Location: Our offices are in London (Farringdon), with the ability to work from home for part of the week. The Ada Lovelace Institute is recruiting to the newly created position of Associate Director, Data & AI Law and Policy to join our senior leadership team and develop a comprehensive strategy for informing and influencing public policy, regulatory initiatives and legislative debates on data and AI policy and regulation, in the UK and beyond. In the past five years, AI and other tech regulation has become politically palatable, practically achievable and even commercially desirable in jurisdictions around the world. The year 2022 alone has seen a significant global uptick in proposals for the regulation of AI technologies, online markets, social media platforms and other digital technologies, such as the European Union Directive on AI liability, a forthcoming AI regulation whitepaper in the UK, and similar initiatives in jurisdictions such as Canada and Brazil. At the same time, data regulation is being reformed and iterated in the UK, EU and beyond.

Interpreting critical variables involved in complex biological processes related to survival time can help understand prediction from survival models, evaluate treatment efficacy, and develop new therapies for patients. Currently, the predictive results of deep learning (DL)-based models are better than or as good as standard survival methods, they are often disregarded because of their lack of transparency and little interpretability, which is crucial to their adoption in clinical applications. In this paper, we introduce a novel, easily deployable approach, called EXplainable CEnsored Learning (EXCEL), to iteratively exploit critical variables and simultaneously implement (DL) model training based on these variables. First, on a toy dataset, we illustrate the principle of EXCEL; then, we mathematically analyze our proposed method, and we derive and prove tight generalization error bounds; next, on two semi-synthetic datasets, we show that EXCEL has good anti-noise ability and stability; finally, we apply EXCEL to a variety of real-world survival datasets including clinical data and genetic data, demonstrating that EXCEL can effectively identify critical features and achieve performance on par with or better than the original models. It is worth pointing out that EXCEL is flexibly deployed in existing or emerging models for explainable survival data in the presence of right censoring.

INTRODUCTION Adaptive planning is ideally suited for the deep uncertainties presented by climate change. While there is a robust scholarship on the theory and methods of adaptive planning, this has largely neglected how adaptive planning is affected by existing planning institutions and how to move forward within the constraints of traditional planning organizations. This study asks: How do existing traditional planning institutions support adaptive planning? We explore this for flood planning in the Lower Rio Grande Valley of Texas, United States. We draw on county hazard plan and regional flood plan documents as well as transcripts of regional flood planning meetings to explore the emergent topics of these institutional outputs. Using Natural Language Processing to analyze this large amount of text, we find that hazard plans and discussions developing these plans are largely lacking an adaptive approach. KEYWORDS adaptive planning; uncertainty; flood plan; Rio Grande Valley INTRODUCTION Planning for natural hazard risk reduction in the context climate change involves decision making under conditions of interacting, multiple uncertainties. Some of these are "deep uncertainties" connected to long time horizons, nonlinear changes in climates and ecosystems, and inability to reliably quantify the rate and magnitude of climate changes (Babovic & Mijic, 2018; Bosomworth & Gaillard, 2019). Other uncertainties are associated with the ambiguities and unpredictability of socioeconomic systems, including population growth, land use change, social conflict, and the whims of political will (Babovic & Mijic 2019; Buurman & Babovic, 2014). In the face of these uncertainties, a new paradigm of decision making has emerged that emphasizes the development of adaptive plans and policies (Hassnoot et al., 2013; Walker et al., 2013). Traditional planning approaches typically generate a static optimal plan to reduce vulnerability to a single'most likely' future or to respond a wide range of plausible future scenarios (Haasnoot et al., 2013; Manocha & Babovic, 2018). Because the future is largely unknowable, static optimal plans are likely to fail and adaptations are made adhoc to adjust to emerging risk conditions (Haasnoot et al., 2013).

The U.S. criminal legal system increasingly relies on software output to convict and incarcerate people. In a large number of cases each year, the government makes these consequential decisions based on evidence from statistical software -- such as probabilistic genotyping, environmental audio detection, and toolmark analysis tools -- that defense counsel cannot fully cross-examine or scrutinize. This undermines the commitments of the adversarial criminal legal system, which relies on the defense's ability to probe and test the prosecution's case to safeguard individual rights. Responding to this need to adversarially scrutinize output from such software, we propose robust adversarial testing as an audit framework to examine the validity of evidentiary statistical software. We define and operationalize this notion of robust adversarial testing for defense use by drawing on a large body of recent work in robust machine learning and algorithmic fairness. We demonstrate how this framework both standardizes the process for scrutinizing such tools and empowers defense lawyers to examine their validity for instances most relevant to the case at hand. We further discuss existing structural and institutional challenges within the U.S. criminal legal system that may create barriers for implementing this and other such audit frameworks and close with a discussion on policy changes that could help address these concerns.

The UK Intellectual Property Office (Patent Office) has provided fresh guidance on patent applications for artificial intelligence (AI) inventions, including helpful scenarios explaining how to successfully gain AI patents from the UK IPO. This guidance is designed to help ensure the UK remains a cost-efficient forum for applicants to get granted patents in this rapidly evolving area. Artificial intelligence is now applied in a vast range of fields, from pharmaceuticals to the automotive industry, and from industrial chemicals to fintech. The enormous range of possible uses has created challenges for the Patent Office when it comes to examining patent applications related to AI inventions. The UK IPO applies a framework developed by the English Courts when assessing whether computer-implemented inventions, including AI inventions, are excluded from patentability as merely "computer programs as such" or if they escape the exclusion by providing a technical contribution. This involves assessing a number of "signposts" for patentability.

The European Commission has proposed new rules to assist people who have been harmed by artificial intelligence (AI) and digital devices such as drones. People suing over incidents involving such items would face a lower burden of proof under the AI Liability Directive. Justice Commissioner Didier Reynders stated that it would create a digital-age legal framework. The directive's scope could include self-driving cars, voice assistants, and search engines. If passed, the Commission's rules could coexist with the EU's proposed Artificial Intelligence Act, which would be the first of its kind to limit how and when AI systems can be used.

More young people than old, and more men than women, are open to artificial intelligence-powered machines replacing people in a variety of jobs, according to the latest Media & Technology Survey from Boston University's College of Communication and Ipsos. By more than 30 percentage points, Americans ages 18 to 34 surveyed were more receptive than those 55 or older when considering AI replacing people working as journalists, hiring managers, trial judges, spiritual advisers or leaders of religious congregations. Respondents ages 35 to 54 were in-between. Men were more receptive than women to AI replacing workers in those jobs by almost 10 percentage points. Still, three out of four respondents across all ages, genders, ethnicities and income groups say having AI replace people in these jobs "doesn't seem like a good idea" or is "definitely a bad idea."

Humans are naturally endowed with the ability to write in a particular style. They can, for instance, re-phrase a formal letter in an informal way, convey a literal message with the use of figures of speech or edit a novel by mimicking the style of some well-known authors. Automating this form of creativity constitutes the goal of style transfer. As a natural language generation task, style transfer aims at rewriting existing texts, and specifically, it creates paraphrases that exhibit some desired stylistic attributes. From a practical perspective, it envisions beneficial applications, like chatbots that modulate their communicative style to appear empathetic, or systems that automatically simplify technical articles for a non-expert audience. Several style-aware paraphrasing methods have attempted to tackle style transfer. A handful of surveys give a methodological overview of the field, but they do not support researchers to focus on specific styles. With this paper, we aim at providing a comprehensive discussion of the styles that have received attention in the transfer task. We organize them in a hierarchy, highlighting the challenges for the definition of each of them, and pointing out gaps in the current research landscape. The hierarchy comprises two main groups. One encompasses styles that people modulate arbitrarily, along the lines of registers and genres. The other group corresponds to unintentionally expressed styles, due to an author's personal characteristics. Hence, our review shows how these groups relate to one another, and where specific styles, including some that have not yet been explored, belong in the hierarchy. Moreover, we summarize the methods employed for different stylistic families, hinting researchers towards those that would be the most fitting for future research.

This paper is concerned with forecast error, particularly in relation to loss reserving. This is generally regarded as consisting of three components, namely parameter, process and model errors. The first two of these components, and their estimation, are well understood, but less so model error. Model error itself is considered in two parts: one part that is capable of estimation from past data (internal model error), and another part that is not (external model error). Attention is focused here on internal model error. Estimation of this error component is approached by means of Bayesian model averaging, using the Bayesian interpretation of the LASSO. This is used to generate a set of admissible models, each with its prior probability and the likelihood of observed data. A posterior on the model set, conditional on the data, results, and an estimate of model error (contained in a loss reserve) is obtained as the variance of the loss reserve according to this posterior. The population of models entering materially into the support of the posterior may turn out to be thinner than desired, and bootstrapping of the LASSO is used to gain bulk. This provides the bonus of an estimate of parameter error also. It turns out that the estimates of parameter and model errors are entangled, and dissociation of them is at least difficult, and possibly not even meaningful. These matters are discussed. The majority of the discussion applies to forecasting generally, but numerical illustration of the concepts is given in relation to insurance data and the problem of insurance loss reserving.

Argument Unit Recognition and Classification aims at identifying argument units from text and classifying them as pro or against. One of the design choices that need to be made when developing systems for this task is what the unit of classification should be: segments of tokens or full sentences. Previous research suggests that fine-tuning language models on the token-level yields more robust results for classifying sentences compared to training on sentences directly. We reproduce the study that originally made this claim and further investigate what exactly token-based systems learned better compared to sentence-based ones. We develop systematic tests for analysing the behavioural differences between the token-based and the sentence-based system. Our results show that token-based models are generally more robust than sentence-based models both on manually perturbed examples and on specific subpopulations of the data.