRsr&w)xS;-8UaTn7&wY$*hU1jy0ZY5WVw-H9d5v zy#N2G4>lTS_HpR_3utTC%IMd5>^|MLC(KD*ylC>Jmm*iBO^_|UX|;w!#IHpeuKq;JjI+O^HQ@YIB*oI4xx zt6!<5`W8P^R)KmFCzc23 zOPPdi6O|@TR{||juw$8E&~0YPv`kxcT3xi#m-erE`4_L}=hcWWFK`QO{ayQLE?3=G zzXLlJVs0;zWn;;&c)fCY(Tl?6O;SwiI(z=qtlRg{{zBjPiv&bh? zXo?o^+Kr|+_K3!`dVN=U?)2bA@V%dAd{!T0FKk>O-D9(HMr!x_r*Guv_**4wm)(0E zpkbnNP}^H$!?mCYZ!NjE)m#qs_sUvd|C3p9P4iOmOP<+o?fX~vhVMRSF`0!eTQ*A4 zYUhUQO@A$aF4=CJ{M~jzSbNS4>-9VP=EoFC&Xhfz5z8f`_hh9=Oy$v^Iu^frD-5q( zZk*u1@9?7eac8=g@*6fQ?FgTy=O`Qh+<5-aa;a!phly7WO)}2RJ<9&?&E}ZWcQ5ah zoPB!6tMSg_y+5`v!cD8+C0Y^_l)7L!?Cj#%zY+kkQN>*2N{l<{qrY-g}sz(7t-#;aREt3qC1vguk8B7&Z5}eC&}QUF{Ng9(rUg zW9!-Q;@0U4Pc$}K99p(*?VU#t?09YfqkAyyo>u_N9~T zugR#rH(4nie{Fw)fahf?^?5Z+zxVvS%VHjQ{=*~nh;45S&;9#nsnVHvzd4RIgNtj4 zz?Pok^M~edD*BmxWsj@(%X_ax{FeUtn*P7{U@kwSHH+t=17^2B-|MfPmaX?g%zpPT zp|lwf-eeb4*dI$3pL6i`zc-(IcA7D-V$);JEI$1;eBy+}QyP=F{FgsA=v;PHu+QRG zsZ9ByXo(w%;TK9HK8u*&DY3Nwdona4`hrJm&gPsSrnUz|D?hFIv3bF5anS|GemvD* zpZN8%e?rdeS&Xx%x3#4-?Ekx5KPhbw)9SRxwFl=+mp@Z&w^RCh&42GZRd@RZG(AL0 zy7*RReq1a+|Fow3FKwIBBdHIf?o?l2n_(0bUoyKcuwqhG@3M8DS1s;;`s4au$(wcR z0b;+e6xEfz_5bnnta(Dn>_t}(XM4JqoBVp7T90t8>qFah>)!`WtzCWIb$fZy{O|7N z-!3&rTw4?88kB!wqv^fB^Y}Oa|G0cgS8u`V)b!7byU!=5DK89W*&f{N+IhU<_=^w0 z4u0=uN$@NZDgXD%swZ!fhWEsqMGlv@6!|9?@U`!I)hko{hVx3?KIVW4wqI4Q|NCK7 zS9iJ8<55%fuJ3p2_C$S--fMh5^X#pVT{|P+ao?0q57kfbC_nS=r@z$Nf^&vuRzBLB zUmUbj-}6+Z&*q(Mz9&b? z$!$@M(1yl`rT*X5#82~Ii#p~Wm9zb^&9U^YC%IccJ_tTo-Cdk3x8t+ex5}^b9}n1; zD=5l{ovYTFb+Iq$d~ILC(csexo~IbR_PQ@Quq$-+i>(@Jd9lKsds;fV;+|9*UNv0y z{L|x87WNJFRT>C35(2ZaqoHa=%(+wP>^yJ7##FH1`2YVcXTNJ!wjlEz$`_HKvr?>&!9 z|NNG=J83#S?$nvN&zx^Dtdf-J4dPmRW%H+`%6)m6d>UJtqIzS?Ehm)!znSiMp0BdG z=}W52C->i*4sZMX^P2g;&RttBo>P<)T3xUxqi@Z#?fm!7o#VdO!EkO{z}&=jd;fW5 zt>l&#{e5ZSF=;=mf3_yi^cd0>1o^Ue7dD0IKj&RvZ*Cqd+miUaIeLY*PWj!v9g~lT zElxXgp7(s;cM@|(tP5@-nx6L`kO7EYx=C7t<|YG`&#j$~U#7;v$qC28WD3tn zbNtqHGX0cavN`&t^$E$GGl!P+3LJ5c3E-KVcDCZ&ALcmb98r-wC48I9Z+70?Eq6}5 zuSz~V{*!Z@Sw3R`|F#Nd5#PF^uly%J1!f6dV`?om<*YCH^jqRimi+|BJ(qr*;*B`_ zc*pg*$9(N~a=lRCSfo&{`)<$Y=X35vdEc55cx{%TKcD?Z_hu$%Ei z)8liGaLWG>Ss{5KpyOZg{jTKuyTqgO_ezV;{VTdAKY3odyy4EB5kF&jvRHRqy;E}c zY00g}8E-ErMd(LN{%}m#Uv2JJqoUbUsuxHe`X*|bZ}l-GZ}-FHBG)FRN*>Fox%cEc zcl{~N{CaDnMnb|yy(NM z4;n5-GO{+61&PIS$_v+)Te0r4JCP~>SNfaXpO%8T42vxPoPD3{TFlG6{=XsflO=UY zn(Jz^RI4p+Z&&TLDK6;CtPk(dHs3sLgN(zLWjEW(_dHg9Q~##Ad7`q9=jU0$|9U2x zzW(u3_j+KqMvnSn?++4&Zkw~NW*t!WdYIdILojdOPqmzj2entI&nip2xM<~4-ngH$ zge|}Qt>>*1h+g9^?YisjwK;zl-o07X9=qewq+-v%75UlSoSyaT=2oZ1Ox1L|mcApa z>(tV@5B47Gy6{HCBex^?{%>)eil?0p%*VJrg8FJM|32wBRKyWM`NK|xON_@<}cO^F*%g)Px$ zcTv($UF2Pu@;QjlXa8zb!+XCkJ-B6jcbb-DFdM&o&#@Z<4-I_VEk3;1-kjsSd+wu4 zYnu+NZ@=-q!FlCXcCYH99oyA*%;{Md>0KTo*tjh<2=FKKbcgpK8h)6L4*0;ug!0EKA0Nv`flxonq}(@Z)#-yDm6VXq`n~N@UOIUAM>mE zdG^V?vTnL3by_Du&!AnF-?s1izIR_!maY!p@Q+=5nqPWP>FUE$JHxU?mWuAL{K6P@ zwsgy;k43rxl7S*O%Fo|DV197D%f?x=q8q~&Pv{T4U1t4kf0FnSZmw1d)=q^}#n%_b zH=S;py-X!TIYasGR*SoT&KJ9Am(8wckpF-G|GB2c{*5Kp0k<1-nBS`G$ly|FtNmWj zYn=AJ<4RVd?zxJ-ivHr8F|BxBMRevqj@_4`KY`oo!( z$9LpU+NpM0%>Kx)hszJ9-~IEQ<@DdW&)+$I&R^>g(V3)rg5$~I7i+hty}$dMb^A_( zwatbPa%QvF)v6y$b(9QtsOEir-NyHk?Wv1%OQ&5)c;!5&;Fh|>HdbrqjE0rY$=Lz7 zH~+u5+^GEc^uXB{XPEeZ7Fs;($E2pE{CAFi*d=;K#-q7=aj9a|vd=QR-rsYW?6N)J zW>Esmn^zy+hcUm|_u5Zm>5A*YIS&mUW%RClyf6MP+tSTnel6`cFxqBzB{lx*!g<@i zM+86r5p36#&)amSF-bwjh&@HGegDUhZ8sCu4VE@NZ!SE&BmK_N4LR(4zfDeOU1YNR zZK;C%|NHR?2L;t1-!VI|t>PI|G~;H$tOvGQff>3Q!c1JMrHU(C8{B&vXTGVuv9TiU z@yyc|7Y_up+fHuotKfavv+$p2dPO7C`CX-lAIxuEn(aL0Yeco?Vp%R(?#t%c)jOX*t&$A3SH)vuc`uC z>|zb8uYHsGeeFBrX2-0I&AL0K5B!W=Q1;|R^8J%%ZtBlAs{8YfWz!{%t)6-p_Zk(- z38h|8OZ>JbH=^JPXF}NlL*cAwXDjweir;QMcUTjgTKz6|{gkAqr>3q@Sy*uX-lWAB zQ*Yh=Q}*$3%Tu{2>ogZOs%4&fGxrzyWV_X{buG04mTzJ&__IRDaOhwo3}Z= zX5l($9nYuxaQ`98w(GpkfdR%{Ih%OnIL)*#M4i~I!|_Y$>7uNcuL_i^4u{>%+mYkZ z6AzlsRdkdEoyb~{!5R_o$Eu0yN%XWN8l@2=9b=X+IJASwU* zNc^X#=j+*YS)d=jso7KRHmz zx9NaFs7>pN=stv8-h7jjZ))z@A$hc$dlML3sg_Me9{=eIRV z#x;w{)-cC$7T$R)|4t?8)3rTMPdwi7>r!z?h~JX~R?T63NA+zFzkj!T>f2{B2bB5m zJ&TqzQF77qjMh}TBoX<1fpQ-+TjP?5fW6mmcm`fge&KgF&};r-X-S`R?RNh%|2@r~ z&&adWv$NH?d&2w7}TKGm}z_?@xHTz4;ypo%nNF&Vomq$zD>xV zynwY*^*U#g(Z8?R^S?j7uRYVEbJel^t&<)s(P7c-Hjvz3{l@W`Tm?_+jIW=jiwT_G z^uTf91ceQjGDSBM17`P~eZ7EnU5>Hh>Gj&rOC&+ zxA$mL^)^m=&Kln1Jn`fD|KHbpwjSc>T`QGc{-O0xZE2WlO`P4{NrQ&#eJpN#|NGcF3OywuXYD_QB__V|fUf)=bj-zgk)G3)t)%y5?zwTARNA>YUbkKb$bX-~pja*2JvAUU%qGkuXJWtZDKEFDncVl298W3D*^{v_ zVWP$Io7L|QE?`%<6maFi)Q$1q)6U#tn%vm2$NW;5R)nGZW*+6+9*UJepQ_%QANg&k zeox7}8XsCj`&jeZBEc)n8%Pk|m!{DW0?6w?;cEYR&5u zy~BCC-40xx_G$i$y27QC9@k$rO8a*2vqQFw^JfWt{PNbbS4+sF=EVL9O*-czzI<}pG(BErmRaVN z1lIo^54QTwSlHO>adF#$B_&pxQT=n{D)S1UjE#q5?7oV}yZFxXoNd)+<#cU@s^G*^it(OL!aiJBj5)4_T}(<=7>Q1uW)R_wuBfhJ2b-yPL<`=2Wid zQ$+Vg-FY-!%<*2E4Xfq}D_tqimXoy+Q}i!92zZilQBhF&O6J9qyWw-EUddQESD%Sl z#H+(O^Wdt7sXs0_=uZr>v^d&Xt6m4$RrHEVPtO)lYe`R;iO>4V2;6%g&9Nwpw{TWS zqWufC=r<ymKmv}9NCx*zl9KOKJm-+2Dt6EAJb z9=9&&+Qxa5ZR%#*w`N|++nqU@r{xM+R{e2bv9XEezA$fg_p2{)CqjZQ#BG#0@%PX2 zw#@AvT`ymK5S8w2=__^F%J?E;NsvW~>H1yQ9g<_4in~58JCPYh*{) z^!Rp{iOHFPDJol5ZtPOi&e$|(mV~09uF&)1S5w};yZAgTQcN%A!dY=)%exV>pnFfof!Un`5G6I*Za;Nm)m-AMPHEAMCqv9_ZPpF@6*{c&5+Hp zI78~hqV|-^+{QhVe>(*lDXuh?%>OsNHE~tU&TuL7k6$y&gQApW*EE{%&5SOPdd?E~ zRC5;pJ(kb~dDXi-|pcvFoCvU&Cadn>kg5r(NFcIsQ)~ zl=(HU!6nDd3xD2Jo$hptE%{_|dl1*s?3|r<{T9q}I5aIfzhC!uaK&2b_M^9YRK3MF z+G)EheE6-RQPIe|C?n`XzoE}O6N`7xvptU-YVCILn#3tyGk?P0Bk$+Qd=?Kh5iC2W z$S(D`es|R}i&xBsg^OM+k=+vTKuIZFxoFY);0Y7Ow7D6*Ed-8*|2fj9dnrM52g{R? zv^PZ(^M5}(I_FoX{>H28^3|qJe)+^O>gtK&_q?Y*iRD$Oo~@Zt|NFWAhxq$8(r#jp zX2vt+%ou<u6w(VzxLwfZr>u5Y_j`}k+{Tx6t*1Zn6um^ zLKCj-@A`M?SmcohX)+f76QXA7Zi@?hz4=b@{j)aJ=cjI&rmxJFwbAX^EFE)~!d}}n zd5)7J8@MJ*_MByGHr!WmPD=A@#>#>$uIM)v7WF@$$`{^pw?9A4`h0qX*+N4X?du+~ z%f*gPkiK-yz$pG)<^8`#;x%t`Bk3ak}AknyKZz>hcek9fuyK^i4kY+{Dr`Nw%{zRFOBI zyXrR<4iUk~jm61l!Sn@77> zlkMf+j8>yOhUWeJf|e_`ytw)6R^P{L6Xit_lhQS#Dt!HRNnM&&9Pnt#;SBrfIXmlu z*C$ znfs=eoJYFNpUA+Wcl}yl$lE zV!RlhZ)1q^ZUhda@CFuO8YtHRC>ho)+lzcQk5^TD$=cBIBDWmIbF6;}V zY<@jh?E2gUNB$*DqF!3#v>s#~Vq`|q2!;;M3ryYf=Do5E=!vSBNqRIDkm zn|dK~j>eKzPJBg|m?{%1%PrUp4$Lv1e_+l}cjszD|NG^}r>E;b*tL3n!cA{|ft_-5P5yGClN4JwAWJ1QDnBe5HNjlE+pXWpQ&a zkM4ez&2%6_OuvTHqx*R1`Gm0Zn`IoOwT)ZeR@t?-YsV*zUl z?j3ktEzH$f%DHTY@|Vt)n=H<+Yk0lBSz$Wwrck@g`~ABeqn;mTKHehl$)=v`X0@ql zhv90AcBh@%A_2EIhcEr}L%!yP;hmzx`X^j>M~Sd*C^=Xh^YL=`!KWUKZ^OLS1|}b| z`gW%_-|Ti?xdM}{a*vMG)3OUzPDh0w2Yl=H{ix}yx-Y3975Ae^p~YET zY0dW~Tt!NAE=N49-r{*Gj7OxY_a&FbkM|N+pFDji65t`)oGYlxYxKB-Ykhg;epjzc z@7A@hq69y!ntGq-B5dAzMO)TfmYuHDB60t4u&Ca756@|O zb)0t$Zp=_h+Y@2joop^EwtvqA4^Ef3meXQ!=IW~!zqOn#r=M7Uq3geDvvcr?ur*7} zOt_sRCmfpoP$T5}JBt&ClHbOf-&0UfSt)oWi}`U+%EDKcotu&#SFgCX;Z15}Tt&d? z{^`aW_8Toa^gZhJ>IUu!r3OasuCsQ;eLlr@RCf)_+OW1B)zfX_jIsiDI+sPFJr_x2 zG|Dc!8~JSi53QFKcVDf_=F?$tu=r%M{949@?JQ2N`xFA=BbKjE$(^__a<_2Y$;m&` zOW!}MlD~3j-9_hUx02@6qmx`c5(QmX_arHEsL$MW^UR~>SvFhWSiV=7SMwn3l~cfa zb)NMZ!q;o~gC<+2Oxmz1cgE)bjCP+~t~W?sUY>igddt;&a}Dj5&lFkD6Q-AQ%v}4c zM9#I2wLUxtZwuYH!NRJ);o%p}N})$=w{y2k_ur{EXZBK@quEjua4PYvmfr3c(Q|%$ z+}t?xgpKANGo~KKtBmD8d|MmWyKmYn0 za+-P_t||E4Nc%7BSTf`9x8NPW)&HNHIz7%si&yJo?awXVJ73=Ft~}oPo^7wJ#mObN z6t+h3UiRA?q+D~}c**0=`?kmItmT?imgY|7KRUUK^}LO#mqXE$bCbB;m$Ba4^~yQ0 zHm++$QN$_rJrnwto{oRkx?Dc(*X&mw*Ijl+<*$!Um~s2vF2(xK8BdGt*|JP8#VBVr%lzv5-XQbgkfqSd0}lcs)|}mV?ThV} zT8YIkzAHUtOX6Phs7d~>_4~T-Cy#t&n9wkTi)Yi@JIRd4^YU$H#{Yd%9aHzxwPe#A z56>h`!^rmN{9SVv->a43$?@MCxLl4iBrU)#L1l|*%8{Cv@Aq*Vm$3?pevf+MJiQ>G zg8kyEpih6inM;k5J6rb0vn}^Mtl7GOFZRjdh=(sG6#oCa|Jhr8d-ls^2QBUA3!d9u zF@?eEPW9zdA8(emSM=o;{n);0PDF@)OnA!DJC&;8k@uf#>)V8$vs8NOy>jxieTEOS zRC2gIW^VW?7Ok}9NaUYw1#t^Ecj^CqY=7`TU%+g>Eq^K^IWyU_1nqKUH(ZilJxOYs z*rb*-T1uR^b2iErUit9(erd13wQV~;Z<}rL@yqnY0wD|6S(ZJoCU~@Nk=-EsZvXr1 z9uVnt`j1d6=C!kQSUVbBc!;SMkG0FQJp`-|y}$=iSeL z^9HN>>wUYj&Yws>tY2__eZCV{{*q6YM~^PP5~%U%=`PzWov_m@47G}1p4#~8?`Mg} z5z{Y8EZU;v&3i&(^_24qUkAU_X_|3E)kAq@)P&t}@8{Y-H(b-ov}6t2%F357p9i?+ z?R%f1T@aM8W=WttlP!nKiwq;9zL^`$pd7*PEwDMoj&@>}{F*injOZy0u_lTV16;VsRa&HUk+4IF@``rS|`~Pm+r@s{5 z&$gZC&Z>3GeKQ<3pRfDfIN`~;i?5!-Yyg2Rj|K~L+ z+Za^C6^;Z6XgjWL$&fs6U%_pDw?KK>T(L^syN#WbttPAGvsty-w4d2;*KzF^+~fD^%uKndpf`*4<1~e34ko-g zcekf3=-kL$B9Sn)RO9NB$*FaD{d%(K zX$|*m)GiiZ4mnz0b0o8H-lnRr`U|(6GJbnE-+am5>xUDo@4f!NQtI@)>@Qw{t&6{B z`7TvIId$QwvO8KA4m}iQny$Px>DC%ui5W&Sw|#BvwlU9O%v3)*BT;Yn6MKhsP8Z#F ziXPyYkvd`Tk@a~yrhGd!{dn)8in9Sv_A$GD6g(O6H|Wv>*w)$zRcpcd6Z~Jim{~mjDuUpER*P^BfEm=ENA-tic^3HSt z??4?@!FvbNa<9o&9s6~cxv^BW;scYk+eB^ElPl$3FbChr+WvP1|5=6jpFFoJUvG4H z(DQZL#cy8kc7GQC^K9Pj%u=2(DS5s{$w@CIP8f&0vsLh_NIc5%Uh(A82Mx}AUquD0 z!w)1q)J^_U{BUi-wa!I99O@4zTni2 ztoFATzOq=&bxL5{u%u+i`*ra~FAx1cE_i(Iqr*X4pZ3j2zCtUjUWAFB&d*=TqJ-%0IGyAQL^dz<&J-^rOo%8?S z!Jj^>Jlou5w7%UJW-3yYm}SyDbNAcF@<%2%?QyO>CU)lbe_fl3=e-#h9XpiX`$??Z z^~}Ad}LKs=as+TZPIfJJ{_=petfZ_{7mcf{rgu4yH2#{ zo8Bn>?AiSIGv3_ul5Vfvo^UVGebE&W5!0lZ22QgrJTq=ix#9QtfwJE-ar>X?CM)@0 zlmtxY%GNcHFV}1myjS;Sqd{)l{o|il?|l6HddIs{+5tZ~qBzgEb^A-#ulXCIfB2A0 z;T!2g_S-)c{`++%*zlNd#6){hU%%fc#Aj^&FKAGz{mt$}fZU(2Q?KN-ZE&r~jxBnb zYX9tuzub#%D;3@)9e?+nndY3Ux;_4P^1SL#+uv;bE%&DC!fl0FO$EGCy8A~Co&5xhm_I>aD;>UUJ z59YXfvYOn?-{1V>>DB2Be6dd?cFDxtd$ex$x?~S`8I%8SRigKBHsm~XTDSjO`kkW3 zQ;%#54*6A+yZM+wl%jy}m$$Fab$$)KquZmCe(}*!pFD^4PtS2U%9tl?o_WvvnT*mj zhq-&d&pV#Gf5)NlCOxM@nK;4i*EU^``|W5V>QS?#;cQLEvdOVauUWY~G>rLh=kkQL zAKau)T}^v)K&A6ol>5ABG5v~p`gI>(D7n-LlB{XmNvEz%}>ot=uWHw7Z*&%%YeE+%sY{!=W6Q5S>xx|6Hz0`7JMq)0z zs_MrD%S`uld1Oox+u~j%RmgJgbcP#82V2GKz~cuG_-H-lUNz|!-}*aK&r55&S^hYp zF?Yj{xR;`bO4r_ITCv1F@ZDj?w)FW`Gd#8wq_L; zoCvEeVJX*=);Opd78bKr9s724hU%5=cjg|{+#K=oQ3wCOO?IBKPuesl#*`lwjj2Cd z`amVh!)2PG=ENC&;Q^-)Nrq)?tGw)&WBp!W1D9gW%x@o^OqMeDD9h#vTOQx+Z*#a`)+lOgO`rWKY6!1@4>Cr^-Us{<>}!Uf8E<( z^dZ_mr91a|(S>M#21Ye@(Wfb9s+)JtXKbBXq3bp4i!$pWFC8|`tOS+g^M2T!`+e{F z$xDJtJf4E*RJqr0nAo+_IDO;cH_VN<*s5hVee+r*W%K#U;uC9H&sb;7{`7>o{No4a z^3RLqYxvbgPW}41#O3&Tb@q*~#n(IzJh7OrIQMJd;vTN}#UDbR zAGRy8FrM?_9)I!s_3M?DoW4{GG?=yb+syO5*Z;G4hPBFW zYY&#{?Kso(VYYStgL(0Ho33@5Tile%>D!PhD7=2bNu`_|-&3*ge|T=MyVvyf)2TJ) zdAeJAH%@st^YtD(p8}pBEu-{~nD%DAI_vE*zl*JY8uYp-^JqL3U$y4$qg|)kVm=KGx+Z0^rkcE2^{pYI>OC3@2|jm)Oc zQzy(dw!3p*YR=>(Z>Mg^;`I4=OsjLrs)pOnyXP+4;^HykSkQFMI5#P8wVDfg&Lv#U zjrQllZ*>1^q` zT#m<|X)Hb9b!pmROGoX~8!RS8wTK?N9=kHL&0QuscdvN+{@2M9j>Uag^q%vO%QUCx zupd&zVt*S2!pdfw?Or4`W8$(OC4!5t#2wAu|4;SUR?nmlZJ(z^c=nvGc^5C4)v0`* zXJ+v|t>wyAYR_ubYbDO8-0wfhFC}mNc=MmX@$)^G=-!g}RMzIFRHVFuyR+CbNbAx= zLAGqeb(0f=+OyPB)DExg*b@7A$M>2m?YvRDk2%GAd0Nd(Ja%TKPGzNPvuW>H_Y3E~ z>#Task#2hJiH5FcadXa*l(5a0^?q;o-00ps`^nywO#A%}8?y3FtJ{CIJooqc`Gu{H zo{eX9Cdxj1$)5jwH~*d1NnA_+9KI4cf4kY%brGhQ6#Go9Cf%vHEGlD}snv1jdADSI z|GBTn{{C9MwM_J-o9Z|2&jD~hd;%qe;FGGIQF zOR~x)t=Vf{91YzU-B!`3w#v6@V)~Bv^X^Y@>1vUfEuHe_f||NG(}_T)o~^F(PMw95 z?l`$OT{e7Qd;hqCufe+JE~zWa-kgg3|J!@c@3rR_xwN^7TKdb%?fot`ul7yeq$TH8 zO*CWc7UENs2|WH_O>%}p;*!Zlzj>z@|FC9LkYA>j-EjDVlci_wsS>~1`^R@aQvZMM z!zxxD)8sQA&v=C+W^Fu@dicei30CdhDqdVc&pW2FsT!E+uk!9IzrW6x&GEl&Y;2#? zt>Q~zta<`X9@##xW{dr1(z*MHExE>&Y09B?fftTfuB`p>*uTE<{lCxum)?!)J0=wA zv1v}a+>X}!_v(d@SvoAt>6sulw}^Q@z8a^>y(sl_+O;+|Ughlj zZF8^aiS^E>&!;ae@zY_Q!81F0$yvjdu9Jl(PmJ`A>6er|Cn=R>u&3zAdds9ofs+?I z-@M-Z_58~jFJ?cTWgE5Q>%&Q_WB2`%db-zW#;XrpPcQA#$~oVu)_nW?;|<&Qw@2sg znDOvikxAbPu9iZcYbLiG)w3r*lg)}s)?K13yUcf%&+e;Ar*FGn^sN6Ebm{Hu?Qy3z z^Xsx4JDD0Iytmc=nwxQqw3*I@0GFoeVtXGPzOeSKR377Vmgv0AwkwV-Pko|k-!%3zT>%G-bL{1N#9Qq zhHq3dLz1U@-pD+6u;xv0J!_U$2U}$7q_=i1zgk{gwUhrXZcozBr+c~E4cc<9Y9(bBnyH`W)mn9Nqu|a}m#6vK6vDbbz8DC54{hX+BE^(nCo@P@1ebX^G>s=U0;1 ze|iZS`s7R#o*C+4+_NP&XIh|l(wwPF+&0~JWG{YG?f3QiX^SPFn0mxEX-wO|C={3Y za9b*eid5F+o9_>7Z<>50Domdn9RIDh;(|EbFC7n*jb9t4E^T)D69$g{SI ziKjO`off99RLZ3-qO2?_;eIwM>)L`1E{7IP{oX3Aej>Fekok=5i??qK|H}&aJ88`S z?P=1R`)$Vg|GysFr(3L@*v;}<#Nv2@^FyoEC*0%QW>3BH#=!Kt+w3VW7D=j^y-PSm zexI{!SnOA$e?r1=*{79h?-$=Y%-Am5-Q6bPsp@x}V`-;Se7!;b_Ka)FTc#b^%BF36 z*6{fJ0~6ilL+_YBezGgirRT-7`vIZNlkP5(etLV|>zD7ZHs@U30Ge1KhBFLIlNqVC;8{zv0m7g%O; z?ci9VQMJNaKrku6%KH7T?f(;Qeq%i`CuO&6Ib-DEQ!AvE;+_7ywHJ6FAuijl3#xz$WtW0NR$IBO1U(c35 zSi=8L^8NqI`3DY&P4H>bQ0l5$y?N@6!2iG1ZZl+u@4E5zG$Wb zx&E_S`JYVMcT+xPFa*jcsIbp@-z_59XfnaNc~y3f$Yrl=nXl*U9~|MI!)vBgdhgcr zE)$2Cxw_viW}W|kcIO+@_a0VR6P~V2IwDfLT;&RTa){E)CzejyF)`|seYf4H)2sh= zvp%Jr`Tk4oF3tNX;aYF^ntLsr`h7;G?nN)9Eh!eKBkwh4M#~>ixBu*$6}&z5#*q}i z#Z!)1dTj2o=sP**&`QT|_rB-WyxJVEd@ILXV52|(;_s>jeoiL6D|gEtp8oHn`x(0r z8g46u&Dk;~JF*Rp!j@dRIB{Bxr;kW=>pUyvJY&0WC-*;OPX8nNpjg$2d*;c5sU2rd zvOO<_tp!Lh-uzC{x5=<-x`x+ZX_G!Rce!GrW1eetSq?7xxyAM4x5a){Z5fAl_#v7hnF1u`U zOH=My@p#h8J^vT~Z=Y=cPc?xpfL&7bUlpewTX?h1vySicj>^}(IUl%nW=DpQpXw8_ zp3)N33+5xdEISMOc&%aqj8 z`5p|$OhKVq%wp?1d=pRG_C4^9-`(Kc_e;UeSJ8Nu$MGY9E{jAazTem+JVClu*fhrI z2$%VZ-{=1*sn7qoJ!Mm)dE1Ypmm&+w7#8JL{y)C|z@EeXiARn;@tEY+FKiz*ip(9_)pmY} zH1d;Jb9sq|QO(g^8##)kj^0;P*Uv6Uny`fD!SAc0iQl~r9?&VXd%^Or>_2nG!-v+9 zyWY6U?fRc5_v7o{eFxa~sXDEbDgHk5c%Jq7wC$Dd4flkyE^l-ba<}VU#`SW7)ES0e z-L&F6@^25^o>$dy-}bKnzip8||KDeFVZ7^A%$O!iPPz1E!(+cU_Wui(-d>$S&Zk0-7b=i1K@N$vwtjlGO>g#`2+Z25EulzKzdgoJd z^NTAoC-iM=752BBnp-yG@RPgG9G}^i<~6Av;l3=T*uG$!=<%8l{ua+{mw!58yFcmS z=Kjy0wbv)^n5?|i&5diJP>YYn+bx$fOqOqc`{rFDs`nQ)R( zMsw4OnXl$7QWomTHrlo4_pFcnZ^G1<8yYlMvdbPkTz=n2Jy-l^_oOqto9@rP�z! zme(^Vy@u6);w6=(oUVFlqGxnWW@ z*V5q0 zLr$OdU;c^*+u}D=9DKjyXIuP*Q(=PM6M`DoJPhgOpHpbH^;pQZdF2c<91A8po;daW z>fZX6aFtNu6E`yd?f!A+&flG%f1R#;^RT+&#l+tRX3Ak*jn4$$+x-(MyZ^pG;)YPp zF|B161SfA;)T{LUUdZ$H+E;FFaG#w2`hp-qJDvl{PpyORNGl#2fN&i;o;yG)e^_x#Ek-2XoB_wZ%cRSA0{Q}duP zXY*&hHqVH!c=lYJ{>O)Yt?k{Dk8`8T(qHArf*;f4RUik_L5(il7hU7sd2 zAL8(R_Ggy)y~4d;{JlCEUqFWfak`ZgvX?wy+VS(SZa)9H_I1-mTta|Ca^uaaA^%A);-{w{B0|UXA|;(jRe6&pz^0A?)FE7yYL;9o46~dVif1JAUQR@7U_Y2fbG3 z3m(&|Y6)^LoO}9bwA#o1Acs{22aBwE1$OhjSw9`?>C^ zHv(#Vj&FWHV|DSno7=Rt&L#aVTlL}Yr&&$&?`M9zSrjMECBi9?*uASI+dc65xlSj> z6Ca9q?vT5BD}*cKsa^QzAHrRq_I{y zvNme23*VW0y?D;kSwV6Cqc*M=wEtJj*Y~JSRLVv6xyU)oC0iau^~Apab^YYW9`nDg zMyGy8Rc-3F4AoS>`!(#_+r>3}BER29?dU2smMg9Q^5*#0JMZ^C4v1Yo@BHp90yC<& z#mj~_?<-whK3A$Z=4f5a`8t-PJ5uYacOErAB=fPgxo!F(hr9JVH#1GDGThdDz{|@2 z&WY*!zdTnla!uBFye*j7Z05Q6dDY4yY{$QvugbJ6nH0(B^md$GII>t1^DS-_9HQg1PY`3x8Zf^TdEPt2YTP zc{0O)3X`AagfD+8bFY~i{<{8g-;&0KSM$WvwmAQo+@oK1+Oa$To~+HkUCQMf^zTR5?%9C{i?7y5NqoI0rNMGG&o1(R zsf6)-wO#MkepGJlyO8xq^6ggsw-&|g|NncjQ~%nls;_JKvwzQhW%sg@ujgOf`>MwWc8VPI5?~9MAhqJ^Lfc2b zo0f4cYRk7|F4>^cI_cw+;C|twOfyS^nRI^qxmtBtJA5zOjIWCfH2TW*7N2L2SpRkT zuekGH-~4^Y_EP8R$^Oqd^9pwFJ@scrb;g{v-_QDQl=_*tXXgg9@AV2Fsv*lg-~UuT zw&(M!H|0&`*Gjq9-`O5_c#mUGTe5B5`YUqR`oh=j`6K9h&L{VH23yu<<%#=r>~Ctx)xMdy zXv6gTVKdjKZb|wryRBWR;)kew>-B#I`xoUDo&W5xpnbsuR;JlnhuF{L{ArJ<&|zb0 zG`HYW<2Uh~;<_tQY2qXe&qc*Wmmhv)&wDs+{y*v8`=4e!dTFdsx+Y@7gxh&L=j?vB zV`{`R*W}9i%cpXBzA~|XZz;EsB)Lg9a)GAlq zpvxd{z24$uw=JJXUr`B`y!Ft*?vMEAh>wpx+kAVm*yit(!*>clr)oqk==yqvV^YS1 z?ec{>&X>2Rte#u8*f7=VHaTDU;UHdU||v#l$y)VG@Iq|mxIFlE>`*;i7;;3 zqT6vRz|?Acg0%wsfxIx2v&X96bMeoUO=ad<fXN^<_Su1^g{r$i%ru-~Sjp1_y>P0znE=~D1dy`h$ z{*uJ%x=;6ZUZ~a-;9xOhE1P1Z?$Xi3!NRnj&+#BPi<#ptQv>h!F)JUq#?JL`IQVeG ziAV3Jeo#C$XX1hntW1pub|o=t*PPh>qI1HBWm`U8-Lv2iD^p{yYlJ^jqq)J-U(b$- zTDct+X9Xo(-H&ai7q|DdnVJf4?6GQ*0r@uV%UfGB#*{gHRbO`gWC8`lxf_KdR+4XC zH99;9RnVvaB}NVwuuP{w(Fdl+15pMOWi={(fP@4%SmL}}A`of>Zn$u8#VLSt9au0& ziG@`k&SNnXY-$pRmnWv)F7rt-Qaq_***Z#@%set|Epdj!< zU87>Qf|~h~%&ua-Y~8hC+#kA5zPO&;|{3-pVXEtn1X${);yH;|BZ{Di; z<{|UAa%!5Iws$_9X3h7Twaja z&*$keovKrKzxI3KIm_n;rLRJ!1er+jP6?{{|NH*)eZSuwmIyv+F72$j`ugj*XOs8K z2gYTF{@t_hQ^x0`jhZk=Y)_uHm;@A`)i6VF+{w@Euc?<{})59f0h zk9)jMYDeC7_2g(Yy}RMOa-T($=VZ0Qi>~4mpZ~O)mkCL%*NwTwbRJv@_J4Y(`25kR z)0WTY9Nv81uG_FJZ1vH{{r2a|_y3MnXlom$%#se{biW@9ZU?b!)XvubsRi%Q1-_!>g9x_eu4# zsn4%53XdsdeP8q3`sdB_b;m59&k2?-&zGBfl2=(-S$Lj!Kx>khX6K?4(T{s19}CLN zHIF!U>ifL>4P~IxM&ZM+r)X=i2} zWVidkIIrRnC!hVFf_1xIX`QqC{pQv0r8TC%p2t-!p5j)&Z%S>$s&7nd;@p_^lc(-% zdiwt9bNBuCclX|#zjO)@KR@$=t!!%3UNWt>b39nxthmG>GxY8mr?S1NOFtzQU4HH; z?4+=CjhN8$m{Q~ZZ8xTTd=NS9tG?6Dm0XLC6!uK`SM9ZWAM4^f?(1E-6wZJC`fbwH zEYq}eb54fu`y{&MTFu++_~f6To?fjxRUB~Z_?hVJ<8#7yW_)dPUXtmx`R1G8cc(t< z*hlB7_dPOvF1;oeoapx0?fi5~`{(=r|MD63eV+S%!`a!}RxVoZwex^wdr;Tf?YCyV zulv56VNU(OpD~3;MW^n$lD(j9W9!3HFIHd5h-oXI*7i6^uKV$hN&8QI_ww4g z>=Z7!@md(ygBKDXgI>P=`j0U=ukN`_pvceG)e#0$!Zg(|WrLUaeeyDQoMFU$0glmtn8)j;y@1w>u~Q#Of(R&t;gInWuhT^}X0@^{XG= zufyMeuNJ)rEpqHZSwPKy-kI(D|K@JHnKpah^FI|i`~QBcd2W55@j<)&A4MmQO*+b5 zi?p)5ydqDgUofqjzJI!r_j;yj&nxFY3KN^b{EO$t(vSQ8#EG~bDSY$VRAiHP{+E!I z4BwU=Z186d^7`sprs^5=S8mFl>uin(tC>HQ*MBe1SiAGfCGW^B8G`Zue_dbAy6|RB z(Z8S1!>`UeP`zs3$KL#a_1Ax1+rICpu)od0nd$R9gS-Wt3Vyv@Ui|y*_V1dNPyaJF zGshI2RIUAeep64k{yqssmi*e+(TwuP?MzILTy&T3-8#+YyrhK0gC65^Hx^tvw6{A! z#P!YQ^L7#0mH&P|Ki)DouHs?qnYq^DYfX*K=bxOu|4*uzUd#!_cA2JYv$EIiWNTPo z_jR?0=FV5ER$quJKBc)_q2)m%yWEO3iRO0-nB{*QVE35Ra&oeI@w1ufMYnUef8_uF zfuDzu?^ADnU2-pfGc<^O^>#d9nx-3lOwe8C;`MbaQ}$%cJ3s|*x7%+^sm45d}**(;loz(MN=NVSloZi^7y9I(-|gGGWCBx9@*H>CnY8IXwBwx zhoVkDI@+!6e`izb=^ZZ?b^m!k(JlMz_kG`O!`8(_p0p1X`S@7=zl0*o|M`1A_ibNf zA^+WYbM>uU1>ad6K~t0#9J?X7RK-w>ODk;AktP=IMT=biG6_is^``qoa^?yDlMi;NG z4Du4{WYORIMJOu!*SEK)=T*OxRQqiGpn>_&HU_tSE14x&^UYPHdLLEFX@{+OFhkB( z!mh?*-Rrhx-yECS3cp?rZ-0Gzo2*uBx0vpt`2BTv%J0`!%xh1LwE21^Sf=z!pv~Ve zmmiunN-uxCOGT(N>v+G5QpLRau381k0baRJPsc_^zC54S`6}$#EwKf+)&#$sl)W_j z+7`_quW7o`VQ+t5TFS=8B+_3i7mx8&!-|g;C?zf%BD{VHxZ+UO^vV#c*5vXpzz!AHStR z5z}0?rXKpd=R&Jc&FlMbx8FY}nLfwSMvi~Kv`vM<-(O$3h0i^$(qX-JAm(WZM`LQ_ z!sulJO`A4ty0F*8Tr5DlKFD^e*VUi9PVX=6Y1%&f;ZC`Auaj<@9d6@&eC6NY$el&1 zQQ2mBcTTX1$22^zyi@sn?$&AY6(0_=TmF19`EYyr)m5Q9l13~`MV`;A)>|F6mdT+~ zE2J(f>Qq+U^PO_KQCkj_#>CbAd|II3u{6kMo{ePY$@rXx3D>T@TfTnZFD>)CCBoBE z3!l#|pX9Z)Kz90h`~P#6`Of}y&iZ}JU)CLeHl041VkA?3r;y>y48!ISE!W*;Z*S}< zR8F5;D#qa4&X@Z4*Vif2rUV5B9yGlkbGU_5xUNi|hpqWwg29`JtjUf-ok#lTZI~L= zW?J2RW6zz6?HMLg&saIWt-N||lYh6EZb9sH@%S3S6|HSm+xLDvCcP$Rr%{Re-!GT_3uDDk ze-l0Eu+Zd<4JaHFZ-!+|e0^u9@nZM>Wv<;~4f&SVzu#qu&i(S@V)n&u zy-w&|4Gx4+;2Urtl? z>?~96-)+G4-RI_78y7x0Qc!SK*HLgs&9TQHv&8n5->;qS zqU1PTFLuY%Y0(*1RtPdwR#wK;|NSac`{m-ouSNyu4J1H;6|nuJ@1|?}YO5Kvw6r32 zm%Z(uyYfuCXKhKbP?YU;yBO8}wTbzribuhu zX!jeR_ZX~xgSTlKOAkG`ahT6q=MUc>_8qymw>eyOnACl3mYi)>i1d@D z1$Tq}ZAF)gXos!gV4s(8f$Nk63#WV0X(tx;Ux8b^Oy5^hHw5F~q{jG32xFI$ANYcg+2l?(;wF+#>ysUPod_t(P zMv@$l&rBb+Gggu*Q@A)p4$XgkST^VT)9LX>$;WuKw6rY#d^r3!xk9T)Uq@g6`|p&{ z)X82dLJxbUzTS0pQ~R|rEu{`s9;4i6S}PBhA1pI9u8;yHlY|wspIl?>b5Y`vGU*7> zI(lKDbL5_i!X0r6yPsV97&SnGx8qJ-bT$BV))i!c3eZ32mL|#qX9XsKu@r(3=ISqI27d_p2 z=e*;!v+=i>Pk*>!COGpk-q6}C za$uTnG(&wr^DD2Q1swl^I21vp1*qv6mEFc8>2!LUuIKX05!*!BY|qa&*WV(u>~f~f z`Q*R9zV7+=>-ECdPI^0=YaRYpePyukPFrB`Ol#Huzwhhox4d2jP7ZCmJlD_LYw`EX zWk!3;yG^Xz4XaKjtkBZmT5>Z;Z|4)CDM54Ue!ZMib}Mt?8sUl%R@3JTs>Dt`dX%Jd zdXevJGlr{s7Ba1lb`UUT-}lBi{oI@lvKKQ%&VT*!s9XO;iqV_>|Nog}UFq;qbN>A7 zEMvshEYYP)mog-Bw#LlVkI;XSe71iUNx89_Ge|{#WE!$cA+^FtP#gZv9rB5ba?VBo{@MnL- zjw0b5EX@ykB#mFxoiRK!)3`mk&$8{}V)w^8lvuOw`2B9Tq(9pj`y{^QTB4i3!WU2ev|UBFZ))FuzJA}Yu7`))Hy1tiY7tlyzkid2l z(Q-ABGBvD#6v&GrwjEvKIr+uS&FY_@oqgP)+?Ve5Z#jG|z^f}Ob8c*4{NNlhO(*gY zGrx_)^>wk8-|v>cyt-Pv{9a|cMWRlNgZ9~l?Q&gHCT&bUzA51#(|z4bUn}14{l4RI zpY@5;rys9a+{d)-{ol#6|0`%De|^-gKj~yjflT}M`<1h$^Y;iY6%mgqaEwUak$rt# zgZ}Owd3(D%^RLZ{&fhDl$Z~gA>Eht!ehl`j^)@E5FXY`Hd8}7@`O+!7($CL}(p)+< zC@Onx{{FvZx=XJ-KHh&nYj)}DYnhr$*}lBGy83YLv3~jWOQ-z0Q+)pFwA7c27Af(z zyk`3K@woi;b&p^9s4d=lt?KKmtGoQ?+dX`5I$h4T>cy#3UTe2r^U{1N)bK-p ztLBMsv)=yK^yjD3`rEU-&mP^DYnyO@VQWHwA7b>{?zC$y&`K} zc16~z>`Fu3zn{;yUW=-pw|wihU;Onyn%TbeNE)x&`g~^kJkI`^)2EAXJH1Kg?&fs= z+{kJ33=$9huZiV_L`g)}WOtkMmyaGjT6LsD&`Peq{r&Gd-|IenpX9A~aq85m54Wv* z+_vfb_xtth|9@F-|FXhHE^qSgFK=!Ji;IhAFP-AI{PL~RI{|S_t4_LSUth<&-~Q{B z;H|m0AKEql{r>8zcm4mr-=j1|Pv!XA|1H@O>s#sNwKDz848d)dlTW@d&A!(1y7uEy zaqE9g65F~rKKRRaG4lS415#p3KJxl}-|6X?l_&lq;r6yzUGK@~eoZcaeXV!>{(rNI z&snm6@cmKy``go2@wf+THlK5fGV=L-drM}pT-6IjxymPkk3Lpx-LmulpXc_K?{+?4 zb@c@IpCipW^X-o{P4`;5O0{ogZ~dRg@;2Y^6x)0}BAj^a!h(25pS!%~cMgDZ!=0VQ zH{P#ax2wzie$C|CsO@~erE-{C4jygnuN9d6z1{v#*H+m_I?d}c5d$J{r|q|>zr1S>u=w5ftlatfOve( z!6zptubvvp@rmC<^Jez?y%j$mw(tCW&U*FHSH~Y0&Z~STnRb4j@7}7f0!}}kisWQ# zSL$w`+gN@vw*2nVE$;HX`-^4THG`KK(I}i*X_)E z_y2gm{P_++WeM{ERo_?6+wObw7bH^g4~4P z)*-1^dA>=ndAw83OMA(L+aYVRwrNUK$QmvP#e1`6x-@TNkzCt!(9pu&ao3|e|5%x;&feH_%kFx}257FC#d2z-MdD8@csalm8xmd*S9Mt^m>GaNV#CZF9sm=I-3IXyLnr zD{t>BO!QEZNsu|t$=>1cQP}Cnv)cUE>_PuKCb2mE+U(uf?O>2_CGFyBOApplcek-I zFBOS;8TI6ZyVjpmeb}mDo2XX0qzZ5 zel4f}n$-EPPTolcHqcPFTWF->y5a}R`#t}LlP)8n1D zvq`~j{kGDgld>sAx+#u1u???xJ$d@Hwb?_@D%$>B;hZSZW4VGmIG+f0AN5#%*+psM zhJ8K_xwjJyza=E_O-Wd>sp{C{!b>kpBz8-P2&}D?Yx+Fd`oOhkMzdaDGAMrL^XvQj z{jt-b$)>dVDp$Jm_bE>>f?Q+hp?N7CrX38PX5kjIt;FZb(_v$YCY zRaCp8_^$qT(}*YQgn2?fKRcWJ?aj?Euda5>*;YNU;Mc+TQ&j_Y);W7t^C}+C^;6f9`NwJZ0+C!p~>T zCwnd3@oZMMhK>%8b9~X$1G!f>oVN8-c+Zl1T6KbMvFNdNvAh3el!qK%4=Ov4ainK# z6Q1xp`1|zP0V?LjL1)`*wORc`ce-6mJILLYcg-cUULk1Sty61_Zlve#nAe?qHQ>Xh zjpdgnC0;0SSZAu65&iD*gUUFG^c7RMxU1ciCa&$;{yfTK>4e1H+1tWB_CNEz5T@w* z;+SBK8MN1M;;eGO>^GCN^RMtUuGBnz#ccwI>XrwoPy6MUK1hAKbXFw`Q|MSm_t;iW#S4qF1U9C8|Mb~hHz$SNxIb$hm#J>^ zLRSAPNe6|ka+CLYz9sI~- zxn!G5-tAzK?db=()edD(R-PIb5%Sjj1CO!To?VR_A4t{-*@rMCR=@tQ|L1~XUB>_Y z-xNM)e?JfEva=mNw|rgKX>0Gk8`BnLi0s+b_>tWh94;VPd+Eh@uJZOYr9(PcAff$& zXxy@@NmFkn?P|*D-5;Xn0m-Ut%@6C3?vM*RKBs@zS--D9}eDHV6+j_m-yI9Zjir54? zPrUr^dzozbhf6O_T3cI1L_|LP{eEAX6&kd8{&NFAFbH+BJmB8@^y$;Y#-nc&S*)5L z9^YJB8ZuEgoU38MyY$3U=g+%qwoaMU)zvlkt_&mq+vfVkPQTB?c9_pG_wi$O>*J{A4@ z*k5muc&H_-bGps-G5l*wxBmF_=uuJ|uk7xIul9ih0Ma z-|uODy{qK?y}3SWpizR#FS}P&_uKvY`d8Q2pa1v!{rP*<@6TRY8C)1UJwoSL zBfFf3jokC^`~TbaN|`Fj^?yDh>>m&lBQwqO<*lvSy3yO7ENJFi? zw>uV;Nms)((nsaY%$-66cdee&d{dNu+qC6gIljjtj(v+!uGOj5Qce&bq#wk&|b!{xmP1jTdeXHh$U8~pa<63LVEw1;Z z&-$GMM`LPq$%_k(`)YrG`gB_V@}^YpODj#by^Y>q{q4=k`TxGC$5p@Gy5URzlu45& zO)A)bc9!X4_kKChFr-P=6^`561f3?FO!@Ix{{M;N^7TH;{pLn&NMLm0`uFeqe&hUm zHlXo*qG)f=Zk>ejRgEf7c&ByTF*wNxS8-!X1-CzKi#kT>|w&m+Jnz5V&`_xq16 z_)SaGFa>;W| z+}>H!7(}N-KW#~&l}n09?UJjzp(Q2Gafmc8Jo{pb?fi{V|1rJE>7;aY`F}` zHxHs;{rd9qa2v1m4D)=spi@~lm&+b^%s#vMyxr-_=X2d{#jg@rcXZX}!J z-<#9SZ#N_F?yk2RigRw1{)lIJc)@HF_a42X-&0;cd9$(iUs&+FFM3O#oRpgXSG78| zb=9lxdsVfE*LCh}V{1;FedLi~(nSjH<@KB3}yG$WVczmrXx0uccjeTwDuQvG~`_!#=TCK0GD&~o6ZJqag_j&HM^^ERkcja=gx$U}+hwZT6(NbHT z)2<1MPu6{LGnS}%s&#$Q)RQSYJ|2_)`R?|6fuNR1-Pr4{nyw~Nt{e}epDsDNuwC}l z)WhqJY|;g-bWrn|abSvOu!g=qzwla6pXf-EA!sVDRXna^%b!~n^FD3(AiDclue5Q- z1qDBwk1oHyyma1Q_t)aX0p^{Ly0k&Vt~)=S((XK(v?c3m*YEfH=QlF57oFDKUT`C^ z-7x!_P8*->sqpyPqf4j9b>-f!mUGhQqg|ptbFHSz*;ZXx?ms{NhnM6lDWQ(U$;S>KW@gDWF%#39 zAR;N%VIv|J_%^Y7jm1uGjqDpJFKrv*p(gD zxrTPHac#H502(Z+`QUiY{(p^{|2&`P=jP6|tF;2nE7?|m`;z>^roZ3r zS4Z97UyPvPor0^O;f41qpI=<=FQ0QdoGE)(yO*Nn;~rzsn2n@ilFNz*Y~9a)eypGA z)8?agxcq+Y@ngNxksFg(FE96h{`dR+^lNJ(b)vRpJdX)DtnZbZFFy5i{aV{ahm=~E z2%S}vkrB}o@@?W$V0yysDyV0e*=`;B=g;wkWm91{8Q&zkwOR3;o-Eabt&B;D%G zqv0ZSe6gIFkoj-9HM>t*HSK%4Z&fTyCSz)bR$<|Uln(+9GTkh*G`ebH7I~;ljNevn z$@@$7UB6b-lhA+vmrMzH^hhX?TT<&{#m&W>lTsR%JoAIx$>`OWBUejJ^mhv|H z${DAx#_~*SO`~2EEI7xYd4QW~+2Ly^<}66+bh{sq0+knm7Q*j6U)3#Z}LzP5)l;@-2OOmk;v&!vBv7YvyNmgpX>Jf z+uO|B+jO7LueY15=9~28#l@JamrH$i6$^#ORjS6UA)^;K!6Ptp6m-!~OLcDq;o z-gePNjojPYmS$dFwk7}myu`z87xz||&#V9U^FmbF&D7}^H>dlr+x>3Wg<03vL>j-_ z`#lbnWv{FZ&b+_R)_1nq(M>v&PO7-Nx;}aSeDeJH{Zl6W`BO8?JpWwbaoOWvUS9rr z`oR7cuC#YaH^o59mYCUi7I;tBtNHzQd(O>Gt);K81;)gHQhSh>(nOAFsTa3o2G26d zbee6J`{L?qarwF*im|&&IM>d(?WOa1af`xXKh*#RCzBO#RJrfz&$}QJd}?|2{?vPm z*3bBTwq~E!-9v35syD=VQ>Qr3+WO=|?YGA*hx-=Jz1y&dAbZ-)&VZ?*X`4Q|-#9OG|D5aB z9lq4%yQVORVav9~B{`So9NsPKF`t=#xn^}hiz`#S-K|sCmNL%OU97TXe@^zN@bLd@ z>JIK>H|lRbG+9X8*HUxejSU^*_VW%e*Pj02;Ige2LLSQw^j+S4)lTNxI$?FWJI&Y1 zf-O4Pg|FUMU+Qx+aTB`ERARE)EM?Qr z65RuCsqc%?HNOY`dIE?IgZC^dOwjbpr*=dqP4Qk{;x zrCo0h3-K&rnfJ$Pwf-Ncn=4}8E^6_Xl$7~&qvz4mtMZ@jJ<|VK@wHs%_9jlV97ZJ* z%`Au8ZPi6T4z^!deAw|%-?SqI8mG>k;?#+s$YmqKv{!9XXnx7D|FNmh-PX*%|L@jH z!x|QSH_ej|HgVo)dDPoG|I^7$t!I9xF~;XcaEqq?tBsi8-@fSBmltIge|LR-#PDr_ z-7E>ADa=k2*RA=oTsfwF#Ztj-Px%`ry>U=G*cA{K)HO|y^=r4lCATA=8Z9(KCWr?>O>tIGAaKV>WOTpIM``SarUd%sWeQ7e>b zkI-qGVzlMh+1cj(hRMf1TnYAHxOG|l{yLx8X1y6Er%bQMfTp-Czuic-d^RH)G;y=% z^SQ;2&1^>=7lLY3yWejPpO~n8`1hB^{dP&$)yT9DIQxQSp59lQpaYtITepOd1S4o6rZ=9p4?~2cK&O` zzrRI!yWg5E^O6YZ$#s(?Bd;Hkb=Esr zee;xFW5GN&uZF8rKHP9WZ~XYLc|`0+!9|<0RQ;Q-O(?zV;#r`hXS2(Ex=gXv?*NC8 z>L(9(pIPe4w(ycms^XHMgy;#L&T;q5_ExQ0rd2O{(6Twn*fT8n+~N284_uzV=lHCy z-kZA|x7}Bm8`^BUDy@I(*#pXb5A$o!E#du|*}-d}@wRc>#7o~q<&S^-{?tmKvvJGH zQ_(w_d&V~ZK3eCLom#kwY0<ag&afjqpdjCad$F#RKJ+f zJI(Rh)dlLIiynOYy(Rhhk-N8=o-c^d^{V)^cKVO+>gzvyKCSXd$?s4)Ae`W?5POPU zyX$Ad+n{&#Z&S~`E>j7Yt>@EqWvp~+X^Y?D)Xl>r{<30$YLH9$lh1$bH|V~OzV<{n zXUW^!sZb_TkO% z^Pi4X|L<=Vl~#P^==0mFsy6;=jJ{XI{wmwz@N?;Zy8VqdoED6^^;_pwaLW}v)4rE`AYtLw|0|HnSea_R%s+Fr{vXJ_s^JTG)>Vq=b7 z*Vj!yRX^|HBWC{e6Z8F(^@ZLjDrdZ1=$Wj!L0QO#eNtw@=2_cA1bQ8B9lXS~Hnv2~ z^Vp`2+kzVwU3obB)&}XxUQ0WUKlbo0I?QVx5^Um>9cGqz;Z&%$q;;8&6GzzEsH30( z2R^G83Pv+|wxwP!T0ia0&gb($D{`uPN_n0_N3$t8XAEI^iX8L^J@9*yJe7EcMjq>@m zJD*JQJ|waKdVKv{`#%r)7v5fx8oBUwhJm3}_tA_?OFI8o>mEI~^o#n#oZH7rW9t|B zdHwqSIzCr=>6H034ylt@WVDJ1T`$(u)LfX@+!nFTwV91qLt7iP)^efH93M4JP0hp$ z3mjD@d)}-0>>IT$=cjgT?BVrJ-{!_l^ixbO^ztZryTou$(%Qx|RVR*zM{Qxr*|7L# zXTV$SDyQb4^PhveV!SntZar+gxHw{GnQC}kwdvPy?_cE4-}>*3M)A@qW=pfU!|&HJ zudjH0@Fo-I0!NlTA{wW|UooAYa&2GGlbvUNJutQV@rC={z6y)>p%tU(^t}N!TX)V;|tG!dq2JO;2pELYi-XNuivlb&aaR@aGU2V^J~Yj%Bzc3 zt$(1sZQk+4pW~ihW{od+%^F@%5GT#mG3kWv3WWy?_xGpV+$72)U8~J&^``&CxvrGA z)9r(H-v0RJ8duyT9&z7&ZRXnHznzK_ZK~b2=s&DpxBh|P*?S^fi}db%q9uY&X!oV9hLf18%vd^Cua&zbW1huErU+!D-H2}62 zpmoZ>rMFrRi+=ypZ22-&;qnCiP0ha7q|`&gqha-zvZ3@4s%Ea!M zOe{{2o(cDVxljk)`Uf+^a)W$R+lb;vY&X);Yg*&{?;W2`Y0tDQ zRs#*FE}b6t=!mf2kwTesmd|D6s^1ubawllgck_9>)6M*L9Rf{z_SiH8%xu;=YAn|M zuu^VXYT*S(cEf@P4sHDMe!I)wg65587^QOQ@A<$qJ+@2|v}|F9rg6XcD>#O>ac^_pi`zync$=5sWv$zB&22C>Uqx@F`*gJ9G_ui))Pvk%ftPa zLq*mj_0P$3K5E$$Pqi6wa4%`FVa#k-P1XMS*mm&@%QtL&Tfe9A^WG}%IHK&c`c{ia@XtTn-%sc`zBBbl=$&tm zv=d{J78I~f{xvbmW^3I(j;GW0wg)Wq{$Tg}jq`M)AB$E9Tv81P;>-J1$6GteG=n?- zt@B-87491g2a{H=Sy6yi+EKRr*8eVYvvwlPR!rJHi z)}Hddvb6I3-6*GEja%FD&vqFdEiYtz8m%z*+u4np{5q_8m+ChJ?mHyj?XaoERCMZ` zs@op_Y@fXUl6R%GMrXs&R*`J^jXm3O>t{r^KXIA`bKG}AgAuW-?u zUl+5-UP=i_Iq~4bw@=?IpEqy+`D5~TO+8&T(IpG73i)e&>QXXU5#C=rd;7x^_rE?k z&pzK{iiDV1;GzhlSK5^ex9)3Wee>Lohe^gJC+FL(bp2al%YNuhYU|pPU#ac=Td&ir zar)M0uFC%$mWgJFFE25D?!UKLa(e%h6A{{6uGfTbpEmfq>U8AKpU)pu_U!qRf9KDw zIjdg0iC^^Beo_6w0}C4@0%vW{bDSO0b@Zam|L>2AG<=&@vFP76(ETeOYQreVenIDG z@{K3Accz~(;QBN>Xnh>dRKKL1a{Bj*&AIJoxZ6r5Kblc*kn`-Z!1?3FUK@3!8|TN} zn<^)GytQLpwE3ok3}@!q&IXMVdrnp}tp8WjBCzn&r?ckwKio{89~y1HAwzTN2Aysn zwdTiGpkdzQg`g}^{bnQkv{b{=S0TT?zIK0pZm#9aC6gH}p3fUb+2s~^PF8zpcfaB>ub=(jk}cQ1yuUyHalbuy{ZxrnuRzngySs~TB(@t?f6Gzx zn{#6A_IqCM@9kx*_-S>M4{yR!3nrHA*W?fLOhTeDmP z0|j}d%~a(2Cr_X59vC?BeVAl-s;GOs3ilM7sj~j>=2zK++;gw`{nH7~d=Ix?k4ygW z;2>z0r{v9zi6vHNb+_MX3hJ`||MR@t&fBdg_69k1T}Ph8@mN9RFD+R={mYF(Jn%4N|=KY=hS`Qg}fY9xCBp! zPY97@R_lA#yjopI{Hx}aS&#JXpLc)1xA;Wy%{_U>M}r!s_I|u^@Vx7xO(!R${NQYs z_;g`wiRKiYGyW6SP5&@;x5$K&g+`n!O{PqDc5KZ5;PB(`84I4dRqXz;R(;ntamYyT zi#rhh{>;*OsT*JY-a6&>(SI%*MK#t~eYy3^wArHRhjpV$-;+^@h%8;&IsXP z4ea2$AbCMkK(d}q{hgE2*?4)$^XhAs$nY;Y_WPIgzPiW0Yd&##ndc?Fe5AT?_O9u3 zPp*~z5v+Ac_~tA{p-%5fx@!^)&G#C#$zA`NbYh2g#gAU~AIpj?r5`P|IBRp{UegJ? zrV?Ylfj*o3J1lXs3TU!xV#uj8TVYx#6{HYhk;L-T)N|>h%Ph0%#2XVn(tYxXBGr6_X`ONGphKIpp*I2^!27|wrfjflop+wq$*SQ z;~{A3)Ux>51i$4c&!1P<*YE%Td;kB(`Sri0H%9dQ`}@22UgdL8{p;oBW%0Pj*y8`6 z&zArHe2(0nCmZC|XZcJ5)PR+%d?EQlX1|MEY&6LbCO*^Mt4cdV0s7ti5%dYbOb>+9t~ ztE~?(^MmGTx8&WORpt6sLqlVQSn%_zyau^vfdwxuG!-)@&L zzgsGPxQ+Mm=JR%kx8=C?NF1DDn7pm)JolQ8gXt?)xn|s`4C$6R85P0Oq|s!fWU}1u z`h2q)*Jdw%lP-EOAUYuIp?{6KO-3L?uC&u?rVN3vPnEV``Y+3`WoG>Aq~@9=6)K(HrU2by!v#(X^EdNRIW{Cd02FPg`vx3K56qD zMa>*P+wb}dk~Jhh&OIFS!6rWY>Mk$mA5Z6V+FPxayD&i_{QLeH$MOVoOYL}r`7A^Q zN*C^9JTz=56F`O?(3?kgH%+fg;pQi zIJa|)1Go5eqo66D9(416y71=Znhn7wcXxM`{Wf1(IGHJErV5w%=}+lp7wfhug=^U` z2C7boSkf&UHhtZrTb|c1)txVkG5(Ns%jFyUBNtbhpV~ghZ$=!sknu^@ zd8PStjB@0J6KtvPgIMEvcbmK{nH8ZUwu_JLR7;ptB4^$A-S-PmD7NQpo!h$pg67gg zN)H1>7mI0l&-7_4vGR3wbzNcOw)kSeO{*^#oGriINR~8AV%dJDi2LvF@9Gmh3<@4N zfVM84RG;tD%*HEWkic+xneXDr&1pNQcT)Je-mMOZ?+XQ;u z4qNO^_`7M7QNx8rk&%&|uXim8(mZwgwCD268EZY4UrsTSjM|pt3EFv43mPNq*4x!l z|L^mB&=P%SK8ps>vTRmTb-9(VT<0qbnXrY$Q~fAg^l#w@Uxfqo?Pu>`^4Ph- z@Z{|KdJoqAEY1k6kH1#?T{kY$GR)Dg|9lP4t?~ostzNbo22IQT`Ds!R$Jz@wB3EBn ze>wa^uSL6?wb7rJ{YA%%zfY3?+L3OQ)0s8pgSwiI?uDqJ7=5{8c@H!0JFmF%^lNB$ z#m~jlcW&@xH`9x53y zo%^~M)pC#jmFn|;*H~clXv3l68wshhnyn2jPpki4>Ha-!trxpjP=fZo_^-O_>whpY z&w6uw+1Aw?P8n7F{Au&&hwz0&`};v@t{of`x908IcPaVi!h<|3H+TAN^8Gz?lXK`f zZ$}nirKOe@7yAVN>Lol{(_ZkXOU-b0&vJp6UZ?hIObv2e$SWy+%cOb9r{6OJAEZ`P zKdia;=Y^Q~F-fQ1eE%M2RaG6GpG^}V zuTPJBDK)D!)8lqp^~S2hVs?M)WWSo{FS)y~TAin}BIGA7S@LCTpo}G1JiRF8OLAciwhOX?1`9D zz5IXo4@UMT)xR>{Hz%>$zyEo5?)gPdxwZkVIx;fzbT9t%@%UsPHA#a62IKT|PgX4MOL}yq6SUv=PTlXfpqX1xmz$yH*URM^ zODjGe6_+&6i;*y2J|*e$GGEX>#XVoIMSEyQZpjE-@gTSR^LhLEOTDMJ{ngRcP5t-h zXM=q3k7u*ztY*^CxN#xQb6(P<=7d0+sm~8ptssvgB|KskFPT`;D>;E|`P2`w* zfA{-+vp=7+?ms)*y!dKp_{DXx)}ZzBdb?gIowIta^Xc>F)m!z2I$I1|`t5#c6hAxj z@XhA)X|JxVysf)A;f5hg{@gnkCMs}7Io)t*x_^7F#P{nHeP-10M}PVh5gF-aBBa>t zoy^iFBI2H-qcU%~!s3MnZqE;~ncU^rEML>I{r=ysHqWEKrW~*3x8abrZk~Mh@yw5Z z-b~5+c0f#Ey1?f0j@9cK9yxrst@FS9d6seIx5YXo;Tv!1riLz=Wc2bv$WOh7RwlE^ zrc)iPfj1Vfn85aR!2+XW#>UG&-~0c2R;_YtP3XSPndj}9W%)nE+G+<0=zrN9k}k8s zrsH;<{oDDM&d-{4@tcWiV?4_#^}e$kf5zVUe`ur6ukW=r;k(52;~aG+on11|x=`hS z=%lTOmK9E3W)gBCY4P#Z#{Z8R=bv5P+_T9n^4Q(;zRk?m4qiXwqWZW+B|jMLt6qNQ z+13uGZ9iIVLy9lY`jP8@glpqR3$<&#Y3cn>)}_Bsue=%c#-&GXTI;$sD#^{#pKmu8 zDP}qDnb5XwNui>Nkmo<+w}#91{*;`n#JWaLH~rM*%?pdg_s2UqEq$HtE-H9o-uqs$ z?X}{m-byWpgsYafKYn|SYu^6^ZW)$#Q;UY$^Rfr`{;z8YJK0;|XQ{O+BW z55zPg!l-nO9Vid(3Cvyx*#GlMAn{i9PP@Z_oC7%O`fjw?7K=o}OH@ zJL%hlpkLjs^~pI;*Z(eF8|yf){)W}m<;PT8y(fi>?>l7cf5&rAYD-`5_l0+SKi&KD zbd7eIqSB4ssd9&ec5o$4N+DX^7nE>{@Kjkw~T+?d1&+JkMfj|JO$lLOST@G zIANNc=V|3$wTE0%yTsyxoR-*an&=xRXj6Co?;ewU)!z}7I+5Gwxy#iv?LMvek0ET{ zr}zfPn8bo8)tlKfi+zhScXwuj>iL+Ok4Hhr2Y^}* z`TKsh9c*UbT=q69Z_h`!7J+@A7K`TZ`NcL_&3BRie7ilLPHBV6lsPq@PS$)l$bQ>a zUe>B)LGJBsiJNAGXdQiXb2H=pTQ~Psm*?&O`)$Lw`MI|jhOSLpYqi$&RItT5=OcX+ zJXAm%LqJn(zOzg?r`|br%4^;3cUE@4UMQ!Xo8#I2Ot<38MR!o|YU$FYTjTVP7e;JM zVx2m5>Y9j+hcwDddkU%o!~afo*tdak_Wg?;FVo|XFF$Sn>}&b`grm2vo~V#H{^uQ-P?3EKa;!Y{*ndo*unsebdi`D<7w#mEayWITsbxy5QypU`?`%^KU*n^iW^Mm%4 z39FtC3*3}w%urb^a&b{|^sVpj*{ipH6RwM}d>=Nm^t9UbrqBByru>;;W&SkLv)%8a znvcyxrG1g#d5!;lwouKR)T8UbJ%wSdje}ClkwZ??r(arCncZjoucA-pM(2L{zv`!^ ztxr7>nV$G|^ZxZa>Naw1K(lco{Uv8@6_b>9to_9Yt{JZq{$s2Nd`*@wX_dnSENyKUQ5tp7C&5VeM zBlG)T`#s-Z^7zu@UqO3nbf3?;H2u)uZ{J0~EM0x`%dKdU^)Ux;sd{VN-_#gk)1RU< zf1SIW=jVIJ9X}rn5cvLD`^Jy!pPuh>d77qrRm#TE#Vtcc*<^vGtiRl;M_0Kko=%;9 zBVyxBFG0m*?L8|FY&Kc9dg40gd8<3r7Uq7w_T^=*#9aM%hdS)%`Mun}dPm9u$t&5{ z8N0L}?mn9HFF|hh{^&#h)8Fr1{A9(sFaOW;hF-lp*<`Vf0~2ctr_hPcr`hWdrWHnn zJt$SMoX|6I_6>NHtQej zjZA9}V`;JTDJstOCVtf7hPus(S zWjxAw48<(UsUGB^Oi+ht8zuz;SUb-~zSJ5Ot!OPN7 zT~QY%9NH0a`HFT&(7_K65C1sw{NK#jzFTuI|I4(Ro4xzTr-$x~%KvKQtU7f1^TV6Z zJ+9}cyqzVQlkwi6O-h)>XWlk(-S{8kGj{EM|C)PBJ*Vp&DW{dc&QFx!*nR)ujk!zm zCPf){vMM-OHGA?lUaOhX8B_aVWy#u_x$W=v&o-3~4>}dSON!^I!$dAeJF%V)S?8o) zt)*{lDrJPf-RX|ympgBHzOMZo@9Z1j`tx+*`F&2;Z*6}O^<8cDE~^Pq zm#m5`7OTH^+VOs$fgyWuWrqwWQ?E;R(i{k-Mr%rWx z%%K|_lR>NaW*R25xyzP{fY$Li3S6oEwq(keZ{I%k=GQb&RCWi=%^DOvIbkKR`#}?T z#HJL^=X1;DuHC3QpCHn=~xNQhhCjZH{g!d&8_bJ9?GWl@*JE zy!QP#s&7>JDMfGppCV8*ZJEzZr%5VPyq50b%2>NS@5Y5hng4emvuhSO*&pbBJj0pa zc8c};J)8O3w$EJnpEtR<=7XQsw5wb!TsQL)ug=~wzgBncdcCEVYcClrVYFN{an&{s z_JtFd92Ls+m%KZ@fiGi*`hyvUCM9YmrK&OoCj>wIak>^$r@Y?gzfDxsl+78>=dN6{ zb;-GnZ~Fa>{(q7#Jly^<|GwR%KiB!&wkZZ&P}nOnXW0kwwf%F>-l=1l8T=xPvuj$x zJ)vu{1&Y=>HLbFyCu$n9&nk0OZsFT-lq)N^)u1frm0r>zR+Ie+4}M$}x#j)k>$IP5 z65S6RTDrz2-RyLHq?3q7PLS)v6FXZhd^I9p?D#Aw7GI*eQ&9QF{|)Oe)|@e4xbnf( z_4k)`MSI`i_qnzI_r~duw00USm~>2}xX_G^!e`&QTJ5U7@&82fgPq|Oe;=)mw904f4GY>Z;jmzu zh-**cJ>mLi=f&gQ?p!(`-v3YSY4Oz{AbFX z5hQW@)QdTXo;puxnj?B*9@nb997m^^Kh<9I--kW9-k|NpS-wN}TK@9evrSu<^e=UP z(#`qv(q{ykSa$k3X1DqXU%TO|Q~QN;*Sg=PCqE><`Th3r%r9q^_e_smQQ$eVYg&ua zcX7FevLCMMYpoL5IAurq$@e?|Uc7(FYUj*VYd8JaTB=jMmZNu8|JysqHYBoEb-O;> zfAjdR-p>6KwYL2~=PkS2KV#Y2tqv>o({A39+vRnvc&0OB>glGVZ*?LrpPhHxe9?qI zZ>DXw{QP0F=TbERc|W%6{-3sX`Y+PbtQ0?V$n;M2y{BtteU~ZZ;8l*!%s3s$qbsV) zv3Bv&+X7{w8}FuCEpGTUTWp{0G{xCMRkyrro=#Yt;A{Q){D0Qf@pH~k$a1plop^4+ z9QW)njd_)YjBl^s^)Skk_+9@vV4MA;fca~+T$Y%rURkBLZSvjw?`8FzTbTb{pSYlu z!D(R-<5N4SY3rW8`&@r=mnwH*$O%(#H=gr}vz0lRTr`($+}xsfY>TV!p2GjxJ%4H> z_gOYp1X|4qOZktmE*U%Y+M-W<+GB1HOta#W%FvDrB?m_?N@b} zY5w153w!Lo+&{^i{Vicz8jp6?%E`Ii+jBoYJm%o_`1-zYrhJx91RhyD+jLs*@#*+~ zM!vqjAzGrKapt<;Z;zk;9546f-?3wEQ-VO#S@M5hxPQ%x6JQBh9XiQkrFQGNwR z1TEUKC~EDZDM`;yPX2j!Zh6s*h3%IvUOcE@_mR8ocJB77*4%_EQ_RMKg(AAx{uv& zHlMfKv+vDU$NA#N3uROIMCt;)0`;cPv?|q-HqT2r(jj>Jz}@>sY%7eJqxCoAX)cx@{fr>=j<^MNDrMj1~lY>h*RsH;C^4$y`6@b9K?g zq)#g*?kPO_Rj29^YuTEtvb7v*4D*eTm5K#vzbFovR{Q7t(dh#B%dF$)es%uzzl`C* z1uKQ6Ezg?Q_h<2W>9rmRIp`raw~CLuu3TQZTG(#tlas7XCIVkdB33za3Oo_YSmiXu zE9a8SMui(6b|2sQZrkq@H)q7U^`sqboxbTuXZlPDcAs~fTPht*Hw)^BNEs|#x_Y_G zBnzEMyr-`fU;jBh=-=6xzMn58SDb(M`tOTHOS#%Q zebb|v(=&CX%Up%Scpabp6Y%!dlDQ_~b#0=Wp(^A4y&sai_U~(aAN$AnMzI!8@2lPG zr>wiJwP!!~%-T`~uEy{K@7Egr-}3*-*WK?HuibpeE^yu!Edx<+*JD#kM3wjO*E%yf zdkcv=t8!GnUZ-C9WL~@EtAs-*Hm;df%j!M9s&S%PLXha9RnAI#zHikAsDN6ITC+;xky|85gk^+9n~(&>FH zCN8YM;UhcVs|E0)r%=t_}}V&ctd1Yx6a?2M{R14$M*QJ{+`)kz*T6==@#~C z)s#z(eY~uK6P7V*alP2}vHwoZ)mRg+<94_ElMkQQOaAxyb4F29pr?=CMi-0qY`Q8& zg-0^Inp?$qYctvX;|na0X6HXy!F|5<{9j>KmCT)8(-PA-n(HgBsVysCbpE>Gq%%4( zI!vt-u6dh_3s3v=#An{_-*#=UJN(tAIk0WGIAM*>Py%g;IW}Y0 zrPZFi`}aM(-h5BH<-z{^zxn5^|J(H0{mQ8OaajHuBY%a0O3Q-|<-P^$*Y|r)R=a4m zM0BMJyG#KCXbkN0{Qouw6gEziir{Q&IREbZO)G}E#_4>A+xU_n9qBARdQPe#$gA)% z?|wHeSE=KB{=Hfa+Gq~iRrqGx?Yz=b|D~d2_V_H}}*W%VLe`r)z$mj(>KLT|VXAotPv*V+7$0_H7eRYh4mUue(Syq{U zdzdq`bgAo(J|W&#n??GnQ)XGYY<{q$nc-7VfN9^7-A8t?o&Cid8}sGs;vc8#Yx)cA z=W+fN*y6_jBI9P%)V6~YG=p_s+&Pl$ett>yz0*CbtfE3)HeZooT&H8e)g$z8zw8UG z7gr`FaTY7yXjza|@V2&N&%>$f(od8w7nx;ZC3th6B}>zu$q^HEuS{`K6P@+TWMiSo zT{S(sU+glqulyzI?j$-e1-6K;(%bg)df3w+$Jr{(9-q#A^XTLIIS%(vci+_9Xfj3D z_b10~+0A>o0>TtFMEpvPlNA!@>bX>MtL0shQ}|LRr&&>SDlODFs5 ztAu#1pKe^3`0;gqWkI@(i%`&McQh0bqRu6eJ1Fl!@Cj4Z5B=1Z`{! zQ(Um#>-VeDn2JCAmKk4t%Kn`*Um)OEJL|uYD(4p zSl$4+k_(PC|31%ueoA}23x}hKYyRYYeUE4GN}Cx}eo6spy67%{w)A=|`*H&~! zRZmWwtoFhn<&)mzpFdmezk4-RY`7BqCh^=HOVFuzk(<*#e(bN`!#8J{{Qdhf7{)*heUlmq1^xB$z=bcBZBT%`ad=> z^CkTM`+a@0-;3~5ENp-45_0^Gnyg$I?zx?D&wk$=y>NX+=CYfcuSBdkW@G=@ena>4 z%hzOs1*VBf8ma{3tceK9&QR?yn53|q_mmOq@)w4N8`lQtObt92sBm=a_Y3O3GA6S6 zxC*Rf^x?mLf0oJ;2kp+{X>Q!R)YY!fIlOS^zcrtKOl#mY?)xGcrD^x$*NI6p6QZA; z|08&Hy0~#x@S%>HmNgMYtsLH7ejZW*8j74t4n1&vmX!MPrFX^V<;`;GoO2gG5c=eF z>GQLywv%a}c6OL}1}(~~JPX|dGt6%G^oYy9(L%v3sEzlKVRvK;Yvx8p?+U$4_K z*~%T;wiF{f{YRAcYz`zb9t0ULy#^K|-h7@b(OfyM8^8izKaOH(!( zZV6FIjJv#sW&8PkbC}!BHlF@?yy+v?;%L{?ciy~soqRJwBlO4T%=C-4??t!WPsz;Y zILU3WbV>k+R-sRvhLfa#+s$2(_7mW#i-;fA+;zt~)u#9gC( z(^q=trMu5kRH#24qQM-R_v`W3FDqOQmCikDNrPDws}FSy)cLExo@qF=sD;dFNO_MTT`w_y2l7X_BZnJyjt@5tI+d*pG@j1FNHoi!My99{iizV_t{%@KL~$aZS23;;6HEF>S^IhOM(0E?i1~x9U(+ z0gKceUq(;8NmDMdyyQ_1iub8`u;+B9m|$|hz1HblKiOLZ-q$M~_VN(&Nc_iN@AToVCszmW01(KOjUTbbJuN~tc( zL3ezT-mBgzZvun@s9@o}@bD=mt6XWxBQZO7NPk=F(z5#j)f=lxErH zxYk>X!adgi2y{qVdoV=k)|P}Et)E}drx!mv{>|mB?OT1}H5Nqw5QTx6MNS20tIi*)CxTar0j9AwW@0!UBcsiBrIpK^ays{t}~l$y!;(!b^VoS&6J<4 z+M81@S6|(cW0tn0HHkBC_w1|R|4*D)%ejzYu7>}#NkWfhc$F0NnWeZCHG0<`TO!26 z_mbuD=iDQTK4<*0UnqDuN;^J~Ikm%a`hm>{byhMgKDlncOSHFLSx=|as@X|-zh54m z^KIhYhx6_G0`}{tss5-cFYW}xPNy$u68#saf%R^`Yg@mHZwX>s`LO<7>eI>o#;aEQ#90?Lx;&Z?ameBK$rGL;LY?|s zS8IG&n-}Vs#k$MVU*{l4ds$!8RF`uLdtId3&pPZXuzQ`6&EzsHhUKhEur`1r%PM>{$ypyibP)0P4a zM!~K-zq4rPpJhH+D^sNS_e2Dd(q=n(wTT@M|W= z0`#VXPDxRA>q)q_CX&VRz#Pls9dEbYo?((H^!wdzeRsLalv?@LH{x11_cUFf6SjgAZWBBCrJ^hs{S9ablyWP8de%&qgIa`u4ZU^woEM2gB@#M*V|Mqhz z?)Y{qThcTub71UNhu zvi7<&WwHjH;JL#)=lS2SpZ#SydKj36T;B>_%RiYgF+Y3PtK}SvR90?v;dpfAf`+Q| zsy5#xF_p(6=M)^zz4z=zvt3$GYthu-`8ygFS1#SUptI-nlNUOC%}xRytcon)telVq?viL^!c3Q z8_Ul)o)B>K+W+?8wY%a>>~~e=_PncV6BnK}SJ6db?%}Je%KR3zD(I^!$!*A06}V~T zDSdx(x{-d_?7ycEXiaHmv@MBLy}+5TJ=fBkl_}?@qLbt7sXZRL*XPvn9l!V8S}0hl zgDZMHf7aftW%2cv9<22{p0Txwuim10biy3BsefmDP4*K|?EFxY6w_6bbiq(V{lw8L z*4A6MdaxYYIjdr|eI9pM)Ow4o+Mv6U`_EnXQp#Gpbm)){szTtYyX^`8{XyMW&bht zPPC>%LEj$X7EKe2_6d?11$_%-7N30b);MdPa7sNnF|KIo(_Y1~P&))xU zvWmZ|_3h(@_3NC!i3M_O3E55rZa7l=*E6DQffxXfN zkALe-7oO?YHT6jnV?@%!&IwUmP7cSI9`bl{OcZ*Nxu(OkF{92qcXOH ziTE~|G+p3y`qQ%1=rm`$vKXH@M}9)KYG&4jMmH{By9TexDj|~|I(qo4KAdIzZ}R(l zKkr|db$Eu6m-xN^rgz2uZwO>ApKX?_#BZ{6F_&JY`7j*{qb#n{p^>Qmm4P?>99Hw=yi2<`L(awKWqOymQVln z<>j00_v>mNa>qY-xqSYzpp_GrX+ABQxonx*ty{M&-d?#p!AogQtI1J|b|Jnsi&wAi zHt_|`J8t(#eDm(zvv0TapTFDv{+aRopJx;{PM@_rR>ZYO-hSTnxT?-hVfCc7Yv-SC zRLFXGs1>x_?9cE0|E+_U`KDJ8|GRhElHG5&-L`nS zWbzE#YBOPVKNU|Qy}e(8)O=<*Y>aqvGkyNkmCNTnnvvX>_~pgLxCgE$s#Hs(uOt;4 zJ^kHVZa1HKW!l#;b|#Il2fEh>R3)1pp49mMgQqp;3l|~FsiE&|d@p%;Y*F@D=)#I4YbZ+Zgtw<$%QsiRNP$Gh`1ZozB+RS@3xKccU*Wn%T~W6k9ggP*i~V(qE&Ecsmc{MGfdY0t0gFZ{#lm;L-E z?+wMoK#u;ybJ%BF$_97^D=BAkGD)oty%+IIN;_|Vx9t9Jp_^I*|KECjcinsui*&(b zRSUjfV!9Q+KBb7Ib(L!Vrg=6k;d$->0k_@<*Xr!LwXSNxyom?*bTzQ=-&&lQ?b4d_ zR%5NhDrgvM`y#QZ~nBs-1yz>_Dc$f8^v1dxBl48 zUeWxnx#yj3L7l>0gZ@judV4gMnuvXhcwC_N_;^&O*@Zd$oO3>Pr>6e>J;yb5>cRuR z90ix%Q$EVrD8Rz8ge7_D^uV?JR}PBWbUJX&cMLo>v3SxE4z8(F%){3tUOmij`0e!N zz`zH#C+`{lxzg0*X|U$@hFPhn6f^R=M+}N332R*uS+TM2(*JGY*OBd*zb!L+KG;5-=itt(o z3)gD*iAniWS@XXp{^scp|9)_`YDKDYi_lyvH*+nw{wxKLxWzv{=55iKu=oJG_fgOD zjuqb|cTL-KOhU%%*BYM$+gcB+fG{PNxKr_IXD9M$s7K6xH0NXQU5ho1x6VBJ`R&Tv zyMML{Ys|KN)3V+#>Y=gC!hj_aLXR&nMSY%?r1|jd($g<@eC2DC`&!EM)?h2o_3D&I zS*Nup21ZqUIv+A^uVeJ96P}(5wc9)-?ALt`5=`OU@9{9!Xv#PJU{|SjZymkYtXV>K z7Z+wt^?bN#%{=i^#|p^@AzUG86>-exq+GN29XRHjS|lY^C46n)AE~|N_uMZlvM-dH zb#s%=?QJ*2-pkbgx;)?FQHQdGX_g4T%?AeOHlB|q%M8ABTCVth`e~8f^{C)_Pzxwx zYnG__-ICzFm%>*&_|7zH1uYPjG)^n{dNq9W-?H1rMNd4Y1Z~;2t>}be`-jW(|4oT4 zySbDvrHx-cF1*HPQp$vejv%h3?A%=$YiAmza$R2LySn<_(;~|zg$MVl-!EOecCBCR zohw&Q#sx3i@H=n!$Fuo$lkM$4^O)Z$QQrM-ll0ZBt#vtDAIEOZ61^T*t?O_9*ChV$ ztMHwFzukT<#<^8%j>smy2cW|iKE8gvVzT@Y!*{_q#md~%V zy1d+9y)W6%?q|xb-McgM^V7e*xmmjYU@k-c>qmz-%~&xvH+uEzomwuHX13o|G0L|VX^ZS`_#>^a@fT0edK(o64Y>L0psL|SxP4b z)EDObe0*o8OxYXrKkQwN?whA3>YNO&U#99OA;k7#lk@2w+k~vOCR{H|!m8e|+a?+R z32x>wv*y24IYE7nlQwIVfClf)sDr7}25PPk=iglTZJJkOfrWC$8jChlu6O&sitVfY zvA-&~lCN7 z?BMeId~9+5MKP8e@9YG)()WZXu5DWGS|1c^Wk1iL*?v*jQemf*`@fU7GoPvn+huiP zwY;{R&&@0A-!f?yUQ6=K>~eCO$+YxF!TUM0XBOVLt}tQ7jfL9+uKqQ6oNqUqZ_bh| zITvQ>?f)lj__3&c_1`CdX0R_YkTX{JYYMrcI(^D`liO<|qg>d2qX#h-YZ3 z+thqrUlY0}=&StvxnhT(nMZalW%=^yjQ01!qjTmL-hXWV`NQS%qN``cjlW-vjyRqb zbxVn>l_7b7ej!ih>A*Ldi)4ImR!Rt$0srd&Dkg<;^b>5;xV(yB!l;w)TyZ~ zuUR-+3j@}KNgA1)FSFkI;pzF_)cgLt>3{eHT_T^Y&hk9nc6Bc2`F+<8JNut|{EB@& z&Cy49Z~y<93y(=(*M6!wL#VMtC{c7_fXS;l=f5o38Z_sy ztC+rf(x&Xw3#K0nKkW4SmHt~9zV6ejYK%^&M813}!PIHQ^i)BpZyTGhbNtlZd4Ejh zY^|o0o+x>pm*>8=V$PvsHl>G<%chF|0qp((3FeN-2Ewt2AZ+{2Wdai!_lqSSZm z^Uj=`)5!nO?w;6xi@=p36%Sj*BQ~e;etvdVx$kk^`K^psmq?{K>6Y!=H-GAV8sfEA zL-*!}f4a|X|I4fnU;pr7`?Rdz;;^*<{~JP@x9`uos^$0RpiiB_=ifeelg;1le*V4Y z(c;S%6~FcyCLiOGtNjuvrXTmlKA11f$!CVa!`v-(uVe0RseL}T{8-fKW4+Rq4;tCo zzCPX?%##u=@%pVm*7~58PpbR0MD_N3Z~`s)dUkg9@#l8GEkP%d-nxDJ<-2!jyWeh8 z_6@fC+3EkIc9Ymz)2Uvm6C!Kh%3L}3{(kk0D_4%@)%;l1b#S7U_bVN>)lxGYQ&*K& z<;I@y(PI*HToqxL&v-V~S+1i+LEvA#$-WN)RulKCS4UVlCa46eW_ug{-TQH!p8xY# z`qBSu|8KsxKjkm$f?T)C$#oakSMfME3xs+`?kW(}iDNjoUi#O0_qSX29OpW8aMJVm zB>{yuf?jFA3QFi@pU)`e$)dERFJ^OpfzX;0Sy4d`mVEjX_VnoUfH=XBsQcSh*PInP z$!u45fM2Zr)VtpfUP_7?nLHQwicZt5k<8yLr(s{TtQm@9_qh?b-RmRH{Ykt?`r6 zc^*$VdX-8h?fJZSYTT4XWwxa-xHHzsStxhmDv*VkWc-EX1Iws+Hixh>L0ix+XRTdD}|b6pX&F5rOS5h*jB zI391Y=B?3ZPyP0O^nPE{_DT-UBYdkkmxks~I$d#P;pE8BbKC__TGWKBq9fBM&-f_X zd-nR8_g*F|VvqQksUHYrgC2_ywBc21OOht9P4kIDXFAw%5tSEO*t0 zcWdpes)Ogh3=mq&(z-{?s1>=gWUs! z+O{pUEUG-a&e}VOed@j`eY~z+Pp3?^)qHI(DOd4_vCr~BbkCK?0pI@eAD7@*Z1ehl zgzMs|Ekf~vYkf_wT{c~8ApCnpygx&GVcV6NYvkAc?_0f6X76tJwm)mpECr z8wg}LIy!Bhu%vN54OFiSEj;_ae27EMsSXdbYYdV}*p0V&Ecs=2a8yjMX=_ zM&_1H5t<~y<*PDPXk)R(!~QD|UI{zoZdz$u;`8m~);Hl{=baz;<}MZ8aii(0J^P{N z*J+9o8^4%F{Ly;zQIMmF{~pVJ-G2|AyiS(y`#iVm>GG{xxAMJPbv0}6`GZm3-rn3( zy_Vja{(Q~i7|rXMO@%VSdeeXVp4)mTX{Jr3(dP8?&wf1af4*w^Gns3DURiE;bl?1&(_Op8 zH~wC?`{$X>z8+q#6AF$9wj1Q%J6%(MtUNGk@-n$IbLxJ*1f6`_`}%s}-L2P+>JG7# zNEF`AuRAO+U)y7E_e&x-H}}kJ^Zx4hd#``b;$LC1Br{6fVr8VJ2p4PEx){y_=k@mjLFTL^`7#S;r4tu7Cn}%yd$4p<*6(E7t?|E9w*CLw zaPscYuDM%H6~bR{yInLX-}}Ssx3A{Oz2bcNFeO8FqF@FK#S93~sFaQ({W_M{hd}GSLb$c1>PklP; z$9>|{kA(p$=N4{w!n)_j2l<(1l|k3yw@iKXi!Wf-yQ}$zSE?pj&i?v;^_uN^QylGQ zul(;@w{!NAn>V*dyNc9pH;hcaz_Pfl}%uiNyj^Z3oWTXOF=F4fJAah3_L z$+qR~RCHRL{lGf|1} z9?JfH|NIiq$p(%N0)I-MZ`uD^GI-NX#%u3ZUvbom{QioIi*L!7t71=GY8kQ=_nv(6 z?ELmOaT}CgFTWinq4&2%yv^!yl6B0i32H0Fbta|M#LG)v_|bDb+u!Ew5}nJI9|Hc^ zMy`L)pvZPsec4~`-|v1)&f4_y=l?g~B!87m+{u5}uXuIZ3OTpkZxomFoSs(x;nOdn zFB1E`%x`9dGA;RF+pWsI%PG59e)oHuo^9Kh9=x~{@#rIK_QIT+GS454e~(W$|FCnV za%Za}`-E978e9QE7p~p%nk1p7E*3j!P5g!Cg*}R2&z^q&`QEjgHzU3sJ~-jD6d5Uzj^tCe82zB?me$pWz_Weu)w$V+NUF5XD*VgkF`FyNB#eqEi0>knXGsg zE7`+*Jm0J)V)rxOw#-(Oz9lbuJ8c<4SdtDLcINn>+aT`dDctqcDCj5G+~U7X`b7-+ zbqa~c!e_GUt1bDO?isN{t#f*Ebh0P1sY)C6jo!nSM}hy{XfIs@AudL-F#oSN#Vc}wza1I zwqHf&&Yim^X6K~J&(9Kj7Vh4?o3BZ$uobihFg~_Yb+H={`_l`zx^v#{`|U1an#Q8* zJnN*d^SzFIY=j$ZD%g=v4b$VRdv-&^m;&BCx)wORHgC@Cc{(cF5V_2$R_n}$7 z;Lpe7*BLJz;EL-FiVEJ!!v7&`O@w25x_WMIZqD|*Wk(9ns7{Y@nzgLd^mNqvyUz?K z$Vt3N5LkOj>U8Dv`Nt*G=Nybop9{M4$l~J>;hirQb!TK{CH;Q8efi3jozI@79qX4r ze`8~EW=2NBl@);=ny(YiEm@{_Bk1>C`=+H$#eGFP&orraXX=RDsB4!EaCFi8!t`aS zimR6E1l5+`tloAX)YIbseidyS^WFbkZ-^ZhKe$ONl})YY$~oWvwOf|n6^*T-d&` zJMozIU#URh10St~JT~4mVZ*kqUAQ8d5 zi}ybq?%ki=z&<;6$-hIqDi^lqDLZfSX$x;%rMrr?F(6X??QQcJx7Nf~WZy{N^ncm5 zLxN9Dcb>4{kaIQgY)^*ZUy+RI5%jvF}HyT5jTj@Ab2%p4>d2@7DM15YLV0 z6kR(O_xt<(li;^4&* zq0PTDRv8oO(z}oSes=X8kKzoIRg&tw+F_-}sr?hbd=cej>MV`xQSlR6BI07{smC$H zsMP(|V_qKq@?Q?NtU?Q-mhRr%eeH(Olagn}&%KiapBVSm$!FiR2=_mAv+MMiO@BE5 zZE)FD%XUHA<7!v+CCf0Km{VJB912sD%AUFYR>bSKx<)3YPg<63G+cB`eDOzHL8Tiq zM;`5EES}`G(<4j9%X5;C$Rag9!xwA9*%@p&jVi3Kx~E6>WhE6{Qw*+OV<&m|T^78WX;tvPeH$U#PE&}a}1zl-+ z+1I?X-}dcV9=l%``}3~Wlzh9Hem&Im`uh0uudc4XS@-*Ge_mOvPLS5rnr`Q3&%>?r9rnf-{QdPcWOXQL0%e+B>?zQ-zIK0K`WGMK zR5vJka^ja=SxL!<1I+v%mg?7bF3felUv`FByMp=m`vc(%{4Ae}fHwMzhQ}NPZ2|f6 z@-pbC;A^+4{wMY(&0ePIRk@pesmN5Xqt(APPX_zj9tB;)X?R@buw3<5)rwfDU}RxY^W zZQAGA>$u_{%UnK{LzNr0y8cm9+!!7HwsQZ&Z5smLe#n`q@M-FdHH-Fql|E}CFlYTW z&gYJcOXS{swg0{;sOPo5<4?K6-{Tmh7(Lnx|E(5Y*B6(?8P-_8Y}t-Cb+7K{IZI5M zJZtOe@U%SvGcQ)&V~$Nb?jFxNGb$%%L#Nc11C_@&E>z|4o-?ETS3ke%l4b?(u;q6R zPshi9+qZq_oqfmhjSDKZ7jMe zJz>d-7whvmKbP}=*d`%nz!&Lz@!aPn+51w299M|67zMYSQQQ2c&U~ffHpy4w?{z0B z%6x5$Vvx;xG>f-HPeFZQ$l6IFylUB*M;k6RUEtzc_~fdq_m7%MNlZ`G!+%LugmJ_? z6E&LP@u2dmSWeS4%OsthPRu(M9G(}?C^~dwZj{7kWe?TAz0)f1hOXvpb#mF7_2RW} z#I{A?PJ0E+tL&X*FEE zAyUX}+y0a8$9`mQFr9L=F_2YBc7b4v(}PuFqF>A}bv5Qpyj8kpuFmTf7WrQ!Q=fl0 z{6-@99CxYft#tX75^=NlGpuUkU!@s*RwLMILWs7eBiplWJUh%W>*sN8`E8S7wyo2@KrK?WyZktYDZ6 zI&?4UG-w3v)ym~N-fTMkvw^w%P9ZzHT!jMYoVoOQ zm1@;*w~B)n-v){pR(;7h)+-%ue@%g7McC>YSH73aeAxMS=c_L5n_D(EKU>DJmNm%o zkVb>=G!N}l=M-8OOHKEj++xt-@mR~+cgB%9v-6&vSlpNL>r4IP7s>mXE2PrAy}R$H zztoO3H3$jb{pXSR{u5`-@1Fsk>T{4?{!ID4&$9de|9x*<{w}7^?pH?H%~bJo_U~&L z((3BfitDYXYX&bX_;8S&e^=Swy?aY1PL=xb?(JLFg!8uFpH$!fEqBhU?%(J6pFxv0 zm7kwYJpbJAm;ei7ZEbDyw(yl92Fv#M^E+^PPErGP4X&;Z-<)z%2sD%X(`$*ejriZY zH#Izt%2mHPxWE2s_MN)pvLTOKzDnQ9eE&wt@chF$;wL*7O<49UP0jya>sz<}wC8in z)7m#C&)oCbW&gC395NeApDbAsuEOT`{{4?1oop)Mn_LTdPjt_6kW3L>`KFq+a8}Zt zcHPygh1YTl(_01C#P1aIGBj~x@w&RQFk0D&b3#aROqT7#qZU0IT{7c4 zH&mzdqv!8Nb{+OT$GO-Wm5)AJvS8_i?{y99_D88~QYl#bJVe_w%lDeShG(*OlvhRe z&#e2x>2tTwJ$3Kzy5rAfGJNN#B(OTh{aRuhXQ3|Nnjh{h_`pk4OYf}J@BdO4(hnS0 zoffkqb3@a&URj50a)+;03#rZ-)0)OgU z?%6oyowH3pf9~CzGrRZPTR+`b(wfyN%0_X5>FG)4_gLchv0wepdz;<;61qX{V z<&~579QRcCFrmWh+c~4iav24qStn-owkbqR_Op7(ZB}~&aVmD2W$jaKvVSiTX zi07jRGaqa+_w3j>ZJF47&)fW|>7pB|QpNL2uVlREsjPIp8v4QO6lcQNmKr6C)|9^ zapBqC*gZX}`IZ~_R`nlwBzgSq5+0RU)9V}N8hYnG;56Uy{psa^9cL03@p>)U#Ommv zVB7B6|8n-7&F}VJi?Z<-lkIF@Uo)@VOxri_yNAHBrQ%!4E^cA+6765N zJ#2k?Q(eaYlhXt zzy7CpT;)^IcY8kjrJbL5c8+Cn#jlskK}X11l)hW(Gs~n?(Yfuz>-hh(KoFJ+8_Ser*@dS-%ZogY54O({Q#8vZhbJbHXJHuo)^O*mo ze%7^mtqb~+oFvv5M9f~|>FDh5FS<5)&z9{gQWLbd*Sr_AD}N>l>SdgtUmQ38_3il` zDzBM&ni}5MJhy(c<+5MRr^)l5O!C%yc&GUM(+AD`&sHvdu0y(+y&$o*J!P zyY|iY`*pQ_*RNc;;;yzZLMLct$cuOHp8ffJKK^x7X*%6U!-&=KQ2JfZlUWxI6Vj>i6)C(5-FuJ$Ly+zcC+|9G<8&NchC!@iGa z^LMV}R16HV>X`d{B187BU6o%x?*F)=&gA~-9y1O^G~x`fdEiv-W8^f@-blxAwIEwKaU)v|x?CjjgbI(zFM+oPX7Z z+e&v zUk>tr_;q+1>$-dIIeXL%1ucaavDBQu=(1b%=q@9ls9dIwTq{L0BY}wzPJOzmxn#$E znLYd6G*U$Y+C%}|P?ul{c8HHI|T^`>B9whq6 z?cZnYy-Je&@;0kJFed=lM&Z}9&+|E0(VMEKt)qLVoOiOwVI}f&WUVa|P6)FDY zsxXJ7NB#DBx|dS^MDfjg$r%u|XpQQd7cClXkACwz|G4n4_Kc^k3Wwp0nPVWzFM&ubSMP7 zY>9w)OaUY4rkvpAeyIts9VQ+5`rOpa?AeC{Yq&!BGi$!>OqVoH;{jc&16s|QKEKxN z|KI!n&u+=QZ1G}2vxG^80BHE{l=k{3n@;N`KRGcGw3YAAm*w`U7Zx~zmN9TBg7*8V z&#y7M|Mwq1==dzR!&|S%9lsjCv*~e~+}X$dcIQ0R&o2~MBCzq#PGgSjfNQ4jwU<_W zy?Xs)?fk5*r#=WeXXfQTwZ8vb?lQmqoP8fy*kAW7;&`gL>S`8WxvmITh?eNA*|R4G zZ7O)^G)d)Qm-e~`Yq#Hf^lJ6`XQ2D6yiS7dnb%xC=aAX$oXrRAj=ZrdD=iJw5u2;y zt92}ngDYqM-*0oOUakCd{{J8T@YqsOc9{Z)e>Z>e)QY(N+*wvucIn2A6Gz44&m0wx zpX2SAV%sJkviVw&*Y(qj-WwJlEd@@QE*2*77=Q%{o%xW9lF!5wYfc6CFRB8vm(&rdwlIzjoTusN1}wIdVQI1Zs(RO z-BoI4KE-p5V-?@EnEFk5ysv7-T8bupu-e8K+2-)lL?hz7#r13<4wlwwZj07EjZmIz z?Omm@@!gfRYk#l$ZhPYLIseI=NABubrXEn7WOhrXLcqjapnbK>q^rx0p8HyRBx3rX zZF(nGTL;zgef?jzeOZCs9Iw}%TE0GiR=;VMe{glZ^PwFIP8lCqI@f zRY_O7E8ibHee8SwO5m*_ zNwLSw3{pI9o?P{_Y2JpmsZCCimlSN94l%g#c~{hWs%zgC-nC0eymv~B>iRox0=;?E zHtFd;VR)|d-lO8v%+#DspDU8yE^(Y}67qI;>7Kon6P)C9Joj5G^Y}F{?Yn1Ty~2-Y zqVJ3S_Fpo$_-ZGXtCIIV!7Hr0QMqfWQ7p&t<#A{P{augZ<~u4R@Vlx?;s&W9@I@A>Gq@9*1uFf2GCBxqBDla3vQ-P-&pk2Yu~@G>p|C96y3^P&S;Q%Nu}&=>GgZRr$+ss zcVf*ZDObTDuUofoS3aAWKEoi9$;+}L$-~Lp5ZLHgyQFCqj z^q1m(b1Wuu>+ku%e14H;kZnvswHMEuz1QVLx>DEe_`|j8%8Jm{EUirQCb%pS&8SkW zGjffI$QE>as2P5B$LDj_mLFS$KU`DV`)d0NZ_cY)y3A|>dv|duhgRv#4if6PwhN@hzhYUI7w#yG8OfFtaOoQ#o{%WbL;w@cK_O)>>^e1wYtCT%G!#R0(;K<+b{Um%G30S zG24_yMgcukZTO zXVv@W8=U3;))mQr_Owj3Qp(BZc{8p(bT)je|15uc!tAa^ki3{Y8sUUohBl^Xb2=Z-lC)AvNj*DZiO!6S7jL{G4U^9*`cyo! zfmdyQzX>Y49}}>&P5tzd%G-t&5@)Ioul}>Gq4nWn_rU0XGOBaZ`r9w7mUM^5a!d=d z2+wVq%5;~%byJu?aJgM}bnLU`_b1OvxTq=Vui_ikYn!#AaK1uXIkEs&K7s-iEeMtZLVOI6crl`e|w`OOW6c+ePzO z9xji(aYJFs0e!7S^H?GaqH~0@zTYdUTeT><uGi}x&q(fj_~o+y@$a==N0o%td=frAIa%{I zJ3jf{ot-S14?eZ(*EE90@IeJg(#8{OA~)}N(8LWIr}$7iAJlrd>~B9eI&Wud&`K9? zZ|?g)j+ukjbMJV)Zubn!Vl~j>L~e1tl;3Z+pTC(qH7Gl@sYRfqy!`X8gW-%Bu(bfM z*B8HBI=u*Vu_Wknu1_b`i?7F)8|L0JdAIAe9;mbdZIzuG9(QtP`n;2%Qs%@&Wy@zT zl0Vt)kIvi4sx9*0wAw5&W;^K)}RCZiWdnz)!cS7ZT21}DOW-BI|a;vA{$>Wn{AYGLg3n($j4jQgT+qIncXV)` z={P&*khK3EmnFQsL6#*x({7)8;3xD!_GXx=Pe zE@T$>iSAu$kXgO*)RGe0l0^)@PmQ8(g|Ho5)_P!H@wKSeRSlPaPcp2kcJ*}Bob*o1 zP3w=B;dg1XTPzE754-0biuOG}xg@*g%Sn@_%Nn*v1$HekxzwgnxY#87>$W|{tG~}N zdADgJmV6sP$@&9~V;-^iBz@l?qIK>@^lH;XkI_r{l!EBtT>39Gh+vkEM>8 zHmLzxj;B~0d$t(P?#Xy`L38m;gJqqQMD~0+6|ED!sf|JZD!a(fxXpp#)@Rpk<&kuW z2+DZ5qM@33>%ZVT0>X=Pqda}zw+m*om*-6uDrH!)uRg+m@@7Ll>9v>7q%EonTr~CC zvn^XRuFamgX8WHXnt{Hz9~^ACRcNnjws7-i_GFz^A`Zclrx-CeTh{!dPwS0%WXEk*06=4QJ~Ari4sTbPu4Zhx5K?GwSN^&#PC zQOBwm7E2b_ny#Lvzj*oT=5yc57DbgFZvKD4PC#v`il@-KozLawRll>$+wqXC&;DOU z+L;*>zqf<#ox1<;+x9(QCM5?M9}{3R&wb}BpU*wMr}8sH(Zf$~z6XjV_MB|JwDsDX4Tt%3Vs=beKEH0( z#^mEgR|4G&|9-vx__rOn*Yx92_r_~RRbMi;-At2yx8rf&oC`}LbUy9>|9k(P+V6L3 zo@$3bs_eS@_U)cOm$DV((( z>umjXYUUW9{~@zs-mmQj8H`c8U)=;PhIqMrzF&B__}sa3r+BG?PVO|jnIe47>h&6# zHmT!=&*zrQc}^<$`E)vSpJj2k?zRWLNAo{S-~Xr8TW@Cz>;AX{H`C{zRk!=dski%$ z(Y9Mz+Mt^%L5nFt;n!#Jh=b4O1Nda)CnqQ0Or0J(!>-mU{@IDhJhFXP#NODvPi4PD!s9K^V{e44JNN9-{ntjh zylRG-{7aYawl11_=fH7&mLn2d1Wb6PJlakrIzK+8)0(lZS7zGpIXCO2!dDh|Xf+GA z9Z_+yQe64D?SA&=ORE3x{w-fK;+x+f6X)PZ;0+GoiT+= ziPyFN;bXVYf8_r?5$oQvW>!RiTxRAx8(u;8SvU4|Gw3fbiuwO2>(ZxU>Qn|{FF!i5awP0}}BuvBPpnHZEkk#O7dM=4(?>gbJ$%sZd!cX!UKn7nqI zjEe?K>!S7$rc_;J_fQFo4M%GGb=jHMuj#5xeHzWuy<6gDz=EYu1S2M0mMhgf9y9J!!%ALfkaOd)O$?2JL z`(9?;q-eM?5X3%Jb6CC7UPNis`cI9%kG5dBPs& zienWrMI(FCky$z@j1lptzGQOGL z?!>#@@6R=|%bmEs@0%&8uLN>tpUo!^P|nnv%5~oEw+_ha`+wh+f3!I|J6|vP)RWlA zKgVYO`L-|KxN`YiM~Od43~J9FWU?0?{Q11#%Nb?Osah=$gQhIMQS|4T&5z~w28FNJ zHhg8Nc)4qJ2!mJgG0Ak${icTb_x8jrsX1@^J!N`qS>pP=-%kC01X>X(B`y8)k@$X& zCBK@K-da!J@OIm6qxyd}b)P2B2i;p+cv5xxf+eTcU%Y)cJ^Rk){pam|7l2NX`hK_E zxcXZTs80v-+Z4^c0 z?U&=`f4>9Sc3gMJF78|(Tg*G(_U&e!$WLs3iC4dTW?-pp$P3zZxJ-EFrqAb&M18-i zBU1aY-{`aYn$!b33SIW8@bRup657~sKx#^%sLA9Ap@pxbuB6Q8dRUz}>&kV1)}vb$ z{AXk_&hELZqZ;^PcYDs2KBWbze={#eBY@LB;6EUxwNu*>lZD z5BAhP+-aKXJl)xOP3(rL3lnSNABoyl`ADsrW@{#CZsvPyf3u<2fp8vq`@Zy^$EqHe z4jgw*SaVFP(R5wAQ5SET^2y|Tov8<7uJJBX8ZuMwa&A2=A*4>rg0%*PxGxjts zIr*=wCuE^fkHihGC6Nny52$`OZ*_0vQfBWCD<0|ITKx3Q zzOxQeDUAEGG$lKGbXq1A3LpD$Cb&ED-o4&Xg>2I`YXf~_4k%q(e$A^<^g~x|_qIkm zWj9lU6KltRZ$7Er%#4OJ_{=N(7jznU)SOxqKlfbHTDJ3x z6MqCK#V`FJS}wRbTg&$KJS)aRu1yyju5n7oHQt~5w4#{P>g}qlLZ_J7m-s|TS1Z3( zR29lUVqn#x$YzuLq1B;6uX*KU3I54>Ez?{a{2$FxdB|;Ze(|g$Em4n?4V>0p_5RT3 zv!l-QZRZ>b6EikZmMwhpY)_dyMIL%`Oj#13`OwrXVAa(FDm(Nh^M4ciGC!|SrudSl zdg1Nd?S+pz)jutk|I2azd*|aBJByze-ADvq)7&D^BW>PS`~B|p^)X*XK{<5#$!|8G zRl}f>JzjuB-|K^^`&lXQ6 zIL|Q4l{#n1zwdXxSk%4a&!^L$5AdCMINQ06=i$HK@4?3fMP)xbKmYuloyCzG z5*R_VtHx<(5^inD%-MD`%~JX4)9LZ&?v~#_>#08XNXJ9v2?s8pw>kUhy13w!(>n3{ zWU@_T3|YGH;>OBfTA)sZM%RayCv(ovKdPxdr$KzmA&!KH7 z;lgzpbc-_R)@smX4Wl?u>L(Vfi*t(4S(cQP7*u`9h^zVN>eesU`@Hf8W6#bv&(|yuJax~`b7{!AnwOPwyWj27z8+uxH>z>b)@d3= zq1~_7?e5dBed!HaPsO45iDAz@kinqgm(AbrRf9Iq?zNx%Ej}Z1{)JyUSC(82KbT+l z+5XRyzWEzUUe5ke=ODBD-mB7?9;@Bz4nE&<*ixvjcjZZUl@ki8GZw`Zg=wEYFwyyB#HTf; z?=P57+HlgN%En-xgSyxhg^O*gd-d|TVeZT$1%F})s zCQCQ<$Lk1qzu<9pd9cvSl`YqZiHotL+-bf3!Eg~bUiH8x4(AkIyS{d($4?a37`kj! z+<5MJ&H8r<|39C(;5bt?)79*of=FAVa@)7M1ZDq233LCgQ`hK|a-8!^#jJLd&n?55 z6R)PaIBYajklL^Vl5i(1dMS6rtgUapf8F%%|7+<|2WDZn{KG#UDo6a-zC3bEhU#JS z%*5}qi7zMVUDJ7&a^-M9sRWQ z$ae>=?yYSKr6*PyB%bH0jUJ&)2QuHC4}^J=-H^ zJ1acCc533`wv9){q6m&(>{qY6M+gV*Blea{CT1 z&6QWPY`)z{UK6#o3v{0E?EHN*<^R5L_nBui(}2hDn80zvtx>&gZES}O&P3|ozIAKG z)hv;2*GCp{-7i#LXS0MK&CbkR7`7TTmfL6fOyc_K=}slDT~EE9>23Q|P~C98_2c3* zbFIzWi_|<1J?^*n+ZdtZDP(j0F=)aEG|mNHboyqq|G5o6-)Ff=|0(qlztW>Rq3PV! zw|8pK>;L@P#Hv$SEXfgmb6QZ4ugRs!mG=9s7u>FQsq+7JuUg)%SBiB)R?*teI#i~NOU$QW!AbK}l(uQ!IV*g_ zVMCfPZ{!z)#*|Czc3ai^RYeF}Zr|rW^KGt824~K8UeA>d{^c&+p)S`RaC#=0P84mK zSeD(nDdP2}ZTaqXN`f4!D^(3unVw58dE$61f~(PAM4e@y`xK|mtW7tvvN{*WeDhqh zP>pBdrXvzohdS1(z4vfyoZ0xh>ix|sKeq?#&K}8K7@_j&h2lgp)dNwEP0Oy`)n1+S zsryoO<-f@98u{K{g29DrI@cWYYK;FB`8iB|?z|<-H4_d!@vJr6c~jzA_B$_&C$k&o zstf*sG#_N0yo58G&ORdmgR1Cz@Ja|Jv4ZdEouoH>W!_PLbeslS*Qd%{Z37 zU-ra-pLOqz|KDN1zx$QBqmt~xmgY$YMG~emp*6aGA8O=PFLh6fP@4Rtsx9{gWmaYFmPjg>l%GMM9&+eaj5Zb1;x+B#`$=R(+ z&XYsVb;G)-=^mYiOqwdH$^zFMx@^to&3?V=vcmL?ma|Q4%RfKSY~9wDwWZ}~eg5(( z2a2+$l+8cDxA|Lg!}eLT^M6`i-ey~X0Tk1P*O|$(X&FPD?T(Wq}H?P$PAWjA1?jr zQ~oTvY<#5D_;_cU!&0X?8M{`8TJ2sfQZxTR@VfZhw|Ez}e?EHQimIv5Vo#y)-59dDiz0NCS{~fWUjGy{Ao=Zf{_>3rCn|94crwWwG{XDi zT=_odoiWcqC(*9ieD2Y@-S3J-wbowjJm=|VwCkVFgd4T5-u?N|ZlCh#NGIqtG0=i* z7RL$d(nj5jI@;RU=2gAYoTeXtZbjhY6<4#)%rtI4%x^yjw4+@!cv-;Ou%DOb|8sG7 zXW#$hsD4Iv_T&2h-|JUi&Ein3_@UolaHjBh(VLCOl{Q>?q;);ET(|n2=~NBQkF}oV z$EDn@^;x3*Z_K)R{Jc_M?7B#f>*-$~ZPx$%fq8%WpBZO&ygViyxo_EAPwTg5e&}vn zaxFIb=PA*epQq!~eq2aAGuxa$TNhOP{Eq2P+UOzT+9PSqcK>_ji-qk)&n^}1oD&|R zJ=M!^j#2tKnRB+^V?blRf8wr2U*n$sH|D?GV&3g{>!hQ0-#emnA#QUTZ=%Gel9xeo zbw5+@)qM5^-FN=!>FLb;{N+(=pFN**_i*CjHpALqCCisC=LPjlL0!F>yKaY^TKeg? zN%DWww2dCB#SiA2`c+s4bh)nIcWSQvU(WA$tL2X-F(&IyEt;rN#%big(?P#y@}G*E zwjXPc$HeGO`SE4BU9Xcs_V&kLuOFPeSI=T+ar}n`OB+vpaBQ*d?nqvKe`#>y=kM&F zH|f1@ZQu23=7QrAyL_BXLpqi*O_klQoW5(#_FhX*&M8b?&TN8ftD2=aRUd!(zs5`@ zQ+}^$W_+l;@1A|nU-G5hy&Bl0kSc%m)+24taDR`051qo|cNmWZ&iTA7WyS0pQ7xq{ zGK#aJayITuxiD|HwOpIX)1@!OpR7IYVs*lc^XeUkQdfRglX;~Jqvxp9&Z@b${`V|n z??+5w-JjL7R@O|;;JYxj;n9@2CzWrM|B=<(D7M8!sBCX5$J~Zpz15SY#O8$A_}zM0 z%as50%#&+eLfi`*G&WvYvNY_2W=+Z}ZX-LM5BH>3mp^3=WfID|qG2{YL;4ci+tVIf zv{y@A_Rh^(>Z>?qn|R=KJKo5G?Pjg+@spVXE=1+2T&h|to#o;-_f^v}A8oyhd`$s) zSuSsEI&-c)|5tI>Y4g4S*NEBA-l)i_wu!hI)t#{rE7gBk?yvXoX!x|vKd-ITVDSt; z;hQCiaN9vW06ks0A7>Y?<}pL(d`+X{Ou&p;an6uOiPr zIGD?_RpNd{=F^K8Eu^(MYUW?RA9HTSHAj)!`J4JQt0yTQb`x9>@$=fMuU)IwrS9Wj z%Pe71WU+O6T(gK%Qmf-~?)8_C8*A#G`YnGaH7rZ-&?~)Fa|I7xFgmR6Uzp1`kNcYM z{@IcCNs-?dDe`{MPL+y^j{NycC}sJ=odGI6Nt4cLT#YK+pu6_Ktd_oSd8g+2Ps&JP ztg1>{b1lR=OQrGE(fy&S)qJXQ)51H~KFo`I%>VZPI!;9i>oOhC`T4fCwl&{(-+y`~*#GQmyWHH| zH~atp`}2U^{=tvO{l_H^ALh3|16o-*ecu<=WqxzLqNAmQm-#H*x^=3%eC-s?;AI=G zhDC3DzwdX^-O}rYHxk=-u9|Baq9wZJ+MSZizGr3{tE-0u&I7OFnBdI!@Lu)%r7?QX zFC4HFIBT-{_myD(kGJpto0he8ma#dXv>E6sfr-E0?d}I{*y`)!dv<1~b9A&cL)7az zj3yU3nP;=_TGe^+PW}J<$UPN;@iyghH)hOR(e{bu*pU}1Ne3P{`pB6b`O4xVSg5PQ zXUe(@|Gimu zJNNER32_b;&n7>Utx>%}E037x|52O&|Ic$tvz&-?dAkx0GSz+CJRh`dcjN86-5>81 zpP#708J)AS)jG^eY4YFLe7D&(bGIG4boK63_G^&_7cX2mP<-C@IH&p?hm|2o4-Pc; z$XHHlWM<#=d|vgXOP3B!i_V+5Ki+d{z5g|1$>W87yNqjpmE`UIx^3&Zr~kL5R{O0# zu5f9dLbi_6F0U8y@>MhD|9hgYQ}c=QLfZlE6;}_%rEoL_Z9I?{ynIvES1GypALZq1 zeB5oYA}q`54+SzqODqDKzTz7v+4 z426;w3q}Qnw#_nRVdi?X=dxdbUZRcTA*)C8zwYwXlxzsfF-}#Fi}{v)NYD2uQ&3{i zqlw>*6VA_2?cJ*4c`I2Zc9X)Iqemp1CU5w9E_i|E+GFW^1EdXi8s+OTTfNw5|Vy9)iZ@k(PA@ukc&-VGdqFI7)9+-ps)J$N^28B42ILr9ZB z=fruhnhVZF$ZYjk?PYfM!V-zk0SDA>=P;fX6_}*5YT=(I?oT?>OKzGUGPT>y&r#Fm zbGNWOF7BVu<7w-j-E_U%b8nI4{udJ?PJj9~)ud};j%k+6(c||Q2#Ky(VmWVnT%==k zFt@MOUCt>ApB^kspP!zP%a6sR1DU>lULC7@?v+Vj+w+gj zb9-pI~t|X*v?IO0I-C&bxK3dLI8#A(1YLwZ$A8&7^$R zPu`)|{?Yk&LX-dt=%jqm1oqD5XI!tJZI0ZWW?1{HBx|b_Xc1}o{o3+%spV%)uLtOe zRX&;MKEpg;ZvNjl={uj#t7iBC+JrjC|J+G!n|<$-*FL=#o&OZHpzVS)|5MPd&x?Q8 zh$ym7Eo!wae)a)0Q4X5TRp7V~_55Jk-kjs{|9^#FTN8PBVY}QccDY1}ARRGH5w1BE zk2=rHvz4Bj_G+?wV|W-rvWVo4mv~;F9WtB~$b^ zE)qVVeEEcrkng0H87giOhZi_9|GYF^|FOLO{$o9h?HnKc1})`N|NpOiO3<4fkNYe| z^mpHL6xiW4qo`-f-Me=+{0%|J{O|ebR`+#vJg5-)`~ALudAYf*tu1Ii>rTO8-k6Gq zt$U+Nyg+C8_nO~3k=$=Pt-k%@G26>G_g}tuoTsSrl;-k;p2QOq6hTKh)-IS6C?a^= zaC%G;=kB-Lq^;jMY{&otxe=bP2E0^zX|NQ@t%(rmN=kRS%aaeFM zL;F`xa%}S1FGY6^bq{%~ZtOWWebTuoQGc%uV&}hiY+WXGbb`<>iI+3(to2;I`++$f6tojZ#G}za5wQ--=5jHYRi`eE2X^6o8ErAHTS#ul6Tqv&ol3-GFy`~dCmD% z|2C^#|2X;76tgvnZ@w)4@%wMRo2p@9xr=vzgGZ|gn`-M~Nk99j{{}ntw!FDoqEmW5 zo5k<6%7=>)H7^%5Z+kaas$KVer_!V;8Lk?w#{|^aZighCX13#6%D}`w^U6f_j(;_g zd!NskxgcEU^41@$Inr+qEYq!j^mU?lMcG-Qe}DdHl}TSe_G;aPj~?^ zE^b`5FyatDmu8>;=HFq_i`J^G`gS3hFXL8{%@#f-lP2-Fm_vHI-yFQHd@%J_g0{xg z879vw>i(|&-Eko#_s{_^Mp?B!j$;-UN!PY2mAo&Fyx;S3YpMMNHW_AdHvQHOEfPwM zVO}AEVQbzciB5~kp160J?`gwZP7%{{Yj7M@dwwou|KD%Lua~ue%DtJ!=|XLZ>$bA({XJo$-j5Hp z^Erjp3`$>JiP>*h?|*Caw7K48Ym)mc+lqF+>2O|U%GJsg8+$jVP@AAdeeUb@4g z=J-RXCpmI;tKuQA38ySqUkiG>a$%{{#sCLaIsgBU<^Q}mZvSZQIXO1ItjDibuXkIZ zA=({N@UK#)-~eMx<PXW!3fl@8Y~UOc#TdR*7mY58@ZXIHLYXxQeo@IeaSl;)&w_qXrf zz5C^h7YR2vrLKwC*!1mN8L0CWwkF~rXx2^s-v@RnY3az#X} zdDPuAdu#Z+Jn5o|!=wzR^Xh&N6E|MGvS>zh{g>o-|9-B2@#>Y=!&!Pi!?=^Rjxsr^ z^hnuGa^|z`Vg6>{5VY~dgm+T2q@+H-J-k5njz5QwQ1K(rVvZ}f7#-%{)pb|78Y+5O zMeZom8>q3O0?2e;WFPCt5 zr^{THj;qI|gVxOF4pItqvtTdl?+?(P-ceO0vt3e1TXu5Vzq->_ z{nwUzW!{f`qPo^az0JcSNVwTSOysJ?lDo%_bS~Jqw(}zUo98O??g^gkYCisS-;VVO zpU#z-g>rAr(mK0=Djt@_YIP-i{UkNn{I2XrvtW~C@y%ft8{g?} zSJ4b#Q7Xlh9eFu$Y0xJb6@{0nVyDIW-~3zq`sb_7{2TZ(ynoFS_2WOMwytVA!^YB_ z(AbHW^`@L<++t$*V*>NtWlcUeLkqg!vxUugvwJJUQ|}wO=7$a_hjGsH)Gj=xcseyU zK&|>9cWvM2vTOFUr*iJN_2u(IQ%4jMVwUU*&@ia}mIK<`b7rQo?88Z)JW38N@tmw7*8OJZ^LaA$e?IoeT2FiSEDf|v z_|#LQ&E?|8Lpi=jWEL==!m5f7pS|dfFmf8E+MOj!D>@ zKfT(e)k(2Ey)Ch0$|Uo970Uc6Tdqwxo!Z7HIm=mSbHe%%t(^`>EM(WnZo55i$+ga} zNj2*qoCvky*A%UM^B*tI*Bz6u`_H~+VuJ1QjGRl`QdVkA<;vN3G@@@_rHb{t4Ys^X znKr(=yShce-{6H+#G+ndwLJTYwq^I<#?DotM!ibdQtr%z_iQf9icr>(!P@NN)4H)AjDYt(T~Q z*)e|>R>hCD4?7YrHGdU^EC%=hpw?E)4IT<@cdgN#M{y)7Sm8`if&k_f$>yxm6n9UKOu>OlaAo zr-fGOTbuH-JG{H}&Tsmk*nY4>@b3{V^SX-n$Nt%dpZR`DBtRr*+vjgB*ZPx@JQQnB3U`+;9CoAX+aa!h6`uibiGXWex@!-U?0RdU%SKGV|; zdsV;vcyaH-4GxJZ??2}qs=cbd;A4hR^Nn3QWUc$}3Oc#x4VrF%d9+Y zbtbCYb1U=RXAGw%_uMFxzV_#5pw?T{sHsYwcNcZDtGsN^+LROezV_~ftNY!*RQpb5 zE48>LGCN||q!zu`C*ph--FVyZH(~Nag%YiAoYHI&U+z0!p7x^Y{0!M`iC3HJm##hj zNV?lkXCD7Nf!dCSYj$q&!9ib+HN1RYq^?xPJ(X4IsZqCJo5v2G)mJC{Xo@mb+$44R z#m3``><-z=DuyiY^%OrYtTpgapQYSyGs$ad)ALHu2o8^=Q444_jb-t(CrbpjM)BVN z{?VpirErPhzW2hdf=*nIES^1^oxg15O3nAujd30iwqB1r4Vvq^v$Hrh)zdm6(e2r% zvar=xCj3l}dQys*%3%J=;G z-_rdypE%s4&)NOX0cCU0Rk!N43q%sPwmtVgwBgjv|FvTLw!aM0=U1z>%hs`YvA)^< zzRu>;ba#dcL4vM=*P?E*@gzKGVBEqh>2!P9?4~Iy^W2-1G)xkNPj6?d)0RE@>-vN> z?Y>?&R|{s`$xpDF_o^?B)Nr~x39g$3*nUAuYnsX@LA zR-9}JwH3U3W37c8W->jbV)cw04^C-%v$(74@ z@m3CzAkLnx*`ey@CETAQH}`2SSh{qXiD`02(su=pr7!rLt$LU4cD!^oB;~mO-|4gO z#LZp5ePUi-nCrKLtnFu2zx_JXdFR^!XC5w_ls7`Gp|4l;?5W$b?oi&HKcSX4PVEi% z`W~6eV>m4@`Ng>xLaho11vFp0>+qDa$$Hul>u;&Zn~=&Ud^f@7qyMe?vIce4Dcm(r zjF%Vu{>vX|%=J>bByxzRVZ&LWnmI9NbK}o6W>*fjaO?o+L@w9Kejk| zpz-w26CB#md^^%6EXO2U;SJ*-?jAJ-}h13X=T=|79x%t6tuJ=ns~K^ z7zIU@UWEpld=tyQlI?wU_Vpuojyzcvp1h80+Kr15$>#SYlDoZnk~%jAO}YH-W@_5C zsQ2>OY3J1##JI`Koq4vFe&6lKYMqe7XPK(%GctK*y^CjF_6Bj1&hW%>Ucl?R-{+THp zEYE@k_nMS2xd}$gm5W@r`DwEB#)S1dpH)rWP-Ck1@1vHH|H{nd*a_F4ug-B}a41?f zF`aYm!f7w$BNes?csg#sI%Vy`SKMl{H4INgp49Byq`&@U#O2_Z3nO%jKzkUzUJd_z zI{x1zq2Xz=X5Xyd-M%XADhN7=qWoT^I%q=S@$r84n1b@ty4%556Foeyza(zGan+X$HXexy zp#kz$FBEs}+BL%<(aCIikEvwxtN+{r@1M%X+Wh$KzVqv{=*Vq3oPn{;Q(l}%c*NoF zwZ&{om+Q9~rjzfM-)~NIj{ewqK_xfon9>x5hfhy^oA0)xDC>64X5HlLvHH=M?I(YJ z;rZiMMMSMcl>X97l8s(W!kQc8SdP^_iralfirG3@_SVuo-)pO%&N!mFuwj*1NwNX+ ztQ%R+JvUr?B_XS1-@htPA#ri3Kz84PZ^x28WlY(6Wvi>=N2x#d+0s>?q?>JCYR#WF zou_TvyPu|Q4qi({B%@ayw0fzVEbBALB{{&ehf9FfGb7pTc2aRfwup(j<5r&5X=f78 zPwzHE#8o{tqjPswX(A9CF{V=l=GKz5M0=YgR|5f19Hd zI%m!Ph1)uqN?fPO@rd3}UM#!4edBAD2|GnEy2+PT)+!zsT5-54S))(F@9o;u6-BbS zJfcZkwmxB&&vb|g-|Rfl{ybEq%t_^JxXUob{Poyl#BO=cl}Q zd-?Yw<_-Fl4eTP^8xH;wxfav>J+5-HqUDD*s(mJhI#>?Bkzv-nvm|59VpFy`MxjYZd2j6C6^;3}!M=K#Q_9WY?xlIUUrz*0*GuSOjQk=X zbZhskEsHzZp583Ho@r3U%P}eSGxxFS^{M}>riEoJne=1d{LmA8_J0aMry(tJ?T*Ob z`<3DN7m12K2j%IfQ~6d;P*R-w;pMw`&mJ`Mr@g$iw4}T|opH`qP|xq*r$^nOv7JcP zytiAgKid-Q@2s`6$)hYw^UC|V<@X-;7@u?CI0!moNzh&9;3QS=8TDUl%I;OBUyDfQ z1#MKw+yA!=wAhK6-{!y)&&fZ2p07W*_xrum+ivI0KB?0qW!lv#tiCDdrV&Wdp;qpf zZ{DcPKfln|CAfHE@wuPnb)`rD7reQ6e3HJYaOmrpvXe_~e!WPx`FMQ!j?de-U%q?s z>_m6jvk$Ja3A-CQ>iMs{;j%=x`~Lri-*P+pi*jaed(AU_MbL$iS5xO^@FZMLIQQAc ztygO5-hC-2h2HIW%y%uWI(Ogax$nQMEO84w^6Ba6*!p{4UdmJ)Xe=o$ExZ~U{_%n{ zf8q7ma?pHT;m@bjFWXtzf(I3fIjCl7G1)>SuPmDP`^!*H1neyZ`C7 z>UW8ezl-*y%sXy&EPUVX>&b^t2xf1%K5z33vs`hm%9oS&UyEHf{fT1j)#{qe*spxt zYuB#j(B!n?&sM5=S@^+`{bA+an2YlE-=a=h+j9CcR?n@nF`r+;*C_O4%7J5T>ns*2 zDa{IG@mdh_zHalOiQy0TNj&TbxioLL#wM2+J~`IkR3_^GToAK7$8^`tbWTBanQ9Re z(T=5mZcJS>br!>h1k)dFH-t3)Cs|d%_ zf5o1)?7r)y-&#nNXtg{&5z{|Y2|7oDF7z!7_R5*yUfmUWT!uUD!LR3=xDA(Nb<2PMH|q(X zXN`u~jLK6V|Ge4}9I^d@@Ris}`*V~R?K9g(g`OI?L&i_gk-m%JahS}0LPd6Fx zzR*x!D7O63hjj%CwyxnKA01T}?R5{A8w~d6y26zu-Hl9 z=mYL0TU*3tajUZZbmcmA{Fu~)C&jEx{y~=wH(nK}a1pw@8*T`SG7+KC~z;kLx?}|x1-J*H#%w`GlUeA0_wYbCT?xn$eonTx^Yv+TF$KtvUHb;TnPR!qwI@fUc%%DMy==SQsd=b z%cnePiV>SKxBA`AIc2vpK~rTxE1yK@{0^;|vi#1T%YvXIXP(cmuRFGA$H!yRpAT{C zf7utVSy%pkucTr4)~KgXCi}T*v0uJYb@ify-t^=X6BKhc9u?d3_uFmILT47o1A8hz z?|9s24Qkqe4%@g{eBO5E-sd@>p4^n6D_N#-wO>QaZl;QZ?)zD@Uzf-E+s$a z&y%LlntU0pHG)~8i?UqSuABKa|93*m`5hl03+!`G4>#W$wf6iD>C3a1e6m^3KPT|` zELLtYgZz6oSzD#@_y0BX_4U1(-XielZGL_7|G(eU|Ns5|{B8NYXKyy2PrK}E{uESN zfjY{d0t<8qSn~0{x5_5-0)LukrM;T*`J8qC>h=3(<)4}5x;E@FXn7fEedVs#>!Kg- zYe_u8YkubdBfE^l*0{4<1TPme8yWtr-)5S{*u>ozU;maDbm+jp4?pBJ!n0ZqC6%;% zs(s|~__vVY(VE=PoPTb|Rd0NHec!V`Tu&c${&Seizx!0oxwF4F#JMNk$ewR2Xp*_rxe`(Tm)X=XUmSd$&|Oq635 z?TD7xwc*IT_Orj=YG$G`Me-B&*NIbr%-jsK6Fn%xk0y*A+N( zr@lTSU#H@q*ZRkk&pf;r)S!LBAlvGvx89=HQ_VAtEN)$RGRI_ARmz76A`>#MiZ6a1 zAg?DOe!=^Q9^>T|tDkRKoqRw=;QBm`MeM#;jYFm`P=9Y&JAZHD+^vcn9;r`NJs&;h z_G_r$$!t^b(t!2NHseo+9)8*L$*Q^Kh}Uw)XE*BS=yh#*5IK{zvUZtk*Ttz8e{Jp@ zUfsJ;>YB#&*Cv&%J)XuUd6SM#TqqaqbYAFZz}8tScl)+)Og_+}cbPqolqx*0bf_V>QL!$WmL>C{$L)N-_oQUj9ziWES&iSRE#i?KKCxuJPh~>&^ugH6FO~^^$Xj_&{@HPRa!h^}z zcm6)~E8CiX>B97{tGVt?zkO&$cy`|Avu2BT?wq-H`@LD90i(dhZXYjs>wm4R_c|fe zrkKC?s~G6`t{WAPdskk~(pWmfJU@;(chC7(tJlAKma=H_H2o)&Eu~U>rd_*nCfHB& z*TJvtwm%*;wu+9h0bKI^blpP6y;?|1tXlFR4&<;a+9-M#wu)6(8T zxe$Q|N88lSKQAx8+p9CxfsJKe`}3b3uJaZ2{#wpI|9zr_!Lfs3<#$WN>;ArupM3tg z<@Y|wE*WBuLK>}GpF*|Ob^YSzu)ct2^xMcy&k*$lATpD52#E7o!~S7f!^;v z{W-3i_ecMHcwbPh>C^w;?Zt1zBqKDpd;g>V!Oggd3(M55oLc(#`@|6Fz z|9S(n*EKE|O56V=;#S6z7u)ZD{r`*Y_`U!gfordS{FL!M%ET^HkuZ(>UyYlalZ2yQ z!u|JijvYNd|BzHfP43CYBoC!PqBN$(r8wfcbTNNI3#_qdyOvM4m9Ge9W zd!=^0^4rg!$um*W`%CoW34!O7uUskhQRO?BRTTChQawK*$7@Hru~FYF(-Lp*$cR-9 zA4D93J9VF*EBzF4RjOl7@(~x6sk>Y5_?kHJgiqqiXgR<&VIR9LWBZ(Pwg0BS4Q?$- za8M9f=)olK9OZs`UemF%zNx$qyw+^os=O^Av~B6cWp}fj&M&@uJ|NZeO)pFCIT=pMcOq{jZ?7lDLJ zcYGdS&bD2myK$L)+v0M|d93x34QKvOG`}rYe4pFW9XdBy*!<`v(2zb}y6#qPXwRq6tfja#>DF*VM(lErhs!dAjws%`3m z$V-~LD!$DP-|@e^|8rb5d-d5Fht0D67j-W5bMTY6KH-nz^r>lDn|T%?ly2tmgZuftl|_lhs<;)9G5?4=TA-b=EFb z(wbhptEBf#%}M3uhi6ntT)J|_B|Tkz=N#@+e%4QK+kF1xRQK)je1p0>YFA!`e$uUU zzcb8YVqae=1+@eTJ&)qo-l2i*sWW)DxOSqfAQ+o zAqnS&0WVq|)h=;~|M|i+ui_CWsJZ90R0wnu+ElOB*?GG-HB-yp9Okn=b9ei{C#<}$ z?|gcCIy1L)*0Ooe3s38APZ1K;W-0J|FfFX?|Iga8-q-)TmZ+NR@0hy#-LCHa`~O+3 z=9QnN;PPmRkZjQUYZ7KVdRJaf-*A0i_2oNvSdKkXuWFyLK&R!v_t0srZ+!o)t=fO$ zx15mox$iTo5Bz)bSAW5K%MXqkH`21r=Ij#Azx#W_<8!N+PwsngOT|Ir`G1pHaYscX z7#=J9w>lYljOmeskf--j_seT}MVMD9hIma1K4&4yW~TaAvgwgJ@4K)x%_D&o>$WCb z=9RGj`})t*X}cr$uXNd*&zW?)-PU%i#B9}ztrIyGfAsOu?c?m7y!L~jiZ%nhOE7OXf?N^tH-Hh1y3%z?+lx}Oz8CV@=I@~eqcKPvpLPRJ|%RTVz)=>BZsF< zH}aH(zujyOfB#EX*_01(?S9wU^fza+zuPzkSI=Ge z)28vmhGPq+9(B95HHNd-VDHt_$6PAb#3riFz1F*Ue%#_|O&2z|>|3x}z3dK)rK4rT z<9~le$_=A}`;umT`dRPsRBx+(c>_D|uIq+5n?di>Y>y)R9b`ZT5cfoyPzE;oPI$H*4M+=4`!YaZS>&>(B$i4M#QD+O3T&j0BG5 z9rjXR7sR(ZYi;u^F`hz!K>3KLEBF6xRTr~8KRdtlLWumSa{j-3&EC!@CLUK33{qX3 z8N2nhv(Lmw4AMc<)mmOozWHUt--^_K`4X|sjIA<-s!JlRt_nS_STEqQUB^{h&N|hZ zHJtUzvhSMynT4mX1@-cZ>J+Ldv~^9@;a5rj^T0abl;b&BXKw+ct433JITzlG%KqP~ zySHlczm&^dGg}vMOkQqK*Kb={_b>nEh7cvb*H2g!bd)ZJt(o}HX_EFk+p?%YvB-ew zGS-ql$+3IxD$4|igqP2qWf;NoHta)V$egNQGcTC!C@+e9%M|6!yyu7Z@Bep$7QR{N z+-_9)>51LJS(CV)YJx`FxQ z&tuDt>n8hFzC5~r)0)N2bC>z6ZwsBWNg_D?vG1|MS1XsNF{bT|c{VLNPjUYFV6CY} zXAhcK_?i9vh7t@?AkEJ`RAK^9W;`-=Y6R7d$&At!vnK-JHOYhdb&w?3!hC-XXj$8)+9OE zEHfGFHc#u^<6Bl<)|l3&rtZ0ZMMfFd-V<~Bok~r@+^@^-6|2mQs6D~JH^cU{<x$CXE>t(W(&L!jzb-&IsyL*_LDF;kg`9oQd9Iv^J#f15!)AuSFZ(alaV)X|ycG^`oGsV@0m2a;# zo+x+io>L|ea((9ZM{73m$~o&4v{)PqxN2CM{bHk_hx|>E1l}ovIp(?PZg01?D<>NZ z?v>4CnmXs>asCg#rmhi9nCfled2*WgpO)73Z%=Pp9(S~2lGsa+;zt^89^Q(}19*K( z0+;-@Np|}3jZKQh@uGSc@5XB(Jqs7{hVp#9AmHiU;j)G8%96z2lDiEuwo6VZuMt{X z+vZ=hX!V~h-$EPMPeyp3sIGZyo&Mp^A@R!ZH?IqZ1zn!i#3282fdRv*!@vBvb^KOU z%-i-(F(84d^PH!&#U`m)D8herGqAargU4IU2VT zCpYeEO}hDfYJdJ;Ilqbf(k4_q(NxMzynKkk>`tLh_oMWRCo9``etzg)@u@$5bBRae zxo=$l`*(Dhwy!();^Awfv?~&9+e8c}s`4$i<8S*krI@AQmYMhM`_JEQpZ4L8clV1f zt&(fnZ+0Di_r|Wy-b-b+{JKXelZ$`5ENpz!$}#c#g(%~%)#;z#3HyI|7aylCGOKYd z>!J&bl)D4Pp6=YTFyd%JR`ca`o(T&w^BvakZoLuY9L%V-Pjw5E`*$Xuyu{x#gEih+ z$$n}~4%_-}GjH`z^)3IpSC@RayXSb{ecN{Nc|VM~|9>jK7SN@ZeZt#&-xEQ%b&qsx zmOo#y#hOuZQrat)PYYQiat%3McY3x=J#-?d+cZ|9N=4_o;i>Nz*$!QknVk0id&9&|DRKSud@Byw{JOXr7a2)++OpabF6xO*1YoD&2-COGamoA zSou6~?X^zrP@DUmv$R>}g?MOwT(V?kz>)B-J@N+MCoosO>9j98age<^DCBhNz4%Qc zsRtu`&jp8Q+s>&tbW-O3T8Xu~Q@vCtORu>8I;QsPRSrcX#UjloT%jBP6}Zc0|ND0A zKIp)@9bd0STR!eFo?(=F>i8_~L=mCz$2tfb^h>A5ojS-a-}C;r&n%Od#!jZc53)DIqq=pEIuVZ|SqxT3vtJujy8&ZGSZO&*$E-RqEQYig~Y-#yTefAc)o(`jbg@?r1hbEhQSu8Id9oounpbN1r}^Z(BH%x}{pE?#bM zfupO`TOg7t@nhjyDUaEWJuM6QdG}7(%h-5r+N=wH?pLKuCav4x=Jok%r|LHzan-?I#)9R$iLRTc#~&T_EFj#h~SyMa$$b9kz}d3vUbe%-g_eJ-=9sMQCmE zl#+~A(Wt;M!4>sOIOpgYF)d+V%GCbn(egR=&kf?Le>2Z|CCEJCi8t5%={GJEnw%(k z4?4zg$CmBdcb8OMyZd#9M%k^arP(XEynQV*`%ehpm?jf@%_!+H?~Rx4_63Wct%?`; z$G>Gg)1G6TOH_Ey6n@bE$G?A0HIKe-Rlg(CtfflrN4AUkN7!8AWXXJc?eDuePc;g^ zDsw;8SmZAK=*9zX#|)E=rbmu7E$7H?^I8y5d%4i(*SpLK{w?_>p8}S0cfR0#XD6Q> zb1%j~R3T7AV?ugtKDXJ8D(`PMe_6!+`~BJG&kb3dy&wE_CdTUgTyUy8Ute+mhkl7z z*Gj&)M>8&{9E-AfI%i(g8bzTasU4>b4D5Six6eJv_gIa&>ww5bGnbVN$t9Bvf2v%w zR_pDXGexMWqq+WLa9!Dj#1Q)z&zhgw^5k%x(Eh;G-6PYzQm8NVvI)zIAda5raz)B4 z$EIiKOpS8k^-bZq)qKJ@Ls1|~K-+QW3W;6+B9{Goz^=D<#)0i?OtniL?62C2-u%zN z>paWi-K+o4c2}QQydJmgmf&O8Y0oAd`ek@3sz&+4WR+&41uY&e9=X^4thIIA8syGB zeQj6o;c4y1)I_~KFE2>jrKMOHx9QuD-WmVyURK<&K*eg+;wRzWr>36_YQOQlwvAWX zZEsxq)~jKQBXk~V^7~h6EH#oyj!NuY)S=vG)8yJM#;6_k{?fm7iq35TD?^NSJey-# z4BBzG@fzqLH^rqXA0HjnI4`)srSOV-T4Ji`9?9M37-Sebil2PG^12kXwpIS$2X?bt z8Om{$PerHcMqhhgtSQ;~N#yt2?ed8dX#$r*zqZ)^`Jg(`3lv$n^;w5<--Ctia!KFjZJue8DRkiYB()!(=l?&W zxqQx{6@iO?g>W4VExMew@OkCUpGyvw3b3?**2{V=J#=ZQ_sS40o4;Q!>%{C3SZmrX zuAg?8*Bo?ZdD6K#mMw`VuB;4}Eq?ucVXwOCL_d=!Tb9ZlxB2!%e&^q9w|{*8%pH5w zMWf}pa=?|HX|`}`ACuX_%D?>>^q8?SL{?%gdsI*Z;Oe{jazyF%L_ zef=Kem&>H{Prd8h^2xd8MCi2*c28nnyv|@3+IFkq^7@@Kxc61sbjQaZW6TSmygBC>%>1O|a=5e#7l^#BdT;Y^;nW4!f)~eaShMeH1>c{mssUUM#}%Zi zyj-0hd@@{X=;FDsn`w^Ode({jF-vpq%$ig5)Boqqg~tOj-!Hl)ckyDd>UDO;$A1od z5t{ofhUv4h=FJJOpLcEGTckO6|I(h<@3;l0%&zr%eEsQy)BmMES#o@GiF&NrdLpJ| z@|=YCz8g6!HvQjfT4AXD@5#~=QVDkr=hR*eol}3};gL;F2m4>VSoheoyGLc8$duMY z@e4m)$$o0^MpcS2=h5SePI-kcIom*=qu(X0@@k*O{W6xYQ}AS3v9DOiHkf;FM4g|9+}DXa7!Q zTI~hLrS6a06)O)MR!L3i`?yp{^y??s3tV=M*BMqmO4WZL!*iBwKBYpb=51~^rubY;r*$U_;?8r$z zFsu1S+F9Kf37TyaW?1Q$?Kw1mUS-qK_xl{zh9y>3^9PDpujns4*RpL|%*F#7wq3nZ zce*oY_qT6b3}w6>IvX1lyd;ioDLeaXzRiKx*|n!$dmTFV*z)D0_)m)$`zr*A?z*oZ zylKK}>zX}gQt=f(R@~F^Yi?C5lWyF4#OP#*CwF7?>8(N$EE6Y%)Sg^Wdj07FZT*lG6$Tr<)|K6z1;<-T88n?2L%(W3r_f3!fc6)HW^w3S^O&h&t zp4Jgi{c_eYbKkjC30_a}4HLivN{i+rA+8P0_lSH@cV1jQOMNz!87b z{&JA7RkrSAb^o;GbITreX|G!lqO~*O;EOd))2;q!rsTi6vJy1i7n$T{Dxl@5xU#(z zbQXz~m6e7F7ibOEo$B{{L8H$-vewf;yLNcZ?@V~R?RK95Pv!HuVed;7nCQj5dl=LW5u8KZZApXt-S zW_2#<$JKsMWM7`UI(bse%Fbm@okcr)`jnWS3SV9I!a!}+)eDD$&OFzg*7c-`>Fb6r z0j=a2J&QD&6YPFInS67`a@#6RMIWgPOTVYB-FhwQ!UD(0^N&viDsNW!_V~-;zfaWd z6YuS*?2$B9d+i#tug22f<|7Me2X}-{+IwHucfTjE+_GhhLHWBoIu5*tCkXr7OjLAk z+wiaIHS-0t6}|EQe_fX;x!|~E+qO+#uSM7E-Kw~@E2nO)T=DVP@}k4K+dtjAbd=%9 zv9pU~Cb+u@TJdFO=020&?VtYrZdsaxrvJ(p!LL^?TD)s@jwlgk|x1QhaXEU`tu1-{xyJ(~9Rpp|ffQwQ~f6K?G{ObwjVt(OZaY-g|VwBLs z6u~Md=dB_JiKqJBd|WJlXoA{@+N^7;pZD*OoGs>7qY-hVLMJ`GUNl^;+N!?(o4yDa zqi;~a>lH#T?rB_Z*~_<=b;_sA9*4CXBm3i26uwQi3zDy@IT?0&-?<+7x$Ml`6TB@r z|8Y*;eP!PrM!7x@CCA|Jb}t$ma<@PD@;mSOqn+&+{+^Qlae8&dwdNC{1twzBRvoKzto8O<+(Eo?_4ypLB_A`{;<2Gbr^}<=eF;o~F5dj}ZD!5rn32o2 z=CIl1<%=f0+Ymap^|aAanE<&i8M(M`ol{Kxz4rSTe2dgM?eTlxYwkN~O6hk>n5Wmg zX1OK4&qsk}YM+&^s=T!0+GQIhTErxe?(&RkTdJgZStfcj+(k+cQ{J)$EUT>u^D_7Mo%C!nm!itXHmj!c-LHM-8BdnHZ_nMfrD?h6 zVT<$c&#vS8IP-ve{LSOr_RT!!KmYrml4;-K8k75E>}o8O-FgmWG{66S<#p+|TiNUF zl%BkN-eWd{W#I*n%kzb%F4@2Q!t3Mm^>dbbPY==%+3{jg_XnH)qWEpU z2ppF!j}e=&M0D;kt~jmcg7dcD3!Y4LzjWow5ztw4i~H?fowF>sF6?f2HEOEUz6VUp zcJxgWvOgi%S~{hOXIkMKm+gNKEML94J72bXPVpz9g_j+h*^BR0J{P*~yleOAA6^et z4<^j%Xn5XLnUw2zJcB!K!tzUZT_^C*kyy{@Z*~0wYl~ku_u`kD;g#Rtw$AzY{{J~Q z>AuJA|34}(+I8+)Xtu8Ty^6H6dk4-SH-J*(er1f7kSv-N72y!8(6%d@nb zH|_m=PbhES&#=1hyMMoU_fpMG;qL)YL5;>qlcJV(m%6P#ys!Fv+N~>^ESG{_NA|s! z^x5k-Aab$@odewB@n@P= zuT%T8pxG(qXo8;H|M&xsPGET-}RiaVEUx9QjC6$zB^6|h9%x$;M?=7=-!^EdU=1o*4&H# z!ngL)VhtOc#UDShtxfJRJ5t*Hg{8UO%4y-!_vK2(^PKa4b|vX8*c`Pus(<0hOJ-HM z-|RkVxV`yPT6HRRN*f=;$_ZfsB3(~UPZQ+wE?&v`QoV>XNTG!#NNbCUh2Y-D6KCf9 z*!??r;e!;hH9{QOvMmLRH_B9B-fC0*b*s*g_or9tzE`*}J5ihM#;j%aaffEzGrg)M z{^sO~m%kUrYzPm&(7Ld4t*PawmSl;I@8#CL)!;Djm@;9Vys_q{8Z-N{R5juI_m-{> z^*dCx*z(6O?TWg4rFYEUN1gJ%zx?XtAB`?m3l_Wlx2iq1kxjHwt z1xP!s>B}!1`QIh}i4-neo3E_>D@651DAjUJi;ol$9$}eD~^} zikqT$>b{ohywrF+o%iT6o4K;0MXK`A<{p|IwFdJP&S=)CUf8H;BzW|i%tphIt!l>t zBmx#0_hrZ$H7NJ}Q1cBgD@v_Y*>}crSK{l4**zO0WK~0TosTX0xii|i)u7u$O3aV@ z6r0AwMAj!R_6^Uq#BYe+J;VQc`j0&s>y0PIDhhh-ER?ovTAaUc;&uI>qSs^USOqW0 zNp`u)YqMGzt>EdNU}4AgK}NQFjr4^D8?Lax1AWcT8a){v&t^|(Yya)YkbV1x1ZM^oTjSQwJ}zZkxN)|jeZBW-s5FG(dCTG zGle6UFzuh=T*ahltF@J5{Ynpm3W4WyzUZ=@nZ>tnS)ZH0m%Irt|6LM4_it)#rw-5I zHLKV+BphrKT~)jx=|gIXeoG|B#FI)(LOC^6-Q_A(%I_4qvq^rj=?5K5eLHV=FKCAk zXe>$lfKc$KK9dX?^E??}UtiEJn8<*_HygpnI|Z!`Gd`HRRHRTQopJfKKGhw8&wV|n zD;XY3@mxCR{i>PEcPXebFeos1x;TdHjImoS7p2{i)O}IxAU-G4+>wZ9ZL4 zmh4{nrN$>`!!dy;wLTIXzfKdL@wYcJ$2yUzG<(7^6%oOW%~g@k#~7I61%5q~Px-4b zORUpRGnk2et8D$F!k+oo)63uQ=zjk1gZsUTkE*xqe>7yRbrbj@Qsmmz%CuHjSLCy6 zi$FZ^EA&yf^ZW<%ulwZ=S}mA>+K@?aJPBn@*Q}3A=B% zw6pE}?k|iXY5KR>ER{J7*7Mf~^DGppI>J~c8k6Zzb=?4k0Fk~?m13@Y8Pq|H7wE8AgV!^=Yl z>vJznQx>hf|8>o&1I6o)d)m+2%4>1thGTf{Aq(Y}&#WyBvxPn{m(!c+!_0Z8O~D~4 zu$g_sO~vAyIrD2Ht3JQg`Ez-G#lx5Bork>U8){FTb>exEiKzFJ=7y(F^|Wk7t!`Pr zTo$`UJelCj<}7pUM`zTE4f9Jqqh}sn zVsLhe+YCc?We2Wqg*+doi~BXMzEJy;%4jV4J6ZpE`u;d+ors$scAnSQ5qRmgddcaK zO1Z`U7G1^P?oW5+w>h!7-|pCK{k<-~FQta8-kPI)>Uq(WF4m?RzWd)_ynM5y`exCo z*t=IAb?i{dl-(+|dhKq$`1yvtg1dc+g&60(Vg0K9aiieL1#2z@e~i@cyVsx->)_IzxSKr{oY?}cTeByboQNa{-Np9k6x8gYWX}_AZKdE&c!K+Wm)rYVv1X zvl2E4pZ99<;cc51ESmUd$^YM*R=Iqd*R8*6hPU2MmDOffvrO~$ehmXn-8H<~9kh10 zYq!|NyLWq^S4uqA>H^(L4%&bcox4+%p<7J%QM>&g#j7oU&qYk`Y+jzCptf+IzUkBr z$E-S8{U83c+qx>bJSRUt{rTK-&|1o4$J!!}zqn!e+;fiHlx=x?lyg^JJEfER{=sqk zzbhxpZV-E@d8le?k%-_=JKJLlHs?e2RGv)n-z(&#sv^=9WqL&7@R!)-#ZULFzFBx& z)}fN)yz-?s`S=g>?^J#6-Sc6(_)OF6Y0VSWl4Y`+r*L`dZ(h1}nr!)-SEc7|;cpHLd?wGfh9fFR07>e$C|H?{@Py9QB^Ykdm`>{uP^> z+)>?+XSmDN&zYUKr}cVVb*}-}#-O0?r0~W`Lg$59_MPv$oqzfc^Y`@LtL`e*GZocY zjfv7U` z&Pl-q{acke0_A4zTU;tCyGTHwui@BtN6keBNA%e|CV$9N6Ta?ca7iuBn<-G_L+8@P zLf+atSISIVeJP@a;bpbU#`gZ!M%@4%qb~>Y4NC9Z&RDfXSW&$2)QU+gafdRmH)eld zd38ZZ$?u}{?Vms1y0u`=KJ^8ccFL^1bK=!JF59=UERFp_lad4y7D;U_YJD`};EZ`j zQ;Yb0*Xmwb73#Cb&}>s>$x2yz9iO%5ze}U$`DB%+~dtV9sOv zNI^}$ieYl;o2GMDJhv^H?xL&AR~YI#rRZNf>!KTf@A}s;=f*PG2Jn79{*t5q;`!Fq zlFLKmA09izl+B;|Lh<+J*LP~~?45YX@T#+seedk;txQ*5zcb#)zjc+gw(8`<(yh5o zObHu;RP6G-bguEA`l9*#gqHoe?6$$oFQ(Yw+}9fe0$Jb7tf>Z%QYHT+$$ znERDf)1KzXM+IF%F9_-_5C~ZB7~cO{hOa1($<<#Vs8Ic{Vv z;*0CvWKg5$jGdZI2k8tx)COQgGqO6NS7$?+;%qPG!F3eEdYB%kk3!_1V5% zzW?205|SrOpY`6+>85VCrQ7@c`isBcQx7zmJ~M{t(5~h2s?T#g)?HT1+@>lX$OvS$jt1`Nzu3jDPo(uE_`GKG$0Ek4hUFp^m8*^^eX8_gW}l!vtwX0pY|7M-wJKq98uv3>xH_Ldy^-|! z?9Hl2*J4UOs%kti2si)904{ipjV7rtIFA^6t*gb+=xAowW4H=gRPd-U>7JJy)2vcJ11kA8NFg z7M!zue&O1+V|u&a9J;bHc=PW&5sdHNygBnklA-VawU06Nf4_n*o|~_AAX_EL^5c=o z6(6UDZ}Rn5(s)vICA*aA{PNNV44_jH%+u)LNuR!VA!ba9?u<`&f{IBQ4LQQ;l$#kCJbUUrEQ zQFrn83cPOka}Iw+hsqA`+Zt;HXLe7yH*1Rl!#h9emzIsyjG@UB_bE&-(EhThF81~b z`%_D%MzRK~?%Ov_EcA;(Ma1hk|HGR^b}T4u$vUN~^x0wGlRqjiS1mnu#N(x-MAQ4^ zONRviOW9qpw>^-3=Ebs^*G!y$S2}(R%iA0AZfc~JffLKQ%xx#T#WG|si0_*)-D17` zj|a6SB0E*rPEn7()6yE#cOfgquKf(V$NA=SUD9x^Q5yXcC1)l_*yK3=WLMgQZ4Wd$6Wbsjh;O#55+|HKDl%XiO9m;XK^sroB# zL#CP4-u$ya_kI6(cuir$=H=!ue0!EYG3aETIM4O{*LuJ38~+Vf|A;;1VtkQ5CR5M- zaOtTy`^ElcoubDVZ%omi%sR(p@_H$=`}Yd}g-6`@mwG1S)mN)qR|4i8`EKK&6#7xw z{+A&8yYI7$#lFwj$zEOaSo)25x?baY4j%0+*VOs>Z(M$rl@3zKM*#sA#+@;G%0CN4H{4r${IkuX6Pe3&BR927_Ot5DUcYzRHpko(D#1D}4jL03 zS%Q-$xLx8?WI38NarwNeuG@LL*YfZ55^=Zra=|%g-_K_f$rWENy8rz5egFACKR^H1 zhirk^ig1ybUl9~|c2{PS7#gpoyaXSiguo5B&N0+45nF@QKu73&Ysjlao|4{bPez-&|cS9v)v? zy889XORx2I?hE=oTOxbiPPN&2yEFqObU*()mDHvnHgn>EZMSnz-!@JQhz@q%7;&sr zwu9-~`<;5f-|n~H{pQyEm}`BK-wfC1)`uB+rzQP8u&95s&!nZsOHO{&Xe#QM<|=c2 z^GBCgYq#bUsZaYX{Zg(*zNYcCozUl- z$N1;KH1WQ+Ab*vT3F87-7;C&s}LN`UMDE%`lOZR{nSVO z&zqh5)9v%xH8zjlm$0fARn9TmzG$Q2<1PP^RHk|!=SpJRIES~E{Y2M)Wvx97$r|ok zbQHDhFMry;%0`@1T6^vv|3^BHZrq8Re$s4OHOv1;JLl9_H+|1P&gHiw=GXeLg9Y4w z7cGricrc^ur%nr>8rOwH7dt;Kr_^-EO+V+zPMONYGw;-mN%?OU2Wd^cyjF@a@xkK^ z!OyEiC1gLZ*kAfRocXlOORwoa`?(%YFK@bJ{lWf)MOfR@IF3TMZ_M@ar|o)H|1k3~ zQCqgbEwJJB)6OQPQ)hLf8~@IWNWWWJ`QV`ar&rST&wGr|EqQ(``?lTbFW%mhcAc7k zU)D`pDL1`we&sXCy#0U6+IS>E*Y-}nq$K?Ll>yJm6eEj1XNk5e*RE|7`r+~G_O;mZ zST;VH6Gu9QSDw7S7zWm>x^mqIJ^S31W zoE2tTY`RbWLDj}ByWfBAFHisUW3sqa-_S0N4QvNbEotT5U74&KFlpCGskyrh ze)Slid|G62N^$!6hm~?SbHvVn&bYlz*URgZX(iX$YqJh~ubnk}_RCvavscgC`y__V z(IGZg)~SPwYqg&(YqLVa-mlldgQBG|Tt}IX%T=%W`|puguF|~8U*g;XudKRn^s)5! z!iUFJ)k{fixIXWW{X@o6OBs#_=4?KD?a#9X%{M9@_XhSgi(E*unGkYcVJ_?C#--xR zt}$H5dUWFk*Gf+1Kb!m&xKgsS4EwrEY;Mc{3qD>n&v&(1=AXB(Bi5Gc8Nd8-96S)?uJUymnRBAefIa_;@ahs2sbMZzG36?F9#lAiZXDV{b19f&*Zw=$n#qE%!OS}n@ZnC<*F@DiQ(VQyhhB=%HgKt zoj*(TR%oqSq2zXHf77-pRwhi2J1;n>-M_}x-gn$c^z!@0zu&DJUW(5-f2ZI6S-G>{ zvmeQQ&&_}HZ^%_rn|V3I^WDDkSOu}m2FD6M9u@z5D|`LNYti`|uZBfGtc+W|Dt6KX zPtDAnoRqy^uO;8vQTStD|D;o^Hfo+cXZ`+6cziARatQfPp9?VEwy~L_Wk+foww(s+q~*` zmS*=VlCMQ&>$V82oKrukLoJNiynlb^dHer8ocwkkJ9DbP_=Ft$Ui)s(XTE#2-(%nH z{~tGHbwJ^VD|fcEygnX#zWBWTao_9x%xg2V^a>ubJ}>^udtH$6{kb`wX0HQs@-~?< z?v%Rs@3-`vx?hqpbuXXhY`mG)kk}medh_XXe}Dcs%+L5@pI`X4yJgYdy<$x#z6)k7 z>73wp+*ENcSFOk5ogdo@r+B%3+IZpQB@fLg#{>I*zdJ0IU6ux#7xkTOwsuwG)T6!DRmMqfA zT%^h4r8OnQLv?y(eJaNyj&Mz)-*wA;`yV}#UEb1 zj@(kfXsIfAb4{(CHP_Vh!oL_VeRkk*(QA*_SU8(2L$)#KiHz%$DhbsOB@PNaadzxM ziwq5=U)x7~S>AQk&Gg{!c^+&HPp%0TF7=nllr~hp997}6jYraK#RU#Q{s6yityxKr zB%hW{I%<}$c5<%YcI_4SwuFX!6mHpY_ST^ck!!Pcdz5URCVH{9%-($ZPebo@>%Wi0 zOWs`RboG|fFc;nVvQ4@o`Id=WkHkSK+1nvDnp!Vs-j{V0cu*-pZJ)WPNyK?pFmK>-RHq9qvAFe|YKim{X$DV~_oM{e98KM9x5oOWSI#{p8H9$nChMGtXZB_}2?Z znKs{>eRNO1{g#t5*M7KU-4<8NsC>JrTmO;1|NqwFbC&J7+wO_!PgXQKc_Vq{EVXq7 zT#6D_B^r(bOXf9AZ8G;-8RDY)GSFv1NcS$ah+DZEBYajD`TBy7IS=*7&C2r16)M^( zv;A(FG-xKTU8abm{>NeYOD@(t&Z}Fb!acTbyzVa1YGJX`D@(+!tSLdYb6$v%@269Z z=QkuCX4LqZYE&p{v9Q1?rm;IcVaZ0$W!ENtt%;2+QrGFdyv>SRMlmxh?+~-gwT()$ zWoPg2o2T_Jx4 zYg=C4xfv$9bX9_S$oj4SRYQdLOkEf{{r#o=`l094oj7_81G(AnpS*S3?q%qTj1I%V zmP?0%@=h^oB{MH|=`_?~-_ghIwLtmwg)40#FE2HGHENu8X49l=L33r+Eb6M)SCSVD zkLY1^zY)j5;}R&ieA&C|d&^IMyYP1JcZR(EkMnj{E}rr2nZ3ow?drylt|Y$MbJ%Rk z)D5ghb>cIXs*2L$fTH)>L=m2GiKSsg^f98rzMxqKltOn^!dW$ zvd6E6$NSDU%k3y>dH=iS^I3D5;xC4pTlEkAd_Mm?==!?{2b*7BTFSjS{rofW{Xbl1 zweZMTOt>CjKX+g4@1Xej{PT_yOCQNQ*PBmyc(^@SYwCrGOGW0DT=JY#a>?`CkK~pA z6f}-cRc|la=^@f;v93E_=SJ7mP7G$1G%G>u(s!MhLGS%+4 zKORos@qC?i#rwrObu3afX6J9TWD>n?!eJySzIN^M)sy%p^5ve75D2=zjW@_^b%&H| z&9|HBUtVAD5B9ee)lAh|HHoFqGj&~z-tsHH#|sN$ryKA@Zb)GKelNQ}(93hWUTn~+ zb%t$`o6{0|694`Axt8a&u=BTN&z6~Vo_Si7VkEic+Lqkg)A;RvBuusaz!J8?hk4!W zr6;4!@|H&2o6^pE*wto_)CIM#zxAS_rB9DBE>z3A zzw*zDuBkDuUZQb%`YEPvf7ZL19*pJ_65Xo7<7VOQVV%lpn9 zY1YfUE7JM2gk$fN_>@%Hf9*%t*Y6eoe*eFKqd-$( z2hW-K4HJsb$)0Z5`~A@oVgCc4MOHZ({rj!3a-NBaNx`p|%Y)snm( zTi5^p{xbe}GTGnaagT9EPR^4~^?3`{t?LU~c_cD@ZtJyK$K|SZLO-%ZY$#wn73eeH zZtly=%a5nM4qW}UJ^=!$I_08%X<^9MgLE@beMnh>vg*W^h7dmZ_`zmv6pzdV~Vu2Me-93J(+5~yH)Gh z9bV4P-%;>JLQF5tXNmH*TYJn!W}SRi#AEreVqV?5^*s`Hb9&A0w(z~RRy4L0Xwvu) zcxvO!eUB5iEbVql>>Ng?CDD{-cv$M0?4b^;aakVRh~>XiFSnRmTkcs;h4_y6la-w$C-imF~sMN5`GK4Pp>_D$6=cmwA=)7dO5 znBd~S;HEDssI(1X7Nr+Tbjv8XG*`C8c{cZV~(`*N-8mOME(xoNA_mgL)Sw>|zT z9)BcolEDRy^RDiU!E)7euHUa{=GL?6=dCVrPu42g9~K{M%%!X(`_NLZ{?B9ionNm- zGlGuR|5-E7M{V-AZIa19J{;x;wFY|4?=6VXnRNQ8gh_^gzs&S@MPxX_)MPa^<$rZZmzCr zY2}m+qVDU}`a76STbDB4YU)Xw>}#I(WX0uxAfX>;Ig(wk)!2hBJ$kqzxqs2+sJR+q zU4K5$|DSSV!sLnTS{C$7FVrv;MfVlHT&cEwclO5;<7Vh!S}FeCy|6LiafmB`+ha?&9yE*^02+= ziD2`Jm8%myorQV3r(amc+cC>V>v3e``WBW&rcoSI9tZH%Z0dWv(7Q@PT3Y(@5xuTO z5jD$LJ55`jSL#G;XgGGvZPQJib+3zly=Lb1Kz|KIPI?Uqect?hT>*j4`iT&McH z8MoF|%$u&Yy6okp*4z2}=jNDozyB>$^bYcb`K4=r5f0K$qRAV@B1J zfQ+~vA)(AiDq0*JQFl!`9V&gUUSJD9>KVS%!?M9=pV;|{EqzO_-069})9he3Q^+zt z;VBm#8A`vtNNRlcjLFI4Pg3J8A2~1AQ~Ugn6(7`3R+{{4l8L$5BTKoNIczU?ibzMX z-Su!-w~z0u?4PDpD<0Jgo-SVAGFa|FFv{Y!Irzv)aTcpW85}D(lmz^LZ4#O|L3{n4NuUz*{l4EuX=i3kF`5xF{nJkyM}ZAbr$t|?-h5Ac z$=9Fz&Tq+F|M3vF{)gMb_1?a*yz5qfsGYwcq)&5}kSO<=DW_BK)f7wB|9u^A`QiZc z%Zq!h{cXRpob~m6v-!N;kA41TvzI4!hCc3b>V3TPN%rjvJ9cy`aD3=?eRcav@$I$S zKYTnce>r#Ux{8}T@pYdxC9k)}w3Vmtb6)@Tdh%=8?aOy$7_PVbEuOaLv!2#FLmsBH zhR0={1z6_P9h+%mm&sKvU%@atZX$Fcx*9F+dQEQOCBKL9yorzOsw29j zuK$V@WNrM)7p%84N9^IQ1r9o)mg^oZ?|eVIN!@?7%hPLHentOV!5QK7;Mca~6=D6nIja5^eDm1$M;tl*?Bw=b=fa0c zC!TXWuWz2nG^P7~!b;OPy+t2iuRocxDdn>y*FL9qyDLu(k2bB9dnK@cr^mK!VsC$^ z$hI4N(KKa$l5G{JW%8&}GV9grh#dutjv|-zCNf=D`?_l7qAsmRi*{di+O(~6OW3*3 z`_!jil87~2v3lA(b7k#GQ{M}_Z4vvycgSen%Y6~?WNDt&Zc#i904`QzXhsYwLkwEbPL0Y6r(wn$7Zgy ztWrI?dFRfVHFooZvLkwq zH-~@AS<&{wUTxp@a|ORXUUR#zed^7$_mR7_UdNx?6}Hbq^#9WpY8CgpB6@W=la{!6 zb}EZ{H3sknuDm%*T>bwcfe9Op=FJTc&umF|?fo)ImBlUi_Pr=24(D6*A6v@ZycKog z`N?UZLBSJRtwKzjmoPrmm~wGK;YHuxlp@Isih&|c@rO!9=B+*uSaC}A$Mty|v{wD- zZ<-*`daOz`G^8Zxxsb!!M*=(dyoy(uRBc_Sc7!okYZA-aTYLE6+JMU2 z?;HN^_;TuXl3>TRtE-O0JU#pJeZeJ9XGxE^5d!c@vQm#p}3-ni|w{{A`hY^#f2 zENtI&x9m3K61mEK?~OAqDAe3npM26F`54c<+HaAdtc6* zde|;+lyHCnG%OK)klX8pf{P`elZ4k&A@SG>#idCT?P|9@e4oGX?7Zr?Ck30?l#-kC zSIXSl{yyXPcG>9$CMia8$NB9V7x!DWsd`TnU{$=dmF-62#sg1I_HX*VZhzAP58qtd zZtv7nw;o)*BG6S4BRI*!qwLmF`@QD(nKnh<`~SdsUuMLSwwpTQF(r)a_kELUm#fmS zz5crOREmbktWGEA*jU{ZqXnk&=l(UUUca+#ZrQDg&TPCaDr%QntRBtEUdQN>tCE$K zCEx@aAKd))TJ+`J<@xJ&zuRRpF+V3~NsL}G=py#aODebh!yhhY-*8;6dc*5=yMy$m zgAVMuawQ-*`0}gYvA4GTSE8)y`iT3%}j!THx`1VUF4DtS09f zVrNZ-tz|i%HkAZiQZ*8Ea_2a&n4zb@v*VH@mw0G!a=w=Eww$Q&)fJ&3fk*q>vzorI zovT`>O9dF?)1n?uh-YNqA&Yz zLDH(WF7_US51ibtGR#YpIQ@5iD_-ZmGh)l;g>$W(R^Cb4;3;I`HKicn664D?Ax68p zwEkUB+%h#zJm^uoV3e1SPRbJ27PpA1Z>t<;oRZ(hAI_~b>7VZ8FeU>5MTJeV1y*-m zSXn17jWP;bIR9Q?+5N==zy2ke?h=3>seSfiyC5N}xI|Q6@Y2!%t`k?U2u(RPr}|#Ryt-$SdV4-F)!8Q4-(LOp zw~46NkHnVi3z=t3i2403BmCjDtB*J$q*I^WDY8?53usEOisU-Q4^2S~QQGjYLC?-f`*tJ&tR>J2S69H$W^~N=*(~1(r3apIqaLzkA3$~vHWd!TVY!K z{M_S9-uj@c0#g^y|9>XWyr)2>b>lquwXBnPI27ORSeIn2k{WxggQrC*_*3AmuKBK~ z78FSqh#cczW2CXEbbpN~D0%YtWHoIUl6bjbtAk?l$u~wpQn%d|P5qV~yQFqHwMk*Y zvSrhzEvmQ^oRIWTBzeL*?+_7*g>OQ378y7RaW!kJ%)C|QwaE{)M@4hjf& z573G%j##NMeffq8!AN@rgK2zTYThcUjRGkGEkSkq6PIeO`jOv0VVcv^cERemrVR?4 zzL+R0bUmFM=2Enh=e!VW?D2?si%k?bGQ%ey>};JmC9BrnO+(C7jPvpF4T3^F4##a| zn|prOhSx4qTiGzfL-^%^Z@+6!f4U`Mw62+xd0y=^{WCSsbI-}y&eAozoiTNLWaq{7 z-eudifsR_=M@wUE&U>>) zPxJdA^y{ha_B)3T^V^?!adB~QRl3>i)KgP5-)z5MXVG`qkzLkhiL#Qtm+GJDZ*NZK zZohlX`u(26Q^VstH%6q~*pQgB_v^Ki7Z(l&Ic{CHa%E#|`Q54dc0Z>S*V|7sK4&qx z=lP?`$SvEx2ChuHT$MXnR8iI;s!=RC)ZF`{@tz3@>^VZo~ZFD%e>`~Hf1{{d_tKN=-)m)#dx{23UCeQK zg1`OWDJLhZeLU2yZ&dfE0+cJwZe55|kKI+0c&tZqrSG9duH8Y7ptEeJ=|oQYC+8~o ze(!g=qe&BAUS7UD^x6}vi-A5DdnWHaqOtdrm6yhB&#UiuhrZ8QRQ7V|bfffh>^$;z zP0sw*J&XHfTAphxdJ<=P()a+^C5g4s?=&U9KU@AUg)i{1(3EYjzisu;VA^xzkz!Y* zjYRJn5%1NDy0ljPXbklIuupVSj-KIMmZwio?w)4#M1|`tn}A;2wWFsKChzc(xp8Fw z@`p1GEKEzctpBo4sL7}O+e@*%-`;*usJ)-(+weSK_qSPVzpeAVzK$V9i|N2Ey}6g~ zzqT%odR4IM@X7yr`&M81{GV-4#0uprhP6RlJr^?8toizh$z$>*4bx*BBC`xMlv$q? zNxsUyrLiA8`S*xV4}E2{J!qH^|sr2)-3{8u5VZE;tASyr~Lk37RMti5BqP; z4Y@RLanZ%&rLuDMe+t!nW;kq&Q0X!;HLYyYNP4F}KOp#eo4x&C@m=e0cb}8BDmoH) z{KN0h`VSU)>oL18ywhM{dZDai!ndf7_3XN$z7tdPUEBnYtxfRV)ie35VAh07&dM)0 z$KDUS-@ez(#K~jMkA44dy3IEDu%VHGWun>@#l9&mbqTApHct6JEjsVyo12>>w^SI; zuluE$uyTv1e2f6gj&QK5utAv0c_}`?|YfH~IAs?)`rE{2NPorlw_1ox9)foBn+Hz9Sui z$~P(|^S;@exgbPq;_0-EtPG|3rGg1ZPcLaYusuCI`_EDD32w)~y|`xPwE0i1(X9YI zv6Cs;Yj145rZ7Ej+pn5+i@LP-Nw4C(=QZ)m<)a4o5@Ry?}B@Nu+>Nt*%B8vfL-&^^sPbMJ~Dd$6l(*BW=T$4Xn@ z#(G80JeHv3?9$Q6qt+!5*q~bI6@B%(($X}koJ*U7UcTW{**D{uhttXxH+~dNKcBLh z#j#_tNZ%I?5w0!y(fuqo*He$4pLea}P{+N!)t6U?>o1wICI3EXm`N)_ZK}kECMnzM zZ%;m-w`b2;dY1oB$b`qsX6Gr*Kfj#w@OH((;GRPofA_rJwbHRn#Py|>mhVmBI~9+6 z?-U-Fy;J}HFKDA;&ep48cdA~mJu}O+n_F*3L*e6Nh2L(bZ~k~p+PL&pNZR?T{(aV8 zp1#}tF718ox5R@@tS>wk$DDZbY0s}u+A-B{zuJ6x(0t{})di&~SCyQz?|(ShE?@BW z>h%wAHlLq#GG)iBRjXfIOuqXgLaFJ*zsngaObb}NZbxqh>~I*(kBN!SMV#f4K`RIYf*-oJgRQ9&Ui zCo1jlw_hw5I9@)mSm*mhDc00;#iA~)x{wgzJ)w?AD^kN=1qXfHSD?UmZ(5XZ>x@I6 zu5Vv;a%SAiNmmn>bZLdPq#U}_GONa}Up~uw;Uu$*ldky`wK`@erL5j^;9$UGizl%k zmb7Uo9a&<&PvFq0%iNu2Y$Yw)YbH!SsCaRRu0XG)u*NA)E>*o{;L#u^$(vS>)lD zj}A|IS$06J^HxTQz-n!&*%w+H-(DAX+K_Tm$nMt*Wi^`*4DGUYKZ?FrZ@*gxI$AgN z`P}lfV?C0fOCCVCdh$q{_3VDPtNZ2U<;5?TPG&^{y}P@6TVh zObw(_Z}%Ig^Yd(9-q`rqh%?UVvhRvHL0(HHaVWpIzu!K1x!=A zoS*gEGdo`AKe+5~uXw5K(83rk!;k)xf86%gFFdwlV$QysYA-aLj$D)QFmRL<6mhT& z&=QSu!t zCr)@76?Fb|N>FS~xb&1)xuHk-8()>Ogk>Bp7U{SD*RoVsNx*ZxPmieJexZrQoEB<} z?(E?Zp7No^Ej6|yWcUt?~{9|#K zt5kVDzn<}u=$ZdDcFX4&P4U*-*>Wy+SHbPK+b5iVDpB!7!68V;%=p=y;+v1JS8wp0 zpUctI0J_%l%k8c8Yi?y|{I*M!5Ny*GwUN{|*JkOPB9c`6(YEZrXnMb7cgQ5$vj3`y zOLjh5)cxbrX?@E-6PycW+UNdy=de95J3K}-EW{<-yVB%VKz#81S2Ze17M@#8f99$C z%{ehUf8WV9k(+mXx#WHFY0;Hy*EU^rlQv8|#4;r)bJFyaDJN2lG?rfC%3FFVRibT6 z=H<43e}4x@N6!u`F~3uAxMcRpa+%hNOWz&aTibb~@BMFylHYfQ`haBs4uwWvp>~8&QJSu_HpH>PIV3OSr?*$FE#nw|8H8T>{f8#9@dXQqfM8qOWS!lgjMAx%mSJBXrk9R-j z`+v}S+I#p$^t<0CzW;9oc)z`N$??Lb-MSrLzf6mC(<$d&Enc#|=4F<^|NWh>?%ZCb z)VX$2-Hxk`EZTbn8vB^0gskZ4Hc@=R&~p3Icd^VERR_%}@{iaR`?iFxH0WBfa;@X^ zt`k0OJq3Qo1v zOu2Q9fAUesu%|LALf`t7R_83(yX8vl_jh*#y#nLo{cmr}of!0Jm)_H&nXzRzTTf0_ zzq~y^-h2AwF6DlkO;gL`l(t;lmK(k3#3i}d>r0m{Yb)A0XO)iHvB&FPZ+bc{Iw(Bc z{rkJS(JM>ULJxXvJ?Eo#cwY6plfwQsjv}rybw3`?seCpw%rICB)aq0Fm#L(`|C3R> zY?%aT0C0ZoPs!bH_Hnm5HQxXCZu^{yOPx6zzl!-(mr6~KtCLKhTPhYMU9T=RbvyT)65c?wPLqxH7}uDRF6lcb%kQrjL%*rG5K&&-V6m z@Je1!d^5vPq}$bQ)@Q}wWj+tj?%#hfw)~#&&X`9Fn7=*0nLa=D%nU=&*$^|0(~T-V zBvp};;3^Md;bY$GpC7i%FIw7MCevf+Q}ZP7*_pcell$!3 z=6`?V7@?tbh~c`h_f6T5b054)e&uX@wa2YJfhEw=VWEMVihz`PF!L$qyN7;U{OB?{ zHW=IifA#SGya#{H6R&1YUHyNi)~Xecjvp`ICGUIMq|d-Gv#RoQaHo8nMA9LF)RH@W zi%(wPwl!q^mURmbYAlHe?ApGiZTa2e@QCWx3kRNfPVVq=GVbMFx>b?uG|N(>t(E<} zW-m^@KX29DH`i(ri|(n$)ids_)dHOvz4`aM-Nn~q%OflQDkOl;z?l}Em-ytwM45^Q zjnmGFXL227DlIK7d428dx6+f-IQK94G=-y(L-9ilzi9Up6_W!hnl>*MG&5MdUbFd< z%Ay!ODa27i<;W8N;W@QoHTl;q3MM+KNOzKZ|_%2UPb4``b=kyZxS&3aCP! zQ*=rb)L4A8^?IBL7wb8z*E(glbIrfqEsqzg-8%ua_(!?VqUqPKUnQ4{4lZiV*>_az z#f{BhCTa$QZbB-Eo&Nj%e`e|Y9fG&>Z;RjGE~>cLH%c(rYpIj+O&`6v6LvhGw|k~V zp;GMbvgGr&-yZxp*nIL?&iq?@DnEBD>bSW%o!PALR^INnpq=d>ZTby(0)rxx-*tK2 zyc!;VwuMu;;_uh%H?z<0?buSgH+p;CpFhv-({F4@bm(5;r8>>;m9~0*t3XWAOI6U0 zR?vMepsT=J5<9NV0-e`Z{eJKC(|WskG*vg>pFelq<`6B$ZS_Wh*LxOm-2WcF(*5)8 z4STe{PK*BX?Az`9$KR~qCmd?Af5e>8_&W7R(LeK;iifUW?q|AxyZ<@-%GGNDJg1)6 zR?9VA__ir4IV$6-==O;Q2|ZVDn=W+ZmN$>T?ex7zslaBp%>9}7f?Y-JC02cWS#P$A z^WOI(M&=Gn0}Dk%|2&z%^82*6%&Pv+@B5z4J^wUBY)Q+arH?#c3JFC%WIew%b+gGq zWzpjiu@wiRjqfGjyR*|H#^FYdZvw05qJ~{_j!$&wd-TDXUvYVi$*h3r)}!)5Pm3ha ze-7}Pc=~C^7H-;>|m*a#{^K=B$=a?$n5)vFh8+&OWt`u$mN{k=z8#p6KiyIqgi zmu%S|wDQQT>~$xjve!=STBQ>7|7p?8^LD>^8bHULC~!o5EznGzJk6!czHjT3L( zirQ87_SDzM>z;$UsG#8$UtiwmbIawjOCp;C7rPmL+A@(P@xYIdj|065FL|m9whAui zkv?@{q4SSVuYa1DnJqh{S6W(n=Km+{>No37Kkm0ZrYatP=XJn%J}=^ z{)gMI%(^Lc;1uCGtMox9z4<&l$iB`+_vp11!$ zr}X;PMFxQq3w=+U?%HxGRV3KacqY#=iF-Al&t6edT-XRYMaJg$o6VqupxEeKV9y zc35pX0g+dwpVGU$MemT`!;EXNiyXe zUF-Deghd%cOq7DE+3&tZ0#A2wC>FlXQsB72v_$!FWANrj=l18{pSp}et}?~wW=vnv zMR$qJ+Fw0tI#XZn`gW^F(s~xJS%kbMPpXrVg@+{j{M8F@?KDz3SSw_4ey;U&&~V4f z)PtZyHf+D&IlREJdB?*x>5S{^WQ(7lQ|(fctNjuvrWZ3KtZI>lljc;eauYMNOADRZ z_4a&lin*@JrF`hbtcBI{+8`)N!zx-8k_O zOV74tx1)2nihjReZ-3tQyUbxf$zyHOxhGZxEcPRgezCqYZTc;xNo$k|qHc)4u$ zvXUEZZEYqiCkK6cIz8T~^i{~V8%f;P;_LsK1X}(1a2T{O=|;g}-nak4R)l?fdAS|5 zN@iQ`?PazFQ#+GVnfP?SobD7>S6cdY_HWSIdHcGWUo-7$e|`9TI_O3LY%Re2|8op@ zK=bw|pB90ZOMrS?vt~)ntNWF?n&;Pt!=P0Vp!Lyzp6b^pu3oz>=~$2C%a()vjq`Ii zFqYpd(=NYTtY2UCfl*AKuW+e?QPagr)aO_@VCsARaF@_R-oO=shc-NKu$3sf z)cK^iGUlSwU7rO(SvSf}`{KS8J8>*BNc!^P;-7EZ_op6cV4PF)>11Y**@q8}UtU~n zPVTd8>(<-V0jkrc$JfnV=-mFOQf{V?+R}J6Q5j9u%gcNpFKn0diuc~ORC#XLvq@Q@ zvr^P-0}c0HD4Y{=ggNJ_K9BQ~2~$pg+g&8n4raxw+ok^X~3=ey@6_ zO{I~SCg`wbHUD{MKykZHJW4CMuc%OlUr|KjLX<$;tmJ+>K2;gJzh8oz4yetYU-OBx z{C=(Z-srtolZ!95X}mL(wy7{UE?1rNs&xCFxSuVr zI4|6|apJ+j=F8u&MW)MImAyH^E?;v%ZFWx6^U5vRxBDVDr`^mw8hW$r?X8awn)!uT zz?1Nx!@*8WP?Sji@oM#Yj>8jLxy3(yy&hlxpC$igi`H5vuO$qbEb8**BGx&ZP0f3x zkEhQ+(=8m)S*SFx`eW#_y{66gd1bxc`zhqVXXIgv(VP5T6Iny9d<$;JdQgXLKd`a^t~4rr8DnLkA3jon);v>Y89a&AMM!| zM=z3Edw9myl@pbiJNJ}N)!7o1ktD6d*pfPJZHLuIf9WeT4U~8e-B``%#M4)zt;4|M z(X1yr;iuUeo1M{iYQ9wx4MiJUoD?r?$qqjMGQBTpw_S8%kDKP}ec#vrnl^PYXbP+T z=jr$zkGixiJ{(}aS$@BErd_SoahYNs>vubpK`RKI+xecpSlplX<;BI!sk~8FWTv;D zQgQZ7{eA3_viB8HVX0@AYLhud4PM?powj-9s~6hq_Z(ssk2%n1{qDq#;^Rt7mWo>S zH9xjkdE@w>pPzTW*>rlx-*30WtK@nNUsefioMHR@&SXXBwk5yKs=j1^#%j%GKYcRU zf16$7KL6u=vY-nBK;y?plML5R;8c8ZWu@@zwcF)7EFLg`_Tb#vX}q`U zYt+l1|Li;-M=bchOxpP0vyXSm-`}-zS0@Z1&J5PQ1S}*l~1*@lK3M=#~3h8#9TD9mx%#)SN|IPWgwk2`3?zU%lHl|NLoi-sT zB5}ILp-}sO-}h|!&=%Bnak2a7gY5Db*2mk6=|mj({eJ&>DjlwY6fV=H{Cpwn-QLd^&yowQq+FeCqArZn+G~G1G4DKX&X`NQMf}n@>($aup94 zL4!PBUS78R`{nY=wQG-lwy` zHu5wbh~lY`+;*=jTdwAVW7XGJN9%sSbvK*6G(zXo`TBp8#p5a(Yro$$7i~M4wwXim z#PiQRvesg2O?SWFXZ`uv*~KAROH1AyJLYCp`fAF%!|&_=SHA|`gp+wxH&9%6`sqDi zuSHvIY)VlTT9qT>ntAE%Z@Z;IoeCTl|Nndj?H9iuUvJyY&c7@~YpKcAR&Mc2`)aH8 z_WvoGHGB5XM_t+y1_=zHS^sv~vWQs*@Av=z2kM!w+5K)8=zi9<+ir1bsyIcxdRus0 z)_r4y&u_K*oQ$=)TdxVql%Bcx=FWb3@%So9`C1ck_16hJKNddwIsM-;`?NiWPdfXh zoxfY&%i6bP?Jcgv=VwG5QnYIX!vFYgtqMOH^rO=yiu2^*28YEx$6ORA@(CI>2MRi^ zt@yOIt6qN<=e;bYZC7JoZHvBmbnhdzEA>y`P6&~5THxZ*ax6WvtgGW~sjLc@_O%I~ zy5-Z~URzZY8usUZJa00O+l(&~wF_8WG8TEAUmxLba5KER=3Bh?`zbN+ELLAmE%|d` zwZ*mi*E{wsYD~!N-7#%H>w+zA$N96H4@h(h@)Z_pPOHhD%d;&mT$Ev=Sw+U86UPIO zIB6R8HmE9s($;5>HLs# z-&wKl@CQX_$qmQfaYUZncCo@Q=;W`$*>zDXqNc3T?6XG6$9hU^6D78N*~^)IU~P!^rZCUNI%3^du3TC2{AOuv(M_41 zIeM{n8|7{koz|^$>l3oTBc0O-}h7PZu(OV(DJQ5 z`+pUnwmayM4!h~;XJ#0JTn9R0iIJJD-~c0g!Hb3MMi~zjK+9gz&doXLYkv30jg85Y z1_=!8@-+ruzkU_zcD=Pdf4@}t!A}!7Bz3=jGP=L8qxRLCO5VRhwpAt1r+qa4e7sY5 z=hto49ZJskCW~~tis{50Nu3^ZuKT?2(=CF_1Hvb}YjzeH>rUkpo}JURBSrmDpy#A} zeNnfb=YRFg-gxH4XZ_g;vHyOoy1XO(<%^D|djI9Sr&ML$)D*hyrqFZDg>fS11dAC@ zEam^l{Ji+zMd-%=BGBd!hhy7|9{DbAnDjBQWyhhVlTL+M9#HR3lb!0|)l(2|Aie(# z$L2}4QG3;A9TPgjbAhAAb7naA`%lle$0gso!$0%)OZ98Vk6SD-`Vw6oyDhptm@Q{B z_v?%EcCB!^=h3s6!>2_+h`&AP#bTLGB?pC$00~|#%e+j^JFBA`f9Q2|TxcR7^A8{I7CUggn_>F7uWw&oUC4bq|7v@z*_}ymUv?c)Z_ch>p^~sf zbWcQ<^+L`q*zxI^YYrIJPmu359tIDbyEXo}R0=GF@F{QZdTsd)#a)6PNkDIsd zqhs~FrxaSY?X9rtvvTp#^~#9qJb3y4htH8rT?aO;cIoJJY6+QE^t8&%^O{hsMv&I@ zlPh@CE_M8n3(IIxKKNsShzGxLn@dpBwU5S2QnMDOuIBt=wBF9BP)LdA<<>m^bGF}O zuD#pkw%V?8fzrc=o>*+Twqv8I$@_t+NtKaCo@8 z0EeAOGp)R@F*_^JXH|K-ek+EerSrxu& z{keVr-?3-2^ZjaTyA7*~_IQ4ha~1si`+NGcGc(_Sm&W$TZ%fhv-OXW~elF$NnVF#S zb)vF6Xe9UI#$(8D`OWU=2*RIvCKHJQH{<+{rV*AFUV$lVEzh1w5 z>(;5c<@ZkV*Z**ybW-K>^YhOib?eKy+^sP;W}Y|yQj`H~vpV(+{>hZE{%MZKnr{21DyYOsi_~wd-+6|7YS(pxH>+e6&=`MFPv0eU< zpLPArTY}043te|HwJfR4H4ci%l5T5wEp+q8zd#L*X-u8Z?;d2m;Jf5;8P|oxjv}_; zzW>SRj+H-nP`=J*3&N*OoHq<2$m|)mtfSe#Cs~+i>RMxE;xTfE#rrK%cm+`mHN=aouSmE^kcKcBaNWU&uN;K z)&~!|K3w;F#r!=f(^#t3E<0IP{Cji#<7wjZkJfIGUZfMEqOdgiK$3Dtja>9+seaw) z6HEE;o$X&<+nW5{rs3n2MH^bImRvfyz;KCdyG2}@!hQD6R~9Spc-GBPs(GL3)*RNP zGwW(e(fiHcjh@du9yukK+28q4)1&}l|HHbAW=~rtHZN}P1aG+=&5zaJpYW`%ozHni zF{fp>o5c)!FW|9;!Y}8$rZOD< zy;bM}Gmz+E2r?>A%l9aUcOv7ZhnLcdEK0j+U zpDuVmeNBi&&4c?VQ-qd^WM5mOsIe+JDw|z4`_YlkJ9WR`o|$dl54v^v^EvCy*W;=u z`l!8p^Gap}oLJ81o-+3lRoj+GrtgZQIf7um&V%C8Txh{^U9 zakc1k&d-0p;L(Gpub2DoyyEEN9MU|e$m-IcAII&Vf##KN=k3-_pI7;8!TayuzVS(I zZ);=wb~AmxQNo&4>y$W{`mEnsOw)-xbfi=GW@5YSj$f}`G22{FWZWAR+oItF{*AW!)b z-=56bP7!NNk3Lu1CUIv~J@bL+qxK0KP7bY!ks*9P{OVZJ437a-;kW zPL?>q8Axawg4C3FnM&Sy!tRwN690WU z<}FlUURU$d@!z%-#>@Ryt+tnh3tJ9tXY_n{EaBYw;@_3eH~d+fI_J~sV$a+yg))pn zM&CB@&bec!sQq-=cHyE|p_ePyT;SNmASvj+&SfL-A(4v-3pq*{R_}Z^^>{_jN$E2` z{u$O(-f+7jP|dD;r1sh12)cDIo*#*tIp=I zLD=Iz3}xT%>`Yx=FOfCnccJ?Q`xk#cpNz_E&R_dFN6EKR!HUFflcq+FilVQl$FXhX4Ne)2b|94i}=lqobwO=M*r3 zE?IeetoQM!)B5R`mUzC|c012!rcLY3&FRT&pH2;rOMG`{Cun~K=$uK=1S^lU8BYge zhD4i*nc1fghxtL;p`(TCdm->-XT$B18;x-Rvk z7uPI?+S*!>d;aTP-4v{4w|&Ya(6ESX`JIh2x^qmk!z3Hd&9U6PreoLLvfCGL+&E!+ zJqEP$@8tTruiD%0*Hzn`f4pR}-y`Y!KiEKZ?Ek;t_4|`ULq(^@6mfpPSFOK%eqGhf zzF&=JnkIZKi;;FV;=Cr+(`j&PQHag*PNk<;#cH-p$avVWQKiN0HB-=Yj;#kuCo3du zzgwQXS$Fw|-y#3^hs84A+w-P87kaWeMTqlL z?AsrS4sS0g?r?kjy-d7&S2kB&qsu8*P49h}`uo3W-p~1)^cn8`HfTQR72Hy4XZfq*;o9dFf8zT;d|7?|vUu9b zXSIK70+ulDToU9d)OY-uuvyyl+_HzOZ`brzwJ8)%JlbBj;s5i=2HmcY7f9@XXd(62 zZJMg?kH{BqTb&ph<(m~U59(Iw+?{kXzmp!(gvt0I%a9QpRjb(;f;)^ECK5sR9 z>3N&ht!?ptznJLNeK?rJcd7ovK~aH4g#{9u4@#&#tC_Zo^@Lc`(M|W5W=x2PT(l#o zBG2Zw6m#FR-g|0(b4w-n+dnKRTQ$#N=>)^8A-`k(cVCY9cm}SdH2??d9ka;S4vLzpW-D*Aa_jazy_BD&vuW!%sH+OO=+_J(VHvLj) zkECs*{`)_sWix+?UJ7}@A?`Y9#+>Lo0m*C~T{U&;uQa#{Te{LOIk_wpcxa&)xWaP> zS2V{#&Bh6f9vouuuHx+3nvu*=+Hy)XAXM~(#*v8LKMlXd6&>Bho^r&5|Gn<|!EVLV z&p$UYJqBHD_PEcQ;nae(SZ&RmygeU}z1jQyo{6ccVfDA1V|}vT0xX~$l`1gRZ~1*j zA@2k0Su)maP1$_2=u6JoS*B;^SWce*@5}N#Ww&!d>vrzcd_D`>)B5mm`(z(A(1{u= zL%L??@3RyW`zQq3+4QtnCvMM-+V8jfBR8iNe!1xW8FV?2@i~j;0 z%T+v3h+16~QlHtrXvSsGj`aV3KJR?L?>Fea%gf7rrLVAE?~P;$JHiksefIml@3!CW zmfz=RfA@%adhxwA8$DKDusRUYYbe$2a#P}tB}dDa!Xr*X+$xgXhZgv{EYX$deq9xE zH7vNpsjmDX&%2%f?eb>Z&W__g>B1$OxyiBbeta>nzuiX_d&`FwSwVVX?n_p!-e4Om zAaWtFqmL;?t1*PHasKi1X%mAcmC1gpt(922a@}gz1dcy8eyL}dzfG1*S!(T`yn)4K zhSJ_iMr${^)b{v_-ECX8!tt>}p}?Vof^ipj+7(PsVf*uk-P+`X6#tU`t{LkjmmhR- zafwhWiG1oXHG1DWS?vi&?^!u)dgImmb~E!QhAkZiMh8yVbS#*&czsBRnb35Tg%?sM zyzls78D7C5Bf`h@y!gGqKmXg}4EeTZ2G^ClOm1~{oVavMN^k$?qIoqRGsDWu7EM*~ z^6F7uu|jNxRpV+At%V#MFF${_+4m~)-OT?M&d+1cOq0$#<=H;}#FQ^$8kabPBo=o> zN;VmA6<&XOrGClHXoUg~#h*9t9lu!l{OFUvTTN0`RE!<8*vcF^YFR&+etGIpb+q*i zmNR^-`5qne9qajRg6t>5nDRU=T%MOlHIs$_3UTs=IyvPJzPZR#{o@ic^RE4 zN0MbkzV7(*Ec$rSm)vy4n8TBLdKzC{@ZxCNQQz2h?%t2t*LuaPL>*fbTHigJ5Gnrg zfM@#VUgJ3~j+eI=D6Y5v&U01B%KCT2Q}#j?wgR?KPwic`J5PvsOE6Coi0v^Fk2ox~ z?(b<+n@?x#GhV(^y41F6OVX7ISt+tAv8@M^L^4>jf8VOCjWjO4U(q#X*12!N%Zk1* zx^Jre>L;P2r+3IhDZ9}AjoRz~%Eo~m&5aiv5()!uoOs|R>dq)6w=CrIDh=lNMenB; zO*arr>{8|4(kZL&mAHswrSF?572(y-t4|63e|Go$zP;1ml)b!lcBXMVXkz*8_WSeR z*S@cQ`m6L*;0q7Xrh(8<(Q8qke%8#~_o7m6-Q%MBwci(df8|t`ogSg_Y|Gl{X^9E5 zy-rPa*!g2u_?eBjtKaXfeE3rwbPu%kn+?p@ws)_s-TI49Ypgq1!?{|W zcIvpC^s0UF^4-F1+qTVl9NzUsw(iHn|KFmff8u7$+xc{w(T7!Q*Sco+KCeuDC?%Wu z?M5;`sQ10^^W67S7SH9>4_wx0)puC7{LZ<*{5A(7)8`(2a&q$N^9K*aoSx*hyeLFx z-(!sy!RD;rwHn%$&lWKp4=j|MEi^^zIEVKin^Wb}1Se|MZDXAB_(9@^g=|X$M5it( zV*QgNzx(YD+uM0NS-0Q$lRod~^UW5gjwVfXGWfsr=bV~TnlfANZ@>9kx_Z)=porU^ zFMhuW;+*Qzv|us!_2P+P6VLyCU}52}|%?d7IfyuPAyf%2Can`O1E?Zi9jAqy>L&Y?6t5@u`qCMvgW{=Ck5gZJ-1ricW&&K zXWS3Gl-ws4%C?zbF(`YXQ8wdS>b|W{<9HUziT5w@RdU_-m1@V&nj%! z!Cu3Rl_xFlX4K@(DA(O?W6;ibT-{dXpxW#{wcyEzW(X+y-dr5PlPW^{nULjKs6iyf?1dFzs{R&Ms?y>+U71f8JexPC;48s;cT` zugQJ;Hy38;Yd%W3UDWZ*9>bk8QvdpAWPfNhnH!=Vko zBwkEq$aNQ2ne;$&S5al1`R}Z}9}o3CRD@y*|NTr+F)>@ODxlXcTbfe%?XCaXe|CjUGPSvC@BI{`^>NQRDgM`Et3rxqp71 zuLn)0=(t}ODcq9rdhPbK)oZsgB{`(7b=5q&Ds(kyi4JIz;qr2S`I0v=df|0zm1Eib zF8I&aaXshdHC456ii?t?+3csAPU}Cuk=+0Eob`K^sa_kePKz%5^YQrSL)`jP81Fe0 z$4<{Ni`Em~@VL(!bkG~9BReDQrAFGB83*frzde3sW$@{v*B8dCibyQU(OfE{1vX1xE zrQ5EAT?>5ivh$!%ih)xSk4lSD2hS<*V~c#>KVm4dPb=6SH`yrdm<5x+=cgYnPhKvX zIa_|lQCojIhsF23cbkPQ5!svB_?UB*@FcG5N88%oIXU#-Kk{j6@1MU*pYPDAG>y*N zqbYV%Ax!3{3kHzYijdbj7Ls#|;b#?wpAT0Uz?o?(-c9dk({NTs0r zXZBJ3f9%RzR14HyVkRwd;CFkLVW@6ebP=`|Kzm31y;z$+U+iC;`|c1Fbl^eAZWqpO z6TL%|TZE>u3(5vc=da6o`Yn9kbED^3Ww$E0)a6QaCcj=jL8)0p?pE85N8PnY)HCN- zH*C+lvx4Q_k|{1Jk#p*28rPSr$^O)H%Z)jFq|HS8_U+0vSM4Ivn%wS(3B220gqF#) z>Q((*qWsaYBIwaojXhITj8{#1m%#h{UXdDm-COpW;y?TWMy>+CcJ$rm=ewSHy?v_( zyUNsVhYg`g%5@vxe~c-;&#PnnR)Dqeh%c9$V&Rel{)cWY;Wj;bcB#B$w7!UvT+}}; z{yhcqzpwQ!Us`CnOS^sk%18e7JH^dziY#dsGt~7-><&4|FZHzY|ALh)8d)0Q%>gvMPt9E?rt4?_2BCzR%wf@!zhi@G>KJ@qG^R|u#yIT>nswdC?_wIR# zOD)gc9n(B{4@X?Qa_H4Gxoc})CT!Nfs%-4(6LH{cQs(0mP1nR!6*#yw7)3QbeJ?57 zZfl!Yqx}3{iB)^;?}9RkUDAT4DJ#^zE&XSHtkX{J^OEL1rjP^!wv>tclDkcA9&jnt zOD-(dZRuf*-S}*-z!AwePD!n9+Kuri9!K`h_FHTuufzWSbIS60Ra)hD3fV!l0CR6C zqXVZ5!_!0eKs{B^f`XkfeNRtM=l@j`9xm>7e4?_-Q>VKZ)=NdQ1uBK@)0rCTvHY?` zvV>s`3#eTVI>*5N*Tw#TKCS815%ZrGSxyN89ee;tfnkJ^;eeT z!y=7GUoQJU|8_e+egEHY&R!>%cuwB&WRmv`qf{=?jm$w_$9g24wWdCrk=&PftVc3q zt)yYnk>7dmcSr8ocHG2wsmKYJKevut`F7#@4zGthIA#2kK1KF~x(M#@Qf%oK5^I#c zu5sK+<-p{MPA{!Vm6O)7yET^lcxJx;Y}#zU#BZ_XpKl2JPxMhMknvn7@Znn5cFRx4 z)eCM2wr{*1{>{N+Qh-W_46C0ij&`{K6s=5wpd&wO=j5H|MQ^-|4U-2B|`Y0>|yq;2C|zHTs)=9TvI^_A*$ zi_V2ZQE9d{%;kUX&;1fHU$InE%~#HI*(KK?`Gbnlg4RUch{9Y3BpKf6IZ_z&CZyG=(0|AgMkPww z(N-0omOkCW&L%V|S1t5$6_+q)i3szadGna+6q$75E-402R=dE)#Jo_=WwNKri5|bg z@0Y(TaErdN%*+p1{-L@Jc;w&?uTjrK7BIUm!iA3@qDQHe@-=@j+b*PdyN8R z_8MC~+pQs3{nN|d>)47VE9y)q2pC4F?fmiEc2D@GFP75oyq9<6L~b?QZ}}$u%&zxp zyFO)eeqv-bS!nR%)FW>VhIL|BBwVL#&saVyq?S2O>B+v?X~yqAn$LW4?ZYU}0JM?`W>x>I%`lhgJmHvu}%Cx7_}HxLU>C&b)+oO*(NaCQRU%A14?4OJVx| zpIVm|+q&_|`-Z3YrN_s*d6&DSdTl(cW_snCO5ic2)1`$rW0 zYzT0ieZP6SSAy2VZSMK%+r1n0`~O%ecutJlAM$nigW5kYw$-hCU2fj_<&0TrUoRFj-ka#oR(K^dA+qJ$w=&SWrap^D9P?_wMS`|_uibvn>V>tVfI?`@ zml(^xT2q%6^ZYS13%lF1XoXC!mg^nRshe?iKc8;ee4%hoIcvhwV$iCz)UM2x>zO}4 zEW4MPuI4+7<%r-;1&&i+PEJ~-_J#RkV_28c`Pt_EpoN5Q_Iy4Ex=Hyx=O;F%6wTDg zUgPPfC!T(K>MQ5%+qW$rG%%ldT6AWv^>kmen@f0Vyq~vQME$&d|KGHk#_7|#m-x@I zm^eFcSEsO_MdMQM=|wLVwjbl^I=%kEKlXRev*UkDaf|6B+|J$pbm#MVzqh}QozJ^R zXyU~RHN8}&R_XQ8N9wgrP8Dm4%bAP4RGa9rWx_^n?TH5i^(;g;3SZW5DA>TZq~ydE z{@&|0B0Cmb%G_sC%Jn?Qto7~lzs>e>)w;H}u?jr3H*MltAMszmcS5+|?(q7$O0!O@ z)*{iZyq!vKFCL%BXTi5ptF;7iKvrs?7Yj!7IpE$M@?8uBzWwGb=y0zS({I`;Edo(+e{WDEjKOeD>7W+jPHC zGg&;V&+p!~{Nhin_Q|e^y3T58GYpC>&SqOxY+lN{oYibrfUA<|`LCz6PaYRpeA(^z zZ%3WZEzPf0Ph44^dD6V_q_6RhhuiCqOk2DxP&q45iPdbL@ikq+&l@8v=k_s{OR%ZL zOwYR&aqqKQddwf=UB2Rr&DSknX66|lu6{avy{o2#>9)3%Q_fP2SElXhE0CS;!L`UE zm_zx_lx}6yl?&xW4`2H7v}$JEW!5*lZ!^}U{<&UI;30Bcm`!`)v6-9VZ@6#tmwmvy zCsX#grhdo#8@#qB*wo)hdG#+m|Aw{x$+7)s)1FNG8WFxB!&UgaZeH_=O(&0dspUj? zre7k0&9ag@1m2Ssj&2=5-6}OtMGqMUFf8PDst}o@)3m)k{>9cd!pH0m?A1$;0 z?Z+oMjaybYJ-B3VBHy}Lrucx(bxm&`Z57iiMThOuH)dVUw)wDqcjn9NrM}_|)SMk9 zw)9Rusm-+F{p2Oe2VY!F{`o3=-YxkvoV?$2KLE$rL>ci#)mZkmMsj@}?JZ)Sh& zU8mEpLf6D>=F-;foaLqFH`gg`|NBE56a&H;6B$;9=)^U-aqim$UoNX9{_C}06e~({9?Rxme|Gt)uPaus zN^8Hn|Io7Ie$VFUzxS?AHot%CJ;RLx?h{P;y3NPusYL9acI;T_ma;7qy}}pRwtGhB zxn`|jfA~n@0}qc%1w|3IaJ9#GR$XEX;ZX_OC%z+E{($zX_DBZ}u4S{Ecy<&YTzh6- zx$xrctCs8YMDEt_BDNlk^Ldm}WvFLHu_BzQDUYCf)f`_EH6nW||OP#*$ zrdiJlfum7XhUbgtvixUU@46<_WW%uwyMmt`-|kRn#un)Hb6;lbslZgnDc0|HG=t7$ zjV-@Bb*cCCPhT$kPxt2J33=qBHu>qC^+9}IJKxQnqB8lU(FBuY0xXR4o=@!$)mpq@ ziqib^%BeDUwYKhNk?}S;eaW&_;DyKW1%_|-t9$1b%d{(SNLZC*STa4Ryr-a*wo-QTgth%#YNOaAW z{Tq{ye>%X-U+}0?eN)0gCcRxRl!Q82s_U!sDis?i+Bqu*+-y3_+aQ`>vs748i zhgw(Hwfc0@TAoI!Xp>mi;o1lZ~R}rpPRGM>_NrHkG@L`XYKg5M(eDhQJO}V zgwEf`oy$)?{_sNhe8Hhk^@pp|fcV`4 z$x!JqUUtP=J#_^7& ziHWtSvY&(Ufbx_JF77o-NMX%o$d{c==89 zhhX386>EGHTMkM1#+w}}v?-C8c(TDO;+ajI?%U|KPpqZ?H>k)tS=``QbA{uhVg7Yp z*T6j%a}OkZh-o*w_Tj;#>K!%LruIljA7wl2e))QM!pTWjpKOxSSCsg_)GLUST{to) zfwQ`%=q_u|BoQ4I?ck7W;ej7aPdS8pH>R9&R@H4?F}wQteZL3aHvL{vyCR)MF0Mw$ zT|o4`5$F6Wzen}EYhN+Ezr6L}_C8ewcX@ujf86y|Pt0Dag-#G>?7p9qdh&LqK$Gk? z8PD3Ts-U7y?K0f zYxm8R5Y?XsOHw0^_uIU<&XOVX%iKVIdQa{%Nd*N~!_f>28F9#-^Z|-kfnqBc}k$0r=|I$~? z-b?d8D0M6IPTW+Yb$Igss?Ke%^VFn*j)&J(NId4V)nH3Ixnq9S-D7nQKGBzYbf#tm z{Ok~s+jH&6|JV{!?fAOB1FdI1L>ZNO{<3Laf533kF1ZbBYbRVU;mD}9=C_w?&3$#q zr2O;V=Ke<4-aS^IxuoKwJk;J#=5lVi=#lxcb;$yiew)uqx%E55jEgjO|9#+KX7S{= z!4|e~E~m+dOD_oo$p!pue068fX%Y2DJg1jzx%2&*?U{eC=SytzZt^WAZvNbNcdY(Tt?!DDC`SMu5^N45K zBdJKIWBCiZycQR>_<1VHzgZH2A9g$Sqyw7s{hph6&XQuzxtlfEj%HG?@u9n`N zQM6LzWl2@Q5wGmnbJcoJuc``lIyPv|KYx6_Zj=7nQpp*PJQ8gGrZB|6ytDLvkk_Z5 zHI`Q4Le83j(uWOHf+s$F(9AD)<=>idCx({F{Ia=#K7bLP+M z`2SYscM6!@WlKf8r|W?>bwAs3+3)e3;&X}9W6Kh+$CiVRTLT?9kZL%i@u^aaz?r$$ z+jTw#P3$cGA@fvWs>`D9{caE?gz%VhtGvD@7r#7yes0l z@oR1t#`ZnnC&6!&|Z9lAz!B_GWl7PV$R z*1q^vk$>M8j^5L|ElQpz7x=PzMz;sgnr+Ycf3kyu;E$A(7f=7?epYnYKFu(%d!Y;G z$x~O??)ekN{$m#J@zfbxE(RbbyNG*vv#YansyXkJEkG?Xdfq=o5%vMjb~Sw zEY@B&reHiEM>Nge6aHQ^$WKJkCw-{eLC~{tU^Lav$xvX8+l2tI`efNd*1Wb&@$5V z^8BNal9D@XVzO~b=`WMDXE&vkHojecmb6QUU#6&Gz#D zjnvkizGA)-#yQx_Hfe!E-#u{`)>u@x&gKa%$?x}mSK~SCDE--K zVZ*hJLeFk&OkTNS#e-e1*G2318gnr5S-nu$wQJXkRjYn&|En8l=DkQ|sm(t5KM&YJ z+p1)WPAJ|fy&n5?R^?2eWipA@|NnfB+?FHhD6rxAyy|I;s|1>k9drBlY5M*Rcgt=c zt@T$cn9^J%Vt%(o7_?pBWyvh3g$EY4%W-|_-nZxHv)OyT-O2{ds;^$Ri>u?bu}t-w zjqe#Mm{+bbPCJwE?99xNu&| zP*~c$t!-((?!z6z^=B5g%bfYXuUuhjW`Dr()+Ms;yz`v8g5SJ4#y9J_S#qNS&yVBE z{2N~$lYUs^Q)=+|>5YRT;j$M>E}grqE&t%y{`)R}m#{^BuAEoDwt1gvWI)q;A6eJZ z*jdk}@mW=E(#h)$U7;zGuC99E(3Q^2S6RkizKKO_Fms=9b;8w+*XsN}ufM+gz{|AN zyfwQ%O>*5n@3bp>yobcIf{@hzb23<;PPk{?@U4C0j`?je{d>Qf|10<|FR{1M_UD1; zAD>^pa9y-P`9@;5U`Y7#jO@2dH*23?#Ap9*vGRh1$F`nZ4?ij7eD&(mmv5|V^3Gnq zB`CVSv9;-G>-Fl&gKv|6bIuC;KVK&^>YzT~A70ZW3(lD?m-k22=zOmJc*Ud9VWO$6 z&9`guJO6%+mNc{TJ#;90{h9^KjoVG9eVp88kW?YMcJ17hV!OAwteYx*r*xNVF6{g- zx!YB9Pks~hh67%V*n`trgPV{HY+1zvg?}MZRj+f)@blR?i zx}oPy4>bR4cTN6q^3&#*%O^@sS1Zz8ubZ`WdqB{v9`){AvsGzdURW&=u8!Z@*|jQ_ zsYUhS&ca95ZKt^Svy)F{#>RGab+IJ7x2a6xTetki@`X*urq=G+xJ7vX>gM|~b#~=3 zM!jqkb;R8M&oDc#7WPm{{Nwk-buIf73?KI@%)A~FZlRLHbeWe(C!wCbP={bDOnh z9!T+x>2%%sG3~|?qZ@)ui&@N8o?xA2m#A6d`Xtxo%FVNz-aTLO-gt=+pVbwWRu|94 zsZ287cH)6AEmc@|Bzi2ooE|jw_$$-3F$Hh@EneI)o>_6jaig@ENweyE`zePqR$g!8 zn6Gp9PtCEHSNc3JN`Kk7$I?6foP$LCiCt4t9<^v4>tCtEwy?SNY9<&NdY4|;ZM%4B*3+r3ch9`fc>HGO^Ma?A(>F)PigG@l z>Kvsi^ZWj>#r)hq83k=5#f{P)sFgfu5Iwl1x>psuEKjkzphvJW;`gM-M!NEIc{IvW1=J1u3!JJJAds{Df zJL#|A_e(1_HrD3fkH1UeQszIJ<|(D$wO z>+1N_cXxJzR{s3owx3zKJL+}OzNB1VUC>e@o!oJJ-(iX}dR1ZrzSYTxx!E zJk%yXypi0myShaxdB^{MzjuB-COy-tG)vOqS<%iS&gN~~%s_iG_WgaE&pah_#nR$6 zaeHT7_OtGNyX|&fz{O9N#n0AEce2>v;;P9MxoE?*zTfxr<}F^adflTr#pj-7$N!hw zzyH^F6LWL%(_fDMoVxwYyt9-2ZI7;0pMU6Cu-QS8xqF%43#>I=7qaK$uWZBK>*pV< z#?1SFox5Xx&6l?uWj<)#Q|Hua%Cm}C9A0>D>-0?zw@iE@TTzn9Z6ccOuXRwk`}%^$ zUa6Q%n*DRtQaO4ZJsO{D$@o92n&4rvqt7|CwCUpGte5Z3ZT|6AZ`Lj6Z4&X0S}#AI zIi>e(|J{>+Ok;Cqu6eXkwEx4@!g%#XOz!J%pFe2wn|~Kmqz+f7nv%c%+BIp<&Q3Q< z>sDl0bbyKo*q$=h*6uztPC^ZE}9 zW7bby!m=q)eCkZh zM}-ZEIx$ZyntV!|F0jrO2(i?2Zo78zuK1>9JG))aR+il<;aC^6XXl<)@vzblhgR_| z3tj){;dc2)s~>-7(JJ_0_hCkD;_L0_RS#(EE($tU_-TSo<*ywt<*#otx_^$1S2^ST zsf|UUjc>QFaOCtB$Y?VOX%Lk#aVeaueLdJi@#4fIEKS$NwqLsTcJte3$^n|50<0Vh z1&?IqgkII0!Yt-1@Z$5bGI1-GJpWyIY%uCHe`Z}zzv&K|6nR0^NEH&-U66q;U` z`ut_E-|`R7qI)(pZP}u7Nl&fCDPl>7!s9pgik=D_YY(chzTIgPyU)L!mm|l6tyBI< z@G~@bb%%StW#^dS7oWUmVt_^4oh;6qKVjA#|ouyYq(Z;S#A+?nzF6uiURXN zS^NDBhl^)jJTA}Msbrh8puDh_N!3+b*MFzLB)yLnGX(rKm6UiY*Zu!3pV?>iGw82C zRquIi?V_5>Zbc8)y8iPYZkh026;05wx}u@Y$=v*0LrX}rX8(axp}8VlvlPFITC8h+ zeoWf@KEKD3#0uwG-!8cCV3LO-RWUl|T(qsUd4jT3~keC$PUyB%S&7LsLieWRzqwZY0s!}Is8v{&udj!Iu{ z@?W>SUGeMJ4B14J1f>8zv+1roJhd))ZrUlc@|9PI(}lqO2HkpUx7CFT?UrBUa6kII zY|oBducME2t(>g%=1;w|)BiNvR4$Eua&|Qq|9|iQe|q)$eW$*>yu5Pt+SlvnhKJjC z9J9>2qT$vn#Tu|oM~sVAMs&Kn#?!S^>%0PYzFxPxuk!P=!e=wn7b%|w-Qrw)-qt-i zSeciXH>T`ns!q&~3ElepX51~mU%U6M?%&+CssI0ee-2u7jF z%H&Cm-SPbT-_Z=`?0)CioY#&Q{+a*U@n89kT_Rb5J)2m0%UI^;= zytP~Bi?92#AD5frqxB8&wyU&X>#C~=<^-gN4 zu~X<_3ejqOyfdZu;766vtzAB;ywW}^oID#tnsir7op^4te*e{@r{C88d35UY&W}wK zeZFmTnW$miv42B<+I;VZ>+83rb;?hOkj?zoTzn&8_CtxxidSF7+V~1ruKwn+OlFbB zyail!M^0Uh)yd`jz}6(*R(178pB7)|D2!#S_DBkZ08)hH#HIb*&X1P8vzMq2k`I8lFr_0)IJA zdIX3m=KOz@?kMRIbzz@ktAjh2P}gn!zqafR+*ib0S9haM)GuPYd@gxthc801+Zaq041=R;g`9$hU9;!IJC?D5zB_uKv9(mUxCy?6L1sj2FBsWo%rM2PqyB%}ePC^K5vpie3p{YG8FF%6ElnpNNH@;q?fQY3pAoJeM|;iFb~z zmAcQb@q**{#ENy@6DAmZ46~mcwB)jA&000j&#&TcO?z(f_>l3Ax6{iXMe(m?jfh+# zy8iU09}US(iyS%>pB$?+-?;3;sU5!(x0IA@s>p5BHCwxMmy)AE+m-8~4JIC}txg>R zg4d3P)UIT?cF3DMnqh`fW`vGHhQ>70i7wYBoKy*5;@Zh{O5#}Gnv@q4qO4{Wt%<#K zO!fNw^Y8t4&NTU|;#Cymy0@`EiS0v7yI$0f!^+n;9Ev|3_Eq`CtCN%7e!iJ;$v{Zc zRX}XTDz8UsB5FLGrG@e#ENdJUkBBxcTNcNZdo$&<)~-#A*Fr^{dJ9zMJy#I@lKNRi zm~ZBiLtj~GMy|xtxDgHFnDB-!|e2zbf7obAIqj6A&qBw43_; zmiv13_|=|am1|yRu)A+~>c*=wna_)}YFF`|T{~ur-8b0hwejHumWieTmIO8yJsD>Y4N`Ae?zYF&GnlvqxO7BkBYz~ z0iy)(eQrh)EaGwxlXQglY`AEguzADZoaT*ZckO$>?t4$~Nr@btNh~w88J!p>2uLgm zoFnObPQCrz<;?a~RrOci**!ngO-{Q+o{`^`$t_0{FHd55mVM{r zM}MW~*%~VILO7Bqa4>03kh(C<;Qhmy-*z%NJ#?LB)0Cv=zfW|bs`r(hDw2EoTQ|JB zvxKcv^{iIrB`cxI?H@8;O$l+boAP9>tM9d+C*=Qf=I?)8X27QXRLJJrLpYIbq7%)h%|{k@-^@}VXJ&F;VyCvP8_#I*2Hs^{o zJP@EIvhvJX$5oz-XE<2)%{LI6t1`jGBrPq_EAZXh#a6acPj2vj6gJl>ieYZjC6+1f zGul_&TM#+h-8{RbUx(S6+fCq!^Rx7H4_~K+BA?Fe`>}sU#^+PFX2%|7niAmU>F?kF zdEMy{199~V&q*KN=GRLn^IVT9=3VJ`cYevk{%f;l&Xg?LDbw1dePQb9RK5Lwia_@t zfsPw&5%_cP{eQ;yHP5ZByDqxTR^3sMV^y`0~ zHau3Mqd0HvNm++QbKl2V&#QiU^v~)2|G5AEt^aqw=JmJR7sHZzRsDDuKc2kj_1*d- z^*?)GSDcQ%=cKuQ0@t^<)`yP#(D=dV#Chq6=C^yL-|y~uTVBsT)Aq1z{qf63I=@~$ z_bY`l=K0E#Jn?^?O^+z8(_bjR;rGMjHL{!$mQ&m-+wSS{t2#eRn=NA-mwG+qa_O!% zXEwGjm$ft8zlX0hHSw?rnVnX;v1v+Egfx@tN1IN4R_V6g6YREpVq2;6)Mm=HX_2NE ze5(weUaYl$`1AETx0NBxqC})dRSUTB|iTswuMJJtd-~M)D2=~aw`L7md^e5^OwfoSh>O^kKpbvENbFG zdOyEBSFKf*kLP-1p~|DW+I(7s*_st{a~~aN-*RIJxrQSLyha zCrx!(Vr6o3(sLs>*0?e%>v%2_IHjJstf%j+vHA0^d3W#bTr*k6vaDj>m54)4j~>1~ z{&AO6+HB51u0zu+<~e8{{!kz&9I=K;QP*+Crn=ghqNjId$mM<5+kF3VW%hct_0<|H zE}c*8*?;Hb8vhS5f7M&xoIi5LVt1K6qla1U%|i+K_PWo0JY0M~{pT;E&Rz>MtMi}3 zL^+GQX3n%)EX=#hoALR&_YYUi(|dG9Q`J*d;Ls-CfS^S-p0k#ef@% z4RV)@Kc5Mcej_oveOh9PNm@zHCBZ_*qDiT$M*}R|-v#=_+IgBc+vti--YVe!;l<-K zvQ}qq{hT52p;ckSf?EOnE#B{@Oz*VOsc8{nN>%Ke!ff%G6${+@{?1I7WgcJU?bFh(=Y?@J zJ1O)Y6rZ_z!A1?;4=qOypZ2>kH#jO^kwrt>;Oi8ob zA8P0GzBb>uslH=IrQD6b%Gc%_yUbCOv9LNlYoX24brV*4^(sHsJ=K_Ww1EHaPno5Q z{1+(XnMg`#q)L02&r$K*D7EYNr!QYbHChy%JSH76FueQVM@sKvW8V;|jp-$K4i?mK z3bhqa>aDe1QPtwSilhUv9H}XVD znjb8dEec+}P=I5lLz-u^**hym4sO;77eX~IWNbO$v@qb%5yQ31nhyz99r+x}&K=$q zHs@pP7Dp|9FV{nE&0(_|Hol8UPxjP#R<7H(t=IAPlHV>83pbvtf4?@rR{MCr{PSI} z*FBzB{m#C+YyenP*c-ic{L*Hxlc06GE_fY;{qxhZ&tW!>>&ij4m`KR#uui-s?eVdYw za@E{_-le_n!QS_^`uR1FrGFk#w{zSY#rojG!^19tS3KV>(s&d+|CdPopGV?9AF$h> z5DkyH_>yPa(d4{+Khw75-#@oH?yJ_lpXbVVeKx&T$Zec=ubJQO#NY4t&%ciUUlsT3 z()3Mre}DDyKj`e5e{6=TfUjcgrXL>;^OxKGKKbtYX4RUd9zH#j;+{E9bJjXoegCiC zy1n0`{yqQyqu!$ANrrol_QkgRy5G?`_xH^$-~ammlb`2r9{YA&&XJXI?Hjp>><_m6 z7dt(_$=jSdwpIIXY54LP{L@xgZePFolWC?i8IS%dXWTbT0O?uYb9?rsh{Sm!-Fo zR$WReinIQ)n@#BSx>{4csNf~#zT!p#3l2C3=!l|^OOshUwk%svv?b%y`S`yYI~Dt#_Md+e(yFp?P2|;H(Kffuo_jAnI@NMb?K_BVrNejZCN+>P>NJ}#@E^5Z91>@ z19jLqShwzQ-6?Znv)S>*?efo7m4-hKbU7vC{oQ@}@46jMiz7??W0TZ3N+>1$d%MkF zxP-fk?X%C>v&NymJFC3y3$Gl|Z@cm=+NaOo(0+aZhwZN_?grH?H4`b$Ag*8SpV!3N zc8CSc%r}_5#OJKp&G74yYcDr#v)Q));Hy-{)zhqfyPWJCq)$wD`gHp9n;AC_PR)*g z@vS%gapv*ORtJm!Dhp&JrTuug`1^99A;bMlPF zg-m;y?WE1hEMK>5v|>M&)N!}jUp2KvFZD|Q%n8*$E8Z3Fc`o{X;dHwv=c{J-7@xdV z`+K{=S&n#3E+-)=^^ElsDm*?pDVgZ)eBH9S?!vXS4_=i`$HUmRI;8!M-}u4KA+2b8 z%3KRoRSAx@C$2QAdU5Y^br3#jJAe1gujYTkKbUCT{P@jkvF@s%EARi>J$3WZ5YaO6 z$etLcu+>TNglDJ!gH2oczTZk(;-D^;>ubhqwbbRZBzwj3IoV_Ukm@iAv8CLqgHC` z3=Ka{W_|&a$0C|GHSrtMe9aH9_R^WXvan*)vBsNIys{R)TyWxX=-D4vRDSP`4CAYr zXutp2`n#nMX0q|b+>p58*Lr37y;IKg`-rnU(`3R^A+_GQQ=1wTqa*Pk#O7=f3mL?Y{5q z+gUlg{hAnC=93L+a>dLogXY?e#zqi-N-@o|z-14$@fs@phSf!?=EnD1D`QQNK zy>HvL7d|+^Xmj4#%X4GIl8YG(0W)VmUbTANqg&bQV~hSdxO;BNHNN;v!0y|PWFJ4j zPm9F&W^}s8N#FaK(*gNK6<3pwslR$Nt7n6;=I#C~ z4?X5?OI&wGJFNWqOa7u3tK)XxHqGPq-?3}?vlY5*e=~zv4B4NRZ>+w)SR&W5{`FCw zuRNDi+UCFcE0=9nGI54jb${5-3h$e9@7K84hzo8FI(PHJ*~)z?93t~3Dd?PjJjJBc znp0J^F5$zJBmBiYeBu+F3KAz>%E>sUHru9d2j9xX?-M)jwny=8f6e`YMVa;Jtb2J9 zcaG+L+tA8=g1Kwkf#7!{{#PGmCtP%KxngOwbN*d-IrV@^XS26mxPRIGh|TTqHS>F; ze_b?t`eUNj^fm7nt)8&hEd23>im4h~dHBR{?%3I2IL*Y=CD3d2LJ0+bfr^a8m9yEJ zpW5t<@!*%MZMK`eF+_?}I9PYyj1B|SvkyCG92S-ur%2($S*0zw!AA1~JFJm;agYzUKXGnVnBLy-p<; zWHcNW7S4%|cY9hRq&rh4|3cQ%5NX4&VP1+;JXAl}c1~&9H&5p9;nYhejENJ261T7} zzOgsI%l+F~>#s-jj&|$4S-xH0eW!Xt_VnXBXN!1pKdSOtD|9hunT_4ulr5K@+8e4^4uTx5{m;$zs!#aU%d&P;%nwh#;!h&U;(y;gG3QbZa8p=&bo&J1X^R>b|NeF` z+4|w5&jQ!1Ba8lv6keZOzB%b9$NJi*^^0fc)ouFhnD_VGS{sXh$*2BWe%h(zxb)D{ z=X&a%x=z1BRvB*Hndy?G!Px4saFb_6*}8)T^%JK$?=2BMea83vq-A2NB8RGE?97fo zJnSo!9J$x#__1EwCtO|YHl43zc3!i+Z+c|5ip#`hVVyTjFD7i6S#*4F`KNi=t3-_F z9Wd5E$vna1Wog|x@zW7=g^qJ(-db|uDr;SbhtQ=EeU-8aw*7LKPM_&-Z3#(kb*i#+ z(qOkVlged1#`PzOQ~#=owC|CesWEzwA8#Icnf71Vdh~4f3BLk?FR8>{=C;q{Cof3?tR5^>xj*1y!jP}rLD3SUyDka_GH;i{|A5m*sQPnx>|Gk z>AA^0{r#7(U*E2B@NyKWn7ou>^5fR^eaF6DkKdoN=X_Ykv&lz;`mG%s9xU7bpD#TA zuhYNZ_y6+q$y@VDsvi2x{pa`F?K@p8On)@`uaf0uO1yAjul)D4l$fxa(L>ey>rV8Z;drA4!8=LZGRM{pzpJ$jRt-19|QZTpf;fPRUGsBY; z4{z4duW$SwSIk$JCSRbIz4~!tcHO5J{5#&BTYu3>xMRIX31e50m zZ7}@dlpyTu@84Mz-dSwMdgYmNU+=k(HzJrXt?7=uEVIJg(qZz-i}D*6?dY-J`|MCo zjs4^+KW?6Q6glsKV~3LJLI?fxcYkT``EgWVO+;~0!|HQC^{*@zE5G;seMRNrO`?BI zxP2!rIV8OMdBvNI%b}9DbkmYwJ`i29dPBhq&y^8RFXb}x@RSK|4_cd%Ldf!Akl z-jU^Vx8QqUWL#08eVsx;WBZnAP3jtA%xr8j>1nH<8&>b}{G8C-!DaAcGygrNjfpwm z9ou>ixIdV?Vf%!{u$TGfOK#m)Wz_Hx-p$gp(%z*8`i0nJ8JWuwa(mv_>Dm34VK1!Vn%A)4z*O-+YSZ^WsC@GB zkaOYDZH!B}eqJfJ>zXgIE$42>brF@`$})M$#|sym-deWNIVfSul9$?1^A@mk`S3EmS64fZ-DCUgGhunl6jpVMpJz^g5G&1B31VHqBq9*eZ7O;H%69?JrqETf zbIQ)IW<8&;EvWUOsO7GuM&tyhxhfj=?hETVLdxb8@&63kK0A2J!Od(n@>Bc^cXWSi zUR~;yn6YCqlZ*%FwIHduYn8s=Pk6W;5RXW*Why3+B4tsYm>Nu^pyC?VdHbYxm-|}*E zP$Ba3#&J8hNh({Sbj#k{xcJhD>CfH!e`V+YJCj~hSfT!Z4{SYgXFnx%K}3 z{GcJg{My&ik=t@4r+T$Y=kJ+#eeb){h-A-8OO!i|jEo*7Oz~Q{HLa>@*3;9|t-0Hr zCf5IZUhl@y`2P3YzPayz&t-Z4|Bu*z ze0lz#bo{?d(=)dTMV(cv(})!}m~f# zuhU)~-v8m&^?j{D7f$ob@1LGu^FB;Y_BTIUmG_sar)B2LJ-t+X_xB-%gtTP`U;L19 zb6%p`Y1Z>abmO5#tp~kM|1!1Jh)=k*?zpTH0bx z7M!cxn{)4$^J2N+_3Br$IfJjx*g5Ojhl(?E@Bh_%zjs@!(%B2f=~Zuo^LGCgb94Ju z`Sx_(^wgtQYtoAzceK-%v<_8ni>&8|%OCRjE7Yrv~-lCx(#*z~#mL^YFF-ulp2@M{>v*)EI*eRaT`n7HH$y6VM!x) zKfk&3br@*&^>dT>o(2OR&q*xjKU;BL0S)tO$N%)Q`~UO&Q^s6FjQfR&rRGlN z3G*K9`@Qe{F4Og|{>)xzt2>_~bBc;5*S-g?;s2%ds~&QH^yRm+j4OD@eKE1S{@=CZ zni8Jj{{>w2k9f26zmZBm@ABxIt>sIu+mVIUIYoNbf({3s_?)@+b?=w2q8*cFJPtPf zCb!DSa;naZx^UC`l|L->_hmFFu=h?Awmu~;dUPGrHI8eMjaw$Y3TZy}PAxP|^V04O zfrU3_U3U7zGAVxVr=u}7Cy(+}NMGQXxBG38%f6#$xBpePJ?&I8bFqxr%xqK3ijp>V z{w-G1OwVbt3(U-GJoAOY=g6s(VzaM(4c1`$aVj~fXkPobGlAKX?xzIOySe1 zKX?>B?EErk^^EjB|NDRaOLRYLmh%QpQT(~+!G(jKeg0c#tj%7fd)Ox_BKnHS^Q1{x zUU3{X$ukWNf^#oz-sBRX(G(;zKhv-zlHXwR)1x^H)Dh1zC*Q^y^b8s{RiDI zhn@?3qrITzwnFZ$JEz+M0&|Z(DPp{~L*;x%dRX_wGoi11&Y9e(+%xfP@4BUaab+Hx z{g`iVNZfJeLcvS}^_Oq87v#EJ@eVzdN3)_2jXPt}jcKo?+mHOt_Nt?|%H*n25t8#klk;|b^YA*$dmCOnXkrO`dK7ESB z`HJEx+=0i0I9j`OPKD3)-L4-Kex$N9b-lSBbB?R#MBlr$Q6l!d-<`KD44>AQ(4Z}+ z)1x0C#NX({TP;_0#<9$Lz2)DHH8lp28xL_6E%KNexn#qauc8z8DG6%6Hs`;fFC3)# zp+zB`g*97K+f(A#8L87LTTgCG4)xJhoYf(?Qq@Z*QQqhGkKS{p)Kn94SspZY4j&Kln7p=+0Sx_SOj} zEf%fK9D=fqvsCYQ3;zsuY7pQ~P-KkT?fr1&(hZu0hkkEPzi|3UgUdB3b0(&p2^Bg< z47&mvlVi5{d+aK<-EH$PNtx&HN+ecz5bE3{V%S`pO0V6WL}eY{vW4QXW|BhK-bo7 z(;}Rg&V8bK^FGrB14B7uL(_)=zFro3<-0j^|+Hdv>AnW|*v4MmV=lD)+4lFP3J!<2 zZB^~@m^owB<-4*08WlHs>UE8EEtE|%#7+exwft%j1!)(T>Y@gp|tqy zRK0`Oe=PA3Q4F73%)8y@!+M`kwTSIGl8sz9H@-HAlK7;`Uo@%2XxZ{7!5>&y8Ncp2 zaQx|(sOV>ENp8>6X5I~7sKt7BVxoq85J#~~)a37prGb<5J=~5zzqw^4`;t=?XV^ks zajgnVVlDap>_){!ue9{zl5b)wXBE!vHSSE0Zz@l^aXDSh^w|ZoMcF(0Z*K9@?aWk> z(k?tXcPmG#akE?ZR?bVoU-+NBc*%Wp$G(0y+l5Bgm)!H2xpIp{fA8!oA_CIide3dl z-}C4n?}8N)FTcJxTfHVKtVpiJsp+}$62(5#l^z);+UG+4X7=8Hcd64&P#e( zHrp&SyR9VhR*xh9x zx2~`4-T(LY{-aXi46ok4RpoJh_WXI^yhjHbnU`dq`trrZyopm50)+cAcB}QR{cQ(u$X= zvUWP$8x&L{_V1B@>MYRoMRy*@MYqWr>EVxUw%t9H$GA{sq1Ouc;*K-(?xO3MmA;DwflTVgx)xTrhjV7*%v_4T3KY_u?qv_kNv>xLue_gAsGB!4+|J{^` zy)M9UOgnJf{!?mc@eVl^@3skc#WE&3KG1CDYKeB%_0Tz0+@z~{uFH|>lCjAmOC7=7 z*vrP+4>b)cPZVW&MhC}Tz8cD~|8(v4$5XbhZvVh7=bJrqt?A88*A5FatrniL@yBc4 zLfy2gMd$AL_~>rc;5ORmm$yE%14K4(B|a&skO<5 z&VS{UZ7n~s_P;BdS7YbE@wz5$jcX;-OUIS&0WVG^>*j1oU9{}!hmDorE`x$CNB`=aDQn!t!&?xC7FeXey>qj%rL*=tG_MZ>X=E%J*h=i$4dE^8hdTu zvE;4h;imM>DqXI#Gj6HZ9Qv8Uxx`FIa=XKyI|8|Ct3P?>xTl9Ko0hh9BJYKSy~0yH z{YB@BnM7HIYM%e@`FBS0=j1IdOJ5z8ncH3Y?)eX0RU)d}j$25dU$f)ove_ACv-f;is&D(UJXiG8ak=WA z(%07%m#R!Z{qgnwf3Iu)JeGg{z3%<@3oo56Zn&89LB0Nydd;ig`Hw!G)_=Zv{$HIS zuXp=?zw4{Cwy3vWsj^UfQSez%!`t2NlOX7lIJ=)G{Ws;LNIG#nd-m+byLZPv+h|SY z^0)cO^1kl-Zb>=0XP`}lKhM|Kxi49EcW>3MJx9`uU9JUY<^MaS`{(xA_=L1|vvT`b z>mG#E`imcnsPX@J_x-)Y+V!uW+JF5h{LrjZQ!H0$QpUW6rgvXlFuI;)5q|B)&si%E zytdIlCEQo9tMsc)Wa&RSvuuOT)Vy^^UxYL(7q9gGaVx-G^T)--$L}=WwqkEgsI*L3 zVeY?k&f+UilZ`LhX!ANPi#Tr(KHrfy>dne^#~&Tnp3N`<mPv%~_kKJn-(Hc}*uU zWO04z#I~N5D!f{~Eeo_&cvyvc^^H&UnQ)v}sAUY>@OF;fImb&GN6wtxA~8Rws6wyx zghH{LT9L#md3!6bX*Wi@kjasZLva4p-Ddvpq z8LLfK9?^VS<+OQW=PWkS>=uz9M;jI|E|%#GUR1@kGPOcu$?69euZjlfXjHMqG#;0D z*bpYM#&f0V>h#OI<~xHL%)*b3tp9!J-|^5DDFOvKX|vqokCZ4Y$+t~8ZD}E9XgJTn zaO#fEW9K;zOl+O>$Wq&TP4v}nF~OjyDJ9&~{CFHsCO`fa7pD9E(TR^-##3jUoc4Q> zQ2Jck`vJ5zkc{7d}5zQfOeu ze$nFNSHHHKrSHY^#r!Qx=hd7DUUOBQd%cdsjoyMiOH?17eLLqFPv3R92Ej{_{3-u0 ziR~%af9Bt`EgPq(NSyJUFm=A(nu6zA=L_nUcvaSl>2;rFN%HGoXYo);BFe=i*G0F_ z<8jNzpKL$u%nI(Ty%lq)uWeamr^T$xI ze>kZJM#(sFl&reBHCz1o+-kiCHec?2nzsGJtm}K)w(tF#+tb_saq9Y-R`Y!ydquik z!Oh!){B;8Nzkjry@3z@dZ@RMY<-UbgGRNnhw<`G|@V@%~?;E>HwYT4^(hd|+oVp}x zE%?}y+qv66g3R3ibN2p+{Qp1jS02@lJ7|6HV_#oY+U?u#a+1DZ+4%Qh`;XuJ|CxXD z$sGD_JITb=^TQ#ATDB9y{+>2ZKQ{laJCL1M@iTMTJmKd;n^~UCm^H)0-NnV{iqb1% zLtmZ#_cIgDuX+4-uJN4oiVbgkPBFiHapcn4Vk6^i+ql}?xpboAo(YLe-Kpm8w)&0j zy^;c7Rk1&7dswqA?Jht1;gj9?_?lcx!|ON$9;d*3)54Y0V{TpDqBA%Dty0LbNBcK> zTMCCO2rOw#Tw~QRU3NeK%ac50W%?ebEvX`I4jAK((`wN4=- zOvBJ3;#tuC1360%UR-Sa#xm^u1nZlYS_)f3UTIFPI(2d8iP+|E^N(yOI*|T(mC)U# za#DfZ-RGo4)tv(TC0;D5ekrua$2G=s_j--YNi$l0M$O$aD?sPjjlJ(JE*F>jWW9X# zN#c!m5QlBisl(IfiYed93d+{_&LWa}qJcH2F*7Pn?b*y3xfe5BSIlu=-x#Ucq0-}j zwCA+MpJlt}7i}x|Zmwj-AbpSNxH4LkeeHMXgT zZwdXBnZm^wsO-ksDB7nZUD1>)ed=6(jAxDJ3FVE)E*WU9+}Prk$kWq*{YK@Ab2YJ> z^L3m$oMX1=DcN4twYr=h%P?&;PF2`?jy+1-U5UMODz{w7DXuI2%x@=m@xI=6Vb;CIbl#vzGrdl? zTCSgahtv18)Rxjo_w)*5EvD5-ou3p6>D_q>A6Pw87QFm3q2zQyPJQo+vX$w4R{!}k$0j>@#e zMRwlTJek~YdyG5&$DwooosY@0-~0D%d-3(y@{gc(tl|5AUG=sL=WyJ7v!qF9=3d81 zDzfkGlX?1WK5@LS|NndEi$&d5U5l z?|-8I?~(qG&-VX6`?YVZT@$~pVpUVp?{$5CJ)i&A{gD6pk(qyD#`D=TmhDRRZuGl* zM`07|JC=n8*}BJW@f6MfbfMWku_$ZW!Nz;%Ds|@m^qa%3%GIoPG~uJM@Gnl`#6?qX zzLa_zG|ymtf>Gm@P09JavhC6WDON03rv&w%uUx%LQs&&`C4xKm1kawdqjcAL{ROL6 zPY*rK)#H0*#ysztE3%KLpJq9HtG|lTaqYBiXL}C{-`QTPg$EWJCupaZYyf^FMHX*IarEKlLUcT2W%E+14d1A++{|m)9 z4xYN#u=r}ryS$^*rmBYNyjJQoou}_PSw#PXXQ9ll+`G+d;)2s^lIH!Ltn0+Nd1k=; zk`A9OXS)8~yw%&V*j+j2w84hLjt~zO%RATZCNEUYj1?+Z3R$vuLFu;@Tc3;1 z@E3~ODq(y%sWM)^HR;5`KlkeAHofMOGv2$s}H_3>&1^Ei>mmd6%?yOP_py3G6hx=Me!|1UZ3)u(Z&?EP}_?(O5X?cYDnF|AeMa9gewv!m3q z^@8o5l^0aZjz*lkc-U0VKCE$C;`@J6Q^U@v&aP7M6m(j6YlF!{q44wNQ%~K<>e(ux zEt{kN`qxoUpK#6NZM}Qf#9TalZ?CaU(T;QXR*D&K?p3$`Xe_Is@gma9>G4L}308W> zI!*byULV#pSr{HUcJj&m6*Fe;eY2%7si-_DV&{dQn;ev4no?Q5d@0edddT^>;*&p1 zq9!k|(KAmcpY&UsA8dI4_KBb4BHfi{H#coH+4kcD>LoEx!Jb(=4at>#4u(={NT*Yrp5zx8q(?q`%#zeo6EXY#+)J#6WZ#l@~gsi~{)d_J$b;>$(% zpNGWv9r*CUVDaL`bL#*7oO_)^QA31liB)PsLPOZZ)^qkb zExZuODJvthWOsGqx@#-lv`#Mbo&Dm~tE8u=rs~A+lW9=k`0;?<{>T6GM=Qi!7Mbpz zcjKu1-sk-pZiZ~FqL*&I_3)f@gyUgLzCaq|r@5j>C##%&msloW>Xj8+WN&45?197k z$t55C_HH`eqocU7;z!TfFiW%hDTh5e*}wY~pF75wHtTYanWjo*TN-cvY!vn z)V#KiW9NfEiOauf%APtL@p@L#sepHUC!U|qxhpe4C2XP=#A_FH|_!mIg&&}IX90awl5Dwox%H?~%{o&4C59L)LqDogKYAsZVJMystH z`qJwS{2O^rx|FlrSkpXD`FM?T;;REP;yhnBrr$4Y3+K6XJ5;fE%jU$3Z5Bo+t_Zcr zJ-#exe0Ives_v`V)dsqg0|VAPe&zZ4S)aqD`_t3E?s|H}?ZPHbT^`*`kA{e-C59E8 zJ$+#n35yC=%WdZRoV!`E>c>*Q4-S)-cW*s??a)12AD@t&1(!Lt z|NkIxx!8Bzjtt#>9v_!3)R1M^uw~!ug^f1l?`O8WoN@BvjQl>o3-%9;1Nbzb+*Nw9 z{qbqxkz1jCe+}v2(bT8GlDUN@$hIaYn&F&io zCUMu=qzbwv&tjXstC1s{(|BL9ac|`2g+Bj1`Zl^hi!|ILJop1H+?d{`zvep`6-Jmn7_B;|@zaT=VOkqOq*VAFET?JTbo+!&d?En9xKXPl9 zXyS$`3>R`tJuh!j-mqzg{`IzSrjXU4EdnK_r5AHdL93(>^4EP}ez)hdpWeI(%wo*t(_4zWx|qKDt(^8zACdMls9GXG*}+>SV--;Ny5gJ ziiXo_>|CYDLTbG4AVG>IOGO{yWHg0ZtAtX}8q^HAQ{2`!q?{O)c!jis~ zE47MEUM_yq5@Gcz_ESslgU%cMOYhqzD(Z7h`Fz)APx%~PRp(h5eDCB_FTaX25NMM# z9SP5U zu)bPu>!u(3lHM+hV+)&RQM2UKIcHwAZ|5h*%t&MD7tv%s^T_DC=7O#1kFR|6p8G&k zMbqxJo7ski-|OV;49-8B`qw7kTmS#Y+F8H1%Ri}%{-w$39qGa4q_8Dz=f}w1S*pJ$ z6&~XY<6!p8ju(FFexzF<<5JWX0SVSX4NjYrtm5kqe0TWCw^(n@fsEee!Ba%8@Nx)# z_*1O+;MT#lPdXG)+>m+X%aSI&$AWH6iJ?hPyJXt=e2fjlmQIMuDV`Um zU=SI!w)bdM$CL%49yaj-dKzrMxW7#8J|}kY^M-|sB%`x73;r}{xc2|}y=wNGg?G#M z%`djPXJYxBk*)JYBf~+3iHlr7>6kC3GYer&1^tYt_(K5$-dV4=k?5}yEbosN_(xQvMITa-&B^PepI`!m9 zPbq2XKrh8sm)Tdk76xc6*s8|Cv}8)g+R8s4k84i#Dk&?Ady>9=${AhZ-PhY$?*0Gw z{j>4={|p5WujP9@7mjvVupo$&qgi0BNuW%iW;n;82^O85izayO+!V3N+T8s3+wwbp zTbr{4yMHCGHx!j}3GFuG)%DJ)ntkh|<*}EKC&z4EHhF#R|9gA5+hA(}M3PTxnCIrD zRqgUPCzx_~OHDy)ye)5OWSpJNp`RybR3`s8*nd3Y>eJv8)*jvuc7yA2<%kItXol~9IRGJ<3=)nYm(EjWGzUTE<#>X3U zMO7VJnYPe`)rP5P&AT_L|8Ex0u`zbd&o{nbQ`eDXaBSLYsY_d%{hsUHZt8t~`$Zmq z<-etgYU!ergE{Rh(q=UF@$i0?OYD zW1d7tTB3{Cf(dl&rX9Ffo#E&u#V$7=Q~!N~5z$I~U|_syKorRmpyDQ3fpm4zo$WO_I! zl)Z`*&+^rKom43nca81-A;;vFgVQERFsm&L3QMt_UHX@IO-5G2tEZ8_s;f6lkYKu! zWN>5MI;9;mp6EU{{Wwjnf=QZv{@1_Kk$0~iy(i9ZSdlmB+c_(<*r^7#foU}vedn&J zg`Lp(7SSp8^0BH}=f{QnCLZ9QsW0Z)ByoDundzr0);Z_!NS;^k6Wf%VDR=$ z*&^~_=acK}6*sU5PFiuxB7cd}Dj~Urmwl9VzVzt6^jvNCPbEpkJ5Z}NG`wxgJOwUc zq1ysGHe`MNwS|9z`Gm_Ct=3xK-P(F!d&gEs_0S@%g)*)k7JhH}BTqCen=C%V{7L2a zstQ%bYZ4!FwH!MhTTW=4I{SL~{!;Po8!>4Odp1oDNr`s*k^TaAx+*gq~yHW4xAf&Ft|H z`Fgpl)Twu>s>I3(b0<~wIVT4*Z+6%YkE_p(4oB!>Yb6sVUrz4KNKKR+@->dcivOYcsjUYERGA>aS7cVI- zEvA_xtjl;?vK4Uv%rS;_53G zjxO50bM{%?%6XQy{?+A&w%(rg^Wx^@n%6f2^KRd1QWnt)t60~1f%7b{+4cPQ&t6On z{5D^E@@AIj?M!Vh3`@8cIxQ1oU+Aa)vdaI`%|{om&04-wl|M+?Wfo&_)I%kOz#UPO zLN`?XmfH4hz1l*L9wkLJ?>;WB{+g}nxi4qNO!^unQ>c|THN@D5c`vicz8&p{n^k8; zy{^2zEKIKYo6YBgEZ6h16!lH}R1K!FPMxr;=fSh=T{nLp5_lYJXgo2oPA8#iNs;H$ z^D&{`%M!R}&63?^Wo%;lOdx2xhIRVw)mW8*s?bF!Eg6v5|&nnzHL2w z#hOpWkjZyaNJiG_4O@>bEG?Kf-EZ289R+D|g1*y((l@-y)0r5h_cT>1XMJu-M&{|@ z`;%O`To+xMGiQoeUvhZ#8)PL&4<7lLf-oo zch6GJI4Qvs8&;+2n$GjDKKJNo@Mn|lS1#PW=`c5W^Qw)V|6ljz)oT@eJn2x}SDPy?(Rr>2<%7 z*3X>B_n71OM~RGB=eg16k6mN>?RWm-?b(aXo(s9my1I64&7ZsSX|5-q$JamJe_71p zhTh9V-f9UsVF3;t+{z|S9$uSOZOr?ZUgB7}Mdi{qfz6X5Qa3)k{6Z;NR7#iot=1!p zgMn=>tTVP~H+=qG*KuT7hQjW3?Xvdu>d%Wm-2eAS|K`3_c1fvKGvAhE*XP%vb!i?E#b-Ly*eP5->G4b2tiQn?u6ZpBW1a!unQ=EQ&!r3a9 zk4|mp6jm=?pj$U>;c>ZSCvk(Iplv2o_jqS`_I%or_xx;xRlD+ZfxXvXgbUviIMK0f zmKfWvT{n!&S~h-Ey1TdZ&8>jrFF&iMwRNq@S+Vr?*-5&p6`o&tBoBU@Cbx(w#H-7| zXG5;u7WI&saf?Di=N}YkO|@A1u}wQ=libdnw2fZwQUx;HqS`WV1GE=@dJ%lYv+Y7x z0hi^o)+I_h&mJ{I=k4H*u2{d~Tn(?Nkmkn17kRIjEZ#YBx&Qg%s+?K-_NkTKZkv9* zdydqcMVpt;US{CDP-ar(i!Nikuw35n>)K!5K(7_7J&$k80A8p&LGZ< zHwE&Q4xGP{^2u)AdjVBWg;mQvl6qYC&Q5=FyWeoRv`35Uqnk$}=SRv;tT5ZXeXne{ z&4iAO9OTUQn zmM%PSsma6Zoapn64>eLJ9%f9uCbnB_vs0pubU61Cvl~{r;xf8tFI~FP!kPT%M5@so z_thOz6J5ETFBZ+1F?adygy8)24c>~+W1WM8<@*XH=Sv+wdpklUTyOimD?Y{U(w+s= z6hbWA60&=vRP4M{ZQ@?X>^=5+`jT&P(Xxh}`e&KBSdLBAaDVV_m(&rbrGKPPNP2Ng zeKINCwy1CZ{tfvn10yufs2<;GF>k(t>COb@6-S-UKV8alY4vA=V8f?DE!U?l{Q2tb zN}r9_t_n@Me%NVoVbr__mV6Ty_r_I4hhGSnN&D};TvBe%(#`7`z1?281bEBlrEFXk z;e9!U$0@O=`F&+i&)Ede`Lk+x7jkJlky&KX9~+vrIhS8ED0Jfi6(7Gdm%`%vqg7`{ zId~pV$>A4f&3IXqR5xwgFR@q7z6-PhPHb3J&M zA2YgVQuFWg{O1$h1TQ|xRKD)YP9k|k7HAzK^9-TI;T+YxmzOFzHEN0{N3P* z+MloY|H|$z&pSSyRqS;0w7$2Z!TnSCOrJ=;i1Iyma^o(&)M(sA*^8MPR^S8cK zl>V9iy|zhoF`s|^!}<$h>&|t1C5P5BTfZK{`69WA|d{jtkJ zL-DCbx7Ya!v@I}|3{+b@PbqA{+8KYAiLUv#^!LovdGCm0 zd`&Hf;z=&7u_xC!S0wKHt@vZna~?46Sl6p?dR=LF z@rN&pQF9{s=FM8ZeZN>^;<}i$lCnuwSC6;->z%QjfAUHR1FmqXuH$Ye&9(=GpJ+;T z7HG^b{&1u)=YDE!xqjcZOs=Q{#`bo8@87LWkr7v#J+rf+sBqf8dwDBbL^jE_f0I=S zk6*TR|NbcLg&%(Xc8HoIC!;o7|H0(lMosAqlP_#d6FuB~c*n{Y!krg(oG^*n;$rnf zJu>Tcw^N;X@Z2LyynnTx3DZ&B#w$3>E9u4U0?`|0F^wNixK0pTAu*}t9dEc{Z4pbW z+C>5DtAUb@8;>L@y!|@GZhg+2^?I8oC3swtQ1O!JvRbCZ``K$_)!nKSR~fE}Ry(LV z&bhb3b%t4~bmRM*5kL0i{=RKt@lEOPS-$i0buQn#*^+)!K-0}@@|N&fkr%fz8Jc!z zPW$kO$EU4_SF|w4wYXeaMQV#e-@_9#gP$1L{gst{P<7;~P^5p+j}w*aZry0O!Zsx> zt!|zQPsWQ3)|srQA9dEUf3QmWWmR1$`U%qms<^As?g=ZG`+nrkI+^!dR zF-GI=mN#3D6y@dhwY9M=@!4Euey>8g`rDhtySqX*ICD7q`ttt&bN;`N087T&o!{?O zTb91MvU<|-)IEVS!Yk{R3SG8Oe30|Ivp9I--)0_uzl}+u+>-u} z7)q}=KDlfi>wLYWDK&k8Ohb0E7N^q_&+HZ`r8)6))(WjNOEtZO4>rY4 z*o(bvq{%8x29dM&?>6%I;(FVO zd&jhuQd1_aJnos|m?GH|BC*oLqrn ztVlh6zP9H;Mo-HDBb9wBn-nIllx-Hu6bp?vNho%mJ*}$H`}oR>PK#Z#S`)S?n$0>P z;lwlX%8RC>9xD&EgiMjLS-1PEZ9=M}wa3G_lLt1u<=Hm*utsmH$-WH?o&J4SO;^8M zm!FoKE?enc@Z^WZS<}c8nW7h0IF;@{xVvNSWtS(*{=yR||6)`~1glO`7J^bue&F*V&-|G(~0mjAlvRW|=_ zJhu6EBl*wC`F}W*las~YMtgNWud4a`I{x{CgU#J$yr*|C{It6LG%(a*O_b6feet!C zPlC8#v+#S)dwp$x@3}UsS+8@x@lBmMhp#}VQ-o95_^?CkuYYA}E>1${8r2U%9ykAzOqjEjCr$L)-23R+yk3MXVx{!nmjey z@?0m){q%`|2gjJ4j^22pal`QDx2R{$l^?#VD}$%i5f1 z+}zyaIAz`0DM>M{HGg;RT_AcyaU+)|TdE(=^5@Pow~8>Ws5ji%Zj|B|8f~HAqzA z`FXLid5*d9h0q0wuNgjX)idNOanhU4JoQ#1o0{ihX{QU9uN>+6=ErgP%GKRb)AuY| zs=C#VgDFNa^ThRwmoCgYrF%>6NSl>;^X#*N5luzj)9%=s3se>FDX6h8p3Hdr*E-jv z_`sj78$6X&uD?;qTcIj2iN$fn)W0$8NYp|Wj&P;e?h{5L z%C1MJr_6dC`LnNl$xMqvRo2Dg^7=td$%k)UT@ll^iM3OA#w_jSWpB56ycJxP6+3;> zp6l&bru!{hCFNjrNELYMll(I&>+clTftN3Z>saH1*RtED= z^9bIs(JAZT?(+L?@v+j`vx{3k3+kB_uBrU^p>Ek_VH?8d%VIXL%PQ$V`s#*T|J;|+xWavJh$(0OiI^3uN5wa zw#H{K``e#A%x{0jncwzE?)JNF?|*~Zv=2c0s_Va{*S8t2ytyqk`pvDa-SPjw#y@}f z|8e4}r=J!nEzi9jvF+>rc@;X3mv^wTdNWM7*mmQ}j;W%)e{dQCT$RUyjxOc_pAEliabG#(@g)a zoStNLa@o>9eQ%S#G?{Eod3?Z&OH%&$*T8kYcW>2YoC?&__$F(AWSVX`bLEyM4ZY+e zP65A|>U}4+t!~}0p|yK;_RE6m$eXv0ziZ@Mp>dAy{G%IuOI<$Rxj6lResJ+&H?_?H zL53Q>ONB1nzUNjQtgO{@Ibr2n0d~X4>&MG&J4}TdJ$XE5Y^W>s56wE$6rtFo@VYAV zE1#H_N5ti;uC=kcJIoeqDQsUSAH_Z8^DO4${Tp&$=WR0C5HTfP%;gHJlSB(kvPfcx z<4Os|gBy)*q`X}DGBq^Y+&au8aHi)B>DkMdE@abv@Z*W+iK&_~+xuRwQRq?T5bh~h zv3~X9wM#8Sv!@EI+#s@NJ}o% z9d%btb0ROEyR|Q>?!yz!zIig~dh?#|{$1~|beq$=b#pf?>f3N}sm^7lpkB3OAKt9I zd`8uwcCXPBO!_;`85_A1lQpH(-+82If{T-_Cs|1lagEToo{S(dJOF-pKW@>h-HjYpuh zy+3B}|0yk3@qlsP*R}Z{KlazlG=#1W``DXb)4bTd|I-0xegiA3S+iz&pFC@R|4eN8 z{iEyuoLaAQlJ7+L-TOv$LNP|%dmG>S-q;#?cS1&v&2m1+Y2RbY&1+lZ%D$Ntz6hCk zv-0eRm=pYdZ;~&}Z=Jh$OWbb3ndcWJu{t^|e!fi7>U5eO&kWsZ3ny(@ym`8*u53jo z-c+YN+@6X&=@#x0qo^Z9u z?PazJ8&=o#O(=3z=9yl#IWB_RQ}g48oxgAGepxW<=B{O(%7;^*IUV&8`Sj_8VA~zd z8#~)(^=4~oDTt)>di$k0NbB5RxX4*R%KlQ$`xi@3o^%j+c;tZ#+xkfx7A=$%T(zYn z_{NoAkyYHKH?(qDCt0Pr*7EYsb6upmY}>T9=rZTI&rS;K8%j>OvGZG%kx9}@9tr7| z-c*xq+7q@pz2+(mIwa80amoGCnvC}AhkuvdKiU-|{daC<-`u%Ng;af}Xz!_br?B{* z$eUM+yVuU2q}$=t+bPPsQ)-fh%dWPS34I={Kc3Do{aF?DS0^a@0%wrw6_>WHy=OBL zJ(e81*w$loWw#xR;xw;<$t`*M?wjW)oApRu>uTGb-}+2PU-rI#X4$m2+T}@s%_5cp z?`9Xz{m*{v(@jTaPKoJVML!Oh@?VIJIQVSp-%jnlLd|xM$KBO;3dQ~RcGGIQ-5ScMVFhe)ksUJY1;h! z_@%=gNkYfdj$P|9ulQ2;L2O4|!%nHg_I2N_dwP67zkB^o(V4GVsl$7ZobQH+fE<%M zf4upPRe3*4Xk{pgoHAPZ=hLLOMd?{D|Hqe|zqEkoNa*3v)B_z;-b__)WpeTsdSd+M z*Nx)`wk51wvu)=m?_k{>t0K*;?f(_`+!RaIEN1n#o5g=L&ilzX$F*N$&rjTPGx18WPjuI&fFo+2-lkg*xNtgd zJd?BW#F0BXo{JnDWZW{6JGLGx$`#^#u69gPPS$(u01m8&BfPi=gQQu-7$^X{jMr(OZmkc z&p!X~R+f>Qmu4~N>BZ*rLOW8W>?^d-o#I=jdoV^K>~?8Vh{T5H2NFF*oV+`D_dO2^ z^t2M!>RsA+WQmhjrxM?(6$W0t=etuol3KP*xE0`O;@rY>=f7OU)dMp^pWUo=zp>?G z)}B?1cA12n7Bh8QcGEgph^NctsE4M&r3Ix8jV)+&bzIZGAV_&flhb zo^rbS%&V&V{yyUGd?h?9@21aE8iuk79i7MQE^sX2l&I0X?k%iSRa{nE zh$dX*CAM5&m2s+u%(xZ@UI$?2t`@O#gx|@d-K@Aiw&0#%KYE)+**eB zoKt_w+4_G1Meg#>VGU1jTRfd`R`=};1*ar~#3O(1=(xAFbFRu<_NZp&^!9cM&FLMj z40A8cDSWx^{K7*y$*v1b8~tW?nKo6f)#RLE+@+v?v-EfFh5OUf-e2N>A}YD(dh@YGQI1KTH!68c zN&`;aJQB31Me$Ob!9^9P#TPPiJxa9N7Ogs7ulip^D)rL-?yYK`CcA#gb#3{+LFCw! z3n4PTN85hRIs2~s9?xp_OP^vZ6H~(fJT+!JzVY(WV4)<>&g|P9Zy$8HMMa)Jzvr=X z$&I%r>9)UibM^GO&Y3swY4-X0`Ola03zSBE`SZtiM|7BhO0t)cnxE1unf@NJ4i=e2 z;Wp0ApHo`|r<_(aE3e8w-4OK$&;*hf_TFw9Th3dDXfz zrtjv>o32jV9Bys7)_s0@8pHcNpZ)BztUseXN>VeoRH)-6wxem*n$_x-T{yvN@4 z#UH=3-bgtaaN72^y+gUTwY1r{qQ~d_rf64u`%*d2x_HX-WBtzDTWTK3bupLvbZf+# zXEX=2ZHv+MTfv#urJ%Ce>fx0uA_^-*lvY@=w@(#V%xmm;V&ld@Kc2bn$JxTYA9*=6 zB%R=U`TK$IhrX*K#gl6u&wMX1CFkDm*LFHanV#xqYPlCy+~Rxbs`Mo)TZ3D?KkVJT z5_#=c)i?Go>VAFQbP`9!vkwOM@9&>4&$F**Wq-zxC%Z@iym$v^Co|dNjZr3wKn^%|pPx~2!Tnh5oeQWbd-VEn!-#0EjvM4L@L8OJ; zk;0j4Rz2_2eV>||Y&|=?Y*Xa|F-4Z+ete()d^~JpUe^<}-TnFTJjJ-{N7f{BEbdtI z*4c2`?qy<;xxWpa43Z_;v|XK&1H2|Hbo8k8iE3Rtl6Yw4L_t2jdCEcymiRU-OfmUv z>3P1o?7-H&XVSWBKHro#G=E-jyzlpfl)@6P6n)PFdXI%7=Kufm-2VUjS^;k1lj8e- zxaw%HefYok{*T`IhvtcM{qYE`?{Sgp-*e{DwdnIFg^veD6;`B75)NkM-8w1wIeTVK z=7Oa==l%NnI&;;^r(afHcFAbT4di2L5sdJV$$b3W=*FdE>#hm6^&Rg=t$GrUcbJssw3)O==J_iz6{y^_*p>c>O+i$6-l{lCoItgtrI-Mhdh z?0HtjL+k!PWz~#k6Slc(OAI_q9T)Q)YuKz0Aq-~US^ElzLhcs%3f%S_O!N8RmrCRI(( zJgnSrb7=4Pd%tJZmY@Dx@!v4{ur* zWixHs{y3h-BZpiSUcStK{$=N44#9^zyTtvbuQ+|^%pD%tyRuu%w+HM`w0*eqb5C!t zu)AVkapS<0ZOH@)#>2vs&zu!M`O{7-@X01gu2!2{(=@Ip zT{2?vHC^-P!`lzvrusa8R#9?4_>FDNr2ao=4u46xmbhV6sgLI^ji6X%j*08cmrQu6 zcG-+a@omU%hbC2>3z8xiZiXFR8LV!&Pet+Jn*hPbhfds4S-bb`6JxvFX!FHtX_A)q zU15gva)W1|O-yQ5)nQsJp(`pmcgDh#=O5kTJ8F@blh(FDX3}@#4Az@5(|qjwBh@9& zCx>x)weo1o?~pCbH5dM>*e`ec^k;Ve4;z2~7tZyw=Zk!D>D4;z2=#qaKTcDx*fqPnWR zwjT@WjG1~N_S5+dJB}V(P~uf|sb_}bIy=1?k?IalywV=GoK#UM%YC+~;Pc<_mnz@0 zAJ}?u(h3W=sH+|yL~9CNOMQeUo5jxF!gl%9%V%%)*L7FqvGF&Cnnqmj+R~G-am{_5 zdqV3ogxew{g_45|MS~`#U+_?w7!+dE)TywjX<5+gO~2FME&c!R_W|#dcU>hQ_Ry`6q#V?^VwIZuvUQAeF%@-LX^@zKd z`>x)0eg5^ja&hIc^z;=+42u&xa;+^QQgpU^ePi7wma?QbmF3c=8RneEeQ9Uff6aaU z@_+01iN7D5y^v-Y$MIu%?fs`a7a!kQc6{!h?Cb0sPCnWdDRX@Nq)_(O=5@c`gnmB# zKTSs%G`f81V;0N%+xP#O-QJeFc9F7%3)gp7-R>&(CjeZ|{%J z-&;EK!QRjhvx=u4IC#)d%sM>x(SwQNABxR>pZ7B|30k-=%-G1v!`WF^cCGG@@U_d9 zEu3haew^c(@)ARiwG-5qs`lkxoT4o-mB}D;eVxQ{kxe&C)-EH^D$^XtA?`0uaih`v|Ie>*Dwz(O%@{zR7Uz^g}v&a#HE9@R6JyuIVf zC5QhG{Oaf4s0T3yKmIHup&5Lg;qg&UsoByQtJf-Sf1UM;E3%Joeu~z zkC~r#zkK=P>4^`9OzMwj8VB#OiCnnM&nRlnf_DKXid$w%h+`1^FbH&MLg*xpPL75fdULS1TSVXR^U-bMTdxE?9s>O%) z%lr`Z-&4`?dR?`6{`)naOWg zF>dLY*ty71{pZ7zoFx$pg{D~8+xo@2+x~RpuMcIvYaZ(y9WTz?YbvrdDJ<()=#edJ zXBL?zmmQk3R5M+6&bl=s?$-CA-@mRsIsIJm^|kU3 zrfn^su#m5FcgDMl#s_;F1=<7@5`**Q`~Uw9&peqbSQxcUVfFLoEXC$kLgq_X+DVms z4V<}DTE!@InNN%3X_M&Xx)ZfmHux>i3u&62Fn$d;JXZF_rV4v`vGgmsgVawWX z^(opC(;_+!y?iAf*^s+&*ZSG(|NZ^HB*D`r@~ZljC$b~!E1Q${p>0X8Y7Uq4`zoX!sR>9cNo)FbPVLUMs;u9)GWR8l`>x)l zY4T*oRwcK|T#I)d%5gJLb4trOx`#Wk*MH@;rFG8oweR=LTGxNi@!vDw3$qi~g?+yB zA@JX~jrm0tFKo*1|8>mU^-3-#xL?(1g@K#Y#8XMqJ71VRVFIsNDK{y*H+-`_n2tx1|Wd-mg2@wkX{5B7>~{9&j!cY&@= zpfg|pKhwK&ENiD7`z3Sq5zq6s=Y@Y~Om0r^G@i7sQM6+1S(ChbPR`D{>Br6+3r_2J zvt^U|7RQ}oQD;+xlH7%?n=WkAhz=-Ho!XOff@RCQ81LKd_gtU7yBjh~$nW;%nztw4 zZ~FfuGH=JbyLT$DvTr!?c!I0Wmq{@$AEsUVrt5QLeO%Dwf9n;lb*(wEsW3s*S^4>j z!h@a6-+0bH{-L=1{QSdfzrK8(;jk`adF}TwsoM6(&WES;D!K?qv|TV_$xwwy!;JdBJnj3%Q0F$9^7PF86fl;p00Kzn{Ic<7F7v z7A03PMOCRl-F;gOt}fWy>oQ|Yl+M(5akDl~kx;yFLqbO*$lXT_p-Z*Tk z&HwSN`hL&JoBQ{w_kBF_hf__vSZ1EZ$zSv2^6qTuo_8*+sCRCM?A$F=^E|SDZShNe zxpLW_HLG-{<~C|OxE%S}@^V(N%xt+Q)#u+l{1YK4ociO<@&Ea^QswO|bz}_KG{rjZ zGF^K9Ytj6;#-r7n81B2j+cz!y{a*!r+fSyyYCXGkJG?Vpd_(VNIxY?lJ>MmuboP;g z*xu7(YfR2Mr7oXxHEzcgp0=RiZ#>41E`|Xt5iaYF*4%rjy#JGC#yZyHM^}E@+$vQ+ z&2Hbd2)&w+tBt3->-W9P&Drrk&ad{T_KQW!^qvQEDsx?mJkh@Qm~tV;vc(O_n2eP5@l)UU?rqEzU;S$L zhu6^`x0zlRjdc!JQ8ZjBboS79|Jfx)8(0J!;)Eg?6Zf4tJ^6XXt9Et?$vMt1c;^4y zdH&+m*j8^o?;Q;XKN*Ri+v?LSd{0{9pV739J?8AwazB>W|K9%RS^i(KzkmPMeA_&K z?+TgXz}R5Tce~%)&8v9CDOdBsQ71D{Z#w7UE$Uf2tN-h^x&BkutK;nzu-tVd&F=5J zx_{5-?Oz`0b?o{1jo)909JTX(`Czh)UHzo$vO8yXZJm2z`{dH?xs8t(v#|Ra7JcD) z-p1a!SmF`OL#ZCEq@2drJ5R*4^-aB7k{i>yIhDaG`+%O{l{TBwDt-GqpOu1>yQ<$+ zG{o-BS6AuoW{y%6dwzVC$o__<;_LUkaJn}A$+t`PlTuRH#M`5?em*VV_W8%>_@|No zGo#Y|Kb`r=sTHgE=)?DlpKt2k-TY@3R<CPGW)sAruALgu4~_dtM7`f_^h~o=Cq)$edPU3H3VBnz5Sk#HF)hbw6ceYn~q6zs&TzNo}#R z&A#*rxqDeBX{2O);n|*Z1%=}?+zxtKxIUe8Q=eqWXcVD~LxTN89Q~riM z1#8ytkeObn+4A$g$0x1Hp5jeGUR_5Y`L{lZohET`(SjPMnH@s<=ife^>Fodc#^n1C zADlEU+4fZ8MV{LG)R!wV(_+7S?V5cnQ_o~^Qg1=dmR$=Brm1l4zBM7PQ+Zihnx%PF zTeI_Vjn^HIYL1-EuQ%VmW;geAt4~)FU#c#-P`{Tw|-j9bWJwM+(CK0l=KREmBg%=8wgCEOSmv)^j znz-|4!}t4z_U3DMv34`b?Y#2dPw$+>^n?CoN<};GBn7Mp(faH1err$a9?=i?zVDk3 zIVrU0{ca6mqr;u2>gs;{ z*E!biBQs$Ax z1MUyJN1J>vhVQ9(rBU54laNz1#X_j&)APFCyp3FrjO^mKCz##eF+5&2vCuj6#DRvsgT)KYxWjxR!)Ki5_Trl(DgSWi-)c*{6265wc7MC)FPtn_ zvngUDw_o3B_vkoHh2p0ZXLcwlD$jYK5MTf3wv2W8oW1RRic1oG>y2eid)H(}AN?v_ zc5&ibMfoP<^_R{YiwLL+sEMoBE^S)Fy^qywij1%7;>yey9KZYIAO6^xm^1Uac-^<~ z7sb~e1nzFRqx-n`(S6(I@9%rB@4lnDDN2gd&a&+4p5E1ExsMO7wmwg7(*kM_|6jki*ZpMZw4ZYS_r2d25*p9c*isu zZ4w9P3xl*7f=`z{VEt0?p{wsj&*{>0kulGBj20Zf$S^PRwG8V=g+m?d7-x#AsT@)D zQ0P=~RBUQKp&H{f$*(;0?cV#}|7_Hcy}PqSi0N)g-TeAV>t5a3T3-J3-uun>pV!J| z-8B`mmw0gXwdt+5EhfGnbG;9jZ+^J*tjrDT*6(wEgwOfmUi>n(o~?^@U-a9DW$UKj z<_} znONGqJ8&7Nnp*twYdY6fZ!N5>tj#ZUY$=}hPa|pnF(z3-JkdW^N%V1cibcHRr2XJyIs!CXRC7_aoChxeY|JOhYb!#A`}>2 z>*#59J&brEpK-ZNva?u4Y*wT4X12+#OVk#a8a|p}U&qe9ugvs{GskKBjdRzo+Vs4o zBruula(6@T&-d=Vr=+NI$kI8E#bf(V*JHEv zYhQY|B%av$e4cj#^O~(Gk;hE0#~gmU{rv8W?zt=l9Omp~T*78XZ` zh&h*=3|34FVYtovDP@k4YqzF?f=U{bfZ^ssq08y#pPba)|MZ3PyQllu-#>pC|4)6t z{R7c?xA$~D^|wDZo*cLrw@kK7Bj5T% zK$ZIS6~aP0_ISl;{){}Ywe zG_5*tU6CvPdZMex+!@U?-Nfh5E|$rTk2(G6aNW6D{`<$3`PV;Q$!z}NccYzLO`dMB z+MCnX_o`UjeeGKQzP7y*+weMja;jv)M!f@)-ZA|ii^Qa7t^f4r8L!Q^H^F}%wu;}} zw33tAaQXZSIqtq%dr2|ph@QsO^0!}&E3DW4aW2}o!ei#eO}g7QOq?Rd$y^b&rsAXE zHJfc+>hr3abYC*OHBl^XW{eYQ-Eu2e?aQ}<4~*=emmBw|UwgQD#v#WmFBBI@JM;3Z z{IFSEb;2_3dYxMI**8;_1+{$9hUvmF& z-@LNEvfaKi$7dXHsuvFX*HypkNwLcLy&mr!oRkY)BJag56l`y<{B?UmYNg_|OVygl%!=7595#`_c9i$40^KYiJMH#1xH{@m(kUwa>as5G!Y$L zP)D0*<*G}3k+(M}&pIevx!Cggs%xCnIO-d=zD=kxjJxBf5Dt&RTm z!D@dfaLA|JTh|f8%&QuXDPZXSo@9Px9_V(+jpN^axZU@!hsnI{lz&AU)iQJ>K&e?a=xZ$ zLgndh{oKU)wQ7a0s?R-ma`;)|OI4rOCWopFubs4S-sU4O`)#7kz29Zk#ud^1&Ry3O z{x=USpGZUih{rN_W}*{b#+U%?uW%E4`mpt5t9Kcs=J0_S;-5uP0@sCrAsti;-TL zD|`H0!O@zfs>@uvrP}PSZEl<%@%7RA9sj3$M}B(HtP*+1G5A~ZrxrOWN0*GxZgJNt zv$jh8oVAl-j^fErMh539Zl&0K{&f1y<<0!{wVyK2*gg`en(6hR+Q2P0{9DW3I<|b5 z!>c`J7B!|jxQO3n*|F$Nn|kWMC(ahBpW+`qf2O`KhrKxar@Mtp{wjgVf{(l1V}CB& zr=z^7y6{KX`@F7Rb~AplblKD4byd>$cmCjB6aUrXH=AJMv?Psl@_I)@EFb@zXQ9Bs zwtddSPhZQ`?B(WL`Xm^9?KpC!!n9%W|0KQValh>ssvl`xwqyIW_3C#ff3`U`1 z5>hQ{Y9^`g4^3hFZCLqe;+c8h?>+k69q0H{FnQ&~^|Q2J7xVtR_Nigry^l3BtDQd9 zPu(FT*?lUm>}}cXb?fxZ^6#CAOrLvnSLthuw_7e3*zq%*UiN%~xr4lf1j7ZNyK(su z8X@&)x&k>x0K`Eu#>98Y$`=YKzE?Az~a&Ks8|?7#O1%Xj+G*MGmwbE?LWdHZJD%cm}O zNbf1)6O`b1bntj@=LQKSo!=J|{xPx_ocjHb>G!@GF+=8SHruDQ%T+cUuixG#&KAdZ zn{BfBu1WI|<3~yP8F}{|fHT{d4dl|kS1x@2XyeswXE!hfv1OIcsM7fV^#9!> z@ALQd%Kth2Kk>Bp`U?fqqH;JmKYF@NN>Pb)TPyhZuuX>HwM~`YlP$Jf$@P$ss7cGP zbeCe*y&tWWN3H(=F_js~V`GMPuEW9U(TNy^z8@=6TSA9F{b;6Bf&8aVEefqp6xcfxJ z_gAae7rkD){nKOX_fMAF|Ku!we(veN-|y3}t%(f1<{9~6O-{$XopF^vKF`{C`}UNh zXWQ16f3D;UxUzB2VQcpnwk^{--yCi^$^OBeJ8i-y*6!mBnv$u`pC&Zy=?wPqFfUb` z@UVL+!_lv6VuHfs+P@Wie|>H(Z`~&AzN^w}I6Gggnx`#nsW|`spUchPp3Amme?ZXkvC}X^Idik6>nc5tMrJlVTqU@(X>Z&nlR##c#=dstTe68hl|NpmgRwu4{ zW7m7AY(Y+Iq>+f^q^Aq6H*BuFSo_-goUWb@)80RsWpA`yLI*HPxs$HZoI#4&hz=z z^EQYHxhSe__~JLqN5b7?msHDEiTw{nf0=*%_^GY;Oa7bX7jOF}@2|CZ)nfnfhOmFi zt?K`3{7T8(+jd)gdT4($*5D9-!io2%e=DUQanNl#P;?~S{#>|yiP-CRv1bl{zkB}j z{1`fHZo%(-;+>VoCFXIrehc>AvF-muf}qxSEb>8roj>He~_TQ0SjZ1J(k;bQl% zmtH<^V?(olJ%35*Q_-Mc`z4$;0d;ZrUKIL&Y~C=pFyc6S%TM=I1_q%Uo-U3d7Ks@~ zsdn7v5sIY+yiCm-E7A++CbFAsnU=kizpOvLz%}K3=&ZbQU?U=SKepc|9 z*F3Au&n+NM(dyh!we#m?=815)3T`_fc6Fz1TaT33i=&r%mHlsS4qY)lKK_x?9_{<* zL$crGgx*+NT$9>u{d(JuT~nvef4Fj{^%duQbW zWp2;1nM`{GpVmK_tC~@65wZSVlBoKuw{hy-y%noAeGe^pbWm#kec3AB??!Fwa-{#P z@>#a|$yK3V&W~(4If<88md!0!yL_&uzVMq*chJnInYTqUSGg{ox?zT-Pt3kR<}1k^ zU3>hZ=gf%}RAhPjFXy$eE!UgB$EuE1KuUms_t0oRG$n*zo=8EB7@o7l!Rqlg|;jVKZ}8h3F5n zg`FRrk1gF6(PdJyM{Bn~<2}A9i5@pTmM-1X95{!q?Mz8YU9{xoHywr!S3a7`Zq{7? zRDVbDuet*3ZI9#Ab<<8{8tcc;wttyWA-Z@~hR5+V+W_rgy)nik#B6ghP@e>ub&Az&e@G`N8iO3O+4g(&qC!_xW?%C*QNWU+lPM=sJD> zLd|({pRDD3*Qgr5xzBeo`_96*|M{%!B4_Osmi+wct5tYR;n4}l)6UE|xGHqD#j6#I z8}=x0J4{l^|MBl+M0)v$s|#vUCVrRxCc@}1Ak1cXZ}RtS?YOt?x#}EAZ0-!s*Wc!E zKGvZ5UzjItLf?+|!~IzX>Z*5MnaXCabZ(P=DxRv!YHxAQu=%m)?TyaIo^`HB&DgPa zFZZeBS2gRkTyvf%-!$I#%aN&4HMZeIS)Z_V(4B2J*Pm-z`F#ETuxk_E7;=4Z+i+Tb z*Iha5@@MP!PkYO={Vi{)-1P@q4%QW)I5lQ%djD{Hee?0Zhu?oFofoscbomM^&-ZB! zoIM+lmapHw@HMl`le4ESkI%6zj@XtXd3m}2@|!tHYnNWl3O!$b?$Xrw)vir%JStN^ z9L}E-=EilfOvGwmU7J{}Vtq%WU$gA#S?l7o@;`grc-HH) zRwzqJ%O8y8GPuW6W_u3FVWUdQ?0+ z9?#G@z2O?)$w@E%L^;mu39Zih^CeBTe$UTLmaWzz4>~(KI6Nm^xP19A=(;nx+Ao3U zEFSYTDIBQwFE2OGoE4@yn;~*qXsyQSdsRwGM!!TJynTA_!*BWgf>X~vJW^EdvyXfI zFDL!?uJbBN$+04?E`djmipR&;hHZ25n6yM|)uTC!uVx9dFh)+BxJ%acWcCS5qG-Ln&jN7;S>%VIp5Ec}iC@7g+@$ctz&>3zGhHZ_FjF(K7Ud-tE zwyv|ogPpZPNlD3QQQ7XZmzH|}++P3N9CTZN;c*$~wPDh4?+OV{Oay!BM8~YNYU=ZA zj5epASL0yH+xzv}s{eDZ-S6z^k>&c}cH1vb`1o6?bsNk6L^*HoHd!Goc|PXZhQ`!K zM>-?2Egv*6|2R3J-%-%wY{sO<3!k=?-H~5 z*ZunSYtD|2W-gEmu&walk<)qNMozJ8W1)Q{3Qc9l5 zWFsgjc+)G=;b_$9OG~{Y_t)8Wi|H~21Q!cVH1yg2(8a|iW%nbCXRlVTe+HVvp8w;B z`j%&YE-5|6bv$?5w5wl6WWRj<`m(EwOWBIuyQQDYT#MS4bJOV7Ze^o&md`)v$r~++ zTqVY-q?9}*$i&sfCB@}hRFlDhN_Uy#i}zY9DQ%MF`rzW?a*xH$`k|V)F~cH_MR)W1 zU+wGYIPtCbmz2$OnF;qLw_LlFw|({TNh*>Xqo!Z7aQzlnC^I?r=Yq{XS4AeiJ$;Es zI-(@Dg&I#1ozCFM#_Cj+_&x zuX%euy6xJ%`{bq`1r9eK&%g%tP2WG=yPUPv;`N%%pO&4ml0RXQ)^l^^nQ3n|(_fu( zSkLpW$B^rti_5WzhQ+6?Ihfb&dZlIevD06Gg>kldz8Xi<#e2Gfl84oNXB}B?_f>P< zzF%3aZ`Zj=CU|86!)3*bStK7Zc zYwziMPEr)rx1QZQ{kHTxsaree-pyUFprn+q2Tp|&QVh1gUM#-4YxmJ^@#61y%lSEb zPQCy8>-zq^L!F5h!?B3T7To{ki7uEYoa;AMgLa-T!b- z^2tf6I&pg>7~b1NPWyQN|DW>=F;y>@?s*;iUa2oRY)wR9?)mET-TM1ZXfB^~s8u}f z#3I-36PtQ;PDgCX5KNz6YbG93!1%Uownbmzy@zui|Gxj|`RUKj%#5k~`81T9r9r>`=V_nWW^1crD{JQdesTBO z%LPhGpPnrRJJ`TXzwguR`+wS|YKIHC3ND{tXEp!VmE{dKvYUBYuC0j#r4C<-Hl2tK z4cqtsef#D6_s-QW2&2ID<*8I9W|Jls+d5Wive*ONv^UbEyKfZ0>ANw{x^2F1J?efp& z6rW>!uUiK(lJ4Cm zR_+zoU&mBDY;8%55Dnox)bPIU`|gPBpD*0)PwlDvZ1LrSGw0z6^Z$KWenVmZmVd|V z|FEB)rn@+9eevhB=EmjkV%BV}ct6v=-p>Bt^?KHXhlg6%#O;+jas9XHY~MbsR~mZz z{}ieD&T82@&290)so`-aci;b;r{FKF%e_-4c9#fviGR(f$@AA-m?T&8;b4|*Lgb3063rXk80UAKumC5K7MmLzuWc%O8^z#f_cLXY#-kbbc5Ulx zo@$#&@#gJ#$QHIf?(Csf?v2-qUM`(JX_;nz_3hgok7uOMt86QMeeL0#$19i5V|rjb z|0hrIGM|H%;cI7hFX~tsyu9cjt2o1l*YW>nrENah#w*P*!@k~5Sj}g}sywHCVeh8| z`z?%H&(C>cntr_B+OXt@hgwTYOG973KV+cN;}o_w%5_?*&EGGV4o{ZQW=0DuZE} z@9bj_^J}$do9CxpT@`xOC-%8dbh<$(Tjklb$yIy(1X!-T{;K$!>B7~kt)|m-&UQSW zVZf7VHapZ{)>6rHmcM@gUU~hs#q$^M-m$HiwR!sOTob9Q-)5gpE8P=S4=Vk@4pQXr zm{;{m^V+&t@4a#9zrMV@`sU`5PT`-&>;JenDS+aT0W{gIdiGM*u{X~0e-s?9iobuc z`16DJ+3~-nUSD5-f7RJT!u~b~bGP4ho3+emrctZT*&Fr$|2FRFO0Tc4x4SHMW6#Q} z)kkf=-*Mg>xBP0>)6I?73`$>xFn}tRODd_Cm-%jq(!KT8EOMHmfkDIfdB*1~7IQsY zq;ZL7UdIUwaL#J6c>%h7`<&%6xk8q9*|LbOVY+?E=d9n`D9o?j{ppnU&GP%Tor^kj z&Sq?l@|kZZ+hF~Ek8p$i{IAdFl;5jtNj$-B|HBcSiqhWAtA6)z&E|7TJkIAVpUe2! zd~|6tc+ev3$B^*#)m2bFSrflsuHpH->b~>!|32$PZ|hOx8i2#E;IP29HPL<72%M z*_HoirVAY}{JO)ijhWA)0d%JI%gf6@PwcN*GK;m?F8+Mkox3^FOP;|65LdZb?w6>SmvVa}1N&w%;w2K4*E(?sra)VdeZi3JKrd z-2C%Me1F2@W4&{#Ze?EmShB3StK-BEaPC?Hx?JwzoaARcl3Q-S)mnP7+F!(VPSvZG zHD6c9KRv+A&+=)(87Xg><1&Ru1dkN@l$V=lUt6>AYSza8b-#SpNTv%FoX( z-o5KvUvIxT{rt0b`#*}?YyOMzS-ntTSaUYm@Vw=7nRh#%%bm0T|0nC%`#+!0r{CO^ zI;ZZ}%ZTjE?YCVLL*Cy0eeb&+C@bIp|Mxz>&ELzKc0Twy3C31{ymTB@6R>qDJgCG9snx* zE-lPS-LUq!_pup!ywaW(*sY(E`SygT;q6sXFYj(}xWHHY{%!8|;Qef%ZypZXN=nJi;I^uS(3>3n6Vm4_+so@#FW_Ng-o9z#k9B93Og$Kp{=xi@t=p`H z+S?8P{QUG<=PbvehP2I|B5qutTwIQI7HlbZ05xtRc9m#;es=bDmhY^sWy|HN*S4L% zGWE86W?I3Lzc((vo?G0Kc;bBBH{)mL=kK3ftp#r-KiF`X?{Sy*x&so<5^az7F?il= zu=Ne*v;XrU@Se1w;LYGEi!_y#oaSxfXx5zSu=UtEDQmr8iPIwI=K6Yy3QpYU4^Em3 zW2Rq|{81w1KmCkR>1E69!K_IxE>F%nYR*zpQeu^k*kqzyEEy>B&}jSJM{44aR0lWVIyySAn*$DTLBWZIP9Udubab4sSO}_i>1EtM a`!(|gOe(&H^D{6oFnGH9xvX