From ab4271962c83c0da16b5e806c8cfd6880142fd6e Mon Sep 17 00:00:00 2001 From: Nitya Narasimhan Date: Mon, 23 Aug 2021 14:09:01 -0400 Subject: [PATCH] Data Ethics (Single File) --- 1-Introduction/02-ethics/1-fundamentals.md | 109 ----------- 1-Introduction/02-ethics/2-collection.md | 3 - 1-Introduction/02-ethics/3-privacy.md | 3 - 1-Introduction/02-ethics/4-fairness.md | 3 - 1-Introduction/02-ethics/5-consequences.md | 3 - 1-Introduction/02-ethics/6-summary.md | 3 - 1-Introduction/02-ethics/README.md | 179 ++++++++++++++++-- .../02-ethics/megan-smith-algorithms.png | Bin 0 -> 75127 bytes 8 files changed, 159 insertions(+), 144 deletions(-) delete mode 100644 1-Introduction/02-ethics/1-fundamentals.md delete mode 100644 1-Introduction/02-ethics/2-collection.md delete mode 100644 1-Introduction/02-ethics/3-privacy.md delete mode 100644 1-Introduction/02-ethics/4-fairness.md delete mode 100644 1-Introduction/02-ethics/5-consequences.md delete mode 100644 1-Introduction/02-ethics/6-summary.md create mode 100644 1-Introduction/02-ethics/megan-smith-algorithms.png diff --git a/1-Introduction/02-ethics/1-fundamentals.md b/1-Introduction/02-ethics/1-fundamentals.md deleted file mode 100644 index f86dccac..00000000 --- a/1-Introduction/02-ethics/1-fundamentals.md +++ /dev/null @@ -1,109 +0,0 @@ - -## 1. Ethics Fundamentals -[Back To Introduction](README.md#introduction) - -### 1.1 What is Ethics? - -The term "ethics" [comes from](https://en.wikipedia.org/wiki/Ethics) the Greek term "ethikos" - and its root "ethos", meaning _character or moral nature_. Think of ethics as the set of **shared values** or **moral principles** that govern our behavior in society. Our code of ethics is based on widely accepted ideas on what is _right vs. wrong_, creating informal rules (or "norms") that we follow voluntarily to ensure the good of the community. - -Ethics is critical for scientific research and technology advancement. The [Research Ethics timeline](https://www.niehs.nih.gov/research/resources/bioethics/timeline/index.cfm) gives examples from the past four centuries - including Charles Babbage's 1830 [Reflections on the Decline of Science in England ..](https://books.google.com/books/about/Reflections_on_the_Decline_of_Science_in.html) where he discusses dishonesty in data science approaches including fabrication of data to support desired outcomes. Ethics became _guardrails_ to prevent data misuse and protect society from unintended consequences or harms. - -_Applied Ethics_ is about the practical adoption of ethical principles and practices when developing new processes or products. It's about asking moral questions ("is this right or wrong?"), evaluating tradeoffs ("does this help or harm society more?") and taking informed actions to ensure compliance at individual and organizational levels. Ethics are *not* laws. But they can influence the creation of legal or social frameworks that support governance such as: - - * **Professional codes of conduct.** | For users or groups e.g., The [Hippocratic Oath](https://en.wikipedia.org/wiki/Hippocratic_Oath) (460-370 BC) for medical ethics defined principles like data confidentiality (led to _doctor-patient privilege_ laws) and non-maleficence (popularly known as _first, do no harm_) that are still adopted today. - * **Regulatory standards** | For organizations or industries e.g., The [1996 Health Insurance Portability and Accountability Act](https://en.wikipedia.org/wiki/Health_Insurance_Portability_and_Accountability_Act) (HIPAA) mandated theft and fraud protections for _personally identifiable information_ (PII) collected by the healthcare industry - and stipulated how that data could be used or disclosed. - -### 1.2 What is Data Ethics? - -Data ethics is the application of ethics considerations to the domain of big data and data-driven algorithms. - - * [Wikipedia](https://en.wikipedia.org/wiki/Big_data_ethics) defines big data ethics as _systemizing, defending, and recommending, concepts of right and wrong conduct in relation to data_ - focusing on implications for **personal data**. - * A [Royal Society article](https://royalsocietypublishing.org/doi/full/10.1098/rsta.2016.0360#sec-1) defines data ethics as a new branch of ethics that _studies and evaluates moral problems related to **data, algorithms and corresponding practices** .. to formulate and support morally good solutions (right conduct or values)_. - -The first definition puts it in perspective of users ("personal data") while the second puts it in perspective of operations ("data, algorithms, practices") where: - -* `data` = generation, recording, curation, dissemination, sharing & usage -* `algorithms` = AI, agents, machine learning, bots -* `practices` = responsible innovation, ethical hacking, codes of conduct - -Based on this, we can define data ethics as the study and evaluation of _moral questions_ related to data collection, algorithm development, and industry-wide models for governance. We'll explore these questions in the "how" section, but first let's talk about the "why". - -### 1.3 Why Data Ethics? - -To answer this question, let's look at recent trends in the big data and AI industries: - - * [_Statista_](https://www.statista.com/statistics/871513/worldwide-data-created/) - By 2025, we will be creating and consuming over **180 zettabytes of data**. - * _[Gartner](https://www.gartner.com/smarterwithgartner/gartner-top-10-trends-in-data-and-analytics-for-2020/)_ - By 2022, 35% of large orgs will buy & sell data in **online Marketplaces and Exchanges** - * _[Gartner](https://www.gartner.com/smarterwithgartner/2-megatrends-dominate-the-gartner-hype-cycle-for-artificial-intelligence-2020/)_ - AI **democratization and industrialization** are the new Hype Cycle megatrends. - -The first trend tells us that _data scientists_ will have unprecedented levels of access to personal data at global scale, building algorithms to fuel an AI-driven economy. The second trend tells us that economies of scale and efficiencies in distribution will make it easier and cheaper for _developers_ to integrate AI into more everyday consumer experiences. - -The potential for harm occurs when algorithms and AI get _weaponized_ against society in unforeseen ways. In [Weapons of Math Destruction](https://www.youtube.com/watch?v=TQHs8SA1qpk) author Cathy O'Neil talks about the three elements of AI algorithms that pose a danger to society: _opacity_, _scale_ and _damage_. - - * **Opacity** refers to the black box nature of many algorithms - do we understand why a specific decision was made, and can we _explain or interpret_ the data reasoning that drove the predictions behind it? - * **Scale** refers to the speed with which algorithms can be deployed and replicated - how quickly can a minor algorithm design flaw get "baked in" with use, leading to irreversible societal harms to affected users? - * **Damage** refers to the social and economic impact of poor algorithmic decision-making - how can bad or unrepresentative data lead to unfair algorithms that disproportionately harm specific user groups? - -So why does data ethics matter? Because democratization of AI can speed up weaponization, creating harms at scale in the absence of ethical guardrails. While industrialization of AI will motivate better governance - giving data ethics an important role in shaping policies and standards for developing responsible AI solutions. - - -### 1.4 How To Apply Ethics? - -We know what data ethics is, and why it matters. But how do we _apply_ ethical principles or practices as data scientists or developers? It starts with us asking the right questions at every step of our data-driven pipelines and processes. These [Six questions about data science ethics](https://halpert3.medium.com/six-questions-about-data-science-ethics-252b5ae31fec) are a good starting point: - - 1. Is the data fair and unbiased? - 2. Is the data being used fairly and ethically? - 3. Is (user) privacy being protected? - 4. To whom does data belong, company or user? - 5. What effects do data and algorithms have on society? - 6. Is the data manipulated or deceiving? - -The [22 questions for ethics in data and AI](https://medium.com/the-organization/22-questions-for-ethics-in-data-and-ai-efb68fd19429) article expands this into a framework, grouping questions by stage of processing: _design_, _implementation & management_, _systems & organization_. The [O'Reilly Ethics and Data Science](https://resources.oreilly.com/examples/0636920203964/) book advocates strongly for _checklists_, asking simple `have we done this? (y/n)` questions that improve ethics oversight without the overheads caused by analysis paralysis. - -And tools like [deon](https://deon.drivendata.org/) -make it frictionless to integrate [ethics checklists](https://deon.drivendata.org/#data-science-ethics-checklist) into your project workflows. Deon builds on [industry practices](https://deon.drivendata.org/#checklist-citations), shares [real-world examples](https://deon.drivendata.org/examples/) that put the ethical challenges in context, and allows practitioners to derive custom checklists from the defaults, to suit specific scenarios or industries. - -### 1.5 Ethics Concepts - -Ethics checklists often revolve around yes/no questions related to core ethics concepts and challenges. Let's look at _a subset_ of these issues - inspired in part by the [deon ethics checklist](https://deon.drivendata.org/#data-science-ethics-checklist) - in two contexts: data (collection and storage) and algorithms (analysis and modeling). - -**Data Collection & Storage** - * _Ownership_: Does the user own the data? Or the organization? Is there an agreement that defines this? - * _Informed Consent_: Did human subjects give permission for data capture & understand purpose/usage? - * _Collection Bias_: Is data representative of audience? Did we identify and mitigate biases? - * _Data Security_: Is data stored and transmitted securely? Are valid access controls enforced? - * _Data Privacy_: Does data contain personally identifiable information? Is anonymity preserved? - * _Right to be Forgotten_: Does user have mechanism to request deletion of their personal information? - -**Data Modeling & Analysis** - - * _Data Validity_: Does data capture relevant features? Is it timeless? Is the data model valid? - * _Misrepresentation_: Does analysis communicate honestly reported data in a deceptive manner? - * _Auditability_: Is the data analysis or algorithm design documented well enough to be reproducible later? - * _Explainability_: Can we explain why the data model or learning algorithm made a specific decision? - * _Fairness_: Is the model fair (e.g., shows similar accuracy) across diverse groups of affected users? - -Finally, let's talk about two abstract concepts that often underlie users' ethics concerns around technology: - - * **Trust**: Can we trust an organization with our personal data? Can we trust that algorithmic decisions are fair and do no harm? Can we trust that information is not misrepresented? - * **Choice**: Do I have free will when I make a choice in a consumer UI/UX? Are data-driven [choice architectures](https://en.wikipedia.org/wiki/Choice_architecture) nudging me towards good choices or are [dark patterns](https://www.darkpatterns.org/) working against my self-interest? - - -### 1.6 Ethics History - -Knowing ethics concepts is one thing - understanding the intent behind them, and the potential harms or societal consequences they bring, is another. Let's look at some case studies that help frame ethics discussions in a more concrete way with real-world examples. - -| Historical Example | Ethics Issues | -|---|---| -| _[Facebook Data Breach](https://www.npr.org/2021/04/09/986005820/after-data-breach-exposes-530-million-facebook-says-it-will-not-notify-users)_ exposes data for 530M users. Facebook pays $5B to FTC, does not notify users. | Data Privacy, Data Security, Transparency, Accountability | -| [Tuskegee Syphillis Study](https://en.wikipedia.org/wiki/Tuskegee_syphilis_experiment) - African-American men were enrolled in study without being told its true purpose. Treatments were withheld. | Informed Consent, Fairness, Social / Economic Harms | -| [MIT Gender Shades Study](http://gendershades.org/index.html) - evaluated accuracy of industry AI gender classification models (used by law enforcement), detected bias | Fairness, Social/ Economic Harms, Collection Bias | -| [Learning app ABCmouse pays $10 million to settle FTC complaint it trapped parents in subscription they couldn’t cancel](https://www.washingtonpost.com/business/2020/09/04/abcmouse-10-million-ftc-settlement/) - user experience masked context, nudged user towards choices with financial harms| Misrepresentation, Free Choice, Dark Patterns, Economic Harms | -| [Netflix Prize Dataset de-anonymized by correlation](https://www.wired.com/2007/12/why-anonymous-data-sometimes-isnt/) - showed how Netflix prize dataset of 500M users was easily de-anonymized by cross-correlation with public IMDb comments (and other such datasets) | Data Privacy, Anonymity, De-identification | -| [Georgia COVID-19 cases not declining as quickly as data suggested](https://www.vox.com/covid-19-coronavirus-us-response-trump/2020/5/18/21262265/georgia-covid-19-cases-declining-reopening) - graphs released had x-axis not ordered chronologically, misleading viewers| Misrepresentation, Social Harms | - -We covered just a subset of examples, but recommend you explore these resources for more: - - * [Ethics Unwrapped](https://ethicsunwrapped.utexas.edu/case-studies) - ethics dilemmas across diverse industries. - * [Data Science Ethics course](https://www.coursera.org/learn/data-science-ethics#syllabus) - landmark case studies in data ethics. - * [Where things have gone wrong](https://deon.drivendata.org/examples/) - deon checklist examples of ethical issues diff --git a/1-Introduction/02-ethics/2-collection.md b/1-Introduction/02-ethics/2-collection.md deleted file mode 100644 index 323b3087..00000000 --- a/1-Introduction/02-ethics/2-collection.md +++ /dev/null @@ -1,3 +0,0 @@ - -## 2. Data Collection -[Back To Introduction](README.md) \ No newline at end of file diff --git a/1-Introduction/02-ethics/3-privacy.md b/1-Introduction/02-ethics/3-privacy.md deleted file mode 100644 index 93b6e22d..00000000 --- a/1-Introduction/02-ethics/3-privacy.md +++ /dev/null @@ -1,3 +0,0 @@ - -## 3. Data Privacy -[Back To Introduction](README.md) \ No newline at end of file diff --git a/1-Introduction/02-ethics/4-fairness.md b/1-Introduction/02-ethics/4-fairness.md deleted file mode 100644 index edd8bf2b..00000000 --- a/1-Introduction/02-ethics/4-fairness.md +++ /dev/null @@ -1,3 +0,0 @@ - -## 4. Algorithm Fairness -[Back To Introduction](README.md) \ No newline at end of file diff --git a/1-Introduction/02-ethics/5-consequences.md b/1-Introduction/02-ethics/5-consequences.md deleted file mode 100644 index 634f3ee5..00000000 --- a/1-Introduction/02-ethics/5-consequences.md +++ /dev/null @@ -1,3 +0,0 @@ - -## 5. Societal Consequences -[Back To Introduction](README.md) \ No newline at end of file diff --git a/1-Introduction/02-ethics/6-summary.md b/1-Introduction/02-ethics/6-summary.md deleted file mode 100644 index 8837cd43..00000000 --- a/1-Introduction/02-ethics/6-summary.md +++ /dev/null @@ -1,3 +0,0 @@ - -## 6. Summary & Resources -[Back To Introduction](README.md) \ No newline at end of file diff --git a/1-Introduction/02-ethics/README.md b/1-Introduction/02-ethics/README.md index b59130ea..a2eda93c 100644 --- a/1-Introduction/02-ethics/README.md +++ b/1-Introduction/02-ethics/README.md @@ -6,35 +6,174 @@ ## Sketchnote 🖼 -| A Visual Guide to Data Ethics by [Nitya Narasimhan](https://twitter.com/nitya) / [(@sketchthedocs)](https://sketchthedocs.dev)| -|---| -|







| +> A Visual Guide to Data Ethics by [Nitya Narasimhan](https://twitter.com/nitya) / [(@sketchthedocs)](https://sketchthedocs.dev) -## Introduction +## 1. Introduction -What is ethics? What does data ethics mean, and how is it relevant to data scientists and developers in the context of big data, machine learning, and artificial intelligence? This lesson explores these ideas under the following sections: +This lesson will look at the field of _data ethics_ - from core concepts (ethical challenges & societal consequences) to applied ethics (ethical principles, practices and culture). Let's start with the basics: definitions and motivations. - * [**Fundamentals**](1-fundamentals) - Understand definitions, motivation and core concepts. - * [**Data Collection**](2-collection) - Explore data ethics issues around data ownership, user consent and control. - * [**Data Privacy**](3-privacy) - Understand degrees of privacy, challenges in anonymity and leakage, and user rights. - * [**Algorithm Fairness**](4-fairness) - Explore consequences & harms of algorithm bias and data misrepresentation. - * [**Societal Consequences**](5-consequences) - Explore socio-economic issues and case studies related to data ethics. - * [**Summary & Resources**](6-summary) - Wrap-up with a review of current data ethics practices and resources. +### 1.1 Definitions ---- +**Ethics** [comes from the Greek word "ethikos" and its root "ethos"](https://en.wikipedia.org/wiki/Ethics). It refers to the set of _shared values and moral principles_ that govern our behavior in society and is based on widely-accepted ideas of _right vs. wrong_. Ethics are not laws! They can't be legally enforced but they can influence corporate initiatives and government regulations that help with compliance and governance. + +**Data Ethics** is [defined as a new branch of ethics](https://royalsocietypublishing.org/doi/full/10.1098/rsta.2016.0360#sec-1) that "studies and evaluates moral problems related to _data, algorithms and corresponding practices_ .. to formulate and support morally good solutions" where: + * `data` = generation, recording, curation, dissemination, sharing and usage + * `algorithms` = AI, machine learning, bots + * `practices` = responsible innovation, ethical hacking, codes of conduct + +**Applied Ethics** is the [_practical application of moral considerations_](https://en.wikipedia.org/wiki/Applied_ethics). If focuses on understanding how ethical issues impact real-world actions, products and processes, by asking moral questions - like _"is this fair?"_ and _"how can this harm individuals or society as a whole?"_ when working with big data and AI algorithms. Applied ethics practices can then focus on taking corrective measures - like employing checklists (_"did we test data model accruacy with diverse groups, for fairness?"_) - to minimize or prevent any unintended consequences. + +**Ethics Culture**: Applied ethics focuses on identifying moral questions and adopting ethically-motivated actions with respect to real-world scenarios and projects. Ethics culture is about _operationalizing_ these practices, collaboratively and at scale, to ensure governances at the scale of organizations and industries. [Establishing an ethics culture](https://hbr.org/2019/05/how-to-design-an-ethical-organization) requires identifying and addressing _systemic_ issues (historical or ingrained) and creating norms & incentives htat keep members accountable for adherence to ethical principles. + + +### 1.2 Motivation + +Let's look at some emerging trends in big data and AI: + + * [By 2022](https://www.gartner.com/smarterwithgartner/gartner-top-10-trends-in-data-and-analytics-for-2020/) one-in-three large organizations will buy and sell data via online Marketplaces and Exchanges. + * [By 2025](https://www.statista.com/statistics/871513/worldwide-data-created/) we'll be creating and consuming over 180 zettabytes of data. + +**Data scientists** will have unimaginable levels of access to personal and behavioral data, helping them develop the algorithms to fuel an AI-driven economy. This raises data ethics issues around _protection of data privacy_ with implications for individual rights around personal data collection and usage. + +**App developers** will find it easier and cheaper to integrate AI into everday consumer experiences, thanks to the economies of scale and efficiencies of distribution in centralized exchanges. This raises ethical issues around the [_weaponization of AI_](https://www.youtube.com/watch?v=TQHs8SA1qpk) with implications for societal harms caused by unfairness, misrepresentation and systemic biases. + +**Democratization and Industrialization of AI** are seen as the two megatrends in Gartner's 2020 [Hype Cycle for AI](https://www.gartner.com/smarterwithgartner/2-megatrends-dominate-the-gartner-hype-cycle-for-artificial-intelligence-2020/), shown below. The first positions developers to be a major force in driving increased AI adoption, while the second makes responsible AI and governance a priority for industries. + + +![](https://images-cdn.newscred.com/Zz1mOWJhNzlkNDA2ZTMxMWViYjRiOGFiM2IyMjQ1YmMwZQ==) + +Data ethics are now **necessary guardrails** ensuring developers ask the right moral questions and adopt the right practices (to uphold ethical values). And they influence the regulations and frameworks defined (for governance) by governments and organizations. + + +## 2. Core Concepts + +A data ethics culture requires an understanding of three things: the _shared values_ we embrace as a society, the _moral questions_ we ask (to ensure adherence to those values), and the potential _harms & consequences_ (of non-adherence). + +### 2.1 Ethical AI Values + +Our shared values reflect our ideas of wrong-vs-right when it comes to big data and AI. Different organizations have their own views of what responsible AI and ethical AI principles look like. + +Here is an example - the [Responsible AI Framework](https://docs.microsoft.com/en-gb/azure/cognitive-services/personalizer/media/ethics-and-responsible-use/ai-values-future-computed.png) from Microsoft defines 6 core ethics principles for all products and processes to follow, when implementing AI solutions: + + * **Accountability**: ensure AI designers & developers take _responsibility_ for its operation. + * **Transparency**: make AI operations and decisions _understandable_ to users. + * **Fairness**: understand biases and ensure AI _behaves comparably_ across target groups. + * **Reliability & Safety**: make sure AI behaves consistently, and _without malicious intent_. + * **Security & Privacy**: get _informed consent_ for data collection, provide data privacy controls. + * **Inclusiveness**: adapt AI behaviors to _broad range of human needs_ and capabilities. + +![Elements of an Responsible AI Framework at Microsoft](https://docs.microsoft.com/en-gb/azure/cognitive-services/personalizer/media/ethics-and-responsible-use/ai-values-future-computed.png) + +Note that accountability and transparency are _cross-cutting_ concerns that are foundational to the top 4 values, and can be explored in their contexts. In the next section we'll look at the ethical challenges (moral questions) raised in two core contexts: + + * Data Privacy - focused on **personal data** collection & use, with consequences to individuals. + * Fairness - focused on **algorithm** design & use, with consequences to society at large. + +### 2.2 Ethics of Personal Data + +[Personal data](https://en.wikipedia.org/wiki/Personal_data) or personally-identifiable information (PII) is _any data that relates to an identified or identifiable living individual_. It can also [extend to diverse pieces of non-personal data](https://ec.europa.eu/info/law/law-topic/data-protection/reform/what-personal-data_en) that collectively can lead to the identification of a specific individual. Examples include: participant data from research studies, social media interactions, mobile & web app data, online commerce transactions and more. + +Here are _some_ ethical concepts and moral questions to explore in context: + +* **Data Ownership**. Who owns the data - user or organization? How does this impact users' rights? +* **Informed Consent**. Did users give permissions for data capture? Did they understand purpose? +* **Intellectual Property**. Does data have economic value? What are the users' rights & controls? +* **Data Privacy**. Is data secured from hacks/leaks? Is anonymity preserved on data use or sharing? +* **Right to be Forgotten**. Can user request their data be deleted or removed to reclaim privacy? + +### 2.3 Ethics of Algorithms + +Algorithm design begins with collecting & curating datasets relevant to a specific AI problem or domain, then processing & analyzing it to create models that can help predict outcomes or automate decisions in real-world applications. Moral questions can now arise in various contexts, at any one of these stages. + +Here are _some_ ethical concepts and moral questions to explore in context: + +* **Dataset Bias** - Is data representative of target audience? Have we checked for different [data biases](https://towardsdatascience.com/survey-d4f168791e57)? +* **Data Quality** - Does dataset and feature selection provide the required [data quality assurance](https://lakefs.io/data-quality-testing/)? +* **Algorithm Fairness** - Does the data model [systematically discriminate](https://towardsdatascience.com/what-is-algorithm-fairness-3182e161cf9f) against some subgroups? +* **Misrepresentation** - Are we [communicating honestly reported data in a deceptive manner?](https://www.sciencedirect.com/topics/computer-science/misrepresentation) +* **Explainable AI** - Are the results of AI [understandable by humans](https://en.wikipedia.org/wiki/Explainable_artificial_intelligence)? White-box (vs. black-box) models. +* **Free Choice** - Did user exercise free will or did algorithm nudge them towards a desired outcome? + +### 2.3 Case Studies + +The above are a subset of the core ethical challenges posed for big data and AI. More organizations are defining and adopting _responsible AI_ or _ethical AI_ frameworks that may identify additional shared values and related ethical challenges for specific domains or needs. + +To understand the potential _harms and consequences_ of neglecting or violating these data ethics principles, it helps to explore this in a real-world context. Here are some famous case studies and recent examples to get you started: + + +* `1972`: The [Tuskegee Syphillis Study](https://en.wikipedia.org/wiki/Tuskegee_Syphilis_Study) is a landmark case study for **informed consent** in data science. African American men who participated in the study were promised free medical care _but deceived_ by researchers who failed to inform subjects of their diagnosis or about availability of treatment. Many subjects died; some partners or children were affected by complications. The study lasted 40 years. +* `2007`: The Netflix data prize provided researchers with [_10M anonymized movie rankings from 50K customers_](https://www.wired.com/2007/12/why-anonymous-data-sometimes-isnt/) to help improve recommendation algorithms. This became a landmark case study in **de-identification (data privacy)** where researchers were able to correlate the anonymized data with _other datasets_ (e.g., IMDb) that had personally identifiable information - helping them "de-anonymize" users. +* `2013`: The City of Boston [developed Street Bump](https://www.boston.gov/transportation/street-bump), an app that let citizens report potholes, giving the city better roadway data to find and fix issues. This became a case study for **collection bias** where [people in lower income groups had less access to cars and phones](https://hbr.org/2013/04/the-hidden-biases-in-big-data), making their roadway issues invisible in this app. Developers worked with academics to _equitable access and digital divides_ issues for fairness. +* `2018`: The MIT [Gender Shades Study](http://gendershades.org/overview.html) evaluated the accuracy of gender classification AI products, exposing gaps in accuracy for women and persons of color. A [2019 Apple Card](https://www.wired.com/story/the-apple-card-didnt-see-genderand-thats-the-problem/) seemed to offer less credit to women than men. Both these illustrated issues in **algorithmic fairness** and discrimination. +* `2020`: The [Georgia Department of Public Health released COVID-19 charts](https://www.vox.com/covid-19-coronavirus-us-response-trump/2020/5/18/21262265/georgia-covid-19-cases-declining-reopening) that appeared to mislead citizens about trends in confirmed cases with non-chronological ordering on the x-axis. This illustrates **data misrepresentation** where honest data is presented dishonestly to support a desired narrative. +* `2020`: Learning app [ABCmouse paid $10M to settle an FTC complaint](https://www.washingtonpost.com/business/2020/09/04/abcmouse-10-million-ftc-settlement/) where parents were trapped into paying for subscriptions they couldn't cancel. This highlights the **illusion of free choice** in algorithmic decision-making, and potential harms from dark patterns that exploit user insights. +* `2021`: Facebook [Data Breach](https://www.npr.org/2021/04/09/986005820/after-data-breach-exposes-530-million-facebook-says-it-will-not-notify-users) exposed data from 530M users, resulting in a $5B settlement to the FTC. It however refused to notify users of the breach - raising issues like **data privacy**, **data security** and **accountability**, including user rights to redress for those affected. + +Want to explore more case studies on your own? Check out these resources: + + * [Ethics Unwrapped](https://ethicsunwrapped.utexas.edu/case-studies) - ethics dilemmas across diverse industries. + * [Data Science Ethics course](https://www.coursera.org/learn/data-science-ethics#syllabus) - landmark case studies in data ethics. + * [Where things have gone wrong](https://deon.drivendata.org/examples/) - deon checklist examples of ethical issues + +## 3. Applied Ethics + +We've learned about data ethics values, and the ethical challenges (+ moral questions) associated with adherence to these values. But how do we _implement_ these ideas in real-world contexts? Here are some tools & practices that can help. + +### 3.1 Have Professional Codes + +Professional codes are _moral guidelines_ for professional behavior, helping employees or members _make decisions that align with organizational principles_. Codes may not be legally enforceable, making them only as good as the willing compliance of members. An organization may inspire adherence by imposing incentives & penalties accordingly. + +Professional _codes of conduct_ are prescriptive rules and responsibilities that members must follow to remain in good standing with an organization. A professional *code of ethics* is more [_aspirational_](https://keydifferences.com/difference-between-code-of-ethics-and-code-of-conduct.html), defining the shared values and ideas of the organization. The terms are sometimes used interchangeably. + +Examples include: + + * [Oxford Munich](http://www.code-of-ethics.org/code-of-conduct/) Code of Ethics + * [Data Science Association](http://datascienceassn.org/code-of-conduct.html) Code of Conduct (created 2013) + * [ACM Code of Ethics and Professional Conduct](https://www.acm.org/code-of-ethics) (since 1993) + + +### 3.2 Ask Moral Questions + +Assuming you've already identified your shared values or ethical principles at a team or organization level, the next step is to identify the moral questions relevant to your specific use case and operational workflow. + +Here are [6 basic questions about data ethics](https://halpert3.medium.com/six-questions-about-data-science-ethics-252b5ae31fec) that you can build on: + +* Is the data you're collecting fair and unbiased? +* Is the data being used ethically and fairly? +* Is user privacy being protected? +* To whom does data belong - the company or the user? +* What effects do the data and algorithms have on society (individual and collective)? +* Is the data manipulated or deceptive? + +For larger team or project scope, you can choose to expand on questions that reflect a specific stage of the workflow. For example here are [22 questions on ethics in data and AI](https://medium.com/the-organization/22-questions-for-ethics-in-data-and-ai-efb68fd19429) that were grouped into _design_, _implementation & management_, _systems & organization_ categories for convenience. + +### 3.3 Adopt Ethics Checklists + +While professional codes define required _ethical behavior_ from practitioners, they [have known limitations](https://resources.oreilly.com/examples/0636920203964/blob/master/of_oaths_and_checklists.md) for implementation, particularly in large-scale projects. In [Ethics and Data Science](https://resources.oreilly.com/examples/0636920203964/blob/master/of_oaths_and_checklists.md)), experts instead advocate for ethics checklists that can **connect principles to practices** in more deterministic and actionable ways. + +Checklists convert questions into "yes/no" tasks that can be tracked and validated before product release. Tools like [deon](https://deon.drivendata.org/) make this frictionless, creating default checklists aligned to [industry recommendations](https://deon.drivendata.org/#checklist-citations) and enabling users to customize and integrate them into workflows using a command-line tool. Deon also provides [real-world examples](ttps://deon.drivendata.org/examples/) of ethical challenges to provide context for these decisions. + +### 3.4 Track Ethics Compliance + +**Ethics** is about doing the right thing, even if there are no laws to enforce it. **Compliance** is about following the law, when defined and where applicable. +**Governance** is the broader umbrella that covers all the ways in which an organization (company or government) operates to enforce ethical principles & comply with laws. -[1. Ethics Fundamentals](1-fundamentals.md ':include') +Companies are creating their own ethics frameworks (e.g., [Microsoft](https://www.microsoft.com/en-us/ai/responsible-ai), [IBM](https://www.ibm.com/cloud/learn/ai-ethics), [Google](https://ai.google/principles), [Facebook](https://ai.facebook.com/blog/facebooks-five-pillars-of-responsible-ai/), [Accenture](https://www.accenture.com/_acnmedia/PDF-149/Accenture-Responsible-AI-Final.pdf#zoom=50)) for governances, while state and national governments tend to focus on regulations that protect the data privacy and rights of their citizens. -[2. Data Collection](2-collection.md ':include') +Here are some landmark data privacy regulations to know: + * `1974`, [US Privacy Act](https://www.justice.gov/opcl/privacy-act-1974) - regulates _federal govt._ collection, use and disclosure of personal information. + * `1996`, [US Health Insurance Portability & Accountability Act (HIPAA)](https://www.cdc.gov/phlp/publications/topic/hipaa.html) - protects personal health data. + * `1998`, [US Children's Online Privacy Protection Act (COPPA)](https://www.ftc.gov/enforcement/rules/rulemaking-regulatory-reform-proceedings/childrens-online-privacy-protection-rule) - protects data privacy of children under 13. + * `2018`, [General Data Protection Regulation (GDPR)](https://gdpr-info.eu/) - provides user rights, data protection and privacy. + * `2018`, [California Consumer Privacy Act (CCPA)](https://www.oag.ca.gov/privacy/ccpa) gives consumers more _rights_ over their personal data. -[3. Data Privacy](3-privacy.md ':include') +In Aug 2021, China passed the [Personal Information Protection Law](https://www.reuters.com/world/china/china-passes-new-personal-data-privacy-law-take-effect-nov-1-2021-08-20/) (to go into effect Nov 1) which, with its Data Security Law, will create one of the strongest online data privacy regulations in the world. -[4. Algorithm Fairness](4-fairness.md ':include') -[5. Societal Consequences](5-consequences.md ':include') +### 3.5 Establish Ethics Culture -[6. Summary & Resources](6-summary.md ':include') +There remains an intangible gap between compliance ("doing enough to meet the letter of the law") and addressing systemic issues ([like ossification, information asymmetry and distributional unfairness](https://www.coursera.org/learn/data-science-ethics/home/week/4)) that can create self-fulfilling feedback loops to weaponizes AI further. This is motivating calls for [formalizing data ethics cultures](https://www.codeforamerica.org/news/formalizing-an-ethical-data-culture/) in organizations, where everyone is empowered to [pull the Andon cord](https://en.wikipedia.org/wiki/Andon_(manufacturing) to raise ethics concerns early. And exploring [collaborative approaches to defining this culture](https://towardsdatascience.com/why-ai-ethics-requires-a-culture-driven-approach-26f451afa29f) that build emotional connections and consistent beliefs across organizations and industries. --- @@ -52,10 +191,10 @@ What is ethics? What does data ethics mean, and how is it relevant to data scien --- # Assignment -[Assignment Title](assignment.md ':include') +[Assignment Title](assignment.md) --- # Resources -[Related Resources](resources.md ':include') \ No newline at end of file +[Related Resources](resources.md) \ No newline at end of file diff --git a/1-Introduction/02-ethics/megan-smith-algorithms.png b/1-Introduction/02-ethics/megan-smith-algorithms.png new file mode 100644 index 0000000000000000000000000000000000000000..8cc7348982944b4aae3ad5684c0c9d4274b42a4e GIT binary patch literal 75127 zcmXtfbzD_l^Y5m+8$`N6T9EFR?i3KDyBkFm>23i5=}tkqrMtTkknXtad4Hd~|IkC7 zz1Nyq^NpDkrm8H9fl7)BK@f(#oRm5Q!Gf1C9LWFur~K786M~3IttBN@tLu9c3U_Fg4aEG!u{IBZ-}a%=nS;iJ8+p-3_$ zY)VOygrLwZ0)lc2Yirb}zIv{&Ry0TXH%S%GdjFmmt$zFe_zeZI;vDXiZxei6Lxjdk zjn`wxp?7!KZ%ho`ZU~JfIQ(fPup!oY!mGuOLxVY2Bt`qbbNYWNb%`J@*f9KkB*=MC z)U!01V&e;O)WvwH4^jwqF$uEv^%;XVT>C=s-XRJK%3>!PGU3$&mT16pw906kh&*ju zo7V@{#YiPSN@k&ygpL&f^v!oPVNU`(fo|01r49V&G+qOI>Z?AoNS2skcigXZJHu;-gGoBl#-Hj# z1?wwwRT6UdDI8WrntTLbymQP_Z8jR=h%;K4X|7LQ??`ICJ0Zz>2lqGAJG4T&XW^mB zA19J_ZbYbkGnm$Vko@UH!K*g^2$PS8GzFGC8?8|s-Nox82R1US&u;o|tcjrTT@XBV zFvSVXMsu7fA?BiRPX9b2?Z;8%GZ?kNquK^ve=%0-)f<-OH{o!rM=Nvo;glR!=b%H%LpRl`uju)Z%U4I^+_`Z#ihep z6<+yM&6-dneECPRY?9hwq%|Bb)Vp@b>&sRz0|ydeJF4y{N@OH82{&xCZUhuDvl#R| z_##Q47^e3aZ^U25P~fBXh~4M7F%mHcDN7QlVz`kvAqWRGuxt{mIFLXgzz3Nv(J^^ z`WM_f5zXQ&Wh=Mmd=CBXL_J`eBf8dgoy_=oGZ3Oe!h0C!*A$YM{KPSD_rGX%kyfc*=OdyCwaO$R488 zwYULyT6CjvBjCpnK>VEf@#Dv2iPX+-)IrprH}HFSzxCmpIID^ z-Z9<^cB_WEI;y&jx`2j^#>?E&96z}?61VYkvI&%=I4xlV-Rfp|rwFHL1aA_dM8ZTe zEov>!>9@tZn&(qnQy-@Urf3g7P32ED6n-g8w%)VKvu3rDu!J~0v*)(=dv9X@)tLK)|Bt>2v~jX=q>0@Lll*`AChxK>V$3T)eEq;^ z(b&cD2bmj{i4C7JzHG~!ryLiHEos|{u%Dl%+hna3%g=FW4kwYd~+++xpUI2ouDh?q81FuY~4XU(KvW`2AtquHzYQ*$SgHNUjguG%jA@JB{UM)VTNuh}!VGt09t+l$+L z`1l0W1PAz*__qYY_=EUg67~{V6QdY~wR;(DSr}Lvm@0}H3#CeyRBwx!%SrR}O9WbU ztSUxV(0m!Dyr$)B2yAi>mJVJX>`uw@dhy7SCX#NZ`K7I-X{BlCQ|kxo>(sVdDO$_g z@Yy_%sg1wMb~PcI;T;+u9*}pqo6m8y5Fn`70f|7%zO zU}3LShwk`IknIr84OcYPqOz1E8w7Dl^WJWf>EgSw;R&W3PNKnwUnYh`*m)Te6p7fpqvk4OcGdC(O z3h70bK$QRje;xm3#!+TTMzYa`;WtB(Uw@h{n=p^@7Kqv^79*$G=8mES69oqzez;NXTBFNre*Ub^-l7B<+bmXd69NLbMflp`>EPF(@E-?);Zfr=9R{|;5y%C#k$F% zC`C4&lfXO9F^&_vwP?!l?1Sv#cVE`-u&c47V+?X?bHsDVO*2eSO&{0I)>GGWahP$W zanNGvW3|*&r&tbDfA3K(SgcT|UTOMUFD4@dd$8`DpDPIFF$QGTGzqiBTPg%QP% z$s5Zb-FsgZ98(BpyJv4ux{aN`^W`#ekvS{C|CFFubTgGb^}$-*8o^p|A9KHqXVGd+Ogd-Va{ffV@=^V_4rW~)67xeRMg*6*sNQAb145XkP@F;prlfl zaFYCjT~G8V&?j57xwbW;g|+!m_Lt{vICt8IgAtdEVd49~hV8#*2@nb1CVoup*{#|& zA5}4~Y#Vb|+c$elV5{XYE#q!=xkvX`k(~D%FK^vpop-WYviYk~L+6$W!24_zGrf$Y zh0Xnsd7apH77pE`|9;|Aa;RO^Y|@*h98;Z`c z?iV9{qwAL?!VZ76_ggQe_T|qtJ{PB88O5 zR5WwM3dtn-Uy=rrK)!We&TGzt&AWmK`9A|2Oyxys)~WmTB#)`Bddc%DuIsM0=c!rN zBFX+ZPZK9v=eDCCH#-Y@`g?{QWm{|fDvaX{Y)tA6U+SUg>D|Yk$8YcEYvoUun_#y6 zoY|Oh{#)=`>a~7g`oqf=^!X)p2I;tZ3WRrCVz+m&CuO9N0t2)cBY>&0RMh4{hHjro z4$VpWFtX{Q3`caB4>+m6SKivc@r7rl3!77lEI|3`FTp;l+6$lZN!Mo{e=gc}$l2Ou z_w?d?{WcLH1O8KpM2L}et@IlyqMnyWOgLC^s_}UV50qN$nbhWVgEaSg$4L)V2rSYb zJt_+Be@>b8i@m0keFvw0PhS@XPFl?@Rpghw9ec`l)oIYKFce)~%cdHT>q?pT8qe#i z9VuP<-T7nKrIXaW%WTj_)*frILa_7=%m){uA1vD<7p)cz&etN*_j&2xwT$Uj-iV;I z1_abUEx@=0{}31IV5QQ`aoSU#^YSw3KI%tP>-!OJ&Sg%vIgTO{c76Q`?jw>`T%@|8 zy7@#@K9L12d7L0mY^vuRmm&aaq^%!OV=o9qet!QDutc@`tNk{_JjXxQzG@m|2t6HQ zL7n3CV8Woq=+`U)VFoQz_0)iXiyvy!i3h(()AWM}Cv-F`4rWrP1r1%>jss~PEDgIl zdTW154(qY~YBt{Z?dU_UNShph!Nt zgS*RkaTmvb_ipufo)_JlY;G%_ylega$aaH`#c9vUu8LJr;y2G!{!@-a4oiNWhq*lr z;qseI+txq#$5S)(e$9{nQalgK!f1=}FS@lkaW`9kFni!@_(!N{IT*}xB#QNHvof~4 zv=rIK6A}7hEH?$^5SB!#Jm|WBktPCHx@e=2V!V2cZmi8L!BoLKV3c_@X<(&q;Lmn{ z=ICUv;84R*8#M>Zjndw4r@XICjH!DpRW-h_J=;Bjib8Qh^xKrfbi#BR3}h??^jHI) z%v+55jN?og%*lm~g)W7dG10hu>v0w8Uzgu0W#LXc&S8Oui?%?TMYrI$! zV$2xI{P^}ZW+5dh`DN<5NB^tIQztQP9}n-5>7`zpx3XkWMx)I>zv-XNI)35hf0mZ^ z?wMzpRHjP^$-H90U{qvk^VHs2%2&uaM<6mbHY}qzHY-~%A&@>3J1zFfbZD99E%@8P z$L09lv2k&3m1ja|`K*PYb$E*2L-w+KN4V!+2ul^Kcd_~9YY$D&BoToX_dRDb&#m~q zf_Y*4mWWZTistfJVN$NzQ)3avssUF?00y0^NQ|`N4JZN1XRG zQHvP_hNnvlOKo1SPSQ?BPAyK+P8-k~QA$w>QRPvDajx(>!ZgE4zbS`V9OJA^G9A;w z(Eg#jR%lK7CjQ;wz(UF5r^Vzp|F-^C+4e30CX)-(YZ?`{$v*?k5zNV2b($uJmkamO zZ1Us<#>G?xoQ0`{Jw?+$>~kJv`b<7(G^mfNXBj@{bOcDg>C($pFxSDej2EAz<|cDx zK6eOrQ`8!yEAjbDNk)|(T~FX~f2en8@@DG|sepq3uK-f>N%L<{wv`X9jy+{#M(r&f zl7pLUOe^uT=e*U?H}}Lh%y&%pWC$^^k{{(dNU5f%x^jrRBs#adW@%o^>`3X!a7(p? zzajfe&OppZ5=bx3ZpzQeA11QD{j`X5{PIvPAjO5Hj=qdvSeWK8M)Bv0={T#>Ovz!~ zi(SK~r8=5i*(~zrM9<@!4!>mBM7&Z4Z8W5C2mCA{?+ZcY}Pnhna;we4#%%uuA412gNh{vr>nOV z4ke}p5P$49&B9b@&KinY4W3GclUoi$YLCN(3@n0hFAx|du!1yupH@UEw;Vnp;0Gac zz`de`&kI6TCo_OPtc6c?7g1tmz__oy^1|$G$5nq*EjbYbvxV6semh36$H^1c`6EQ_ zXCb5J8}(g#YIh@6KeVUF*J4>>(dO?t^-{2O3G7fjFp4U_$1ufd#n;5{ZZe(B<9mJE zgx8kf&3|D*rWQG;kT2z)z7TUq{+5T0_ee{?s42k5;4T0WEtDwYI6^d4A!Ry6Ru{9f zx~jhVS5X8%jToYV0)p{;xE+*Rs_^9}J3BMEHYUOFBUg1vDPAT&C)JEBO{`H%tnf$=< zj`Ka=24504CtoCopv8*m>F~GFg^ryR`()t-@mbEvqQ1}L)2=3Ei?Ud(VZC^Ne;r;9 z_|AQpiT<-no6YFN?BytDx|i&<`E`L&!cA&uk^k`~N$NDO7;XtkQG;0HeDai}=t~k7 zlI8IB)=QK(Gbt*rAL~wBorjsOCnNIxw`E63GYrayn#BS+OKi5)Rfih}`zj8mCk+jL zbIx-t^UQKh3yjx$MehfXNH!=(ze;zAEQlMG`p$CkrS;)WNPwb<-xb{Q+_Fmd{-djY z*59^re+}IUla6QpyYqpAiwYH6#~HHMQO{RP2@5Nt^&8P}@M37X5EeE0p1Woa~IK?cP*>{ zoNy3MN1j<|>|F8&G(y2A_EUC7;+4E{I8ld5PE2m2Y$dIdYA@bEn6##l=4{N}CHdPI zY&7=VnZnB-?%>e9LNy{bB2-d3Q&Lm@)xcLy)U13!GvEC{vBS9Twq>^C(`7WWIn2_7 zbYpyKLfDV(Mi3`y^Gh%G<#>9(5vz)jky+dO+JxlVpXlO0bzaMkNPU+NP+N~QOID9} z$^U~h-Q7}UGk?HFDq8!#uEpKOz2qY8!jWw0^>6bjdm+njTzI?<4gBxt?RXu#9RE7# zIEZfa|Ha>1+WNM*yXLXbGMSq-b*#6UxJ|xheq_71yOl-gB>I(WjysPnf>(%h!#}~p z?JcX8q1VHt)c3r(M}MU4c=o*Nd;-fgEINyk53$vKu6WT3+c{Bf?2X362CSZE1_PH9 zDK3fJZ6jJ*e=^wHIJD?Aj{^7g*(SHEOKjY;DiW7eTjv+$Z1io5?CNabJZ+9sS4`|g z7uRp)wmC=fE+#*Wnq`^ayBK2|YhyNIrM931=sX74B-k#UnICK|ll=U(X#!95-Jjj? zO|?xeeNBMn=H|bi<(piXH`y}UqFC5)sA5REuza*vNHK{fFr@9~93M-4VQG=ACGN9n z3-O!aB6Ip<3*%L#3q?|3u7dw%&yO?h=|$k}kZ2?MA{B)CidiaLeHTJi`P?RBsuF}U zoPZ-`y`fU9e1Mxqtj{1o<71A;IKApI~=;iV&V~%nT#dZU>?l$I4+-?;Y!IP4P zeLb=+Mh(rE-_b9-uNAI39?{qfknX;mts=Lu1zz8`tjLXgDKOXE^uXH{8BtPDL3o>$ z?kyxJ7=1hRBz;hF{IQFAKmFQskZvV^dpnoqkflyEAu!{q>TYuV!zA;j&6dsN!2{r{@whXg(GXpccvzxOO6{B`1cKr7Ec0%)WH*AlK_tyifDuK@{2`d-#LUr>s z1ka2ndZ|Z?NK#{n5O?*jTO(}95C$Tdj)e3D5@30ytL*c}-+wCei9v$y9}tqv=-ZXhuX*!@d^tAh#R{pu;j=M#1j6Ls}Y=NAz2X9;rh%(h$wn+N-tf%ob~3D{?0zOvM@ zjQFS!HZpuuQ&ZMq3q{noZ{N<&T%fV3sj0ECLMj72Jrd);dwa;A1KnHw=o#7A=t90q z{UB|9%<`=W4Goo}y^DF^kI_w*IVTGCqe4PV>;594hGj zhYzFaqO1M=a&>-1nhVW373*DJM$?21WMyTGzM+2ZY*Z%K(b0h#1D~I&%=`Ey0&Z`2 zEr-*_g=l0WCnhFbjB4n)xm{PE9<^R^_Vo0$J)I3s7O43DTbZ7iSg7%Bm{@+}x_hvH zfEz@<*l=DT?&Wp!b2T7-;QbfOms7K|6*))H+V)_w!P3&7KYx@nh2&)oWMq1)Ee83c zTs=G-mYaA*+q$~Le0+Q+&d!F@`Oe99!M}>hucl{bk?b%ef=tmd&{^5o7?e`P6j$o~ zeKp_biBZ1OwH!SbzBuKzoylwShJ)M>rkssxLQRP!`oYbN3=OHNsX3xcO8#cNaqTv9 zPNb-I|2vbHM;k2GuCm2HGB-EZ(_`^>rfi&(vz9ajo7~Zx&PIM_UsnDZz|WXuC7e{ zFB5Gfnee|+^hH-_G{26LU)Y!Yf@web6Jz+b#ewGAw{P=j=tG=dG`RL*3e-qQNc{f& z+v9K!23l@Cdj0+c8wm-?jt)9GKNs}ci;<&UsCQ>kZuu+WU2mh`--s`8O`CdJ6qLmvp@9gY&JU{tAEVlSwONSF;kZ^@qo?KoEJD<@~b#Kp_ zu(7go#BMfnn)lh**p%zFEG#V<7U68U+%{4K@^Es-D&+g$UyyKHqW@H+jRO(-yT6~P zm=D)RcGHEmdY;wfeZKR{bvMXV2Ax90>*U>2*?)=A+jDt1-qq0oqw!~O(8$Qh_56&B zo4dhoWvSMB@-H}wf}YA6lIGXP%Mv+G_fg~(#x3fM_{|>2d3J_2HU|?HgKqBb4UUU4 zMD5_1VqrzI8Pu<>a+>!lWr?)tR2Ua$-Ye@cnGUD%YVBn3J5vwi;o_PqC zolU7UIyk6d|AG!49{!zWs*(&IXcBOYudZfg-QJ$>UgU$@Zm%jRE0-U$93CEmlgqIf zLBeh2qo9CFe`Zi^JL~YG4@Y9A+{nPfdfI>L=5(`UXf<0LPU35BuDScP@68Dn8!a&K zn(V-8JB1n#siP=Fm9w@dBN`hUNf-Qjz7g;+V7~qahlB}@^CM6{3>a|E# zF>Y*b-o6QZy8Ymz*#4Bm9n zENgfH2dtO;surPpdsahEmj_x(OpJ__AwvFl2|Jv;y!o@&|5p1R{?1nPB{0h(w6!I% zn<$@W2>TM^9UUE6Qy(Q?zy2uBCYkoM(Sw%O>U-^wU$9qJ?%|;z>D>Jl=j51?RM3Of z@(P^g1Q3^ZsO8KxmcyNGzE_7iDxjR2nyIPb{2ZHBM`6(}RegN*jrj_S!Fa)ArK+i^ z395mc8&5fXUlcj`eG(`kA;Ir_m=98ID3`agvXYmV4+wYyYdbx)p8N?TmMP#)O+%BL zn+x(|kNM$Ze-f0r!otELje-deQP&+MLqkIztg5OiukdPu-4Sn%PURd`MiAZ~;L6R7 zkBeKVw}*phWFq90lp>;{q9P*f=Bw$LsWq#dCuMy6pB}uQ*zP8a%GQ4{Aik_bS)vJ-^Wpe1@@p1n`?B#E*5^YFqKuJah5vp}u#e`~WYl%bURa9hW zZk`_Rxl&6@OCzFYb7iBo^|bH@c1N>7a#G;oN#4UIlllEq5q%8tG&eV=5Dkc!CKmGI z$fR9v_UsG4zy3!=NJvOTgoKD_rVviZR@rx|cshS_;-nu8?#OFz<6vg?@kq@m9wgHV z3BE!Z4(p&9jpp^uM82ZAnHjVOimSJ`H*Od$HT4gT0%d3{#~ew3-f^k%muVLw%3coe`4 z5b)pAIiY}u{@j_SGU|oueDj1VO}j!ZhfA4z6hiCa*x0D4%{oI+pfRxGl#~>3Zb6|l z(AR?zE72}1{2BgH8)Q&8z;FOOroU zkb-g~zx4F>wgx=joo@D7UjBs>14k{Ni==P}Kf(RKlc}nDa(DTc&v9iaoe#@)#1RkG z#KhzU0f1Kj$Gf_`+6z#;z!wM*!2boNS|%Z3;m60vlKU0raj?kFA0Ib1%pUF!rdgoM zswx;L$-jWh%^DE`s{xhhDnIitA5G)+r(cxjjLD5B(>&{TeK>0V2cYtWX zwP%Ze!o$NG{PU-}x>`s`2zm#~7@xyR;Z>KWHEjJ8C>++PMl!;}!YEWa<%T(B?SV0W zY@MsB9xm`0l;8Qt%cHy<8XWBEURzr`D4Yb?eyf#Vi~ro}b^0;um*VUzXl-w=@QzI( zOa7M2r{Twsk1PIXTPXB9ySq9%oTyFh1KTcXa`{<7K~S397tHNpZf@>FI=58u^lxE< z06J=Vd){5_^T*wUxfv4>5#fFJ+uYpLu)q`cItiL7b6jm*^}i<9JmXJIO@%nDC-MM8 zfDnKXXZ+RfuaadB}3s0atKOG`^9;)cp zvlTqQnhT$>5imkT#mmH@v(?JUY7isFWc9>h#iw%yB_V&YpA;pUiECe*jOLT}q z%(tgtdjXH#P{1c3V6q^4<3g+8H|<>E$TEcU)NBK})B&`0b8+cR2=ZikV2DXi2j}L$ zOH(r;E2|&;(FCs$C9!JGmC4_GsSAKi@`S}5?(W=l)lM@r)g-~D#ibx^A9uXi=+8!)ZIZQhbrb}QT0yB!n{cqt0y1K+qmuF`Sm8PGH zOPS&aDl?HVNJFTRP3#q^@KHhgLDk0l;f6ErTUr(1@Ww4Z_DhYiGcX+-O5nj-FS7sC zZ;$87qEIzBu9lb2*`SD7TU+bv>&wW<=qi>=3U1}1n@4Rj~95Fylx_d;MN4;J!VyN z?d@xSE84V&gC>UJ=oD+~>YS4;cOp`Y=Z{z00va-rXk|IEZNo=-DjaBvaSEHiOe%pTtnBBF$0F;OV zJoI93+`JbMFH0rB0dD=oG&QHdp9k!M%<(*aA?$;1;(W3uZf|c7wU?&~c~=+jBb){K zjRTHF+z<$uKu#P4_IIi>JV<5zl^LiBWIT33VOSI*rMJ0^F+=F2JYSXL00Hmr?%w*} z1zvP^NXST8XhhyEj^ejIuD-aF3h9QEJO$b zH5G{BlMkE@HRIRJM-^P?leN|wpx7?d*`80LP@#9R8eDNhH#ax`u^u20L5SuX94P`H zPQ;mB@$zIB>QuZmrX<>d6tZ1d0>AU=nO5wnHCe(Xwb->R8&S{&ee>1eza%v9Hi+5~6pzbiie z^hc9f$>Ys`g0#Y9b!w^>0B)mXVNp@AyEJC<@tOuO1(Zsa&!2)-)q~|}ajSGA{G<}& z*K=c1QoJ7T+za1p#*!@6d{A+4I5uIb2V4S3mmXtT&WvbKnE-o}q?j2Ob)rz2n)|Kz@Gy$jAs_K0VF- z4BE`6t1!o#YGE*tnYp<^trZMZs1R^>VGS}&i^z~pwdIJ9TmTtCVu|l(D9JyB;wKP7 zNrq7ny5ZqrkmpN{&gQPJ=c|FwnOP>&h)O2UWsJQA;bgDv_JAm91Gl~Y7d>$Y4ro#R zol5)A&`@tLz*&G8wYNLzj>St8a>~lRh*Ar;TLbZ}{`Y6siiu)ONySx@eH(CW{A#cA zSpI#%BZdG4tjx-y;59itIZ5HQO#a$It+IZ@!30M`d06G%i16*)x3$vI9 zNev1rb-3&K&TvEodJ|z-&jtXF+nbw+s}v&&hN^DjKG7Ttgy1G2O@G=%Qib5mWx zJVyPug^`{8-_o!1u^h=yS@8FFck1WNp{9i-$oW5|rKR5j-9M2hzu6lJQiJyw{lRRZ zT5d(_-JgX8AFw+wzhHg%u)8)SE^vNxYM%d~UWD)25JUGMw$v7A!kn0-EkPa2@zbC?5VN(l6&eG%Dj^35vynk!J)S6GPEHO$WZ$QUTVS{(&fu&uQCwVJ za&vJNqAO4D;oHuZ3;W%Sb$mi=LS9Z_2OB5s=c_*- z8*c~@;N#~BOjQmi+I<8SbFt3$-@yTMqC)hGH)bC`T(88VHnJS^d%GxmcvxD}Z&%{t z;n@aY2S*Z8P^iqSYiLXYOKBwI4c^~STf)rq;)8^X3%B2EH38rxgFy0ooveWc#*l(7 z4Lg{5hF@AN+?9fP=FoJYNia%>$QcJ_2|KalxMNrmP6T1*b>NfM?W)J zu#xGNGxqlO_+7U8)56P=AW+ijxwyEfsMZ0S2RNQ_xF>gyJG%j#5+?sZ8yn^T28V5b zN`NlBJUq25IX+wv6>gYn?(UXmkKc{cT7adOmlyDKz*Qve>Q3lFf!z8l17g`s75_j2gH^YkT|_AT!Z+Mu7@MhX4%a%d>!jl6`e~DVVKtx`$RFk}Gh*U@0U;<WWA@&e^d0RT;az^$9f zx|3TG|L42VA-n@})}@G_H> zTXHt28Mt9LHN-_lKY!9&B4c1|6U8Mb^MRO%e?nrBPet#_KAqd_i>AYs2fhiQ-NOEN zZla>1Q>AyeE$064Lc-Ap$}f4f)Tc46t*j^;j%!bjzQ3T7($VpJxH$!~9(aN?At-q0 z=;(!e*{Y1Kx4nq}$>H1|Kfp5c%gV}Xp&zld&`_FiGe|}tnWtXs$fI2hvbO=P{>1^w z0~nG5%bB=98f%y8#>T`{x=btR+xtH@kc$hdnV3B9jpu?hDzoj4QJ4fF!^5(%v4IR& z_>BJv5u+3Bi3z<(^IQ5$RqNcVV6kbKK=Y=i$R!W~|L4c+*>a=jlg`AGvu(xS#G(NY zz?%9A_SAlX=OF`t!MJd&Rsi|pyHNcUuK$nIvmOd1|=`L8rUBm6+kS7P3DB1H$oa3uIp@PZ;;p$#fGupL^ZqZPkcrrf`S4M zq2jC_Krp7VlL9e!=Bmtr2y1hGY?}BE-^GFY`3C_1`uci5SA!hYl(;ieh?GxTqyz*s z680DouSmUG*T!iQYLuFtxUg;aagSUPBO@+k|lYy zI1!l&{16a7C@7Id2NC|kbR{i5ezL8NYc@Z`CR)LqU3)+tq@W$xZ-6VtmG8vmO=*9KR^9?E4A%UyzF0r z?i2+_RZ0r}WzE`$pE3ww>j2{bvKi1Uqb4^L2>qpyuKW4UC``Wjf-{JSNWeqmr%zp= z00aDxjUWcJAG~2@TRmX(e?I3B-dpGrL%Mo;)0JH+$l|?|^YbJ`_)=hP|0!tW)`+k$ zYqj|ZuuvB#r}oXUn^HMi0hg_>RaFB3e*UYx+wL3lHM`s&My4hweJ}QK(iG3DoYp0H zglej*_3Lc3KqUp<(21LXrunS6shL?^Qqony{O4%cmj&&JJbZjQ8}Aa{IXXuF)BwEO zxW+OvENlQ!`fJetf`IxeJO0WKHU9bqMX#q78y$w=S_%ZX^gy7jtt^ZPx(o!nFfJl{kYMwTX^_0T3==tvwjvdWAs)@U%U+ zQim27n=3gepw`FwbQ=u7&BEyu*-8yc4S!8^c2d87om4D5K9;LcYS3`p8+l;ArNul0 zyjbvofrX>3-Q7*><=@`it2ViSdjcl$47_0NGJR=xH@A8q180VZ?SbC|%$HOCjdlKC z3wX)+bvDzTVZAEAY@Yb-eGbz;QvMhCA_jFfiSh9o+eu+unrxD4k)Lrb+-GuKe)-*g z+b+)6vc~k=JE8g=-uHmb>)2$u`#xTwdHFvouV_&H9%aY-?xF}c90>vtx6MG!@+C{Y zK|xdHcz=I?!j8AU6KF35EcI>jrX}$)VNaojFTbb3(MtH9DH zz77l)EaM-Sr+_UY|HB4$Ub6i5n|4rP%_~~GP9@ws$boz6{)H?QlN=QSh;5tb8T;y$ zUUf*8oStt$>OGdGsU7d znZbk5==Zkmd*fEW0hPXPV0)b5F|~BGF}~d}vH3EY`vFS=S<4%EP|Wz>5HU!hcCby> zYFZA^Ni^!YTIPZE)#3aDobWU+|B3QJA*o<{^RE6WE1G5$U6|CzVtu-?nrg;xFpjqh za&ncm>aU$_mKsr>gZT8hJr1VAo>Qm(7#Fc8kiv|jOr9Tjy@2681YkxJqT0(ND41>n zyNuBUJWDG0?RP{(L{BV*7ZG26U~0b1=yioa0|%-EAUv%P^G{P2P|;OsBx+h(_-(r< zaXJy==~qg?9F?P`j{RC(Tp|fP17MW+_y`PE15XwlbFE?`VDkatM;r<$GRksfQDGrC zrm9>w;@A>^HdEtn^|OR2ICJ~UadEgynZT0UBzPuL z#3WGeoW=Qgd8fz6!@|SO^|V)a=9{tGUYH`gP*qlrQf0JRxG0Mla$W+*XLDl%FgGA%07`52 zAxW#N$0^ZIj*qL+kxefT4-QJIp!fFnK47c>)e#sNXvj#$V>Jg%a?RFrg9uaNDM~t8 z+Wze`PL$~svXP&2*xKO za(yvdX(|~j7eY4m-`@~6H*rP?3Me4_%*#tiPDX==%|HMbC||6D8$|1sd>n;Z4aXE1 zbAa;!2>qR3P|)XjNs~PIA7l{|GsX|3y|%Y8pKKNX6k0rt0ENVW=1D$x13*xPdKpem zPOaDcea@Db!xwI=0hvnlz%kGRi6Sli84&o$NQ~7z7T|cjkpR%xB-P#114I>Y4i5JA zfZ+ma{&xX`!br6LKMT;(!HX)G`E0F{C4zy10z}OCZH5CV1=w!jB#J?4HSzX-uuYhI(Bq=^V9;D1*HPD_~HZg^Tj7b)CwY4C9 zfK{NYrj}DuGWhJrN@$@C{D+|-r7b(qa!#}q_7B-vZy=`1t9H!?0CoWQS8Obf!|(>| zkA=5d*bwiOsw4*Q6Pjut+-O!XH02Dv;>@_aoKKbC@m;*hF3Y zKiXni0$dvZ{l4m^Nn}>Qo%}SaoF1&$-{jg_o+OLu`!1Wp(`|7Ljhb+y+S z6OEWO0xMm|#NWcvu>xO9;lB`;s8*v&JmVIxxJ}=s75bWb*RyuUC7xQ6+A5GDiELOEoUb zVR5|l3$y@&6{3TQlQE!-%uH+Lh#O=GczCplBmZVf^|(Q)?FlD(PK;9h6s>L20Q>#Z z?@?@ktH2Ni7)iJ~{m#;I2WTX~xI3;>Q<9Uxl7$1hZ!0S~0w{f>HbF*x7xD(yP<(cF zHt0b6um}p0p$+x-gAteD;9wOmWOVc`{#RUFxSNik?e;^F{~I7ZIgVL<(G;6B(V(v@ zFMrEGy2VbtCqMQP0Znsq8h$McLFS1z1b8i}>FJ9Lz~u)9B8~)590(970(+B3z`_i{ zPE`tRb#;a}51OBtP&bTqyj$uvizXLDgg{A<6B?V}0zLrnIgHfQ#F0C|93&Zm|D=Xa z@?Mb_a20NdBz-p($Ez5r;Je)Zb5}0IIZFK;99}(vlp@N4SWQ}ggZSslMB11+C{w@$ z0q%t(0nmYr*Mn!3F3yrXflNzbW|R zi?RfA?>8`fkT3Fx1I9US6YMX83!|XIYe<9~_=>>La^jzBNna>6(I{Y{EmvmkrZ zJwzg>ozj+}McM2d*f_wxK>1317y$?7-B(Uq+rJ>SOuzvJRZ1bb1RsP43JP$*(%c^U zrO@5i$3RaHYPu@L2&Ag5y>oET zIIsx!0ng7xk1Q~_{a^?-bg6uqLL9|8N)?fjlM@E&?Cb>NEJA<)S66dMe66T(EQlhP z&-Yu(cl|H~`r1n55b(Cpm}xrUpeF2pK>a0AU}FbG`^6AFjUw8>p6mkw-EHK)PA0CoG?&1K2{`%sKm7N`Es=(VbI?+9;#CC|OxI@l5)vF4~Qw9bG zKqdh70?VSIq1lvd%{T9h0s|tEq`dmg9&B&B`M+igx=TFoc>a5GKH2Jzr8!z`;N#-D z17)j7!yT#w#ma0Jq3aXq_Ww6wwYQdx4G4_tF$wS@#VA!#iwk;_zk$*R*A9|iH_1Zp z>I+2x2M^Cuqct87`MhZ7@AxM`_f3p<9ftf6cygy!%_{ASi z0h2+3aMsruU0V50xI&S}$Hv-oJTSc#XjD2R--qe=aUA zfG5JzgHS{Q+Cjr*>A5X39v=0hZ?iy3jyD6{(UurBNC{}PTg6?xOi z6x}m|A>d@J1L&Gp#!bW!N9}j@M9uL^U`Aa2O;1Y$PA?fmoCHRifCb{E=Bx&^6fiMB zih;h8G>tc}&6E|;Uf=@yxo6D+`Iq4nkV~+T%v@znjRtCMS#B=3%~athBrNa=YPIP= z_mCiPhiY=3hYN zn=}9xcoUGIs;V(InyI5CHr!)@gbFn1&)~^DhEg~`jAR5Wu&_cW*VoAj3SiQz)#viy zzn1RtvcbMHIXO9c4>~keh7_pa^g>5f)d>I|_&hL}rV;YJn_69^=!#KJ;~D7b$p==1 zwzl>n80-joWduI!4Rkwbf{>Ats;j9{;iGukt*##)W`JJqA|hDwTV>@}EG)piC&ozZ zaSk!z^a=KPkj0`fT`LB0CS=oJYV{}6@p!)ydr)f9_WhuOKZ^VH>zB`)H+T#x{Orc1 zxw)SNSc1i3GBOVT*H5Cw4dY-n!&pC@zKL_%-vIih(?ouFXy|uK3*Z&sP}P4K2JBDd zgHefbbOkaa)g~?YXjtR|Q$US_*$cyMn0H|7 z2b0;e_?>^0mD#JSs{?Bc2tvTVUl}%5I+TGV7@L^DMGff+#X<@KE~=!YWT+|d`L=;z z00T(@wayV)N}u5bkYHg!oL*Sj+m``{KPSi3-X0|WKLB$$5=u%3KV%dc@xKfBGxPKF zzj;GK(e3hrUI1z@jHSs@m+Yyw1MWQrIy&GU3q=|X;6MO|KlMAktT!13%+Ek6qK?L( zy!!b)fP@FF0*=OO&};>bSYXBzy`f42FF`MeORLfy5}WfkE))^Ji%(sXQ?8 z@)b;a{TUka1AQwGkJr#p#v3%~r%F0dcS#u;zXP9PiV;2^5Zr-gD7lE=4N$_Mh~ES9 za_$H~(c=Ak@E%XinqnZEp9#ly)=fgr{&zilvbFN~?O0|vN`_m3iO*i)>l6MVlg2T- zH0-mJb;$r9&^<8W0`Vj$zbOu1`E|Z~8wMCm-URB`HjXHA!KCNwr8ka4V!2hK{&!I% zd!X|w@|MLPznB|ND+Q}g}1cVbVOf(!r6_I}BJ+x(h6t4)&;KdVetOItfBHMIyl z9zY$sHGt5Ehjy`Yw1naNp&WhAppIOKgYyJt;5_5N1n$gCk{m4$To*^7ENl>Xc+da{ zH3h?#Qq(x~VC;ySwM3^Vh?$M8tgtZKz@g9zu*erM ztLy5@xZa15nh;A-j{~*^G+AHd{VACGK@1H=?*fC(va)^ukEXMZs^a_F_*_C7>5`O2 zN|5eOX#}K^_=-w*cS)yoceiwhv;xu%QqtY;@we9NA1-xyxifR;?6ddte4e>rOg}fs z@ApQ~#D(?}6eHNk$1_Eo9UTv5Dp%a22ue@-j3%v9!CVgrBohXL4`HH|MP^3qpohP| z_juI7;%fg~MD6!5h)nwIX2PWBL zM`>|?VW)*9{67Z!9v5^`K%)vQXyBfI!h;meDPvz5%HRb;o$P>~7I69tHm1Uoi#!rT z@+o@XX_bwRf0Ym{eF=311ziO+2o)lL&8es{s6`uovlD82e@2`w3?F1-Yh;v_ke~@_ za6-bgh-w@#fxs#Rx3L3oOF;Ad-wv1=NU^X0WXK7$I!rSDhV~aT@{o93LMOvKdq{zrqOxmO_wN1TqycU6|O| z8f$AeQvZ3Ffa(Uti&*HzGepFt4)08}IZ)@bzxIzK%cpizIASrseqEiF1!aasMQyKy zg@!V+vi>QQl$H(({`afH<0jTEjy^z^CKf0MA|f5Ft%6=&f#TRCBwzxUR|hrVx{LIB zaA*h>4Gr!2b7cjE4XyU9ET4CZba6spQUG=?7})PECMPE;KpnWf_;jC|oJ0Z2e2)N8Tx*? z07@Phyo(h}&ZmJG_|K}m5Tl_3v?&)0O9X{n?lS}=B=~WiLy>@x5ad1CbgbC4G{5?U zAEw}@iyhuNe`jh+L#_ha`yLoB0YN{7KF~8tF#P;wm=dG`f)p6|54Y4q5ax~i3X~)? zw6Bqof3Cy<6RE8|3*_=^@DL(^-w|m9KL=NWjO+l^MH%1Y6M!CrjnTLg*nbJ}@xA^1 zr-o#Ngjayu<{$hAlg&s;x0AsGRx65J7#$Py56|F=A26T6tO4`!Dt`~|GL~wh-gPeN zAjv@-s)?1?@IqK$FM3Uyc>rxX-O)%F5Dg4R=s%#Bxm~;5o-s-AXX^XW=@3V5o+j$YNVt{-F>|!IZTGo3} zZe?w3sv;srfuHi9yopIpeZ6DCV=5TfYfSo3t*x!W9GqyjTYL!gZlI$;qM!%{1@!~% zAE*OGKdp3h=70|YaF`3=FHuPZtuD_1a9>YfAJoJDK7amOH;7^g+Vr*+uR9Fr6zvq0 zM&L>IT+wdAnf`69o$6%^D++)IKh?@(Jay13F}D z%MrvU!07->2AmP7L-CthU@lX_b>X^1)?0pQC%5GF73U`g^Z86xSp8 z*OTF(X-y)Fu8AH=K0Byij0!khrMri3Cu>qU{m~n6(ph16EEJE_{~DBuESLx_BcmK87H9}AzySc!19Ytb$l&$7tpgAn zKx37_R1b_v00D!07<@46)L=_x9*Rbib1wLiqv>?BlGyVl#3U~#JF$jC-SK}W=RP=nRd-ugNm1W3_Nyt)s011;C0zW&XeU4rL|q&1RYxq>T* zc2N*n`LFx<`t|F8GEs-+bP3pQJbIUxg()d1g&z-6oWSWHg63-1q_DUc1|1$A0{7wK z@>1COP!IGsYBiubT=fz_Udi|!ia@=s<52yn3g-Wc8Y{4!cXf5SMD(B~p97(TMelnwmfgv^6fk*4 zM3<<55<$wy2j`CpW>3^lk&nYbasf5HQqQ2-fsyK8++=8I4_L0-GQ-W@Pr}lV-PTPu zYkpt9qIuOPfUP8lN${Jax>Dypvj{-E|(?CcXDBmqnVCL84_|kUv*wF?5*FQfjZ~rl2PZt&H>o~BrXNX^*b6NE2Z*erJ+c^ zI9P+q0+_B~3NXlWrcBn5Mh28W1OZca8Z~R98ypho1I;WfKK#c%KMcqou);_4-@oREA70HxokN)zzYMd%x09zVcU;dgG(Z}&i?LU>RE(AMeGzRO1KS7b12aeG`J zgE#u+@5DT;7NKikunY#iLd9e?Z57$Rz!cv&TnKdNU=rQm+Wpb-$<(wCU>4}!A-#e; zJTueNj==kQqYNhR6F)4tcs8uo1xfVHKb!ml0vlmb08dXA_H;|A$NAa^@(fN+P9^5t zU;+S6-8yjeuURj4gBfnxEr>v7YjR;Bl}QL@1cbd$zstm~#-J+CJ15Z1dCx49QRP`@ zwu7rt_Uk;lNIQ3_-P3)$LVqQSsCu{Y?KFM}At=q}$(F%9B_^+!n69_=dre*+uhV{S zX?Z%IRNnBuKUuu7|K`_Q11iV0mW)hr2B6rBfM8g%{t@h_U{C@+uCF&27uQeS5+)$C zy8y6}SuC{e!9FA^>Ik^8z*crRKQHQfKEU2(w;R2_=gG)vr1d^Sg|&EG6bALM2br9J zc^AxT9>5jv=zIUS1-3G3SY-q*4KOi4F@$_P=)F5&$_t4}NgKxnUkqp`_^g0sr!wzF zdVVcY^0UL+8?fgfMbJL&uB0>uNUwh-9bBhdb917Tc$0}NG4vi%0jH6b6+KrTBLWyH$OP%NxoPeu z0(&PtT_0Qte?LEV7lly(ZK%t4&4y{90rjWBer60P@Lfm&aL4yAre#;oz9S_5fh4BxarFiI2t!)|&S%#cI?N7CQSiJ}=(F~-gEUGdc?9e9Fa6mq=9I2Psr^X)MbtSWPA2)#P1!}mBRR4bqM}fdD&~R{YP(=4m z7(gZ#&t?}E_5!8{A*){J?9@NV94y2*GoAKrizdCuu>~;B1BfCWU|-?k930E(1T`LN;Jg6~?!SQ5y*)Qj@vpq%Ez_%Y ziVoH2;@+n6e*u{*Vq#*hUb~xf%7CJv>nzcNQ?NUNwo$WL6ZFBrqKnQnWQu`AL4yvO z>hOpNox~-u&q~8<`Pq_v09OFa3Zb|MK)=!8{07uCP+RGFoB>*@!uUF*ZyoIEWo68J zq5|xcP|Gw3zjo&^TGDLVHLX&=c$ck$8~``%kgUjU(i;L)(XkAn7iMq(kM{O{0$mqi zDUuE;?ok4Qg23l$8@7SRLPlnKKMbM55;^oj@~UDK={{tM7sqzSYZ)ZLGk}FC5qNK^ z`Uq3OgW*9T0l;JG0jC1&hNIbP{|;?$=Bm+u?*AgCCkUgBp)C%IQL28PuVZw(0B+6K zR<&NOSTvB7dim0TOvr5tNH_3Gf0tSsi;9r91JyJjVSq5F00&9uJ-6jl2%Slx^WM~t z?rxK)76FZCqtfBzLi3Z8aT~mg*pie_769(u+;kXQaQ}Bts%t7J{OcjSyu7p*qAW|j zNisDMr$EyKtgR0LSa^1}aRdGR=Ait5Wr~j+0D<}Qf_LW!NDKjA8L+=-5K-Sj&&j_T zBkl(1&_GAm10gxk&-wja)xf6%dlhioC4$ibRPoW#eGD)d;O&4^3o?OV-PMAbJ~`)G za&oz0$G?OP21)CMAXwz(0B8mk5D@xC;BEv(MoZI~LF^+B4y1CySn+0dl~+kYVIQm` zP?s_jM8tu9e(1Dx^D`8z;skT^e{)uBY!M z(1gY6lo{ObeEC=kG zTCoE-7p}8b&6k3L9%E@uD}WaVPCZ7S3BcnZ1}K_i1mop`wnkC@s=V)Xd~G`4>L(&L z2BI&K3GngorR7Fm)acQT9Nl%@IrOJ?`p-}y~X{4z14S^wa45Fvg9De09r~g zh$O_z1Cg=Dz6RzqPe=uBkOB}+G9M*rMj5ds9j*cIE-^3#CJ9vrJPsY=;ToVsVPfKf zh7kn%j$aA$a87hYKn&Gs0a%*z!&gG3rKO<+q+u1-zqt^JZ##8b6|f;hK&?tyqHwXS!H@V0k%1$pz{Z5`B;Hh62>K z{JnkN$Wr~5OP~pY_(mNlSYU*)OtL<8s(bst;bJ$5&CrA>2n)pULA<>Vcn^S62Z#fR zU;t^kM4^Z|58P8M@9RXX;j4kVNi7q_RDZwP<@L&O@c&r=|F*Vq;DKz`;=loFXBlYG zl?w9m02#0Xxup2*zdF`>JB-&P7J=fg0doKbAE2ZFQiqiLzmL+ZQT<7;HWTvG`$mOm zHFhE5AFZHH1LY`R?IT#dfD{AV3gD&ztqJ%J;EQOze?Jcr4>fiu)0;!4HCOWIMXy9} zec5tSSiRozMyjj9|L$yNq5@6Zz<>o<2Zr7c^(}YgK*th^yoL)mrOa==Zdq@1>*j%= zMRm*?S4&D_EJ{hSEI1;FVKd5%fImL5Ee4O(?7O%R9E1@wsKRWH;78$g-Sz9&DR84o zhJK{{td)rZVhb4STtGzRUsoz*{^p;yZ3VOgK%fEdroOH1VJP9%a|*8)kP!f1>6O#@ zo&IVAwK^D`oCBmpd_}WXmm?!UI`Ur(2BZK0C<1tu-Kk<+NUz<4SjgvJas|{6&=qWR zp2~muN(T0=pMrIuE9Rf)zrDS6w44FUEjcMk3(z>PutaIMzVSOUL5p_} z&(_w;$i%`PE+APa9Zm$23P3BcW_AKSD^MHi8XLW@cc>D5F1^7l-y`$@+G-QrvoA$4 za%@aY-L!UKyY30X_yn@$EA3vu)&MpYQErp_75UWXd(dgFtLGxQ~5&e5^Yj5?5kD`mFF$wrFwyxhMcDeCsP6f^2_y z#Qu8XE{T?w<$DO4I;LP@1~>l=Rr>YEF&K!W)mK^lJXo*-EiM9NiGQ}*f*u+ftD)k27vw6G90Y?bprSI_s=j%LuMHMz(I$&CLJSbT(!WA z{3libL$`K&gf0LC+gky4`2E5W{0j+5ZB`aIEF?e&&NX~_Vfahxg||etwjuMgYNGJo z8H|gGs$h~EJ)HJ@{&qMRcH3LQAMBm%YA`%B#7=frxI|tDP*tA=Me`sI5yT# z3qUC|4Y-3Futxtw^%8uz`!o8&OXknk7N}Y>l9H=F;5C(o9q&p+<>lq2q!0&e>!Lx{ zz$*i!nH0xIN4E+UXmBho6EiZ%0iU_g1uX5sk&*C_kgPeNyA)$*DAM)Vivor4KdllK zhMiK7loS${M$VoF+2($ACA+43V7$M9AFu@y3IKwus#HFngGU4aUMD5OuuOw#ix5z- zz-9rDoruTG1ts|8U*5RBT2 ziu3b>%a?xj>ecYzAY}kB&Wx18Uy5_)fgke%7M!S79?uWtTuKpEv9Z+~)h6 z=_qxH<=dToC@-J7J~z^7DEnJJssw}B!!adpZHyG~8cV4txV8bB(O246 z@HFfY^at94qZ-_*Mqj{uTwNo6<^y55So3`|RPU!TXeeBU6)8v)*XIcV8Kwk7M=KLu+IWIvhl?d=^>#yk(+3@G-#$T9 zGrkA1y!uASK3wccD6>y(wWNq4r``N*=|r~hl)%u}@iCq)3m~G@L^cJk(YqoTdaeP+ z<13@7S5F;C=snXV@Q|piaE})+jKLgXCd7ng7#RgdiOGD&Igo&=o!$|p%!XCf2@Q&6 zX(1uJRIz^PMQ)@`5YWv;@5*HnI3;wI>DS!&q-j*wS5|?d5l;`h^CfYI291!RL1Mai zc1Q&i0s7_JDikH-V+;{Ne?Fjk7QV+~!-BNBNO<7hdUD-85oh0C=#k;50fJAHG64Id z1lcFwoO9mc*73>(ijY-gs7%df#b%L*v@wMm!pb(%K)a5+gG1;hezr*)KF6anZTpE! zSi(bk8E)$O>tOt#*w}P&K9v!Wa=*UviEgfc!|{rjp&0U1)u&3;sqi_K*UWkb>^uh3 ztN`lR9MlP%sc9Tjd3==u2&17Q5(^sQRnwq>7Xtqs4MLzSRm4<7)WE{x$f7PQy~!p= zo4Q`;L`85czrdlu3;X845@VM9SK{~IBt86;b|W9-Z~fE=31tFk0T6qq2Ns)Q5tX1A zQ8xN4KY=BFcLyT)NCGLfgP)^W@~Qc93y-Dkl0e&%tf-$anSx% zS*dMMTWGL(V+I4}V?!fMdsi4YE-EuIDS4F?s87+MXyCGlZOT-srJ+tn zaUBc=>C0t$CZD#E=s%DEF_keNp9DHGr+Qa9ZEu3H4rM3SGYEN#ZdK_!cn}dH+E~)XWh1IG%bLu7QmjNmS0K48N*pOOKU(a0ebf zz#jbT3%Igl&IKT^Fj=~72*{TL^xm&twpsx zVatltRI@OA%k#R_ewa;s*8b~URa=giE)Q9|zV^#$vuOhfVLs%6-;F;@RrIK793@x|iLuLsM0(pHRfkSZ2P_#^_A_%y!leVvLO+ptEqcTADS}D_spB74=e8o+_?y z%2VVvn&T=ehpAyA>p0yLfBSD5zho{%8B<(af)j((Ap1v4Lg8GQZ*d$3z{7rGiAWjF5XEDpAOR&*a)bKoyS7p~(r{ww_7nQGlI8=k2!mx>a9FA2kC>~jXT+yl3d zf1VNo&0F+^utd%713$jXbiYcKq4UH?mtiBge+&H;j4tdo)lp5d5{%4jI>8dZ-aX~g z#cWA$SZLu1$+V}-8$_+ujZnE!b_dMel9M;(rczy=_JtVBrzr|Jiz!VJvC4)1S=RK! z?Jm+E@sTDBYaJZ@D;wyY&?-;A|L13ItDPSHhaWVnd4C1;qQ8ad>HLSf%H)UDf4$Nn za(N%t6DK@Z$+VY0(zstx@$qr>vmBm5`s{PBo0k&Ys#k+`^)=mAWZ;2wRGXWxI~tjz zV`6RgC-^DK1a0s1hwaAVMbU`w;n&i>;rs`l^V{C&7?i1CO=dB!7MoXdk(ETg+pEmr zv+pILgpA2gtg*HojA_ICYZn`XXz$9mXeI}>lKBmy&4nn0HH+al%Fs<0D}UE9LUZ~!ZH`rN8OEdCp`&Kef!2bS~_oBt?J*M~Uzlt*-z*op{QWFTyT#e2& zPYpZ3u=!#Ud2LNBT4#rf}f z97AN$ViAPW^Iu^--l@$~TIA%vOSk+RFBBCTCqeW!OT2 z@Cvax^!VYW680|zGe*?O;xc0DbUqzvrZV44BV`TFrvoE{;|6qRdk%b;)DMD%{DJkV zv-Sakv}u*5yzfZDL$1j#D(KxxxhY!Lzq?4WU%ge&(nM(ab&MxNWgo0tS%~0MNC`(d z_k{tK@pwq~R}+R`;hQkz+GY$oUzcvwR#axVaJVoNcJ)U6?UR124=6v}$Y`I^)#@y=Z@E>V#zIu`e?ZIEUl+n4Kg#KT(`>IGBTbGy_W+4uK)QKkhhjDAVo6lTkrKbNVwldVx#vBtauO4! z4M`~`yBZN^*>q31nj##BLpU`_qJDA8(YP7Rc8cBn0`pHr@+Wp7{5ZDulb#q$$QEga zC&5=4qSEm#4CPfTEG4^pTkH#^1sbgit`Vv|99w#OON-*jsE9kby{?UDxb+USvqi+3 z72Nk;d=3=8r{~WgOvjp^Z!{k-rbM9}EPl=gQ8{9(uhRwIc%yVBD1HCF-+Lge(ZVFvQ?yRDu{&rDc~XkY*J3z+HDJGKOHMO&f0P)o$@|}%dv%P3 z$=c%5cDjek|LS-ljEGXWv24!J(V+bv-{n}mtPZuJLdJZ^>Hdxr3XDaf70P+-8RvUl zU;3ZkpZ|WWva$_nkeADsORVBBZZNzfLXPdTcf2H0$z!*n3Duwsu|3q}h2)J0WfxzI zjC?oTI)N`)^-CVb#KV(bF{|d_P(dC{QAH#9xPIYCnpOq9YUQEG8^Q_u z4C`EwJYIo@0_h)u;t|(kyF+G7ydh>WN~m?ubv+1+=4;BU-6JIRk9PX@>4!hnKN)f^ zWU^g7bXUVO1j|dmZa2*Oy>i&oQ`Kp8!@X|LO(y@h7}a?=tbVVQ#z}F9)Z(70%XS2xYLV`ktX$coH8jaKap!L?k5#IgvlnT zXBra_^ETEwG*J|#qPGgvIb=f28MB}+ra^C)!s|@Tr(sou{e7*DO^=&Jq5Ll|LMWpiR z!-iyLQwo~aPUIq<_de#0n4g~;Z3R6%7-%0VO%dLFI6FLYQt#k~g1l;P{%pUiyta`X z_{)EyPISCRxPRp7`5;0M#Ixd`>T!e}=RIp;YeakgKvX`SqAF7aY;)Y#A-zGJ>yUZkbWPcJOo- z`(g9O1HxE)y2G8TTmXN2jmv2?`N0dg9qyA{iqi+j^gnasm`~TG5$0{YIo=Cs?T&XX zg$HL+W%F-VulzVooaD<7y9;*7SRy&38eR?MM}Fzl5$)!{AIG`nmHAUS{b&}yn9oC{ zZN78DOVd^WRltD_t*Nt%3P(z{P1Wq&KC|Vso6eTV)-Cx@IS94QS82}CXgZKM*zjPc zNlsOVea`rID4fO^FVgW;JZ)FVeI*jo3TMu6o4s?dDPn?SI}{-Q60HE;N{#-@kG-YL zirMu4xLO|vqZg2zuf5#I0zT?m?adT;ew`2HVt(%UqbB9t(5n$Q{&l~+XSQU^$3-6k z1p}QeF4X7F!*<#j8Ncj;r@t|)vT}~ut~;E3P;Zy3+rdldaZ!rza5b#_{o&6b3LWUa zwzt15HPiF-vv2))5w%6odim2*4kz-u-p{0iM-kt$PFB%c^ZoaIzPN+8-g9iEpZ*Xj z-Pq*Z-x@$Y%&A+cvdOi(7jLK};vTh-=IM^jf^$j~Rs{Jz92Dy;jJ>QN^4St0uS&u2 zK2n`I`YL4mL84{)yVWq&YOBM@!0B*-;zGyK4l(3U!dq(L8cQ5JI@|EEe36q@BICXA z)AuWX4A)Apdm$eIBva}##V0#|h6y>I22!r9FEj*DqmqnsNzU` z{5+DyEwy}_>nasL;nK%|6_9(Hv&+Z%J0qp(ftf}g86_Ym*d9%nYmCTU|6uVOst*<^ z18PV6?)lWH1$f@lX`QC)(O;(MkW1u89!j;ZFUa^OO*QpR8}6HJo-mO9z9t^9nYNO{ z-glg_d(`9lFZbxw&z_g;kH@%#)YpDCw=%+3eAV>KN&y6;!TPthG#(OB=3zrxR)TI_ zO&r*_hK8la?@%|in@>Jp#75_%zL@04@BG;+J}cQ6+5M7ij0Mi9QP&tJ!^OL0hJyTO z$J=+{xvdnJc!YtJSWtYlW-6u*`mZI4Ju0!4I)jLamPq@H#orVkTD=NhJ?$8V5iDKJ zd8V($!9sG_cWW^q^0xX{ehCU#@w1M2{IHX zvh_aRg|b)fZ+IVfT& z#h2N8$g$R&&kVC99jyC{O}(2b3~|V%#qs ze4pbWiZZ4*uv$D--%C5H(L0RYdmcsiTl*FJwY2BYVIU`PO{8|K_4(t$o!GC&F<>`=R@;hEQien4C+nGF?^JCwC zo+7J-X);8%c9#gW`Y7e&P5vB12&iLXM8;myk=V^awR)@S@(^ZF$HIYqw^=AgCGKP` zSI2lM`j=-mb7IJ14fsl&iqACo$6nB`CD+rxRBdwXIaf3M?|1)Xj%aB*9F$qfcRf^+ z>r~NPZY%N}?WXEymV#VO`H}|$OCIW7bqz-rrOH%&=f@ybr2K9{2ifz~^o+MH%BBUh zkA&8V{cK%gh}C^6!ONFa>IEq*tFn1zl9XJ06(7nfhGI==N=CA45EA$_Gx~JAD;#L9 zztwy{H#DklEkeLa$LN)A<63yylTe3}aKmxs<4DchAF+jxgoTgV+c9uA0*NK%ZAv^= zetJMJoXKP)v*Y2i;1GQ&ks(EX>}Oq~uk!3YBDUvR?haktNBWDM!&~VN*y0jz{bP`< zcE>tAUFP;1lhJ=oDbJMgzTYEYgdzKiQikD$6h;Kogyv9Esy6S(m7ib=i+I1lp%Kf9 zl|{j-q+4Vd9@P>V*EulLlWZa_qpiu}@$C|(`%uP2l=>|BW%V?QAx z4`heL(Pxp8Rd)#ejBqdcn11TNT%tmCcifDZ&4r6WvVB4GHk6B3!xY-zq{zh|_E@Wq5P7&}MKBe!cc!!OTe zth8HVLo2FL!FyJhcN=BD@A??iv`K0GLk!51PZmls0>anM3$GZ{LLAh=mR% ze6#$GLf|V&%=Wb;N67}YmztAd@gr8RrO5l_q1@N++8ARfyT7ybXK|>QOrTs^mI^V+ z*lHls9uB2jC~F`VyX=ORKzjVXST3f|66p64;qdyW>}&ix%LxTh{fG43s2&me?#!pv zacLo58DmLb(b9^XlMWvhE@uUYfe|~2Zkd1x#Rg=WSA zwY0K>#`hKP&F;Mk_^w2ve4fgBEH_)J$31g*nm*~<;72@RANGrPv-e?T05-SV(& z)LB$Q=mu}=6Z?aELBc10(W3Q|O#^J#T!dOs-`C7riYvgLYKA8=7 zd7AqCiRz^2Z!pogM{k@rJSrFwB8=jeAE?S1pS!x!h$=dnRQYqV%Ipu12A=K7Fr}ewF5Z8I zf89@Pltp9Eqg(!`Ndcv)Go8&K8ZF#Ec2mJrcSAJZ7N7msnUWUY%d~yuyv)%j)@#`{ zN?t;a5m>T4s@l?X%|CiHgvqk+JQ3m4gm%8~wZlZs)J0nOvLIT*<=|_w(q-{h+rYCD zZ`K{@X-4cZ#Li>-5&2OfB9?R%6E@&`;D1FrB4sR6=Ga57%7gfmTsowxYrp zhA^_LHOhWSbH|5dapY_@0zruvf+07mU+182bC|M!6@{ZTT9m{#*)FW2f!0)rP0E@U zJh)3-RuIuP=}WQc>C%)~WQXm>9^O_a zT$E~*?azb>)ZM%gSvk885teXAJ0mT-8qS9_joM5N%;dB0U$Bk!UT!mI5N*7qiWl7q zv9-#h8Q~Rpa>ha-GAjF*DD$s$p^3*%+NA!ucUwmCdu= zW8r#kq4S2v`(U!pYxJ+o9~X(!Wkfn`GrpVMm==fRB>tyVwzbzg2R@>i*MSNqaE@GFzcUXtL62l8jQxEJh zxVF@bx@|OE!G@?L@peuf-KAU4{1;xrj!RpcmX1dic&2SM5zxaI?1~0z4O?)}HCOnD zzGudyTVq;lHwMw5-jG`t%4`!1OobTgJly*bL~wi|P-n;Ea}eyfdNuqIW?7K;o%wP% z;M1++N6Xrj?wFm}Bj=^dajwFSWEH*l84rWotY0;VqD7i&HztJ3hx}tmHZ0@=+|4d+ z3P%X((9_yXC$ISy77Og7bc|IV|5FU!cdw@jVDFc2-KreXTk{hCERg* zUmELKx+AUyDT6rgAMUV>Dmd|@L8UqO1`qd&aZfMB@AM@(G{3Vy#xCUOwhqG!*{0HB z;xP#hTfI>MU#`KYN>E}TJ4VfkC!NA$_gnc5>#RC*m1$}uTn16;7W+Jn8%h=Bbt#iTaY;ZeX19-+kozs$)=v()Oq5o^ zsiAps9{*eZO-cALDIOLhUJ!1(%9pQHB{io-%-A`0J5nj;zqW3>Rr@2%C2VzOvkTqi zO~UEFT|5>smnyO$?-DF!{8AALR?X5dPJ`jVXeCXVvrad*u)(qqe-%41SR$fEa!cme z3Cg7CmK>%+>{5V_pQ7&j8nVtM9!IjLA5McMlg3W8?^}({4)xQU8_GK@C%cw{&yXBH z%`TO}-pvTK|N}VLv~L^3LBN&ndSeXxM9By}@gLEwX&?vaR5UGhUmao^hib zyX;I|30js}Ps$9pf`R+*=gIknbo|WEg8PoUg!J!(&M_A6rQs%y808CzxC?(!I-SV-Ac32^U8DU>lxZRvCy6}o)iV727 zlZ#RMmOF3DgK1TfWy}W4#DX{t;_UW%g;|bL&y$Hgt{$KSsyEqRIB zy|$>f6EO0|f`N3Ydi$Faj`F6vFD+UjaX)jMpKoU`~{Qn6co&;+Uq&BdXEFEbWsrp_z9Y-S*!PR z&Pi?Umk6eyCb078&-_+bdo->&$iGSwYP(+j;JMe%ZfgXd-;`#g^Dz17#a0=XA`s?WnmQ@D$ zzT9HGt9{M%>g?^UjskbY<0?JTj{gBCosjSpMR+oXS}2>%Q|Z_3qmx$QoIYyj^V47x zg53C2L;mYIM46%7>MX(Cg2d;GZeQ4OCKXH+-;rmwoNVBGV?fd(rjIANZ5KYec>$_a+f#M-ml=GScxUN4(y3Cj{^P3{ z6BKW|@zBXW$HR=RI=SWbo!>mt<$8@4-6LNrmws7p`ZVlbdDfhaF1&RM#Sv$W!KVvz zcr00(asHGdeCh9#^K3jo+3U5{_?o)J@^w4M!p2c2*nWEXl2H8ZA#nFiRjl1#CbxS^ zd;cJ|NTVJ~nUaGYFR!PgC1rY?#~s-08E2)P?BO=J2&7RPq`$uU{DTEoD=R3}+J(8a z01fpjFu_@-9>(rG*PvVRiL=5wj_ar*Dzk{gK!apwp-HZG{>3GM43={GyO$y&4W%>_ zJR&nZ$7K>eA(`5eJ5c-H5{_B_Aq?-S&#lA zroEo<;0pckvLIGulY46f9twv-g>j&SQJQ^!muguRD~n#STtifn6&YvImk!p5r`tIz z?Y?Wzwj#-hm7LT+pL@y{S?+M=xqtjkw`9bS=Cc{vXltJlujA~Z>!xAvhozmyoAH#n zDnId4+(-BDT4>H~`8={!cF#fKaBAULDBH*J*DcTA`xHnMF)+LJ^KFnmbMUkxRtjoh zAx$^piSo2K=%UV_d85#v6V7KLPwr+ZWVvgcWmUNLa%q~E0<#xVrEKN!RWVj1TVdQN zZn+b_8>=A{SwsmU9yh$3myqBlPsa39gOD;62i6=_T45^nT(f(E%e!K zu=v?eM5T%EpxeITMz1#WD~u>s_^zd%J@4bG2t=vJ4zKC~%UF$mvc&D5Q>|OIx&?y# zE{_;T$!~83m37RAUhI4xP4%8>rAOjw`|_u@k=uLck{s92;ChTOnDPuU?zZEu@r4M* zMI;Ya%{TP@MvAtEr9z@zOwTt~KY9=SpQ=wI5ZOL_V7Qvq*jDd8Q&>#@#ExzT#sTPVQv zXE(n6T`Sf8;;zo^?C1U!*|7ET?6xciKI61Tg6gdEIXdi}VzcMiS(_0Kw(5&%TX^l- zE#$rAB`2~yk}L8N#ORFmo#{?QqpL?!ny-flZ3|}MQd?)IQb?Nv!3_w7|e&yet#@g z^61!Itr9L@jeAuy;Z&6qc@kIID1cj5rI2PXkJ7ATjGI`#l6mNqB}y!m_Yih*x2)qj zvecO}+v~RRsuaF!FttZFTW>85Ek3IjdqKfYi7=m5hf2-4fOv@|K&_1?C%I355?!3P zBue%;thsmsJE!PxZY6ibi=T-3s4mm=_+OE;dNq3j=m`9k^5Sz^=JbcdO&??oA9?Gn zU;GUXr&zYVdG3xK_R#JQrNHq%PZy;d*O5UHPMwfQ#D^H^Y!?9*?$wqI58uL*)bWkC zECV-Y$Sk7dMncMSG3@F+SBa~`e7b~N-L=%||5+5Ls@`!1vL zz5A*366O#CRTT5Qdr9ZQ>lURat6hASz2YA8NJjKDG|Em_wMK<~H_#V6-;0T`Y}y#| zsGjrQjZOKy4IwS-R>{erJehPyDW5Z*YQ`rj*6dbzn@#hG{Kb`8ON1T3p&iZ85-*{= zgKlW?%_ym`tSM1DO@8rIBqL`PF^3GPx^)#0=d>!M-VP|^XJj~9_T75sh#v0FVXYZn zy`)&I-CE6HL6o=5qp2IL8Vcte(+~aq!mW{Hin>LAGDS1uuV7lohNwaAeDM`V>9}^n z@fvjN{E>fW{;!vQ%F7Xmz5i1)*(dsljH~<6xPhxOrlK2r1Rs)*cfrC!UL_1m>Bo!L z`wd<;_O>cN9Xh?m1I+Sh5BMBVQTTf)G|2cew6t4->^I!T=SPFL?>7>yGg>NQ-j18$ zhc*+R%{)I^ak?UOMz2T@sj@pvl$quyuAm+mr_?b#iKgAXA|F*&Xz=&9-;rEvAScG1 z&x^87{uA?Rz$korOjg*T1~Ss zu~k|cirv>WumvsMO6(Wf7hPiChhniiohsTcr6@@fZ3}jpr?6LbE%Mx&6|@wv&iZ+K zV@qT0JRE&yeI7(8H1ops=Zc+ttg45{A-T1V(GS1b3W zE2peXFb|h8TrJv`;HtDZUb(ToN_1uq|JSZrVNCxLttXRpdVDH z2GQ;Aw@B!coGn1(bru4gcAqaBYbEEUe>&3H$g__pLi%>7tHJW9EN5W5?YQ^j&i>cOiyzH~W4vE-H}gc)oTmnypFXs+VSSvW zvDaIuGm$#;d%99>nk!Pr-_o<>lh3J^44s^GW5bx_H z4*b4F@?1Sql&^L2<9#H|1WToV<>pop^JN{3^u4esAGbH$(baO?%5>GxY)ne~)lpE{ z+^(fiS9P{hwMK*0`LgxyCd$7VJX_5xs^g8xO``sQhbe%(1I7504zIE{b z*!rrdwz{s}9W;1=qQzZ`7AWox#ih80;_hz6wMcQd;_lXBg%)>rC=SK_1e5BLeJ)~b;xu{6rKhMviNiLkTNY4!TEC{8bA&LF+vo1`>z9?hsSwkZZ zr|lP8Zo@p2Tp|NlBuyKx*L+55D-ncHM*WjXd{yX+)tu)kkp0vQF{Er@#UdT zLLex?6G|z&V_Uaw(L$li7$ISuebxW99?+merRiBPDx6;aPAyXD^(b>%p3M@J`WRw0 z>>kQA9#tRH*l$`x4woOw9_K^P(sA_VeoUam#eTP&}r>>aPkzxw5zoJ^EAkDxjJZXi50w!cOI$yM;o~`ws)U9Wh%jF3#Da*W+ z07Ef53L6`rFYge%XdaguzTbY`(eLiovyIO!Y`#`Bf#cezlGM|GX!SsU{7rW9`3iq) zKMj~pvAp=x2iLXEcQB~T@T^>HS^)6vEr0z#T3cke9Od9vA^EQy=P2u;r#YQVc2Cy;OfLo*Z&*4+Zl^o&yS??|ORO$FAM8FpH(dkmQzt2!hT=733)`DDg=>p;JXj`=&v?7y+`dde5X%enkH zn&Wj#_GEhXsJsf^NZRcXx!dcX^W$rpPV!Ya72$VrHJ` zFYtPVB6WG{*R3p}TwEQ+*6-lG8MYlg)O9gotOGq`S<+g6hn=T-GP7+nwEu_1=Wmx@ zK2`NcMoPy+^6X|h)_cStIGPvL)8s_@&+$S+kJUZ5)$wIaY7xOe(#9NGBo!zKvYuQa znU{>CA`Vf1*E*U%5Hpp9)4tD=s)4fU3>1026uvD&$bh77 z9hp7OhhyHg?@%F{Ou+$cWhVr=K_$CGHp31qca#e&qtqWMwvGbhUOas??+gRV{8?@T z-M^D5FQ^lLp+P@L>~f!`{3Hd$Tnzkn!QV}#Jw$9#ifF-&Wkl27_xCFi9Ddg>iP}*6 zD0*7E#noga=guPoQBtW*D13v_|KI{h!c1`|K^E|++Xj=25PL{<*j7-OYT zDbhbGG9&a-YP-x?{v;!G32w@y%7BOG6d`_|I=$HA565&kfOpg#!yQ}E{{5vl2piz9 ze-yPB%O{ZImrU^sS0)wo$M*)|KYU~SZA9c@XJW;N@btV2-L7^xs?}54^Aa}bzHB;+ zYa@Bk)+Uec$6w>fOBuBv9=?31-*9$jM9#&3Rr;H%19R_Gz?s+rJI1fuR^fNp0ZVo3}T@r;`{1s1%a3B;SR|M@=89-m9sb2N}xyuexAu>8Y z`Ht1Icx@LqZvJ)7jxX7g8zL?WiDiQP`jJ%-GW73KKDfYeA#FdC^XSn(`>k)w0r-$` z&Yq9SaS#L-Q2>eS7yY%jN{=f4#EuFeK-inj*5v{ya0n3CQD6^zxZZb=fP=Vy-XCUe z*Ztkh-Hr+TJ77V;X)r$2arH~kEHOb4kZk-M(q&dp75S51p#{s^!C(^EO@1$az4a(< z(fsdP^NaTSS;ph`!8dywJ}2|}rc5l913;mm^=5@mF5+^!5b;&>B;SA)gB2<*kin8~5D7zfM)(TMr-g+5PCSyNa}9jY zn!D&vwA8=NUGMpJdHE?3(J-NEKp4P5LDipnUiX4dF2>KcmjOI-5b%!fBGGF(>}o`~ z`*6+R(dBSP-s+P;)tLl&ADtWm94&>T>{Y|Z``a_VN!X#p*G)E01M;Ojg(_(3aJPH> z`hH97`PGP375lh^F(Ay`k%ZxDD9_QOz;Ks=HTLJb{z7e3yg@%s$*;E4c*9I1c?HLbr~ zg)RQ43Vw(x7h!0`2XA|+fog%8i8Lc50PZh?Vu4-}s*Ie@8%=>=I60*Wf?=ko`m{U` zRD?kKB8sy9o_hL93YAgR1_imVD*E_eWGgz0h-6fC-Xv>$x$_R@EckOeLBx>ACm-TG zpw%Gxk!Se9hppBy2O`FF_vFN|`?|=!FKQxd;OIc#AO;u20B+De&34NJQ@Z`DV$qvX zzz8dF(I(I6xYtlC$mcB(oNp1kopU2JgI#v-d1*x$s`_!&Mw0 z#rtMVA*x_J-g2%@=c5#qnTI^L^H}!l?@yKW9I*xly5=$2O~nuJ=7oIkS|tTM0m^%h0uaL-?)1;B)i8>pJwXiND57e147ikYU<&)0-@@|BXC-JeNGLx@O9f}$bXJ#r7 zgu8zqG4J6#3u65~eDl+E{hTNhlu9#YDvlp};@KB2LaWY@<)itIC}6ZQsuk5q~T-DlNvl|eWXO=mAIEL1pKFN=7H!G{j=p&F~bX#Cr$4E}qjR{~)# zhP|{iR*S>1sw5W|*UKla-%5p1FgDmuevPGqC=AL>D+xg(5Jnz&mGO|=j^E!x4Lpnq z2>WOZ!v;`>zIge)a!|G$o!JrdbSf(jFzsWQ4BDO}Usy4V!9}d5ZW+*Gh@r zrcCl?5gf8_BKcbk&+kkl$|6}MlBqx8Aa2V}4284_b`xsAP_opgO{7{X)f(mwJZcMW zrwScMFvBB#VN3Yykv?3_+ykAnt6(4U<4?bF)rBZ`pA)N;Mtg4OkmSg|csaZN?8}AQEq{;A+vWr}=rmbj?F)y`SnXs;1*d z$+nHIWluXha=V-3hHzgVhW%wM)()VShwP{R4m0`j((BpThmqgOjBE#{=j~`xGjaY8 z3*cwgTFO=K{Km^{{MM%REJRhxNJOR8bt_e_&*7K+xg{SrH&-Q|y8dr7D{lm95TAG{>=w zf#=X-X33YXXPLCN%(c&am^Z0LI4aM*87i1OJ$ai)p~XhsX84i*bEjKLp;uQUQqziZ z>`^Qykyx=9i}v=Cedvs-!_^V}qo9w&t1kCfr9J$eTo$XfyuAhw*Q#GvdHMNHUWG6O zRbqcdiWC%Ymy=3SRRf6OfN_AZ4S+@xk?mepHn>CWnj7+|hTY%}f%Ur$&L&+BseT(% zK=lj8h!QU1zvq$=iATRL)v3vEs8{$?>JG#4l9NBfWW(4C78}m&w28EdWIlB@D9;7j zkB+@bEsoC!N`pgcjfH=I9JbzJ3lp{+41k9L^AM*?oF0le?2LL!4XovBEDxzu=`rYNlOSz0W^VMf98=!TM*)tvQ;0hrV%$>D%`5#3H| z=ul7Rc^j6N8eEdt6N}U)Y-xRQ{BKD15rq_pYB9j*1;2j24|3G7nxr7*$u4CNE)42G zZUkzNCahYE|NVmmzQn4F-t9My5=kvugOZY8s!yB}S>W-qu?ls@1!LD1(!Rqt564+Dva!dH1Eavr4Oe zcUNN}(94_?p*+2YQGs|}!w)mA0+=Ks(a-+6Z5R+`R4K+F^$)&F@j=z2e~=>8P@~Vc zzJ^HnaE;q*G~7KR-;ncVCmTyi4NJp%ff=x?Gz^O1>S^s1gs?KA1>?wa_53adb`@D8s zNs;#a>@-+3W_Kt4AAb@nL1GPl#zIYV9uY%vjfGu zkMY?-I*xRIb(OL{z|v`(Dn(L#8CJtL&qMz{vn?B_2CKqQX#e(<4RHRA4B)D&(oyFZ zI2X~EQRGpm?x!*!qlTb9aguo7nN1`jbSTMG%!a&+{!uL>8ivsE@pE2(A$#(m@hoMD zI21p8OfhnZKq8s%>ot@~#tNNh*bbsXB!Vtf6@jqFfI7mUZ9Few62agodvRwT`#b6N zvz%-!b6h|NRoWmlZkd8&H!Hy{Q!0(wUtaBAZ8uLEzU^0}bV>;EwI+F+6zVszU5c>s zFXS4tlWx%ntbJ|xF;wNV6@?dSGWc@46nQfxLaMM>gib(SEeYYC-jLrXpt+C|c?giV z|9Ec12w@7eROiCjQ0r^9>?0BVO;nxlgeT7MMgK%AB zQJy%#vx4ogRaQ8H0-x2}umYtrNMRm<$I1s5v$Sb-KN`m}HDe74h^?`U>iLc)mE)@%dBo>CNTJu)aI~x z(wlh7^H4lV4MKz#)k4Xbh%NHi+3tye3suK!9m1-CVqMisPr_E zEv&XXavH;vVqszKIY?sJ4NB{yu}CYHioX`|EZFGgTh^zmV=rL!Ei0vo3NbV|Xg+}H z5)er9oUJt*7WDa2)i|EdG${$mYY2BLZG}(^AotZhuIZ^m65*Lrg%-yxlL@zBwVDV9 z)O9;Sk~pS5Z|;Dj%iKLOMrp~DGuYIg)(o*_Nny|y`>bv& zk1->HlP_YeRf#rFv7~Eh*L~Vv!XJ@gL0SvOsH`6x_uQA@_`${ zN(ytcGSJr2Frru~QaWS`nK>HRRk^>*KjCjG!`KMg{!E_Mg6sX=ph2-gtaM%>G(lDa zAJO?xkpnvvbF^X3PMFJMd2#4*K4AC94`2-czS83JqeYXqyS4u3<00^O>c+)zs-D+f#rI!$`=YDE3=`qBqwn-;bT^Pvx^$pp>3T!+!HL9ZN z;dfNuSw9~z0&+AeRjiN`Im$dij?cBz5NMK)V*InA#9h!O^#&2paTlup16vzX3AdXX zl1}jZ#-90%?0HYBKTEM}%S7{lEN2-=i&1I&^|ZQQ7t-fGa>}5O@R!EIwxq1@|BE?! zoNGl&)@wtz{Vs}#a>t$Vc2oH)rhwa2cAY}X7L&>MY6O6O{2{Lp(5G@!c(eP@ z?zzD%>S3hZ?6NI@^69=4&lnWx4qxRjRwYQMWddv0iH}mF-%eV$Z_9R zq~2){SG3;*HByzZEo^w<3GBgulS%k>&W{C{aabM-zkq0RjH(r?-yxF3MIuBzdR|7g z$K#;}eRbqQ>NQE;!Ubc75+PGpWzPJ22(DS1n6Y{f_jj=lo6aFns$JtVSge~3z1Mn1 ztjh8?0}22a1W`l)Xw4@p!m;9SxhitIuO}AQ@7@0c0xMa*4`c@5V04=&DKGLTS8um! z@)UvZKgxo?GEi0Og-Zke3+Wwo`j}EXt{!mz%m%s%ZTT|?b{H=TgOWW;5Jb;xh^g6j zE{0GQ3V7u1_CJ24O{7~G#af-Tnc2XMxmY@o%hqd;Vrxo9P?6s|eg{kx8DfOC4UtPI zIl`DW013Y;AOqdkef#=w+5*_0W`PQGzf@4PLQ4TK8&s04p(KmXa7=kxj9@Yn;|E=z0jhO4Go0Ah17a}{*fv~zsx-j zCt9`#l;=Aw=8pobHs}b5lmp}uMYPL9D-#E>pO?n4MHXXVL4zaowY$tACBBDCoEOn? zTUB6A!nvl)oVm^4L>5dee2A!7I6>B%a1;{~q(JEoFb`4iJs9Ic zWp3>hu><`Aq+){%Lis`bUJRI6I0hkMn-BxFvdOa@K_E#hYR{&Yi%d}=oPW;SA|g0A zW<~8GFLuTh#t|QK2ndN}DO8s2e5pZZtvPTJ$*3qGgPt>4kVK;@QeKRclQcrFD`0T! zC(irFls7l!TAK)~%hvxarS#?w}z=%Ro^ag-^aJ9dLm_mjq zuA&V}aN0~c#SSjo(#(?8h48-&?jbp}>v(q^) z+tJwEYJfQhJ*+kR8d!6l#wGz?01$l?S;emYm-z+o1oDXp3=a%Jf;TU`MXi)tu-54~ z3i_YCGS)&4 zmcPt!f0T3QM~$4}Xo9Xt2-(A1JT?BApVEuF;e2|=SJ z7ZtvzWqSH4%0}TRu`lYjek#~Xz6u8ga_s%%jni}}vtKrWczZ#Q@chm=4*!U}>Etw< zKnqORVn(HuWarbZYwGlBDTmk4@Q*J;%^T`H&Iv}QKZ`+;LjqK9ZemC4ymSjfz9N?@ zp3AcWG>%J?>GPfK-b&FfuMt-^;vXjqU>0q0=iy^dmQ!E$N|cI3gE(S-rBxnbzOmDH zw+xb8c2T24AQo@V@n>!sFS>NLYv4}dv7^gl0`OAS$q$J|v3@Xn=%-)kD#|*0^$jEU zpc|bR?=2hDa4(k=vIC#G_g9xirb(ICX&u{-LysgE#fk8s!rKEOy#54gRg!q|+6ka%>d;C@9cQN7-9o|f3we|9Mt|PEXOfNIc`{%$)ThSMr zBFSDf!M{xIeFTLOK@Pomg1bsbh4t*qEy&pT=O^X;#CWh{o`rZV529Hx5F@Ub;GVVg zP*L{euUZ=DjTA%wAZif7;KOnQSIoU%Ygp2)9#k{d=H@&$N@pOeI+`efXLP}v3fhi1 zpK;Rz^&Zp-y;PwXx8o3jwrcYi{lh@q$f3jK#d%TkSW>W7!_&OSf^td+iz?b5iUUB5 zo9^+aB^$*D$i$ED8P5O^h)t0$zkcE^QL=$;$In`7#X27C<-9fR zW0r>;P9ngwVA6RrJi2A)CY_gRH{J$yj~WOb{yT%rn1Zs0sa>fVhNk)hMH~7=%|S)Y zZIQRS+TFdu$3igq(I5Ohjz&|%{|q)v!+T9u55nARu=}!1f?CiF2cYN$QzCr2|6cG9Eno49O&&xMM+j5o8=*;WCz3@tczP>OSjg$}dnP2Y z*QBc62OFR{6b}T?F^NF;qyR#c?%Wyb_gDb6>~?$~jGayJgZOn&8ZnU{0>QKai6)=; zdl9nB3vs$oZ}3)Ley(~G#2MMwUVY$-okIU98hf7Bh#rdbgCEo8O*}fM+we?m;>P&t zRPfj(l4+AJJUl!BYkHCUnSZ<|v_f5wu#6NP(DINAq*F*fp{klmFwY@`?zu&lf;o@w zJi}X7s0kh&xU8f>6cwKZ016JL!}SvZYk^7 zB=JTM(^#x%@188Eei9tOgx6!ZpfsTt516HL`nXF28JH=qcM=70ynMg0akCe;&l?hWqC>I)?Nc&5Rag03b zZybG>oPYy|eS^an_(22{-)?)A`;$W2AYGGA&U7=L9RL_YJfis27A4l_0-xLi?~>|LQQH)s|))%yIuJ^SHj1m{I*JEtfD+YhE`9+e9>8^L6KZ zZuctVgU#LZbrl|KyqV-fayI?^v&y-??L_S|{nP4++iZ)Lc|TS*&raNUi=a=5S7~3S zh|i96aHvOj3zx34*G|dgfy-(^mH9kU=)wx+nFW13QwRA0yf+ zTtdz#6EolGnQvQo(PG7!fSG0o<|+Xmii;=%C>AB4`W2NKOYu+VNne#qqrR*2LZz|# z!mW(3BKXWhixY|L{wi;$&gLcnPLUn83zS!W0y)q(Zq1``ju2+1VmSRxs*GqoghON5 z_G^@0WK4-H3F2#3*o00gSiJ7DET03B#Rpo8-D`Go(!7SYgpN2+OBG*ODnYI_fc^8b zap){|AS|kdI^JD=yNM?7gHWh53i+R-y*~tRM%l#sw%v{}TxO1vendbN+xK@fW_U-j z#@v==iVKGcu)~P#edwQx7*7<@C_=Nyj&jsR6iIy_bN&ta(TW?-q(@m}q4s}R9!{FT zw=px-$T)WK_+`g?aY{YijWR*Eu!2`OWyn-1*aQ76+83JysMz^XhF@nhdaOUd17>Qi zjA8|b9i?RO$N<=hWy~yjghTB4R=cyQ<9x*C-zjkpkK1DRJd>Wg3C+9p%bV*$vIAVb zCXUyN>|zJP(93;eHepz&-U(Bd!>OnqBsvOWyE;Yy9%@0uz7%IS*zJl(~^ID*?)f2YPkwy;x369XYk zw)&^slSZ~pcG_!n)Z1V{oE{9<7*f9?zU9+ZH6T?7grhjdW4D8ykGd?$7MC<`y0dZ_BBRO}`o;mHVK$ z==seeTIA|8#}}8a-lHA?&$qp_TEHQzG7KRZjR4P7&zacly-OGDiab^c;a#oFs#$f8 zRVa@G%Z?wonQ1=8kIuF0cqw~Y6-vC@YArW zAAyTpRd3|yb~nyF=ToX%q1Do#+<%sJskxR}pGbI9e2p(V(_McChw%d!8J3QlA$EYPcBg}d29%T8M%smF^x{oX`o}OCAhBwjdNEMXYDYKO@XyI1_Zf@n$m` zL2wDpaNxEG0y$L|J%29nDJ?(%X7RUi4S^&-fi{SEf6sn# z1KEZkN4rIl1|pP7TDQ;b3~t23+s2 z72i?8A9S9(AntY8zFr7TT%sNkNR*Jp@CJW54b{FE$-m1PQ6#)+sig~rP_7`0u-5X% z`E@<-E>e>bCUed)d%NoP#fNwAIR4rqRbJ=68Q9+^ap$#@_7nB9xz_d}o4l;kivMDa zNf`s6(D=><1*~}wxWuUDgzjnw;CYmvktP||@sSN7TxMC^uX$9S>c)7+fMs}NT%dcJNRMDvqW5sNLGIIL>^qYQ@!0LaBi zPHkS=x6du6F{=fa zW|rG3IKe_b*nZ)?K+N1W8SE|l;MaD7NE&c353ml!8lw}!5fdjM0AG*o-QRfiW0I0r zHP&L6XvFW>ddyMfnUuWQ<${JfHgt)Xn0^xdS|cV?HmZ7*NRmJ38D|;9Au5}!Ulm7; z;lO@WNCXs{+6@V#OJfiyro)bNHeN|M>LsSpUGl>Pt2(>**(7rubW#X6R&E*~_y)=_ zjwLAz%fGyMcnit}Ia)GJ1%eRSx*v<~9_rCuUyU&UiNJ!y;6cN-koCBjX1GDrM3HnQkHf)%?c z2YKTx13}`y_UxU!s$NRcITmSWZSH$_YA^VIxRzKcM;FSD55Wa$+n4^ydBZ~~OQ1ek zUo-5kKQzQ>En0-BY9I4HJ`(j6LRv(AOVPytUD|vP*e5Nt`s@-hEr>C z$EAdYF&s53I2I&?#1ID;?)k>EH?8MmYdE{LJd(MUyyE#3I=rh%R{w_uu%%~ABJ?a! z41squ8NIQNeg=obb8K}w`$SN(FtHCD)M+=`_sI^WRc?lCjlvU!95zd^*2U5fMyuby zT2L?SmH{hjmu?}3gj2hY73C!b&__cnr{oI+k@q&yt9E`nnR)3U-Ca~R%_3tXey?vL zUJic*oQK;A)|;QD$LD6WEs}4gWP1eIds=uq*;+=4I4)o8ijV~8Y=riVuB~duly<-U z!16epwZjZ-WS^Z?pYh`3r9FQeK06j@nmn-UD0sEy{q{L^m$lQrg~5m1=&R+Fxxm1o zp0w{$%{&C~gw9^OE8{}fV$v#V$nXFD*c$zfDKzEgH_W25x6_@PEjUMB-(wibwBHqLEL}#rnOy|p=d5#8QEggTfs*`Y5r(Y9(A!n=3kW5!f?kqTl0$?y; zE7D!CqV@~-qug|AXHgqadv+Bz-GuB}@ZDaZWH$t~q1ZP}9`9eic||sCvLli5VPkq! z8B&xkaG1!E{=PZKo19XvL@m5wH#3{f>K=&nHZY~0U!+hX^PKO3yeGwl#(Uf7OGgBRTPCYZ#(|7!aPUsG5ezxA|(^m=N5W=Yt&)@SGYGNc3A5 zlkk(Z|7cLWo^6whj35_}&ECyc0B0U>uKqGli-Bx`;m5#DC&27J7};K2u!BdN$bkjt z4kKH-20OuaI-lPm`V~0CU0KBa1@b!c&%+B}ryRZG&9S&+NRs&aPOV?}!ZGtQCTIDHTFG8jdF65sGcM>dv^Pvf9IYpz~Z)YBHwtC39Z zo$s)5#cjQ{7waWnvNg5ppi{Z4<76gnq5t0FZkw%URQ>C!pS7RrNzl$OP$6e^m&;Uz zGVAdBx8D0jF*SC4m-jcw1@Op&2&Mn-rp_h~yeK4-9S(yXk457D+EP%2hN6X=z_810 z8}!Hot@L8xN149;CyZZb2n4xir;+U+k$vN8$3CDxd#ScvTF_xr?NBv8_Jsac2i;j7 zGcemNd6zvfvh*-BJ9*k~jUqF@xEW@(H*fWEqajXZ_6gfS6=bgS4@%*csj|zd_ z-8%9rpH&7)D_OSSlpM|q%SA1lRRMlKcX9KKxDOpg(g+mtIn-_rh}H$3B)b9F%*1Fu zGSHjI*2#kt049+)Yv5a-KUS#>v@TQgqa7M?gZU7S+K**jucN!Q=n1t?0v!J3iCifY zx9u(DqKgl{w)`5M%Lthrht9{ISTFes~{voyCqwYNNI?Zu*H*i3!7f8?dIBhB!Q zR$|9bJ~PyFlnAuY@H)Z=@GH*{0i~LcjNI{Na7`BoxcxS~mCRPU`jhn^hr*d7J$IW` zt*|J2MM$5$jRt)9Ssyat9cZPsq%*d0#jCNQ0s!v{DROx(H>w;lPH{{$^zZDyX;i!XhAh%4}m`rFuuFEYSG za&K*P-@(t?UVBlsllG6nMLf-^d1BYtbT322# zTM7(@zUzN;{qIl4mwA#7&TXf7{e1HazZYbH-S6BeYt4cdfikBLDHx&H=f^fL=280% zd#CeJUJ(jVn}42@Q8JYfSmt@jmG1TWDm4gk=w_u9!~o>HV(3qMgk^b`{G?5I!`+BY_v+-@mIOw$4}YLsW{@H)Ym(#eu1ZXIxB9G< zKqQQM)@4SrHcLDKUY*B~oOt?A6}$C^x+4I^N?N&waVXzuNhi09i-;`hTUvEC;MX5q z8ztmG_1SRts4ga#%}$ft6)xX{B7e4yqUpUrm2|ml(l5j~e@wal_C&^rR~% z&?q(BT+5xk9ChM>Cx-W~B$KY$g&MN4q~Kmi0_- zm)v;g;2!7jpo6016qF7i`U+3^GZ4Fy5c7V%F;OjP1mO)3iZ~dGBuzzO7dKd6VuyeLFgX&dl$cq4)c<5H zsgfl}VC~Y(#s??3*-@SFh+8yM2=+BGOwM^V_ruD@z4AS~{jlb&IY;f~S3{D(#mUon zYjaeCC#!;Ghzu(fwN}aiFthA}J|8YxCIY~EIZF2P?cDhMvQhiv`_pbVF1xY!BSoX- z&*ZDuj2^E9dr_%EBjpw!T@IG@oP}5T8~W>0HXxx8z{fPw>Le&0&UJ6Gt;X9Nja@WQ zAdAJpp6qF|IsNfB!R11WY{l+F72g#mpr6Ps!`HLBPOWy-+j_*Y^|i1;xF>s*%t-_= z@81VGyW>Zz?j2Ygq5$$P?ycs_u%%nL$Mmq>Z2W+4J$cfjW6jfQw+XNus~v(`Tswg1 z!MZ2cKmuXTE`9}J67Avn$jQiTMr!?-n!}F>_zj+1@9lgCI9OrCOAT)G(o?{78=vOYc}~q4p3Ql5>KZQGOW9e&vm@@qqG%z&Jk4v0uznvwBSTd&56a& zf9xHRKk+M;d{u-7=k-mFnEWV;O-K)iC0R!GVC{K zK-0;W>}C?t^m#^2+As_taPNj6A*;WC_8#r*Rn4+N4^~{-97K16*>>M#T1vI)Z8 z&VxRDjM}Z8H(k)&3tq_B$(@x~p^ku{tiW8)O3|jPg@Iw7d)ezbs<>=kvvwd)Slsq=&%Vx0Y&_az2tWtiFg|osP;= zpFCC+XK!V5(GO(Lhv9v>HA3fg#a(p22vgq(svq2=c0x>LF*y275cUrNhO#C1TGK=s z*Q2|JeP63DflG0kpNW+akR?l`4Cz&Ksj$Jq`rVj7Sdr35Tn}#Td*+*rVI5@#+*^c4 z`PjNQ*0NpguSsyQc|fB87<;ssQUJY4dBGzm0K3&j)h5WVv(ef6)uAvL_fYqD#d3g} zEhTs_#O*n_QJbMk1b|cusJ1lrO=gj-2560C0CwgvR)jZ1ff6ROARtZX3MFWt$n_7| zQ?n|8hDx2@(7>LyEm9!LvjZ4Q7FXw_@sAX&;L^kbt*RD^(g6=Lh`tr(-%Y%L-v@ec z5d+3!x}9uuMW}cB!RAcxfqk$+Cyk1ik~6r=hq%+A(gQt48#&X`+ivkO%umLS+XmMt z>KKRqXp!ijhnO8>T@)8`-TIli7`Ao8!Ad1&iMVr^GY zBc~tc*7)kzuM(eq@rwtVWR$t9C!7<3UX$m#jGAfra9H-;%kj{ZR=lIo>LPCF%D28A zEXI1S91mcdKiD4OwisS)MO=NSo+@S9WSy+u^|oX7hgoP^oRw9Ue!jDHw9y+$CHLeP z{p(ZkazqU^Yw(G`-k-I0(64{=3hHMRp~uJ)vD)wjYCD#-PkhEtzrVNq1IwY^+kLtv zu&ebdXKPEshvlt$VJ9#I(>1S$qrqnDku;h54~q)pTs5;!D1sbnhdNznX5TE)rZ7iq zRyO|eDzG4@NNn@kGE^?gL3wprz6`;fMIu~V-&NfBm${l@8@HIF&0;NiUR4-NG%7S6 zv_`O$3ZFPOa=B*ZE8ebFw>0?%ZV?-l7^X)(MrqG;5#Ux1MR-J#lG}UIjAc0$*oTCr zVgKau*v@#)ZR9&_(&vJcBxWKW<^2D?U;pCZ&Tu;Wg-Z_?9|+@ zb@l9&hfV|$8%~>7@##ND22yj=6y;eI(!c`|^%cX0T8r(75`kh70vc^)qdJ)+!Vw^r zh8+Suts}4N{eMBV>MFaUNOBIvLl7^&T zQ!z$pBKdi3{~l6{6}i6_VTgzJA*Hu7MhNmSNgyQhgXbVLvNOX^>Q7*o1<`cb@8R^) z079?%Uds3IKJQm)yvQYv^X$^h2XpFA%){<6P5wqr=w%Gc>^R^#+4}8c8voB~0L6Q@ zV*5D4_9atwI{BFavyggSW>sXkev_^qoOVeU&O8LGy0fPoJ|c_iM}# z6Vo$6w6YYRO8?Zc=M~t}e{#vEZSAq-bW`7h`3qf;%y}q{u}8KuUIKtLF{Vw&PT5RR zCTKu*qjs$aL#7~ZEPTw2#`RRwg7aGT4jAUh~?Q`6fXJ6Ksvx*O zH7?|eZu~d7N^jE#lO#Sxc^TS6BJ6_KOV~z|bE@66(B|r@@A_f$KP(AT4=2ol+niwH z8EpI`7!mwE{AWekl_>k*?(VK(%?G~47I4i}!wQEgLH#S8rZA#|M6r@G)&V*CC> z?RcY;9IS0LJWjy;+stA#^(bKLKC*aORn^DT-Gqb$1(xWMfk23wib~$3>%N`TDoW*l z5TEUPEO)q`geC23Y}h;MO^E-CYrf|5AGWvbd0z|ESIM|%yWj{RBn7N+|G|GeV`2fV zz?VJa%IX^fB;(N5z=@L6|FAaZgEP0{QpGaC0^{nb>CT)D@>t;@m2`I>Ic|8(|NVtF z5@m$Ps$RmTr39^LuAh8A$k<%?(-|m3$c`EV{p2$ushXBxBA&*;l$9Uj0_mSqQGOO4 z#5*&0xskpsRyz4#WkdX=6h%dS`u0ZXp|z7h_9dX0oHiX9i$t+wi%Q0Z$qom&wTq^L zDEpmcsTmftlZb(-Bgl|y2Pp$Q04w2R2SO4U-FU~aF)909{+x(`q$R-s`?pN5u7x+i zVP|O6h!hN7@(nx)5j`fiKjk$r7jd2`g(pmk%ijS4<@putmlMjW>8J+>!4g7Z>xDSG?7#wy5{jLT0BU<;8aFYupeExf4}? zyuhtmuaZ>V1Yj!7n2O3~$#4LL`Mn7|I}(^fb*lIZlPuY8u~Ev}4pBU9$c&hCVWI*? zskxrnM#&V6Bt(xHIhBrf8)Dt?+=yW1W2`k2889U@S#iHgd(=?vkFkLaf#8&F^oDK> zW=0EkZ@*&145u`uS9BlxU7H7REe9jJk7Y17xuwguY!cX5fnP*Mv)DLM}R%4%2$;J9l+W6rMh;tLf%sU4k$$;-Yp7eb2vX zn(h|N6n;zy>bR(RWz|rfIT2mAdbE`t2tJkC{d?D|Lu$fEc>p4zAy>tvcZ4qK; z;@aB`o+u6Yr;xTa5M4>eYyDbf@aw3XM%Nb|SLONdXMUy~U-c>2-V=>30a%ITlRyxd zwg-mv_vJ0}?~{-JhRAkykjZ@{YlI#?+?YS5Ou?`H@OIPHT{l?=ejdB68bKRHcN@O< z&CkaO*g=Y)}#7vetxn-oV0hkTb0OtJ8`(0%uDw)25 z#{(p|d+RB$t2lJaQKBommZxIEr{%?SK?v|-&#|zkmn|$ishu~e0$kfKk2g`NE4uDl zwzlM*Ud8*4HmwdK1UOrFTbE}I4g1~x_01C7ug*fS{&M|#HTt>B&l<|j{6*ni$-fk7 z(6n4zZh2-v`V;9S+V7PZcZ)VyL<*dP3HIGLd{wDErVOB4qs6L7EUG;v86v3a(vKCYDl z&PGVImkwRNCM-@Qz(dU4?)u#*gpahESFTraEZr#e=Cg1%tUq16X#dNGbn`PEmrm$ z)Evd+y$um-RIwi!2)xmAK^z!_d>#8EmB8K8e((pBS*d9u9+g1q4J{as= zWIx{GMs`V}01)N$ggmZPqnx0m`gr577@U`qEWk=Fe_`MG2v+X)jfPOt+ zh3VQD_3arhFcpwD7xSko?D6EXuJJaNN0oqBtHqV9w)OdN;=jX%w*>BPObkmLjOFZ2 z52hI)bn;}$@@>B#@QA#>*K#`R@_fa4-MvJcoX^Xf`J5D@X!h0ij2z< z&f_&2z;2o_9B3jJ((HB`)8Xx}stW05Qv<-wT3VL3r;Vgc?0tP`LQSikja4UIekIu) zXXC4OyKVcE`6nb$)&>7_ zmjoj2ySKV-xUyH}65RN2%h1qj)HDjUJi%fYW}mN zA4TiXe0VAVtF9&Ho)0maJey3g&2)hkAbhws^mfbIoeq!mK2;9ryZjxY^&g^_wFGaH4vy;I zIh>fL`usi{K1`hT=2&_l0!3afY-og})3hF^)OF!R)oG6sQ1w~~aa#*=TSEfAySQw! zxb?Ak)lG~Nd7F*{z;Eu?tW!A_8(L0MK*sv(Ij&OL)^@I=(_rQIQd+fIBk8H9djtfN z4@6!w3OXC$L=!+JO;pt8#S2)>o_Sa{2}oIZ1H=jlsFtAvFazSh7)S$v8Z>|g-@77D zxz76Aj?gI_&_f7c{H^NuYlhn=%rP$c%qsJXtvJro8~q9793qS953yyxP|n&rHU1P6>ggFn#hVoX)mIM zqQ0>S*KlZlPSM~-BmNy3ZUb!!4BZmA5v>^w3?@Q0fzO9vvCmh#w6eBW^1ds$E>zfX zOdE*o7i0nc@TS=uVxJ&yQgYB<<52ne7p z-pKXKDNv(KM?Ad#DD<=#U1Xq(kh)LUAicF?&Ef2iM_P`W54wAV-BN2QNZ;k;%g>m9 zZ;A%}u?4@`m+W+V>iV2CU;Y=A&0`P+P2DGdec59V?%m@A0nS=|4!_+c&)fm3ygABO zB8&u;U|dOT1Q5xUNFjzTrc(<*V?4=(%dl7I%UfKF@jhi?q%B7@)+xqh*YR;a09zdC z1Fn>>@%#ZQ9Q!A&$O*gv+K&tO-WeDU0n0}+xgX&$!?;kC1(|AlQ3$CrD#8;Y1k+_U zVt+Th5Wq`;W=mm|t<80M$VnmOC?_Q5AH&mv^uFUKO!zNH`~nzH@w9RwKh@u8u>g=+ z3vUVVUAa}uz}1Y63fTXX6L0M0{txRI+AQ4Ez3xg=V^p8lpJ87+RM@fT^g`lj-um*>wZ$o) z;`}f73X|<{O``(hx;(^pmvpN8DZ zhL`^^aMv^H=ef2BkNsaz(IEQk>wwwqWae!=D4rGw;>W;(LyCB?*8ieG@FBwG10~{p z#&3>+1pmfym+%2v6yq@W@nmJUMkdw*5LVB=nYWk9up|mty-d-MdFw#Xu#MvY1Am-g6v-*rM zkV4BKo%q}u1`E6e2wX~DlRq+iN&ySU8}Hg1DkGF;xN3qRL!1MIAk|r*ekmW`lN;Nh zrB8R-&wG@KGcB?=MIr@=$2dwnBmn`0@M)1W0TLk+A-zpA$?uKS)3Dyk2=c8n`fa`V zi`!RGF~Ms=i^nh${KkB4T*XrsKHIp`F^HSocX3#}Rx5hj<2SGUBvq6!6{T8a&R~Tf z=-S4HgHNGnRN%vvS~Ewe1SfE&W%LF}r2L6%^2M}i{KnSsM*X!S@`V8iRI7-f&nd(@Jx@4^sJH2?%R(!P(`x6AHpI=B@`ki zaT`r1d+loXHXDNj0=f>Jlgczbc8AQ&jjoGu-~Wt@!x{jSpUWM-_0Aszy1()zCC_2jTUQyEzaN_I-D{S_O7?QA0ip_Er*6t`a{u1x<00e_bB{Btgz;&j-K zPQrbEgHGI!e!#}Zo!{}Ky}Z)=h|gMArnM(D1c(W`8{So~W?NVs@9cbkyuuDbizi_o zViS(%bt)J%h4MN@%^LKx?x`W8hG~@X*KcsB8-@B_-bX-fanX?U%MSX6R-chE*J^nj zy8z#Qa$-;YiJ?nO`<;J+lNPe(XZiG-{r_2m3W6$N z$IV%)N`e!?0|Whyww&tzXaOH7igeKvqP;x|O828#b05PZ*KKf^IY?v@h4`nB?n65DsyeP=Yt{xt-va1KHX zZ<4YHqEfW`4YX9T=gi@===|6nq=-~j_E7rJ-?gl((@PXNH6bif?z%ipEZ~A_#?DPH zQWhEYPEf~6cIW_aBwW3`;_2W$S{F$~mqUm>1bFjPpPSPj0Gd9euK{4}$obCf2-&!I zY)s5dZ@?Ud1xTyTTuz>v!4ee2VLZe-=H~O^zPQok;$09d#mZ!>aoV;=xf}0WDoBo6 zsT|+a+gT=Ew>kHWC3)wTIG4jP^-4yq`jTfEk!cIxm+q1$41);X`YZ3pdfEDVjk!6K zr$g`N8YIGa#iW51r@j50oT2M$qt9}NFIUpdWpYFea*wxzYo50$TX93^=)F+ z2h0T>oBs6^{L}OD%QK;#h}W<_NPK#o+D=} z%a^ODOwDzV0#IBggrmj6$VJcqMhb1L+Y2VSlfk{QZJ_CH4QyY?hwWQZX5}ru5CJlm zQ0-aQ10XqcpC8ujC60Jz-YnQ%^e574sH%=u85A6v{mJ*QT6j_r%00UeTnykNHEW@zGBssF}jRm z#mA?1kp*41t8UgK#K%x@-(P6i9Id*kw_OOLVCK6d76c$LgUiNHKR9Fkjsjjj%O!ig z0f>B?=1w~xAcS{xL*&sWOQ=3ySd-HskF+Xjs?EfUr5crkSs_{Mkt?>D*UjVC`R?>fdtT3{G5A@2LQy~4Q`$0wSfhNdO8{l zhjX2^yIQ|ref_&)tP1ivZnWGxed2mgnE98kj!NT3@RAax#5OL2f@$CLW$<@*?G1A= z+L^B9cW4#c z=AcXk1qoVO9gDtnVGiwbs!}Z;l@dWd3N`GWEXFn)(j7OiHjdz{LrLSNDz8UVmo;>4 zA0Ar0jovvOw4)fnt^~q&%c63&9mOVdzh*9XGqmf9PSclU3g;rnkGZVo{RniKGx;Vi zt{V}ZY(?A$S7~`ehd6W5fTC4$pKa}_9mdD=L0#PU(-($%pAu^H&LUy-E4(h>(9$WD zW|Qy%YekPovi@*ROjss>F-%3re?7d$m$Q1kym7bv?k6w1{q0X=o%i7|m~9Y0tC!g8 z8R*%6X4*UvarvK75PJQ>Ja4(4Mu#gp(5IM%6sP^T7=CZpv2(l+K3(^H8s3?5TUG4N zrzMHaAQSoREA!*wo{d4ejm`{!a1ndIB%#C}M;-gNwU^h;V&U=ZZw5QMog@&K2-@lI zJypu5aUuZ{upaTA-EdO}D_*P2?E5Ca(SxJGpK|ZBJ*f*6KoLv};NKh@eH0T zltn)2kit8GB0U&B;tBGx{;>1C7R$O&w^u(QQ1ru+O4OJTgF7|>;gh|_XWsj((6t3! z)mAg51EEtSx_88tX&&q+fn^gPMrli5!dCgAdCPVhtB@-#W!9LK)6_?ld#qH$Y|* z{=C3cFhX~#UKIlG|F7WorXQ2Y;xzb9dC8!FAZ-92wv8yx=hl657yADLa`{W^Bh4^+H)(RW# zO*}}fK#ZY&S#z(Nm!v0tAx$2tqS{Oa|AIO3ZKn~8!8zA{{SwQ!CjX27{NJ-D&dWoH z`$bB%QVFvxwKK7?k+@JK>5tK{I7y0TTrV; zf>n>g@)kixz6Ja1IUg$z4CjD1Js-O-LUY>-ln@~WxPdo8NLDWOt>t5cxJFHmj{CDi zzh>9s@>`rwt|tYa%ez4K1MH-vlF)KFaJ-4SUiQRE)^*o2@TJ2GQC0~VcqbR+;|)I; z`4OnEY%{F9z7B_8M8k<4H96GfXbO5T+YX=s=As_cuioy%Oc>E5$TjJlE{yXiGKDsG zgX_gmvP3R=%P+2~n+y{b$37A?@?g-$PwMUyplNcGUIN%~{`k4P5{}Tn0mEJ}yP4Ot z5B%@E?kxe7gjg#qEQPioo#KRIiL!kDV&IS^Fwg)V8J13u={6}X+4BGS;Byh`wU1TH zEj`xxkuW9qD`qnBh+igxG)M5|>r0cGk5!Cr_1x=|ex$DNLu>x?>4WNG`>g;|DLWOZ zGb^)lYRVWSrnY2xW-S{9?Wvi}-cea?TAG668^+j(g2$~6EWgy#{E-}!7Ww7^xZKrlB=0s=pr2i zF|JpEfN2U(Nu(}>OQhbWf|Af{It_Jv#Ia5RUN)sVEjP@e)np;V)5&bQ5e-0Wde!%z z+pUg}88BX^9SCCY2J932IkUHB^QPmo`SdE=Zi;Ko^yZcY4R#zQjExUk zT+rD%ert+xma%3GnPujc9}~*ENJkM;(_l|%*sXqwn*l&QFjRYiLTgE} z#a3$1%FbtF;OTW)==6?0>he{Tt92nQPiRi{R0oa<1tCROo^9Z*#!t_FI)|esx@xk* zroPoEPh{)!Wp}F7trm z7wo>p(E|qRLS;X*B=r}DbKM?q501Ti-CYQW{$mw&;(R(^XZq>?I5MpG_HFubnv1aL z`pPu5N~wfxr+=2N*xLdem4CWE{Tig;-w*xC5R;ik>u=V)%q6TN-e--@zoYm(Phxul zdv(I0B;vd}L*Hy(r`)7A_JS==KN(_wU}$ul`BXVpkik25wM39o0DrPJ?0kb0z3}}T zeuHuKf~Cpu;U^MeNP)|DTm9wMP-rg(amp|J^`iG9k)K#nM3-l96Ot(s;(MF4Yr4d) zFYt`Lyb-8&L0gU)on|`(epP~7dOuO4j)Z@_H7DjqwelPkQ%fvwhaWPDA@#jDUzaY| zHR0D0f1l@wfHA6r^$K0T8yv)j3@C{n`~E|8Kl1rzUQ}M3I{xS6`3$%7ukpk_J^JLs zn5~N(Cl-M4R)LFk&)({AGL>sDcSeOuR%*8Z|L#R?P@6)l@krU!TYKj zmR>(t%)5aP^kHBC05JOidG65E>Rn;CHHwJ(IHe02IWW8p^BsYBg zG>23zcf$H&>3_#^HEZ5O4_pa5Q3-5bW1~{ zmNHUyEiA<921YcKuCD2<+aE_OG9WQu%Q2d6wB(AW04u7(AWPD|`S0~X}_rs;Ohfn}mK|2q~&3?Loe1E?|xu{vaL!{1ES8AMal#!Zi z8=2fZYFJPESZB1m>B5@$#o>3Pg@d?n#=*T+b1X8Iy*|VZ^=XS}U}Juk*md6PjQy0H znk|q)Lk6lhevA5sDMWWzJ;%tLIomlnLHqO9mo36<}A?M~^EY z2BZe@rfA{@;!?-R534uc$@dm>XnQjyCT`WH)-E--;HM`6%p)$CQx*FRiL_H;*G^9rkkUt^5Wbe?U^{!PM=pYy%0MN`$wX%A9VASSK_SKO1 zW&uV+>T$hs3?i4SFe3ZJC_rX4yNwMtfVqN@OlxtgT48*kr$qFb43i~r$_#_r~OrU)>kNj z6*7$nQ01IW)@oqq7*ZFdfGH7j`%WdrLZZTdHqlceC^3U_E}Z~iDDN(PnF6R{g{XMIQD3S!p3V>LMNnHj&o_4&IJiz3NkY4F zdc0rmaAy)Q$)rTXZY5Ok6ArckGxH1X#{EZGnJ6$W0Q;gCzoUZ>G{6KK=XdEcTAtlztn6K0`1tu^jRN#b6}AwazNXkX_%Zs7<; zw{OyC-m#{%hKrEXStH2Z2XK#s3^wEEujuDdy)B4mx($J67SnIwzTwq zfbz5YB_~qq2H6}@Mi~HN|MVF}P(#hfP0bE1JFQ~C3}5?f@pcs80w5;s`DXU!2zcbf z+%7R3G=O*=>U(K}KvJ;5FTp?icTKEt0vX9Z>S9v|h9#vSFz`vvmyz|S9>D|#x>JVP zZR^a^643Qk{mW3XX09pvr;1!yyJuyCZa{3swxH(ccxC`CPJ?gA;Q?u9@=BIsIC2C^ zZTX06?FIo|kha!~HVv@Si6e_Jj8e86Oo>K~aT@lhSN6 zj65A&x%aSJOR<1{tKfR)u=b5q?L;Dwew9O2FNJxtLvx|D*fML{M0OsQK8{cMbkTNc z?7w8QV&%e(hKD<#H!7I@Z{ohBbnejuTY}yBvzoC;V8|RJtTvD*C zd(F7-dCTO7to<-sc3E(Q{oVmgC9ljHfB!{(Whbax)%X5#|3#v2M|~_s(Bzc0SS6HU zScFsMW$^t#RMual$aq&TthjhpuRWccUq804gKV`ZJo}fomu8B~^1?L*f5HfmFzup$ zyM1oD^Gaidk~w~1!^=A(ju>Qdmh}N9C{$o0N#$NOHF(ckvyMmnO@1-3YC?5IhrxEx zQTyZD?vG%jq;m`n^+wS%Fe(aKlb6BPquph@u)MNFetx;q3u34wwXec_CfTnudw}rZ z$olRXH*-8QCaog+`#oro-D?aa1oT_d3Odt+br{@T8*oemuQWB=PPZ z1Q*>qRc+Ji@tDlt#kLn7P5bf!lkSoPyFG+O$`HV^k%c36CuM(c*WZzX5XNI;8yeRd zG8o>I+dWZ`qm2I9paAG_<~q)(2OYmr_)a#v=`DD7hWqX%#tg+r*1ISytbH=+E50Z& z_Idg^w*D$|F_p~l>fS9XfCByq_8^NIMkY5z`y|-K=Cr`ud1f#6XL?TUHTZq|F7}!G zRpSbwfF~~qEssNU?sh57ZSMY)6l^-lB+X znEkXdPjf!AlA{%@I&)P1YP`4;9-1uRy0=<3l2~Qpbe6!dZo4Lqj3kIj5w2Amq{7%` zc$S2=`xY-yDMRa`uuxhtqab1UjwKD=bes@ct&@*wq%;1vwDQFJ&cMM31hAK*Go}!K%;Z`Y3q%R*0R1wAU_X>;kfnqaRWLA zqN#BJ!P^9B>09CRg%ANJ@Zi$JBeoQF5~8b@G^<$yf?@`7O5zS7v7vD0@1vt40VfQ* zHA9bE8}E;PdfMsrl`xoAEI3?p`p+aJ;q7NnX%c=KwpMvu5|Wfu3q}^6j!uORUTR7@ zDQs*3Yc9#rR2EDO*Qf|UTsJM!{X@yYeXX9a4Yi*0>`Jq8t?BXirbUk?c3L(*cA=4F zXt;%-`E*{2fRpQBA&f+n*Z7j@IHwk1Qts~$3JtwidfDs})qRu2kzwDrydKODRt*j9 zEgl;~$rL66xTmI&bv2M5+zorut zh&a6i5NO|>JX~gh`dUUKV#=7cSXKM`s%#rq)+w+YwU|>1=$3&klK>t}QQSU*1VjXW zG$gZcD2I-X3$sSPk*(z!Hpd2hHXEAr-u9wG7N|trxZ+?cQu}47ZFKsF$1|PD$q|{jvoU|g|=;LLt`5)Q!cOTYcdqC#M%2! z?of%ecT=@6^WoSZapD6>%{95I0XEP?@@rtGdTE7jho2wDk(>fT|J1TOz3tELeIwq;>sSW}!2CP=HR9e5Tvztp zUGCBna&pC)7PEAGT*vvX9kh`Gkb8Yfw&VUaEEVoMC`$4~i!HRdSn5zW;O$-MfViVJ7So!Ci{->ZKDl5E=hL?l+88`!k*AV_huhnw^4 zxzGs$BqfoF-$@jUbAG8=h|{rC*O#3W2N5}g49<`UDDu24Z;y>t$nwPi3_i2&y<=uZ z!(68z@8IKKeA?lAYIX@Q0ztO#tuV1NN?l zM)lUCC3E6LU(WT7|8`VW4ID%La;7PK6H-G|E*7`f1A;J;k__k#`(C|?s4(li?% z&ju8bdwXvchRc84<1xPTgN<;me{aj)kb2MlqSk5P!qGwuvW~~ZUl{H}NMkliXk$x- zJ1BR#H%t~Lv&Ut)TuUKKCl)ejn2i^fce`fPEuooYPwGEuo9~#cE;PS1)S?}DZqce% z^3u3INId6z;nJG-J8pWpe8o3T`nW% zv#EObvIK&HsOQUfkb*%p>wfiMsyr31JsAp^+-={ynu5nRkCC_cDa_DYfN{$=o==#h zBR3s)Jut=e(T8hm8#4WfzOD0hyiYQ$myu={?^i8za*-y|v4aPxtHH8;+(nV-=$796 zFm0CRD31y%`D{~-PU%P8UL=3EBpBIQ=)}S0b)#V zxAM3dUA^iQiO9*lMr^uoSD1!nNV86)W#E2m*CTz-ub5KSJ1C*1`DxeAvVT(kRgzG~ z7&Ih%^YY>+`t&i5Pl3}y4#sh&*0mE8rv^ga?}SlbL9lY@IUxL?n*7w-g#sU$)ChyOqjBf^(SaXCixr8c^|Oi#5#KCIoR+!TxAuc*`>`d9$} z!-QoX!kVYv+3NRtzBT7HPNaYsPiO0*vQbeHs;en!0k+GGzgRK_dhasg*fQfVf#rm^ zgB$wmxzTbL1+wpUTszL+?VTgg(%xnI%M>R__sMem0QxMI;Py*iv7+0%^J+3E-96%O zb#$9Yv{E%OFkNDRcBjC9W3j4)glb>4p>VTl{_ zC%`u|Xl-Z9=bk63fq^U{=QjU>E4hwWMR76#dU*H@8XCebRYylz&zZQJBoi75<<3W* zSKco;vfCuDAt@Xgicu1E zV;E`FuQ!cdv$HcAI!wbu@IXWMyB|9jFrX)v*rm{E;I1Mz-TMoh0*X-vdMTVxs4>z| zQ!OZe_Ruvv0X3zn&2mYlS)Jr^dSt~ncq3v1whsHUs*FCjA>R63q9P|X1TP}jvldlC zK9Z~)K4ZVWRdxt(FPS9>#1H);#G+O&PL7Ubxw~*G9Qt~**GY+W8BF+Ir`dL%iEYB` zMZmu43xt>Ac!rOFvP|h}+9qVieRG5Ah{^P&FX@)n+l=5dGN1wwtW@>1 zmltF%5hw=mAuurED>7-}?4eob^KOJ$mh9v8v$fi#N3qG850rDzyw8M72$Sqz^PaM0 zj$-=x=(?%M>&mFv>+bU!XunQV`?4<{i18RHA1&&4%fJ$s&A-GvX??nzB7%xy`;!9N z^R@Se$iak--*K=u;z?NVX5vS*4xhKTiA5e3Yc82gjA?&)qB*_fIe@WQvC(vwU`WvLzZ{0DzxN>A!oQ362GNax65gQ*rJ&~up zNG3UnamG?jqx>Nj3IeJ~E$n`IE$Hx^w)GOqhZLan$`mMK%70c34v=SJ4AcH0kW&<+ zr=#?#Tr>_1nYR+k^5zYEX-22GHBxg{=c+!TT@fV$;6mY@UVZ;#>-(v*GBzp9I&i{u zY{&vF1WYDG4v9$Kj7@}lp79;UoCo(T_}*=<<&R*Nt($*P`w7Pl!8&xT_qxVAbe+Ko zZEwK1M?8z1`Q^5@+G^eJ$Hcc-V%3gB158p+xmP=p=Fcb_RzsaPLn$Sd*KVRJa;O3G zmy6GDi4j8JRxAwv6#P6DfiQ-2}rt{16&llYH z5s{I=Mztn?Pgel_ba$l2ap%^sKWt-!$qKWf>T^HLB|jG`F^Nm`m`;c+aQD=}e0V)f zEXez+2$>WR3zurM>2gR={~X?DTf4L%cFHWwJ-?0#7C=JgfGivUK(&_CC~hZx5C{mU zt}isZjrfKeVtOW{iQ`z<5(X~VtoimQBJ=97 z3=b3W>CslSKERItu@%mlMSfQkMFloQgGL3R2iDdimi&;TnB> zb93>q(g^BvbVXyQdYrJeHMO?3OJWP8Ch+`fHchWYg)X zpM5?19sq_k7c+SM@Ee@$#YjtuB6kp%o6I}%+wSl9k%Ss**}kJYuoL#JBjR!DrOy}1 z0EZBk($3!Dyba0T?sybN>a8oxQvcT*(jT_}CWIIc;$}Tsy+?wELy9Y9fB=*Ys(K&S zkNb6}uRjSsPX#MYqz|$2Tt!6*xSr;Sh2a`DpL{%BOnLY2lb}t|;a?(*mDtLTpngLq zC$6LeR(BfG0yp9yP}kB-`0Q|Kse4n)!x!}=LP(fwUYt?a0bBroQZ)q=jvrz1(|$tJ zWgM}f>hd)dnU#W*wn7KW@rv%b33_QUdd0TQqwph^Lh@M$h`+k{-din39dnE%J+M+E zq%T12M^;CR&=DWbm%d6%$?lE2k&E>+}gLGdyojteT!PO^y|o8dsM+ zUcHlM=&CGK7warsq6~H;lI`*PFB0WFktzE)%G&Qzz{A4aYEILt|&~Ai1nM|5o2QaBMvmn00uEIyyRG_>h0PincGTKF7Dzu{>2USKtoT* zf(r=Uw%dfJ_g8Ks^cQ8TeKpL*U?t@zh6xBYp!0ESA|p|wq5}G7e;G*eWzcpVjweIs zk@fz;qPN6WH&yD`{QCOG1}F^NZ-gy&3*R}^aT#@XFf#(#%?+4H-D&jX!w((3zSjBP z*l@BIU*pibvMS^m7EULp)_3#``0{v``&I7fu0bqd(v1(9S~n>?#~U923Z!r#4%Gxn zG=v}sET&nie-kbl5c8lX3U*w&6K3xL#6tVQzaP&w|DqpmH?FDax>!Cuve`)YS)?n%?VNdEt;MEz?+G) z@FtkDez|moNZY@*@(MPdpcC_VoE&O{UE3>Gbwf@H0 zb=t>wh!L@J0`pU{R^0T$_<+4}RdaJ_+|U*PblFFI{lecTg zR308-b5=U59};}`?G+;HbK#5sLa<^(kV~!7{rx3r$xBLSc6TGgZ$r(UzBP{+9y~mK zc5uarlPMBA{?p+Puc2E!I$TA{G?1MmS1bwoSey_q%rNwjhI0!9N*wMs4Fk-bm0Am1H18bQt z-C<#W1f1BVI26sUNnZC~d)N168Ol~S>z5%|^P332#JO!wkM!GhJNqPG{~Ajwt7KHb zcNsOp4;lbvZ|p?vDGhdp&pKa*rbN4b2!n=(mS?|8DpNP-e6O%tcIGmwrL$?`v>n2M z73qS4rjg07v<9kFJ`x5wwFvX3d5(s~n6B^__gRs_0|U0mzmOtA2Dj^%gkew#Tm}7z zkP#ya(ggGRsc?J{fHe&cph3VA$EkL+Mgs_g{lkb+}NXx~eVI++rLM2)8i z9cAe0r5wEs{VvqYmQCX*Q^~$%(LwbKo%@>@jf1V-pF@sM@97p zR}06u2ofcaSTz~|kCQQiyu60<%wi!pq4Icm4LY8L$umZ^x%#4ChM6)wMQ%6O1;$M0 zxqtRiBP5Ji=HsDm-GD_l_K->wB(l7C&-N)$+_8_9@(0hEma62IUe|)XC)(wu4nP31 zC6vN9t_o(v2*B0fw=*Zty%X)SZKeni7+;2x439+F?UGC;x5pB1T(Lygm*qm^5>?73 z`U42~qoB_$oP{C>*ffUw!*@@26D|NC~D1d*%12?Ad~3CD%R zN*<9_CseM;3?O0aza^8-?}HOh5XpOqDwiqV&>)?>N95612e|w9o~fzne}VvjO5O+t zrp8zLbyPy%uZ;5b&z(CMDk}41*}?K%CwgM-QfdpMo^Zshvn{czBMxA$t5{T;jOM!i z*O@ZFqC|*9g-EinAD-$cCid7emNt)*<(d@8_<*QTMg%K=u&{xOlSIs%DEX`np=m{R z%s$eG?u5-zuA6>;SBm!(aaj{R;rB2u+2) z)1olQe}+dEGuxvKMF19~$PM?iIp5QyCe#WwEz9Mh7N~4Pc2Y`Aw|G8J*RIs7@$-gG zBc><6QC1YGhAs_gi9Dtcjn?z#RGBkUNBCmUbBBe^a=DbJkJyMiV^*Z_TYq;7T@y#l;o<92iU4JbKP7>n9 z>L4{G<=Ls&KIka|D+n|LUOZwqH5nmEotX;|jgP~!=f@to7pZ}lu$E;gR|%`rs^~~0 z;{^eHhM-n|tK%)DacXk5iyxuAo45*eNy?~3hD1B18e7hOy(sFBccN)zu-f7|9B5wO z`17z7F*-|P4c%P&-0o)sZS*frv90c@K8JiOxVKfv!mw9gRH`L<_q_6z;yVaDJ zWnqaA_5ZoJoJ1k;QC>`J;}tRqf7eXO%oI1Wi-!lBbHukGA`9CJpEI{iSm~UP`#wDS z+QTDwzQPGJZSmsbu5m5oTZeqb6lEAJYpMWkbX#%#K8;L4Tc&-$ofciW{)az3Y_x7f z_eZtIddEC6dA7JetT0xXDMFTzX=`gG#9_vPIvb?hYH=~&Do~khqzQvf5c8k(`D3Q) zdDHFgB;!^ziJzP*Y0lent9PE|oYz){^b1-%K4v#JgN?*Pddm{&BjpRB z$q7RiJSFKv$?XppU!$tqf}ZU0tctTeH{E_7C`H?$vD zi>h?{t;NO9FfqYz;mSv%zc*to;KE({D6ys58U4KhCRqU_yObToEB(mw(M@r-=z=HZclxt?4_L=9AE4*^BFMv{z)F!a@ZwRFlaROZCcr>8z2AAKjRN{tSChqFA{ z1a0z^SgI^FKqVo^_T z;p@&s3DHbbEXc&YNi+9=mGK`N%XN5U#!DZr%;AEb7NbgWoSw&;&i6#eL7N2m`DRbd zC@|<{L%2CzosrImn9~rkGFhFmT9SI+yla!1Jlb*R-|ta*Eh^0MA#5{RoFFO*8q{{( zGWFXm!6m1Q08U!t;pf{@4YqE%Ktaa1q!BnSPG^nsJ!@WDWA3MHPoAkMm@+;Y?l$O; z*I|9vXhcP>bg8aq#^sNG11eGKX-e2mRK+Iknm`!@b!lp7^yf%P6&KgrwJXTxA4I=I zWndX?3hRy~9_A7-S7D-^%vf3_vsLQV7O=CPK&3vL$6WU8VE9wHPEju%HMiAlyGzE? zU4_-df?D@W1t6s3#?r7x^YidPUXk-9gO${V=HH@b%!8M~o(P&z4V?Sxje%3f8DG7)T22(VyxE^-@k&$*G!wHA= z-q~0W*Z_Q7u?D#R=K(`-_bPRaqzVPzefm_9MQ|MA~=% zwOYZld^$7g;y;F2SS*SHYg9}{Qiwq9x7PN90g`XYOok86rcDI0ea^aqqD8@2IiR9C z&AAeuI(gpZr5)xEQhR1$@AqzOAJKpW!3?{MO4HrC{b2HGy7#!13(Be!9*Ye+t&(yk zFJ@5C@AG3fd$|D*+^Xfje^>mGolr6RbvxX97^Bdf56t9mHJQiKPGNc2K9gh)Z?X>h z;k%}@*2bV+MG)}WgRXLF_($77OUvX?JW5kyGTV80_@Ssr93L7y+QJ;DtBh~`&swwU zTP!)kk8_`4YZ1Buyr@zlKm-a^bG~MN7>h9Y3(^AYqoQ!e<8B`ZVJwN+I?-2#+rT{{ zKv$(;yTkLy-#@n2j46kD&?s`5ZpQ3kaL^5p0165!Da{wmI0+&No$*-v5Sko2FbIN} zS)-ksM6#c|17fuCvFAcvSA4oz4}arHdr6nw@dnwQwX~lHBFknDC@4gyr#a8AvN|e% zm4eYDQ+SxRYEoP3>drlhSi)R1N@%DBqe-jdsyBl^F$tT zq?hgzk?s^}5JeXRq@-&p0dWPS1%#zjx?zED{NC%mu6O=gV&{2g&N=tF&&-)K@3-cA z`Q>q-TUyNy`WNq7VINMH(HY0S-*w+y$JFJ6EFw*5H|Y8ftn%B|hx?>eYAbcduhd-u zQYCaj@9!i%gnC^Xs@&!+p}EW*ZeIj;jTurx?cMI=gW6N7KIgdJ2!200il(7{tgQ{* zYxMbVdf0RJRf^J*lfwt?a++zzOdgt9q?`DnXW>^uH4^ zG)QE9v(&s}?KnumLk?1Uq?kp6^XWRja{DRidu|so;68J8ud2WcUfvH$lEevauu;7f zcKN!E4fs2Ebx@%Dey!;`$kDYzSb}ay=w2rz_w${);rL@qM%qnEu+a0X#gzL4>?H4U zT1jr&XX|jvDQIY@DaRG$e;pcR6iJ+dlN}H8chg#HTMDc}R;uqs`oeqb{`G^t-}8R2Nn;xIsa zHoUy3YC+;rBa%f;gR7&X7w~H0Ll-KC1iCg7OjZ9_^o?YxkAO$v3@SarPf_B3ThyDE* z^xOI5L*#BgpeGJ~=r*GNwY~ic)MpUrDf?Pe%ON9!t!Q;IMQAehJluNf2Jt1fZIKVy zE{=SFn(p2``_?Rlh2dJnc0O3XmATi6p`e+veJnBL*_r+0caQtD1Y}6-?zQUE2I$l(Aq0I|q=+`M@ zsSDbeZYCrt^zh-Awl6;)TS|9;>KwNmUS1u>S6A?Yp7HZsye!%)J?*9?h!;-TxeKE> zOIzrZCInP$)Et6V%@7vvl|C|Z$JGQe6B71(l2i0e(ySzak`4dqQ2z> zb+$R9m%MFB_BptnH;LhG__zCl;Ww^*MLTmj@Z4~twcTL&zfNs+pZv?DLV6yYn%}4r z|Gna}n~4Ll7=ta2zE8P`a7X8l2Og(nqE0)|`sVxLY8)IBU1g*VBW75wG@-1bP)9ID ztTgB_?$lzlI)aP?(q{rjC%vS9y==DG2kv1>w#b<%FRs((ZnJ zlw)y`=YDWuh)ve;2s=wGKCz9;rn?%9Xc&i4P5Bo7sCE@7{Z{7_f|f--`j;IGR}7Ya z_+eN#S?0&dJts`tzj!jCAZt0RByx}gaiI0Y`|FU9TGJdCguG%sIhz}3CvV9?rGLn{gN{&{#( zc{h*?dE-U~dnoQb&>G}OX#eLwV&|Znpz&zm#QXOMw-_c-=zoHv4xE1pn5G3VBGAMC z?P7E>Nh%0LXboOq?^H7I)JyfqaWY3SU87d~w?zBg^QI?Zi$IOa}xlcTMtOexde`H1j3tsHo0(vk#d?^9DLQJ3%F@s;a78w@YGH zzlCox(b2G|E=JOrsp)B)XKblveAbGJy;*{GVq#*(CMN1^spb{e*EPGQqKV@E`%B>9 zV{?;u*U>yt)Z*IEM>8|Cyu3VTXXllal*-D=p`jsAOe;MjgC;?t)%;ra*8HB|@%BvV z#Adf8KjhbHE)zZDva_)<>`*J^qJTgkEG+KHzktB?Ex+uAm{QjMK)p!}N%8SsVtK1( zQW;H6VztKVn(TW=M@MAjCNp>uVgiCwNg_hRt*KhaXDa zeft2@n+JbwW}@45ZKk8+aejzMzZ8Ml1)Z-KrLt+7R|h=qbyrNJz5HMS#tH5A(6~bF z?d`!M>(~#;VA?`LLUaq&`uh5mRa6#uuRg_J!=~$9b&K^J$G^OLBe>kS`Ysi{?C|m;_qB<-Ln|++! z+;$)32NvjYI2%l#A8nq+ny{tT*4IyrjXBS@WVv=TNCgERZH#fI;X?*x#*YOoUl<*a zXiBF1um+?iQ_>uUpltuM4jPbd-zYQFY0eUAY z6W`S(^2e>KFZGeLu!)Dq{?+Bhlf>#tCmLa=IT{=9BSJ7sjEsy>a#mLH$U5}Csi_HM zm2SE78aF7F8RUz3I}8=bgPXx-W@b`SQh=UtqlbmS4|(t2Ns5a4VNc!DZFt+T`*U-1 z&eL^$)&dn1&6a2TyeO>4Vo!ob(LpJ1+n)x+{p18V0CJ@xNSvLba^np&@N8EeHye4ddtMr(C?cy28Z+_c9i#=cFemYw78Y zPEJx$QnHiBQ1BT0&CTHy&AgzZGi$Qu=n??xgJgdyDtcN9ch*+>yq(!^i*IGjk}dhF zY0SY}l$IfIS6WLedB{FKCT4wYEjlsLywair%!;R{XH--a7Z;a}z+?)uB7}pkoG|t5 z_wP=)w}0@jElP>~J=T=E)I%Dem-m4R80hJF`FPo5u`Hy0yStU3%lLSqoPJqZ+2`R?gKnq0$1rJY8GW=VNpBfr| zZ}}WJ$8~&QtnTyLs+}m&E9nfwQ@0iDbq7{4-wcPIjl8WWl^dy1VmZei45o38&9y(X zxBuN4ao1;Ow$*9!>-P3GnBIXr@zqpKNs<^jU}gs^{WLT*7pIF!K=c>q=e7g6eUBE7 z0*oT%VahCTK)t?d?w3p7Q-EZamX??mWB(~y4Bp1#DzW^kM7=<0%=sanl>(^Q^+G1S)A2ZsCDah$t; zy5HSYQ*#i6$xhXil>Evk=GsF{TwBv#WKx*>&1XB7&x^V&|46$XCe4&4K(M&y2ONZs zPVe+7H=3M`Y{q{z589n_tiX7n`(t8a0=EWbN4(V3;)m=3m{U<@sV5{nkaxzQF2Un_ zDckmXXdG&%?1fxrTm1d}8a{u9K}?;@IyySwqGAUJNASTuyJ;boYh!bBddgT(Q1Hy! zwQ0Rj;^lE>|H}LK?<4+gSM>M+U;$?AP#bWCJ=;ND@Gx3CIdQYGu?YwWh>Ks07VECB zuLCfDdHfgnULpd5r}Yhp?Ad1Ding}4-bJGpKX-Tcz1TD^Z!xnMFJ8dm4Ct>f0$v3L zUCp+>e59WJfQ;;DR992t@RzKFghWC@0uV1_2jkh<8Sv0HHa6kOyV22q{+MFozFk<+ z&$1p2Vtm(*+S?(F(L9i}a8AN?b4$xpjwesJxJnxv8*6I3fD>X%jj7-vkrA{TSQ6D> zOD!JT0LoVL|J$0ESoj`5Q4?e1Lgla&+re=JIODnhqch^5x2I>+ z!COYA^Pl2x|7iquFF}n-I&q&&wL;k_A~Vna$M_KoTlJV@`RAo$aTL5)b791kk;-an zx!|c_T7X+OGd4c{sppECs;a7nh6XTpFRw$c3Q!uptloq6x>y{o7LVsmTMcCU%^K!SE4-zk2=p3J%h-9gul7MLb(Fd9D}*4R_cjc((^=5VB`C@OFRBs$s86}O4lo5Vdf4Ta{y=pH4F_4GfJ4kU6s$%fBihUWaj3@xIaV1Og1RnT-pzji@Dm;#K^E1M?4a6A|L!gyR8v>i zDJK=2wCN`LR)rP)b)-lW(1((KTN+AA3rgFrNJ438X#fez%F2&4-&q@tPrNueIoa9X zUJ-S1aw1@q8xg{^?gI7;%+$svt=|@KIr^mMOlb~6*}1v7>mxfE_MM&9clE`Gr`c!|ll zaXsWv-DqkT7qbYsxk;6Ryu7!U7xc`^iWy#YsM~8-n0^l$#1HW!=2J!9fKpt>cb!h$$0^yRFn7D!wf-g{7 z0ja)}0O{Dhk>TN=^-8D&ZRO7Q)-)9yi}S;E;P(Cs=kzWXmzSGYS$4l+Rpl(@oR@)>2H)hN#*dIG9ixBhS6N)l z!NbGD#TBHKuqw{XN zVG~a^iUdIfS7rcY?NDo6G(tj8|1R^bp`qXB#$v>ew;bS4JQ*43>6~dQaoqwSv>PZd zA5TvQq$IWP0Vy>TX-tiA*~BIiF*Tv8q^>UEw`=k0RV(29HTERxBUqLHGSJ8&`z4Pj zubGQRsL047_=TwxKq#z&1mgnQou@G|I}5Vl0&xX+GSGvAgR8$678YXT;&QUH0WV@= zW(KeWZ_p^xEge%~A&u%H0rmFy2ti#4t+`?eGZ} zse>>wqRQ_DGYv2!7=###ii(;UZ$;@6K|pa4_zVhgQ z7o(@&_GkoOAj6k8Gn>Jl9cbo>>Fes=Cm|sLbcKcnut$=hT)wAIbK%1u^*E6_%AnYt ztZbMX8yI&+pEY0#z{tzW%IN6mQnXWWFL43wU`thIAqRWkll87};D4p1LsXCg)Cou= z5>V-CyMELhHKR0%+OxSfSo6%)UM~a2Z!zJzM`*_71oi5|pxo3*TRY_5kAZ*b|6Rwp aVu*~UGXIEIUJi0IA!T_DxpEnc(EkU9G5=ct literal 0 HcmV?d00001