Maxwell J. Jacobson, Daniel Xie, Jackson Shen
et al.
Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in understanding scientific literature. However, these tools lack the structured, multi-step approach necessary for extracting deep insights from scientific literature. Large Language Models (LLMs) offer new possibilities for literature analysis, but remain unreliable due to hallucinations and incomplete extraction. We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates LLMs, structured AI, and human scientists to extract, analyze, and iteratively refine insights from scientific literature. The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability. The system generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement. Deployed in materials science, it analyzed literature on tungsten under helium-ion irradiation, showing experimentally correlated exponential helium bubble growth with irradiation dose and temperature, offering insight for plasma-facing materials (PFMs) in fusion reactors. This demonstrates how AI-assisted literature review can uncover scientific patterns and accelerate discovery.
Risto Vaarandi, Leonidas Tsiopoulos, Gabor Visky
et al.
In recent years, many cyber incidents have occurred in the maritime sector, targeting the information technology (IT) and operational technology (OT) infrastructure. One of the key approaches for handling cyber incidents is cyber security monitoring, which aims at timely detection of cyber attacks with automated methods. Although several literature review papers have been published in the field of maritime cyber security, none of the previous studies has focused on cyber security monitoring. The current paper addresses this research gap and surveys the methods, algorithms, tools and architectures used for cyber security monitoring in the maritime sector. For the survey, a systematic literature review of cyber security monitoring studies is conducted following the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) protocol. The first contribution of this paper is the bibliometric analysis of related literature and the identification of the main research themes in previous works. For that purpose, the paper presents a taxonomy for existing studies which highlights the main properties of maritime cyber security monitoring research. The second contribution of this paper is an in-depth analysis of previous works and the identification of research gaps and limitations in existing literature. The gaps and limitations include several dataset and evaluation issues and a number of understudied research topics. Based on these findings, the paper outlines future research directions for cyber security monitoring in the maritime field.
Systematic literature review is essential for evidence-based medicine, requiring comprehensive analysis of clinical trial publications. However, the application of artificial intelligence (AI) models for medical literature mining has been limited by insufficient training and evaluation across broad therapeutic areas and diverse tasks. Here, we present LEADS, an AI foundation model for study search, screening, and data extraction from medical literature. The model is trained on 633,759 instruction data points in LEADSInstruct, curated from 21,335 systematic reviews, 453,625 clinical trial publications, and 27,015 clinical trial registries. We showed that LEADS demonstrates consistent improvements over four cutting-edge generic large language models (LLMs) on six tasks. Furthermore, LEADS enhances expert workflows by providing supportive references following expert requests, streamlining processes while maintaining high-quality results. A study with 16 clinicians and medical researchers from 14 different institutions revealed that experts collaborating with LEADS achieved a recall of 0.81 compared to 0.77 experts working alone in study selection, with a time savings of 22.6%. In data extraction tasks, experts using LEADS achieved an accuracy of 0.85 versus 0.80 without using LEADS, alongside a 26.9% time savings. These findings highlight the potential of specialized medical literature foundation models to outperform generic models, delivering significant quality and efficiency benefits when integrated into expert workflows for medical literature mining.
Nyere forskning om barnehageansatte viser hvilke lesepraksiser som finnes i skandinaviske barnehager (Alatalo & Westlund, 2021; Damber, 2015; Dybvik et al., 2022; Tjäru, 2023). Det er imidlertid mindre undersøkt hva norske barnehageansatte legger til grunn for lesing i barnehagen. I denne artikkelen retter vi søkelys mot barnehageansattes refleksjoner om egen rolle som litteraturformidlere, samt deres personlige erfaringer med litteratur. Studien baserer seg på intervju av sju barnehageansatte med forskjellig utdanningsbakgrunn. Resultatene viser at det ikke nødvendigvis er en sammenheng mellom barnehageansattes egen lesing og valg av lesing som aktivitet i barnehagen. Vi ser også at flertallet av informantene vektlegger språkutviklingsfunksjonen litteraturen har når de legitimerer valg av lesing. I tillegg er informantene opptatt av å formidle litteratur på barnas premisser og peker på barnas initiativ, interesser og formidlingsstrategier som viktige elementer. I studien ser vi også en antydning til kollektive og spesialiserte leseroller i de ulike barnehagene informantene jobber i.
ENGLISH ABSTRACT
“All of the Sudden You Are Sitting There Reading for Everyone” – A Close Study of Pedagogical Staff as Literature Mediators
Recent studies of pedagogical staff investigate practices that inform read-alouds in kindergartens (Alatalo & Westlund, 2021; Damber, 2015; Dybvik et al., 2022; Tjäru, 2023). There is, however, less research on what motivates pedagogical staff in Norwegian kindergartens to include read-alouds in their practice. In this article we look at how the pedagogical staff reflect on their own roles in read-alouds as well as their personal experiences with literature. This study is based on interviews with seven kindergarten workers with diverse educational backgrounds. The result shows that there is not a clear correlation between the pedagogical staff’s own reading and their choice of reading as an activity in kindergarten. We also observe that the majority of the informants point to the language supporting function of the literature when they legitimise choosing reading as an activity. In addition, the informants ascribe value to reading literature on children’s terms and consider the children’s initiative and interests as well as their own reading strategies as important. In the study we also observe tendencies to collective and specialised reading roles in the respective kindergartens the informants work at.
This article explores the concept of Otherness in two íslendingaþættir: Þórhalls þáttr knapps and Auðunar þáttr vestfirska. By analysing the protagonists’ social behaviour and interactions within the context of societal and situational shifts, this study examines how Otherness is constructed, challenged, and renegotiated throughout the narratives. Employing a framework of fluid and positive Otherness, this study examines how Othering qualities can be diminished or cemented as a result of individual behaviour and societal reactions. This approach underscores the importance of examining Otherness as a context-sensitive concept, with Otherness being both a source of disruption and a potential means for social reintegration.
Large language models (LLMs) have emerged as a potential solution to automate the complex processes involved in writing literature reviews, such as literature collection, organization, and summarization. However, it is yet unclear how good LLMs are at automating comprehensive and reliable literature reviews. This study introduces a framework to automatically evaluate the performance of LLMs in three key tasks of literature writing: reference generation, literature summary, and literature review composition. We introduce multidimensional evaluation metrics that assess the hallucination rates in generated references and measure the semantic coverage and factual consistency of the literature summaries and compositions against human-written counterparts. The experimental results reveal that even the most advanced models still generate hallucinated references, despite recent progress. Moreover, we observe that the performance of different models varies across disciplines when it comes to writing literature reviews. These findings highlight the need for further research and development to improve the reliability of LLMs in automating academic literature reviews.
Joshua Owotogbe, Indika Kumara, Willem-Jan Van Den Heuvel
et al.
Organizations, particularly medium and large enterprises, typically rely heavily on complex, distributed systems to deliver critical services and products. However, the growing complexity of these systems poses challenges in ensuring service availability, performance, and reliability. Traditional resilience testing methods often fail to capture the intricate interactions and failure modes of modern systems. Chaos Engineering addresses these challenges by proactively testing how systems in production behave under turbulent conditions, allowing developers to uncover and resolve potential issues before they escalate into outages. Though chaos engineering has received growing attention from researchers and practitioners alike, we observed a lack of reviews that synthesize insights from both academic and grey literature. Hence, we conducted a Multivocal Literature Review (MLR) on chaos engineering to address this research gap by systematically analyzing 96 academic and grey literature sources published between January 2016 and April 2024. We first used the chosen sources to derive a unified definition of chaos engineering and to identify key functionalities, components, and adoption drivers. We also developed a taxonomy for chaos engineering platforms and compared the relevant tools using it. Finally, we analyzed the current state of chaos engineering research and identified several open research issues.
Purpose: To identify the predominant source of the $T_1$ variability described in the literature, which ranges from 0.6-1.1 s for brain white matter at 3 T. Methods: 25 $T_1$-mapping methods from the literature were simulated with a mono-exponential and various magnetization-transfer (MT) models, each followed by mono-exponential fitting. A single set of model parameters was assumed for the simulation of all methods, and these parameters were estimated by fitting the simulation-based to the corresponding literature $T_1$ values of white matter at 3 T. We acquired in vivo data with a quantitative magnetization transfer and three $T_1$-mapping techniques. The former was used to synthesize MR images that correspond to the three $T_1$-mapping methods. A mono-exponential model was fitted to the experimental and corresponding synthesized MR images. Results: Mono-exponential simulations suggest good inter-method reproducibility and fail to explain the highly variable $T_1$ estimates in the literature. In contrast, MT simulations suggest that a mono-exponential fit results in a variable $T_1$ and explain up to 62% of the literature's variability. In our own in vivo experiments, MT explains 70% of the observed variability. Conclusion: The results suggest that a mono-exponential model does not adequately describe longitudinal relaxation in biological tissue. Therefore, $T_1$ in biological tissue should be considered only a semi-quantitative metric that is inherently contingent upon the imaging methodology; and comparisons between different $T_1$-mapping methods and the use of simplistic spin systems - such as doped-water phantoms - for validation should be viewed with caution.
Algorithm design is a vital skill developed in most undergraduate Computer Science (CS) programs, but few research studies focus on pedagogy related to algorithms coursework. To understand the work that has been done in the area, we present a systematic survey and literature review of CS Education studies. We search for research that is both related to algorithm design and evaluated on undergraduate-level students. Across all papers in the ACM Digital Library prior to August 2023, we only find 94 such papers. We first classify these papers by topic, evaluation metric, evaluation methods, and intervention target. Through our classification, we find a broad sparsity of papers which indicates that many open questions remain about teaching algorithm design, with each algorithm topic only being discussed in between 0 and 10 papers. We also note the need for papers using rigorous research methods, as only 38 out of 88 papers presenting quantitative data use statistical tests, and only 15 out of 45 papers presenting qualitative data use a coding scheme. Only 17 papers report controlled trials. We then synthesize the results of the existing literature to give insights into what the corpus reveals about how we should teach algorithms. Much of the literature explores implementing well-established practices, such as active learning or automated assessment, in the algorithms classroom. However, there are algorithms-specific results as well: a number of papers find that students may under-utilize certain algorithmic design techniques, and studies describe a variety of ways to select algorithms problems that increase student engagement and learning. The results we present, along with the publicly available set of papers collected, provide a detailed representation of the current corpus of CS Education work related to algorithm design and can orient further research in the area.
Baseline data on the distribution of marine species is crucial to be able to address biogeographical patterns and to monitor changes in species occurrences in marine systems. Nudibranch mollusks have proved to be useful bioindicators for monitoring shifts in distribution and have received much attention by the scientific community in recent years. Being positioned in a zoogeographic transition zone between boreal and Arctic regions, northern Norway is an important area for detecting and tracking early distributional shifts. Despite this, no comprehensive knowledge on current biodiversity and distribution of nudibranchs exists from the region. This work presents, for the first time, an annotated and illustrated inventory of nudibranchs in shallow water habitats of the Tromsø region in northern Norway. In total, 49 different nudibranch species or taxa belonging to 19 different families were recorded during the time period May 2020 – December 2023. Compared to occurrence data from literature records and online data sources, 31 species are here reported from the region for the first time. In addition, northern range extensions are presented for a significant part of the Norwegian nudibranch fauna. By documenting current biodiversity and distribution the present study hopes to serve as a baseline for studies focused on monitoring biodiversity in the Arctic region in the future.
Arne Østrings kortprosatekst «Ut av stillheten» kan saktens leses som en lettere komisk tekst om en japansk kamikaze-pilots – en selvmordsbombers – umulige tokt mot en militært overlegen fiende, men mer interessant er det at teksten balanserer en krigslogikk og en rasjonell psykologi, at den skriver frem kamikaze-krigens premisser og forhistorie, og ikke minst at den situerer selvmorderen som det sosiologen Norbert Elias kalte homo clausus: det isolerte, lukkede mennesket som føler seg alene i verden. Og endelig demonstrerer teksten at selve lesningen av litterære selvmord alltid må være en lesning av teksten.
Along with the popularity of Frozen 2 which later became the branding of Norwegian tourism, interest in tourism texts also increased. Therefore, researcher seek to what extent translated texts and visual analysis convey meaning. This research analyzed textual and visual tourism text titled “The Places in Norway that Inspired Frozen 2” from the visitnorway.com site. The purpose of this research are: (1) to understand the application of translation method in the tourism text analyzed, and (2) to understand the process of visual analysis of the illustrations in the tourism text analyzed. In this research, communicative translation that emphasize the transfer of contextual meaning from the source text into the target text is the most appropriate method to apply on the translation of the informative language tourism text. As for visual analysis in exploring general information related to the illustrations in the tourism text that could produce picture descriptions that support the need of information the source text author was to convey. Based on the application of these communicative translation method and visual analysis, results have shown that both are able to convey the meaning and purpose of the tourism text, which is to attract tourists to visit Norway by introducing nature and culture through its relevance to the Frozen film.
Unni Jenssen, Jeanie M. Bochenek, Tara Spalla King
et al.
Aim: The aim of this study was to describe the experience of Norwegian nursing students with internationalization through participation in a Collaborative Online International Learning (COIL) course. Background: Educators in Norway and the United States collaborated to incorporate internationalization and population health concepts into virtual courses during the pandemic. Literature gaps exist in post-implementation assessment data that ascertain internationalization through the COIL experience. Design: This was a qualitative study with a descriptive design. Data were collected from focus group interviews and analyzed conventional content-analysis approaches. Methods: Fifteen Norwegian undergraduate nursing students who participated in the COIL opportunity completed focus group interviews. Findings: The themes identified included, “virtual conversation builds collaborations and enhances learning,” and “this opened my eyes.” Conclusions: Norwegian students acknowledged they had learned transferable lessons from their global partners that could be applied to patient care of the marginalized population in Norway.
Arthur dos Santos, Jayr Pereira, Rodrigo Nogueira
et al.
The increasing number of scientific publications in acoustics, in general, presents difficulties in conducting traditional literature surveys. This work explores the use of a generative pre-trained transformer (GPT) model to automate a literature survey of 116 articles on data-driven speech enhancement methods. The main objective is to evaluate the capabilities and limitations of the model in providing accurate responses to specific queries about the papers selected from a reference human-based survey. While we see great potential to automate literature surveys in acoustics, improvements are needed to address technical questions more clearly and accurately.
Keeping up with the research literature plays an important role in the workflow of scientists - allowing them to understand a field, formulate the problems they focus on, and develop the solutions that they contribute, which in turn shape the nature of the discipline. In this paper, we examine the literature review practices of data scientists. Data science represents a field seeing an exponential rise in papers, and increasingly drawing on and being applied in numerous diverse disciplines. Recent efforts have seen the development of several tools intended to help data scientists cope with a deluge of research and coordinated efforts to develop AI tools intended to uncover the research frontier. Despite these trends indicative of the information overload faced by data scientists, no prior work has examined the specific practices and challenges faced by these scientists in an interdisciplinary field with evolving scholarly norms. In this paper, we close this gap through a set of semi-structured interviews and think-aloud protocols of industry and academic data scientists (N = 20). Our results while corroborating other knowledge workers' practices uncover several novel findings: individuals (1) are challenged in seeking and sensemaking of papers beyond their disciplinary bubbles, (2) struggle to understand papers in the face of missing details and mathematical content, (3) grapple with the deluge by leveraging the knowledge context in code, blogs, and talks, and (4) lean on their peers online and in-person. Furthermore, we outline future directions likely to help data scientists cope with the burgeoning research literature.
Alexander Naumann, Felix Hertlein, Laura Dörr
et al.
Computer vision applications in transportation logistics and warehousing have a huge potential for process automation. We present a structured literature review on research in the field to help leverage this potential. The literature is categorized w.r.t. the application, i.e. the task it tackles and w.r.t. the computer vision techniques that are used. Regarding applications, we subdivide the literature in two areas: Monitoring, i.e. observing and retrieving relevant information from the environment, and manipulation, where approaches are used to analyze and interact with the environment. Additionally, we point out directions for future research and link to recent developments in computer vision that are suitable for application in logistics. Finally, we present an overview of existing datasets and industrial solutions. The results of our analysis are also available online at https://a-nau.github.io/cv-in-logistics.
Abstract Norway is at the forefront of a transition toward cleaner solutions in the maritime sector. In 2015, the first fully electric ferry, the MF Ampere, started operating in Western Norway. Since then, 60 electric or hybrid-electric ferries are in operation or scheduled to be by the end of 2021. With a few exceptions the literature on energy transitions sees transitions as disjointed and slow. Through this case study—based on 13 semi-structured interviews, two focus groups, as well as seminars, conferences and workshops with industry experts, public sector stakeholders, and project managers—we show how the Norwegian ferry case is an example showing that, under the right circumstances, energy transitions can however be politically accelerated, even in what is widely deemed a hard-to-decarbonize sector. This is one of the first attempts at analyzing the politics of accelerated transitions within the maritime sector. It is also one of few studies of the electrification of ferries, and at the end of which we suggest a set of success criteria for accelerated transitions. We propose four main explanatory factors: First, what we label the Norwegian ferry innovation system was instrumental in providing an environment conducive to electrification. Second, the Norwegian state acted entrepreneurially, by moving beyond merely being a de-risker through playing an active role in market creation and transformation through public agencies and support schemes. Third and fourth, we argue that the relative lack of strong opposing vested interests combined with an oil shock to create favorable conditions for structural change.
The COVID-19 pandemic has been severely impacting global society since December 2019. Massive research has been undertaken to understand the characteristics of the virus and design vaccines and drugs. The related findings have been reported in biomedical literature at a rate of about 10,000 articles on COVID-19 per month. Such rapid growth significantly challenges manual curation and interpretation. For instance, LitCovid is a literature database of COVID-19-related articles in PubMed, which has accumulated more than 200,000 articles with millions of accesses each month by users worldwide. One primary curation task is to assign up to eight topics (e.g., Diagnosis and Treatment) to the articles in LitCovid. Despite the continuing advances in biomedical text mining methods, few have been dedicated to topic annotations in COVID-19 literature. To close the gap, we organized the BioCreative LitCovid track to call for a community effort to tackle automated topic annotation for COVID-19 literature. The BioCreative LitCovid dataset, consisting of over 30,000 articles with manually reviewed topics, was created for training and testing. It is one of the largest multilabel classification datasets in biomedical scientific literature. 19 teams worldwide participated and made 80 submissions in total. Most teams used hybrid systems based on transformers. The highest performing submissions achieved 0.8875, 0.9181, and 0.9394 for macro F1-score, micro F1-score, and instance-based F1-score, respectively. The level of participation and results demonstrate a successful track and help close the gap between dataset curation and method development. The dataset is publicly available via https://ftp.ncbi.nlm.nih.gov/pub/lu/LitCovid/biocreative/ for benchmarking and further development.
Despite potential benefits in Software Engineering (SE), adoption of software modelling in industry is low. Technical issues such as tool support have gained significant research before, but individual guidance and training have received little attention. As a first step towards providing the necessary guidance in modelling, we conduct a systematic literature review (SLR) to explore the current state of the art. We searched academic literature for modelling guidance, and selected 25 papers for full-text screening through three rounds of selection. We find research on modelling guidance to be fragmented, with inconsistent usage of terminology, and a lack of empirical validation or supporting evidence. We outline the different dimensions commonly used to provide guidance on software modelling. Additionally, we provide definitions of the three terms modelling method, style, and guideline as current literature lacks a well-defined distinction between them. These definitions can help distinguishing between important concepts and provide precise modelling guidance.