Future Work Research Articles

Generating Python Type Annotations from Type Inference: How Far Are We?

In recent years, dynamic languages such as Python have become popular due to their flexibility and productivity. The lack of static typing makes programs face the challenges of fixing type errors, early bug detection, and code understanding. To alleviate these issues, PEP 484 introduced optional type annotations for Python in 2014, but unfortunately, a large number of programs are still not annotated by developers. Annotation generation tools can utilize type inference techniques. However, several important aspects of type annotation generation are overlooked by existing works, such as in-depth effectiveness analysis, potential improvement exploration, and practicality evaluation. And it is unclear how far we have been and how far we can go. In this paper, we set out to comprehensively investigate the effectiveness of type inference tools for generating type annotations, applying three categories of state-of-the-art tools on a carefully-cleaned dataset. First, we use a comprehensive set of metrics and categories, finding that existing tools have different effectiveness and cannot achieve both high accuracy and high coverage. Then, we summarize six patterns to present the limitations in type annotation generation. Next, we implement a simple but effective tool to demonstrate that existing tools can be improved in practice. Finally, we conduct a controlled experiment showing that existing tools can reduce the time spent annotating types and determine more precise types, but cannot reduce subjective difficulty. Our findings point out the limitations and improvement directions in type annotation generation, which can inspire future work.

Factors Associated with Costly Hospital Care among Patients with Dementia and Acute Respiratory Failure.

Rationale: Understanding contributors to costly and potentially burdensome care for patients with dementia is of interest to healthcare systems and may facilitate efforts to promote goal-concordant care. Objective: To identify risk factors, in particular whether an early goals-of-care discussion (GOCD) took place, for high-cost hospitalization among patients with dementia and acute respiratory failure. Methods: We conducted an electronic health record-based retrospective cohort study of 298 adults with dementia hospitalized with respiratory failure (receiving ⩾48 h of mechanical ventilation) within an academic healthcare system. We collected demographic and clinical characteristics, including clinical markers of advanced dementia (weight loss, pressure ulcers, hypernatremia, mobility limitations) and intensive care unit (ICU) service (medical, surgical, neurologic). We ascertained whether a GOCD was documented within 48 hours of ICU admission. We used logistic regression to identify patient characteristics associated with high-cost hospitalization measured using the hospital system accounting database and defined as total cost in the top third of the sample (⩾$145,000). We examined a path model that included hospital length of stay as a final mediator between exposure variables and high-cost hospitalization. Results: Patients in the sample had a median age of 71 (IQR, 62-79) years. Approximately half (49%) were admitted to a medical ICU, 29% to a surgical ICU, and 22% to a neurologic ICU. More than half (59%) had a clinical indicator of advanced dementia. A minority (31%) had a GOCD documented within 48 hours of ICU admission; those who did had a 50% lower risk of a high-cost hospitalization (risk ratio, 0.50; 95% confidence interval, 0.2-0.8). Older age, limited English proficiency, and nursing home residence were associated with a lower likelihood of high-cost hospitalization, whereas greater comorbidity burden and admission to a surgical or neurologic ICU compared with a medical ICU were associated with a higher likelihood of high-cost hospitalization. Conclusions: Early GOCDs for patients with dementia and respiratory failure may promote high-value care by ensuring aggressive and costly life support interventions are aligned with patients' goals. Future work should focus on increasing early palliative care delivery for patients with dementia and respiratory failure, in particular in surgical and neurologic ICU settings.

Head Kinematics and Injury Analysis in Elite Bobsleigh Athletes Throughout a World Cup Tour.

The neurocognitive health effects of repetitive head impacts have been examined in many sports. However, characterizations of head impacts for sliding-sport athletes are lacking. To describe head impact kinematics and injury epidemiology in elite athletes during the 2021-2022 Bobsleigh World Cup season. Cross-sectional study. On-track training and competitions during the Bobsleigh World Cup season. Twelve elite bobsleigh athletes (3 pilots [1 female], 9 push athletes [5 females]; age = 30 ± 5 years; female height and weight = 173 ± 8 cm and 75 ± 5 kg, respectively; male height and weight = 183 ± 5 cm and 101 ± 5 kg, respectively). Athletes wore an accelerometer-enabled mouthguard to quantify 6-degrees-of-freedom head impact kinematics. Isometric absolute and relative neck strength, number of head acceleration events (HAEs), workload (J), peak linear velocity (m·s-1), peak angular velocity (rad·s-1), peak linear acceleration (g), and peak angular acceleration (rad·s-2) were derived from mouthguard manufacturer algorithms. Linear mixed-effect models tested the effects of sex (male versus female), setting (training versus competition), and position (pilot versus push athlete) on the kinematic variables. A total of 1900 HAEs were recorded over 48 training and 53 competition days. No differences were found between the number of HAEs per run per athlete by sex (incidence rate ratio [IRR] = 0.82, P = .741), setting (IRR = 0.94, P = .325), or position (IRR = 1.64, P = .463). No sex differences were observed for workload (mean ± SD: males = 3.3 ± 2.2 J, females = 3.1 ± 1.9 J; P = .646), peak linear velocity (males = 1.1 ± 0.3 m·s-1, females = 1.1 ± 0.3 m·s-1; P = .706), peak angular velocity (males = 4.2 ± 2.1 rad·s-1, females = 4.7 ± 2.5 rad·s-1; P = .220), peak linear acceleration (male = 12.4 ± 3.9g, females = 11.9 ± 3.5g; P = .772), or peak angular acceleration (males = 610 ± 353 rad·s-2, females = 680 ± 423 rad·s-2; P = .547). Also, no effects of setting or position on any kinematic variables were seen. Male athletes had greater peak neck strength than female athletes for all neck movements, aside from right-side flexion (P = .085), but no sex differences were noted in relative neck strength. We provide a foundational understanding of the repetitive HAEs that occur in bobsleigh athletes. Future authors should determine the effects of repetitive head impacts on neurocognitive function and mental health.

Towards Faithful Model Explanation in NLP: A Survey

Abstract End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to understand. This has given rise to numerous efforts towards model explainability in recent years. One desideratum of model explanation is faithfulness, that is, an explanation should accurately represent the reasoning process behind the model’s prediction. In this survey, we review over 110 model explanation methods in NLP through the lens of faithfulness. We first discuss the definition and evaluation of faithfulness, as well as its significance for explainability. We then introduce recent advances in faithful explanation, grouping existing approaches into five categories: similarity-based methods, analysis of model-internal structures, backpropagation-based methods, counterfactual intervention, and self-explanatory models. For each category, we synthesize its representative studies, strengths, and weaknesses. Finally, we summarize their common virtues and remaining challenges, and reflect on future work directions towards faithful explainability in NLP.

DIAGNOSING OF THE READINESS OF FUTURE QUALIFIED WORKERS FOR INDEPENDENT WORK IN CONDITIONS OF MIXED LEARNING

In the article, the author highlights the diagnosis of readiness of future qualified workers for independent work in conditions of mixed training. It notes the difficulties that students of education face when performing independent work in the conditions of mixed education. Reveals the content of technical, psychological and professional readiness in the structure of the method of organizing the independent work of future skilled workers in the conditions of mixed training and its essence, the impact of diagnosis on the quality of the organization of independent work and their performance by future skilled workers.

The Effect of Personality Traits of Healthcare Worker Candidates on their Attitudes Towards the Elderly

Background:: It is known that attitudes towards the elderly are an important variable affecting healthcare services. Considering the increasing trends of the population over 65 years in countries, it is important to determine the attitudes of future healthcare workers towards the elderly and to prepare them to serve in the health sector with activities that will lead to positive changes. In this direction, it is important to determine the effect of personality traits of prospective healthcare workers on their attitudes toward the elderly Methods:: The research was conducted using the “relational survey model”. The study was conducted with 581 prospective healthcare workers. Personal Information Form, Eysenck Personality Questionnaire, and Kogan's Scale of Attitudes towards the Elderly were used as data collection tools. Data were obtained and analyzed using the online data collection method. Results:: According to the results of the study, it was found that the attitudes of students who were healthcare candidates for older adults were generally positive ( = 63.46±13.42). While there was a positive yet moderate and statistically significant correlation between attitudes towards the elderly and scores on the Extraversion subscale (r= 0.634, p<0.01) and a negative yet moderate and statistically significant correlation with scores on the Neuroticism (r= -0.568, p<0.01) and Psychoticism (r= -0.602, p<0.01) subscales. The personality traits extraversion, neuroticism, and psychoticism explained 58.6% of the attitude towards the elderly. According to the regression results, extraversion (β= 0.358; p<0.001) positively affected attitudes towards the elderly, whereas neuroticism (β= -0.310; p<0.001) and psychoticism (β= -0.307; p<0.001) negatively affected attitudes towards the elderly. Conclusions:: Given the important role of healthcare professionals in improving the care and quality of life of the elderly, it is necessary to develop strategies to improve the attitudes of future healthcare professionals towards the elderly. Consideration of personality traits in determining these strategies may contribute to the development of effective and personalized approaches.

Modifying effect of urban parks on socioeconomic inequalities in diabetes prevalence: a cross-sectional population study of Madrid City, Spain

BackgroundEvidence has shown contradicting results on how the density of urban green spaces may reduce socioeconomic inequalities in type 2 diabetes (equigenic hypothesis). The aim of this study is to...

From plate to profile: investigating the influence of dietary habits and inactive lifestyle on lipid profile in medical students at clerkship

BackgroundDietary habits have a strong association with body lipid levels and hyperlipidemia increases the risk of cardiovascular and metabolic diseases. Dietary habits have been a major concern among medical students due to busy schedules and demanding tasks. This study was designed to know the dietary habits and lifestyle of medical students and its association with their lipid profile.MethodsWe recruited 120 medical students at clerkship of the age of 18 and above. Weekly dietary habits were evaluated by an 18-item questionnaire. Five ml blood was drawn from the students and lipid profiles were measured at Dow Diagnostic Research and Reference Laboratory (DDRRL). Data was analyzed by SPSS V.22.ResultsWe found 70% of students were not involved in any physical activity throughout the week. Only 15.83% were following a regular diet plan. 65% of students were eating junk food for more than 3 days a week in their weekly diet. Moreover, 19.2%, 39.2%, 32.5%, and 25.84% of students were having their total cholesterol, triglycerides, HDL, and LDL levels above the optimum ranges respectively which were frequently found in students of final year (p < 0.05). There was high total cholesterol and LDL in males as compared to females (p value < 0.05). Total cholesterol and LDL were associated with skipped meal, use of junk food and carbonated drinks for more than 3 days a week (p < 0.05).ConclusionThere was a notable number of students with poor dietary habits, inactive lifestyle and lipid levels above the optimum ranges defined by American Heart Association (AHA) that have an association with dietary habits. This is alarming and can impact the health of future healthcare workers. There is a need to investigate the factors and remedies to help medical students to follow a healthy diet and a healthy lifestyle.

The nurse-led equitable learning framework for training programs: A framework to grow, bolster and diversify the nursing and public health workforce

BackgroundAddressing threats to the nursing and public health workforce, while also strengthening the skills of current and future workers, requires programmatic solutions. Training programs should be guided by frameworks, which leverage nursing expertise and leadership, partnerships, and integrate ongoing evaluation. Purpose statementThis article provides a replicable framework to grow, bolster, and diversify the nursing and public health workforces, known as the Nurse-led Equitable Learning (NEL) Framework for Training Programs. The framework has been applied by several multipronged, federally funded training programs led by investigators embedded in an academic nursing institution. MethodsThe NEL framework focuses on: (1) increasing equitable access to the knowledge, skills, and competencies needed to prepare a diverse workforce to deliver effective interventions; (2) fostering academic-practice linkages and community partnerships to facilitate the deployment of newly gained knowledge and skills to address ongoing and emerging challenges in care delivery; and (3) continuously evaluating and disseminating findings to inform expansion and replication of programs. ResultsTen programs using this framework have successfully leveraged $18.3 million in extramural funding to support over 1000 public health professionals and trainees. Longitudinal evaluation efforts indicate that public health workers, including nurses, are benefiting from the programs' workplace trainings, future clinicians are being rigorously trained to identify and address determinants of health to improve patient and community well-being, and educators are engaging in novel pedagogical opportunities to enhance their ability to deliver high quality public health education. ConclusionsTraining programs may apply the NEL framework to ensure that the nursing and public health workforces achieve equitable, sustainable growth and deliver high quality evidence-based care.

Supporting Coaches to Learn Through and From Their Everyday Experiences: A 1:1 Coach Development Workflow for Performance Sport

This paper overviews an intensive 1:1 coach development workflow developed and used in U.K. performance and high-performance sport. The workflow has been field tested with over 60 coaches in mainly Olympic and Paralympic settings in a variety of sports. The workflow proposes six main stages: “beginning new relationships,” “seeking first to understand,” “preparing for reflective conversations,” “engaging in reflective conversations,” “working with difference,” and “supporting change.” The stages are tailored pragmatically to context, and the workflow does not suggest a fixed sequence. The application of the workflow requires adaptive expertise based on considerable coach development experience and a breadth and depth of coaching and coach development knowledge. The workflow suggests the need for coach developers to build and support trusting, collaborative, and supportive relationships with the coach, as a foundation for the coach development task. Coach development practices and the workflow are continually being developed and refined in a U.K. context, and future work will provide case studies, evidence of outcomes, and refinements to the work.

Wellness checks: Piloting a universal intervention for soldiers.

As part of an Army pilot program, mandatory annual wellness checks were initiated to introduce individuals to counseling and to support psychological resilience and thriving. The program was evaluated using a cross-sectional survey completed by 7,831 soldiers. Findings revealed that about half of soldiers who reported a wellness check rated the check at least moderately helpful in their professional and personal lives. Participants receiving a wellness check reported being more likely to report willingness to seek help if they were to have mental health problems and to report higher levels of resilience and thriving even after controlling for rank, age, education, months in the unit, and trait negative affect. Participants were also less likely to report stigma-related concerns compared to those who had not received a wellness check. Consistent with theory on the common factors in counseling and the contextual model of psychotherapy (Laska et al., 2014), feeling listened to and learning new skills partially mediated the association between perceived wellness check usefulness and study outcomes, although acquiring a new perspective about problems did not. While not a randomized trial, this evaluation suggests that wellness checks are associated with programmatic goals: improved attitudes toward care seeking, resilience, and thriving. Future work should consider ways to ensure counselors address therapeutic common factors and should use a randomized, longitudinal design. Study findings have implications for implementing programs like wellness checks for military personnel and others working in high-stress occupations like first responders. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification.

Though significant progress has been achieved on fine-grained visual classification (FGVC), severe overfitting still hinders model generalization. A recent study shows that hard samples in the training set can be easily fit, but most existing FGVC methods fail to classify some hard examples in the test set. The reason is that the model overfits those hard examples in the training set, but does not learn to generalize to unseen examples in the test set. In this article, we propose a moderate hard example modulation (MHEM) strategy to properly modulate the hard examples. MHEM encourages the model to not overfit hard examples and offers better generalization and discrimination. First, we introduce three conditions and formulate a general form of a modulated loss function. Second, we instantiate the loss function and provide a strong baseline for FGVC, where the performance of a naive backbone can be boosted and be comparable with recent methods. Moreover, we demonstrate that our baseline can be readily incorporated into the existing methods and empower these methods to be more discriminative. Equipped with our strong baseline, we achieve consistent improvements on three typical FGVC datasets, i.e., CUB-200-2011, Stanford Cars, and FGVC-Aircraft. We hope the idea of moderate hard example modulation will inspire future research work toward more effective fine-grained visual recognition.

Project ChemicalBlooms: Collaborating with citizen scientists to survey the chemical diversity and phylogenetic distribution of plant epicuticular wax blooms.

Plants use chemistry to overcome diverse challenges. A particularly striking chemical trait that some plants possess is the ability to synthesize massive amounts of epicuticular wax that accumulates on the plant's surfaces as a white coating visible to the naked eye. The ability to synthesize basic wax molecules appears to be shared among virtually all land plants, and our knowledge of ubiquitous wax compound synthesis is reasonably advanced. However, the ability to synthesize thick layers of visible epicuticular crystals ("wax blooms") is restricted to specific lineages, and our knowledge of how wax blooms differ from ubiquitous wax layers is less developed. Here, we recruited the help of citizen scientists and middle school students to survey the wax bloom chemistry of 78 species spanning dicot, monocot, and gymnosperm lineages. Using gas chromatography-mass spectrometry, we found that the major wax classes reported from bulk wax mixtures can be present in wax bloom crystals, with fatty acids, fatty alcohols, and alkanes being present in many species' bloom crystals. In contrast, other compounds including aldehydes, ketones, secondary alcohols, and triterpenoids were present in only a few species' wax bloom crystals. By mapping the 78 wax bloom chemical profiles onto a phylogeny and using phylogenetic comparative analyses, we found that secondary alcohol and triterpenoid-rich wax blooms were present in lineage-specific patterns that would not be expected to arise by chance. That finding is consistent with reports that secondary alcohol biosynthesis enzymes are found only in certain lineages but was a surprise for triterpenoids, which are intracellular components in virtually all plant lineages. Thus, our data suggest that a lineage-specific mechanism other than biosynthesis exists that enables select species to generate triterpenoid-rich surface wax crystals. Overall, our study outlines a general mode in which research scientists can collaborate with citizen scientists as well as middle and high school classrooms not only to enhance data collection and generate testable hypotheses but also to directly involve classrooms in the scientific process and inspire future STEM workers.

Pharmacy Students’ Readiness for Offline Learning in The New Normal Transmission of COVID-19: A Cross-Sectional Study

Background: Pharmacy students consist of undergraduate and professional pharmacy students. They are candidates for future pharmacist health workers who require practical experience. Offline learning with hands-on practice methods in health facilities supports their professional skills. Objective: This study aimed to determine pharmacy students' knowledge and attitude toward implementing offline learning methods during the new normal era. Methods: This study involved pharmacy students from Indonesia who were asked to participate in an e-questionnaire about the vaccination program, COVID-19 health protocols, pharmacist competence, and attitude toward implementing offline learning. The students' scores were based on their knowledge and attitude. Statistical analysis was performed to compare the scores between the two groups, and a correlation test was conducted to assess the relationship between the students' knowledge and attitudes. Results: A total of 652 pharmacy students were divided into two groups, undergraduate and professional pharmacy students, in a 3:1 ratio. About 74.6% of undergraduate students and 78.5% of professional pharmacy students had good and moderate knowledge. The level of knowledge was not different between the two groups (p=0.602; p&gt;α). Professional pharmacy students were more ready to engage in offline learning compared to undergraduate students (p=0.001; p&lt;α). However, there was a relatively low correlation between knowledge and attitudes, with r = 0.079 (p=0.043; p&lt;α). Conclusion: Professional pharmacy students are more ready for offline learning methods than undergraduate students, particularly in hands-on field practice.

ОСОБЛИВОСТІ ЗМІШАНОГО НАВЧАННЯ В УМОВАХ ВІЙНИ

The article deals with the issues of applying mixed learning techniques for the formation of the students’ professional competence at higher medical educational institutions under wartime conditions. It is found out the essence of the concept of “mixed learning”, its peculiarities, methods, advantages and disadvantages, which must be taken into account to train a future healthcare worker. The need of mastering mixed learning basic techniques for the correct organization of the educational process is emphasized. English communicative approach to medical students’ professional competence is an integral aspect of professionally oriented study at the higher medical educational institution. Military actions in the country require the application of new principles and practices of higher medical education transformation. Therefore, the issue of mixed education for students of medical institutions of higher education under wartime conditions is one of the most crucial problems in Ukraine. Attention is focused on the need to organize and establish a high-quality educational process in the conditions of war using distance model of education. The issues of semantic content for English for Specific Purposes, selection of training material, and development of communicative component in the process of students’ mastering English language skills in the process of distance learning in the conditions of war are under consideration. Both theoretical and methodological aspects of mixed learning for mastering English for Specific Purposes and the Latin language, which are studied through combining the organic application of modern distance learning technologies, are covered. The main distance learning technologies using the MS Teams and Moodle platforms are characterized. The use of information technologies of mixed learning under wartime conditions at professionally targeted classes of English and Latin has been found to develop speech skills and abilities that make possible to express an opinion, develop thinking, as well as to have high motivational characteristics, taking into account the realities of today.

Технология обучения иноязычной письменной коммуникации будущих работников водного транспорта

The research aims to develop and present an effective training technology that ensures high educational and professional results in foreign language written communication for future water transport workers. The paper considers the author’s technology for teaching future water transport workers written communication in a foreign (English) language. This technology consists of two components: an algorithm of educational activities for students to master foreign language written communication and a system of exercises aimed at developing various interrelated skills of written professional speech in a foreign language. The scientific novelty of the research lies in designing an original technological solution that implements the theoretical foundations of teaching foreign language professional written speech in the training of future water transport workers. As a result of the research, it has been found that the process of teaching foreign language written communication is based on the natural development of a person’s written speech skills in their native language, from imitating (copying) someone else’s text to independently producing a written foreign language message. At the same time, it has been proven that the effectiveness of the written communication process depends on students’ linguistic and speech skills, as well as their discursive, pragmatic, and sociocultural skills in professional written speech in a foreign language.

Enablers and Barriers of Empathy in Software Developer and User Interactions: A Mixed Methods Case Study

Software engineering (SE) requires developers to collaborate with stakeholders, and understanding their emotions and perspectives is often vital. Empathy is a concept characterising a person’s ability to understand and share the feelings of another. However, empathy continues to be an under-researched human aspect in SE. We studied how empathy is practised between developers and end users using a mixed methods case study. We used an empathy test, observations, and interviews to collect data and socio-technical grounded theory and descriptive statistics to analyse data. We identified the nature of awareness required to trigger empathy and enablers of empathy. We discovered barriers to empathy and a set of potential strategies to overcome these barriers. We report insights on emerging relationships and present a set of recommendations and potential future works on empathy and SE for software practitioners and SE researchers.

Do religious and cultural considerations militate against body donation? An overview and a Christian perspective.

The development of anatomy as a scientific undertaking appears to have left little room for religious and cultural input into the conduct of anatomical investigations. This has been brought to the fore by questionnaires regarding the willingness or otherwise of individuals to donate their bodies for dissection, with higher levels of willingness from those without religious affiliations. This has led to the assumption that there is inherent opposition to body donation by those with a religious stance, although there has been little exploration of this. This is increasingly important with growing awareness that anatomy is an international discipline, leading to increasing attention to the religious and cultural contexts within which it is practiced. There is a diversity of responses toward body donation within different countries, as well as by those influenced by Islam, Hinduism, and Buddhism. Additionally, there are diverse cultural attitudes within Confucianism in Asia, Zulu in Africa, and Māori in New Zealand. Even those within the Christian church are influenced by a variety of values, some of which are in tension, with emphasis on the sacredness of life and the significance of burial being negative toward body donation, with informed consent and altruism pointing in a positive direction. The challenge for anatomists is to understand those within their communities, seek to appreciate their perspectives, and also make known the potential of body donation and dissection for enhancing medical practice and improving the education of future health workers.

Exploiting Blockchain to Make AI Trustworthy: A Software Development Lifecycle View

Artificial intelligence (AI) is a very powerful technology and can be a potential disrupter and essential enabler. As AI expands into almost every aspect of our lives, people raise serious concerns about AI misbehaving and misuse. To address this concern, international organizations have put forward ethics guidelines for constructing trustworthy AI (TAI), including privacy, transparency, fairness, robustness, accountability, and so on. However, because of the black-box characteristics and complex models of AI systems, it is challenging to translate these guiding principles and aspirations into AI systems. Blockchain, an important decentralized technology, can provide the capabilities of transparency, traceability, immutability, and secure sharing and hence can be used to make AI trustworthy. In this paper, we survey studies on blockchain-based TAI (BTAI) from a software development lifecycle view. We classify the lifecycle of BTAI into four stages: Planning, data collection, model development, and system deployment/use. Particularly, we investigate and summarize the trustworthy issues that blockchain can achieve in the latter three stages, including (1) data transparency, privacy, and accountability; (2) model transparency, privacy, robustness, and fairness; and (3) robustness, privacy, transparency, and fairness of system deployment/use. Finally, we present essential open research issues and future work on developing BTAI systems.

A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges

Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in graph learning, we focus on the concepts of CE for GNNs. We analysed the SoA to provide a taxonomy, a uniform notation, and the benchmarking datasets and evaluation metrics. We discuss fourteen methods, their evaluation protocols, twenty-two datasets, and nineteen metrics. We integrated the majority of methods into the GRETEL library to conduct an empirical evaluation to understand their strengths and pitfalls. We highlight open challenges and future work.