Datasets:

ethicalabs
/

Research-Intent-Judge

doi stringlengths 5 64	title stringlengths 4 67.7k	description stringlengths 1 67.4k	initial_intent stringclasses 5 values	messages listlengths 3 3	reasoning stringlengths 134 590	model_prediction stringclasses 5 values	is_flagged bool 2 classes	flag_reason stringlengths 5 727	confidence stringclasses 3 values
08874417.2020.1774442	Story Analysis Using Natural Language Processing and Interactive Dashboards	This paper discusses Story Analyzer, which uses a natural language processing (NLP) library and sophisticated data visualization libraries to produce dashboards of interrelated and user-responsive ...	Applied	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing NLP and visualization techniques to a domain-specific task (story analysis), which aligns with the 'Applied' classification. The abstract does not suggest any new algorithm, dataset, or theoretical analysis, and it is not empty or non-scientific.	Applied	false	The abstract mentions the application of NLP and data visualization libraries to create interactive dashboards for story analysis, indicating a practical application of existing methods to a specific domain.	high
09636625251317970	Exploring AI identity: The media framing of communicative artificial intelligence in Singapore’s news sites	Implementing artificial intelligence also requires examinations of public attitudes and perceptions. One approach is by examining media framing of artificial intelligence, including news coverage, which is a reflection of societal perceptions and a key influence over people’s understanding. As such, this study examines...	Applied	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods (manual content analysis) to study a specific domain (media framing of communicative AI in Singapore), which aligns with the 'Applied' classification. It does not introduce new methodologies, datasets, or theoretical analysis, nor does it present a survey or position paper with no emp...	Applied	false	The abstract discusses the media framing of communicative artificial intelligence in Singapore, focusing on how news media portray it and its societal implications. It does not introduce a new algorithm, model architecture, or mathematical method, nor does it present a new dataset or benchmark. Instead, it applies exis...	high
10.1001/jama.1991.03470130107038	Use of Genetic Testing by Employers	OVER THE NEXT 15 YEARS, under the auspices of the federal government's "human genome project," scientists will try to map in detail each of the human cell's estimated 100 000 genes.1The knowledge derived from the project will enable physicians to detect an increasing number of diseases and predispositions for disease. ...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The abstract discusses the potential applications of genetic testing in various domains, including medicine and employment, but lacks detailed methodology, empirical data, or a clear survey/meta-analysis structure. It also does not introduce a new algorithm, model, or dataset. Therefore, it is more appropriately classi...	Review	true	The abstract is non-scientific and lacks empirical content, making it difficult to classify under any of the provided labels with certainty.	low
10.1001/jama.2015.8421	Changes in Self-reported Insurance Coverage, Access to Care, and Health Under the Affordable Care Act	The Affordable Care Act (ACA) completed its second open enrollment period in February 2015. Assessing the law's effects has major policy implications.To estimate national changes in self-reported coverage, access to care, and health during the ACA's first 2 open enrollment periods and to assess differences between low-...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods (differences-in-differences approach, multivariable regression) to a specific domain (healthcare policy under the Affordable Care Act) and presents empirical findings. It contributes to understanding real-world impacts of a policy, making it an 'Applied' paper rather than a 'Review' o...	Applied	false	The abstract provides a clear description of a study analyzing the effects of the Affordable Care Act on self-reported insurance coverage, access to care, and health outcomes. It includes detailed methodology, data sources, and statistical analysis, indicating an empirical contribution rather than a theoretical or appl...	high
10.1001/jamainternmed.2017.5047	Assessing Health Insurance Coverage Characteristics and Impact on Health Care Cost, Worry, and Access	This study assessed a randomly selected, age-stratified sample of 698 childhood cancer survivors and 210 siblings and insurance coverage characteristics to determine the impact of underinsurance.	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods to study the impact of health insurance coverage on specific health outcomes. It does not introduce new methodologies or datasets. The abstract is clear, scientific, and provides sufficient context for the classification.	Applied	false	The abstract clearly states that the study applied existing methods to analyze health insurance coverage characteristics and their impact on health care cost, worry, and access. There is no indication of introducing a new algorithm, model architecture, or mathematical method, nor is there any mention of a new dataset o...	high
10.1001/jamanetworkopen.2024.43059	Nurse Burnout and Patient Safety, Satisfaction, and Quality of Care	ImportanceOccupational burnout syndrome is characterized by emotional exhaustion, depersonalization, and a diminished sense of personal accomplishment and is prevalent among nurses. Although previous meta-analyses have explored the correlates of nurse burnout, none have estimated their association with health care qual...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper presents a systematic review and meta-analysis of existing studies on the association between nurse burnout and patient safety, satisfaction, and quality of care. It does not introduce a new algorithm, dataset, or theoretical analysis, and its primary contribution is the synthesis and evaluation of prior rese...	Review	false	The abstract contains a clear objective, methodology, and results, with a systematic review and meta-analysis as the primary contribution. It discusses the association between nurse burnout and specific outcomes, which aligns with the 'Review' classification.	high
10.1001/jamaoto.2025.2687	Palliative Care With Tracheostomy or Gastrostomy Tube Use and End-of-Life Quality and Costs Among Patients With Head and Neck Cancer	Importance Patients with head and neck cancer (HNC) have high utilization rates of tracheostomy or gastrostomy tubes (g-tubes) at the end of life, with accompanying high costs. It is unknown whether the timing of palliative care (PC) initiation may attenuate the cost or be associated with better qua...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods (palliative care and cost analysis) to a specific domain (end-of-life care for head and neck cancer patients). It presents empirical findings and discusses real-world implications, aligning with the 'Applied' classification.	Applied	false	The abstract is non-garbled, contains scientific content, and discusses the application of palliative care in a specific clinical context with empirical outcomes.	high
10.1001/jamapediatrics.2015.3028	Quality of Health Insurance Coverage and Access to Care for Children in Low-Income Families	An increasing diversity of children's health coverage options under the US Patient Protection and Affordable Care Act, together with uncertainty regarding reauthorization of the Children's Health Insurance Program (CHIP) beyond 2017, merits renewed attention on the quality of these options for children.To compare healt...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods (data analysis, multivariable logistic regression) to a specific domain (health care access for children in low-income families). It presents empirical findings and discusses implications for future policymaking, aligning with the 'Applied' classification.	Applied	false	The abstract contains clear empirical data and analysis comparing health care outcomes across different insurance types, indicating an applied research paper.	high
10.1002/(sici)1096-987x(199906)20:8<799::aid-jcc6>3.0.co;2-z	Upack program package for crystal structure prediction: Force fields and crystal structure generation for small carbohydrate molecules	The Upack program package for crystal structure generation was used to build hypothetical crystal structures for 32 pyranoses and 24 polyalcohols. A subset of these was used to compare six force fields in their ability to reproduce the experimentally observed structures, preferably with low energies and high rankings w...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper introduces a new program package for crystal structure prediction, including the development of force fields and the generation of hypothetical structures. It describes the methodology used to build and evaluate these structures, which fits the 'Methodology' classification. The abstract contains no empty or g...	Methodology	false	The abstract describes the development and application of a program package (Upack) for crystal structure prediction, including the introduction of force fields and the generation of hypothetical structures. This aligns with the 'Methodology' label as it introduces a new algorithm (force fields) and describes the train...	high
10.1002/(sici)1097-461x(1998)68:4<221::aid-qua1>3.0.co;2-x	Utilization of deformations in molecular quantum chemistry and application to density functional theory	The aim of this paper is to present in a way accessible to most quantum chemists a general mathematical method which consists in deforming wave-functions and density functions (in the spirit of the Local Scaling Transformation). This deformation method allows us to obtain several new results including a characterizatio...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper introduces a new mathematical method and presents theoretical results, including an N-representability result and new ways to generate approximations of the exact density functional. These contributions are not empirical, and the focus is on formal analysis and mathematical development.	Theoretical	false	The abstract clearly describes a mathematical method introduced for the first time, including new results and theoretical approaches to density functional theory. This aligns with the 'Methodology' label.	high
10.1002/(sici)1099-1638(199903/04)15:2<95::aid-qre236>3.0.co;2-x	Efficient basic event ordering schemes for fault tree analysis	Fault Tree Analysis is a commonly used means of assessing the system reliability performance in terms of its component’s reliability characteristics. More recently, significant advances have been made in methodologies to analyse the fault tree diagram. The most successful of these developments has been the Binary Decis...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper introduces a new machine learning-based methodology for selecting an optimal ordering scheme in fault tree analysis. This involves developing a technique that improves the efficiency and accuracy of fault tree analysis. The work presents a novel approach rather than contributing a new dataset, survey, or theo...	Methodology	false	The abstract describes a machine learning approach using Genetic Algorithms to select an optimal ordering scheme for fault tree analysis, which involves introducing a new methodology. This aligns with the 'Methodology' classification.	high
10.1002/14651858.cd006747.pub2	Managed alcohol as a harm reduction intervention for alcohol addiction in populations at high risk for substance abuse	Managed alcohol programmes (MAP) are a harm reduction strategy used to minimise the personal harm and adverse societal effects that alcohol dependence can lead to by providing an alternative to zero-tolerance approaches that incorporate drinking goals (abstinence or moderation) that are compatible with the needs of the...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The abstract describes a systematic review of managed alcohol programmes (MAP) and their effectiveness in reducing harmful behaviour. It outlines the methodology, the lack of evidence, and the authors' opinion, which aligns with the definition of a review paper. The paper does not introduce a new algorithm, model, or d...	Review	false	The abstract is non-garbled, contains scientific content, and discusses a systematic review of managed alcohol programmes. It does not appear to be math-symbol-only.	high
10.1002/1521-3978(200110)49:10/11<901::aid-prop901>3.0.co;2-a	Quantum Error Correction and Quantum Computation with Detected-jump Correcting Quantum Codes	Summary: A new class of embedded error correcting quantum codes is discussed. These detected-jump correcting quantum codes are capable of stabilizing distinguishable qubits against spontaneous decay. Due to their low redundancy and due to the small number of control measurements and recovery operations required these n...	Theoretical	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper introduces a new class of quantum codes with theoretical foundations, including connections to combinatorial design theory and exploration of universal quantum gates. It lacks empirical evaluation, aligning with the 'Theoretical' classification. The abstract is clear, scientific, and provides no indication of...	Theoretical	false	The abstract discusses a new class of quantum codes with theoretical implications, including their links to combinatorial design theory and exploration of universal quantum gates. These are primarily theoretical contributions without empirical evaluation.	high
10.1002/1878-0261.13420	Synthetic biology, genetic circuits and machine learning: a new age of cancer therapy	Synthetic biology has made it possible to rewire natural cellular responses to treat disease, notably demonstrated by chimeric antigen receptor (CAR) T cells as cancer immunotherapy. Building on the success of T‐cell activation using synthetic receptors, the field is now investigating how induction of noncanonical sign...	Applied	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods (synthetic biology and machine learning) to a specific domain (cancer therapy) to enhance the antitumour phenotype of engineered T cells. It does not introduce new methodologies or datasets, and the focus is on practical application rather than theoretical analysis or empirical contri...	Applied	false	The abstract discusses the application of synthetic biology and machine learning in cancer therapy, specifically focusing on how these technologies are used to enhance the antitumour phenotype of engineered T cells. It does not introduce a new algorithm, model architecture, or mathematical method, nor does it present a...	high
10.1002/2014sw001064	Ensemble downscaling in coupled solar wind‐magnetosphere modeling for space weather forecasting	AbstractAdvanced forecasting of space weather requires simulation of the whole Sun‐to‐Earth system, which necessitates driving magnetospheric models with the outputs from solar wind models. This presents a fundamental difficulty, as the magnetosphere is sensitive to both large‐scale solar wind structures, which can be ...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper introduces a new approach for downscaling solar wind model outputs to improve magnetospheric forecasts, which aligns with the 'Methodology' classification. The abstract does not suggest any other classification, and there is no indication of a new dataset, review, applied domain, or theoretical analysis.	Methodology	false	The abstract provides a clear description of a methodology involving downscaling solar wind model results for space weather forecasting, including the use of statistical methods and ensemble testing. It does not indicate the contribution of a new dataset, a review, an applied domain, or a theoretical analysis.	high
10.1002/2475-8876.70047	<scp>PENTA</scp> ‐ <scp>HARD</scp> : Self‐Built Architectural Prototype With Additively Manufactured (3D Printed) Joints	ABSTRACT This future architectural prototype is composed of standardized parts and 3D printed (additive manufactured) metal joints to allow users to build by themselves at a low cost. The structure is assembled with lightweight aluminum pipes where joints are plugged in, in a straightforward, flexible...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper describes the application of additive manufacturing technology to create an architectural prototype, which aligns with the 'Applied' classification. The focus is on using existing methods in a new context rather than introducing new algorithms or datasets.	Applied	false	The abstract describes a self-built architectural prototype with 3D printed joints, which involves applying existing methods (additive manufacturing) to a specific domain (architectural design).	high
10.1002/adma.201606922	In Situ Electrochemistry of Rechargeable Battery Materials: Status Report and Perspectives	The development of rechargeable batteries with high performance is considered to be a feasible way to satisfy the increasing needs of electric vehicles and portable devices. It is of vital importance to design electrodes with high electrochemical performance and to understand the nature of the electrode/electrolyte int...	Applied	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing in situ electrochemistry techniques to study rechargeable battery materials, including real-time monitoring of lithium dendrite growth and gas evolution. It also outlines challenges and opportunities for further development, indicating a focus on applying existing methods to battery research....	Applied	false	The abstract discusses the application of in situ electrochemistry techniques to study rechargeable battery materials, including real-time monitoring of lithium dendrite growth and gas evolution. It also outlines challenges and opportunities for further development, indicating a focus on applying existing methods to ba...	high
10.1002/adma.202210216	MXene‐Nanoflakes‐Enabled All‐Optical Nonlinear Activation Function for On‐Chip Photonic Deep Neural Networks	Abstract2D metal carbides and nitrides (MXene) are promising material platforms for on‐chip neural networks owing to their nonlinear saturable absorption effect. The localized surface plasmon resonances in metallic MXene nanoflakes may play an important role in enhancing the electromagnetic absorption; however, their c...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper introduces a new algorithm (MXene nanoflakes as a saturable absorber) and describes the development of a novel configuration for neuromorphic photonic deep neural networks. The methodology is clearly outlined, and the results are validated through a machine-learning task. The abstract provides sufficient deta...	Methodology	false	The abstract describes the development of a saturable absorber using MXene nanoflakes for neuromorphic tasks, including a handwritten digit classification task with near 99% accuracy. This indicates a new methodology for implementing nonlinear activation functions in photonic deep neural networks.	high
10.1002/adts.202000139	Understanding the Dehydrogenation Pathways of Ammonium Octahydrotriborate (NH<sub>4</sub>B<sub>3</sub>H<sub>8</sub>) by Molecular Dynamics Simulations with the Reactive Force Field (ReaxFF)	AbstractAmmonium octahydrotriborate (NH4B3H8) is a potential candidate for hydrogen storage, due to its chemical stability and high hydrogen content. To systematically investigate its initial decomposition and dehydrogenation pathways, molecular dynamics simulations with a reactive force field are conducted. Both tempe...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies molecular dynamics simulations with a reactive force field to study the decomposition and dehydrogenation pathways of NH4B3H8. It focuses on applying existing computational techniques to a specific domain. The abstract does not indicate any new dataset, methodology, or theoretical analysis.	Applied	false	The abstract describes molecular dynamics simulations applied to study the decomposition and dehydrogenation pathways of NH4B3H8, which involves applying existing computational methods to a specific domain (chemical decomposition of a material).	high
10.1002/adts.202400114	Biomechanical Finite Element Simulation of Cochlear Implant Surgical Robot Drilling Through Direct Cochlear Access	AbstractRobotic drilling through direct cochlear access for cochlear implantation (CI) is currently a prominent area in the field of CI surgery. However, the safety of drilling remains an issue due to the limited space within the facial recess. Estimation and control of drilling force are critical to prevent drill‐bit ...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies finite element analysis to a real-world problem in cochlear implant surgery. It validates findings through experimental drilling and discusses the practical implications for optimizing drilling parameters. This fits the 'Applied' classification.	Applied	false	The abstract describes the application of finite element analysis to a specific domain (temporal bone drilling for cochlear implantation) and mentions the experimental validation of the findings. This aligns with the 'Applied' classification as it involves applying existing methods to a real-world problem.	high
10.1002/advs.202407060	Interpretable Multimodal Fusion Model for Bridged Histology and Genomics Survival Prediction in Pan‐Cancer	Abstract Understanding the prognosis of cancer patients is crucial for enabling precise diagnosis and treatment by clinical practitioners. Multimodal fusion models based on artificial intelligence (AI) offer a comprehensive depiction of the tumor heterogeneity landscape, facilitating more accurate pre...	Applied	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper describes the application of an interpretable multimodal fusion model to a specific clinical domain (pan-cancer survival prediction), which aligns with the 'Applied' classification. The model's practical use and validation in real-world scenarios support this classification.	Applied	false	The abstract clearly describes the application of an interpretable multimodal fusion model to predict cancer patient survival, specifically in the context of bridged histology and genomics data. It emphasizes the practical utility in clinical settings and the model's validation across multiple cancer types.	high
10.1002/advs.202507839	Benchmarking Ploidy Estimation Methods for Bulk and Single‐Cell Whole Genome Sequencing	Abstract Maintaining cellular ploidy is critical for normal physiological processes, although gains in ploidy are frequently observed during development, tissue regeneration, and metabolism, and potentially contribute to aneuploidy, thereby promoting tumor evolution. Although numerous computational to...	Dataset	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper presents a benchmarking study of existing methods for ploidy estimation, evaluating their performance on experimental and simulated datasets. It does not introduce a new dataset or benchmark, nor does it provide a detailed survey of the field. Instead, it focuses on comparing and analyzing the effectiveness o...	Review	false	The abstract contains clear information about benchmarking computational methods for ploidy estimation in bulk and single-cell WGS data, which indicates a systematic comparison of methods rather than a new dataset or benchmark. The paper also discusses the performance of existing tools, which aligns with a review or su...	high
10.1002/agm2.12079	Allogeneic mesenchymal stem cell therapy: A regenerative medicine approach to geroscience	AbstractExtraordinary advances in medicine and public health have contributed to increasing life expectancy worldwide. However, health span—“healthy aging”—has paradoxically lagged to parallel this increase. Consequently, aging‐associated illnesses, such as Alzheimer's disease and aging frailty, are having a growing im...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper provides a comprehensive review of preclinical and clinical data supporting the use of allogeneic MSCs in geroscience. It does not introduce a new algorithm, dataset, or method, nor does it apply existing methods to a specific domain. Instead, it presents a survey of the field, making it a Review paper.	Review	false	The abstract discusses the application of allogeneic mesenchymal stem cells (MSCs) in the context of geroscience, which involves treating the aging process to prevent and treat age-related disorders. It presents a review of preclinical and clinical data supporting the utility of these cells, indicating that the paper i...	high
10.1002/ajim.10072	Racial differences in prevalence of a supratypic HLA‐genetic marker immaterial to pre‐employment testing for susceptibility to chronic beryllium disease	AbstractBackgroundA beryllium materials manufacturer is conducting a limited pilot program that offers testing for HLA‐DPβ1E69 with genetic counseling through a third party to applicants for employment. An important consideration in this regard is the prevalence of this marker in the general population, and its consequ...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper introduces a new method for determining HLA‐DPβ1E69 population frequencies and uses this method to calculate positive predictive values for disease susceptibility. This aligns with the definition of a methodology paper, which introduces a new algorithm, model architecture, or mathematical method. The abstract...	Methodology	false	The abstract discusses the methodology of determining HLA‐DPβ1E69 population frequencies using PCR and RFLP analyses, which is a clear indication of a methodology paper. The paper introduces a new approach to assess genetic markers for disease susceptibility, making it a methodology paper.	high
10.1002/ajmg.a.20025	Life insurance and breast cancer risk assessment: Adverse selection, genetic testing decisions, and discrimination	AbstractLife insurance industry access to genetic information is controversial. Consumer groups argue that access will increase discrimination in life insurance premiums and discourage individuals from undergoing genetic testing that may provide health benefits. Conversely, life insurers argue that without access to ri...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods (retrospective cohort study) to a real-world problem involving life insurance and genetic testing. It evaluates the impact of breast cancer risk information on life insurance purchasing and the incidence of life insurance discrimination, which are practical applications. There is no i...	Applied	false	The abstract contains empirical data on the impact of breast cancer risk information on life insurance purchasing and the incidence of life insurance discrimination following genetic testing. It also discusses the application of existing methods (retrospective cohort study) to a real-world problem (life insurance and g...	high
10.1002/alt.21846	Corporate Dispute Resolution Strategies to Make Mediation and Arbitration Better Alternatives	This article is centered on the desirability of instilling a particular culture in corporate decision making on responsible and effective dispute resolution methods.	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The abstract discusses corporate culture and dispute resolution methods without presenting a specific domain application or empirical data. It lacks the characteristics of an 'Applied' paper, and the content is more aligned with a survey or opinion piece, suggesting a 'Review' classification. The paper does not introdu...	Review	true	The abstract is non-scientific and lacks any empirical contribution or specific domain application, making it unclear whether the paper falls under 'Applied' or another category.	low
10.1002/alz.061634	Leveraging natural language processing to identify social determinants of health for patients with Alzheimer’s disease and related dementias from electronic medical records	AbstractBackgroundSocial determinants of health (SDoH) have a significant impact on the well‐being of individuals with Alzheimer’s disease and related dementias (ADRD). ADRD patients from socioeconomically disadvantaged groups are generally subject to higher risks of adverse health events than those from advantaged gro...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper describes the development of a rule-based NLP algorithm to identify specific social determinants of health from unstructured EMRs. This aligns with the 'Methodology' classification as it introduces a new algorithm and training technique. The abstract also provides details about the dataset and evaluation proc...	Methodology	false	The abstract is non-garbled, non-scientific, and contains meaningful content about the development and application of an NLP algorithm to identify social determinants of health in electronic medical records. It describes the methodology, dataset, and application of the algorithm, aligning with the 'Methodology' classif...	high
10.1002/alz.068929	Development and Evaluation of a Natural Language Processing Annotation Tool (NAT) to Facilitate Phenotyping of Cognitive Status in Electronic Health Records	AbstractBackgroundElectronic Health Records (EHR) with large sample sizes and rich information offer great potential for dementia research, but current methods of phenotyping cognitive status are either not scalable or suffer from inaccuracies. Our objective is to evaluate whether deep learning Natural Language Process...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing NLP techniques to a specific domain (phenotyping cognitive status in EHR) and presents empirical results comparing NAT with manual chart reviews. The focus is on the practical application of NLP in a real-world medical context.	Applied	false	The abstract describes the development and evaluation of an NLP annotation tool for phenotyping cognitive status in EHR, which involves applying existing NLP methods to a specific domain (dementia research).	high
10.1002/alz.075674	ALZHEIMER’S DEMENTIA EARLY DIAGNOSIS, CHARACTERIZATION, PROGNOSIS AND TREATMENT DECISION VIA A SOFTWARE‐AS‐MEDICAL DEVICE WITH AN ARTIFICIAL INTELLIGENT AGENT	AbstractBackgroundTRACE4AD (DeepTrace Technologies s.r.l, Italy) is a machine learning‐based software‐as‐medical device able to predict the conversion to Alzheimer’s disease (AD) dementia of subjects at risk within 24‐months exploiting automatic processing of T1‐weighted MPRAGE brain MRI study and neuropsychological te...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper describes TRACE4AD as a tool that applies existing methods (processing MRI and neuropsychological tests) to support clinical decision-making in Alzheimer’s dementia. This fits the 'Applied' classification as it involves using established techniques in a real-world setting. The model's prediction of 'Applied' ...	Applied	false	The abstract describes TRACE4AD as a machine learning-based software-as-medical-device that applies existing methods (processing MRI and neuropsychological tests) to support diagnosis, characterization, prognosis, and treatment decision-making in Alzheimer’s dementia patients. This aligns with the 'Applied' classificat...	high
10.1002/ange.202306185	Nano‐Impact Electrochemistry Reveals Kinetics Information of Metal‐Ion Battery Materials with Multiple Redox Centers	AbstractPrussian blue (PB) has emerged as a promising cathode material in aqueous batteries. It possesses two distinct redox centers, and the potassium ions (K+) are unevenly distributed throughout the compound, adding complexity to the interpretation of the K+ insertion/de‐insertion kinetic mechanism. Traditional ense...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing electrochemical methods to study the kinetic behavior of a specific cathode material in a real-world context. It discusses both experimental and theoretical aspects, contributing to the development of strategies for optimizing battery materials. The abstract provides sufficient scientific con...	Applied	false	The abstract discusses the application of nano-impact electrochemistry to study the kinetic mechanisms of individual Prussian blue (PB) particles in aqueous batteries, which is a real-world domain. It also mentions theoretical simulations and a discussion of findings that contribute to understanding and optimizing cath...	high
10.1002/anie.201304762	Lithium–Sulfur Batteries: Electrochemistry, Materials, and Prospects	AbstractWith the increasing demand for efficient and economic energy storage, Li‐S batteries have become attractive candidates for the next‐generation high‐energy rechargeable Li batteries because of their high theoretical energy density and cost effectiveness. Starting from a brief history of Li‐S batteries, this Revi...	Review	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The abstract describes a systematic review of Li–S batteries, covering their electrochemistry, materials, and future prospects. It does not introduce new methodologies, datasets, or mathematical analysis. The paper is categorized as a review, which aligns with the description in the abstract.	Review	false	The abstract provides a comprehensive overview of Li–S batteries, discussing their electrochemistry, materials, and future prospects. It does not introduce a new algorithm, dataset, or mathematical method, and it does not apply existing methods to a specific domain. The paper is clearly a review of the topic.	high
10.1002/anie.202301629	Ammonium Ion Batteries: Material, Electrochemistry and Strategy	AbstractAmmonium‐ion batteries (AIBs) have recently attracted increasing attention in the field of aqueous batteries owing to their high safety and fast diffusion kinetics. The NH4+storage mechanism is quite different from that of spherical metal ions (e.g. Li+, Na+, K+, Mg2+, and Zn2+) because of the formation of hydr...	Review	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The abstract outlines a review of ammonium-ion batteries, discussing their state-of-the-art research, challenges, and future strategies. It does not introduce new methodologies, datasets, or mathematical analysis, and it is not focused on applying existing methods to a specific domain. Therefore, the proposed label 'Re...	Review	false	The abstract provides a comprehensive overview of state-of-the-art research on ammonium-ion batteries, discussing materials, electrochemistry, and future strategies. It does not introduce new algorithms, datasets, or mathematical methods, and it is not focused on applying existing methods to a specific domain. The pape...	high
10.1002/anie.202308397	Toward Sustainable Metal‐Iodine Batteries: Materials, Electrochemistry and Design Strategies	Abstract Due to the natural abundance of iodine, cost‐effective, and sustainability, metal‐iodine batteries are competitive for the next‐generation energy storage systems with high energy density, and large power density. However, the inherent properties of iodine such as electronic insulation and shu...	Review	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The abstract summarizes existing research progress and discusses design strategies and electrochemical parameters without introducing new methods, datasets, or empirical contributions. It is a review paper aimed at promoting development and providing guidelines. The paper does not meet the criteria for Methodology, Dat...	Review	false	The abstract provides a comprehensive review of metal-iodine batteries, discussing research progress, electrode classification, anode protection strategies, and electrochemical parameters. It does not introduce new algorithms, datasets, or propose new methods, and it does not focus on a specific domain with an applied ...	high
10.1002/aqc.4138	Marine biodiversity conservation: The cultural aspect of marine protected areas in Ghana	Abstract Studying fishers and fishing communities' social‐cultural structures is vital in policy‐making concerning local marine ecosystem sustainability. Previous studies on marine communities seldom neglected the role of culture in marine biodiversity conservation, especially a marine protected area (MPA) establishme...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The study applies existing research methods and frameworks to understand and influence marine biodiversity conservation in a specific cultural and socioeconomic context. It uses mixed-methods research to explore community attitudes and cultural practices, which are applied to policy-making. The focus on real-world impl...	Applied	false	The abstract discusses the cultural practices and willingness of coastal communities in Ghana to accept a marine protected area (MPA), which aligns with the 'Applied' label as it applies existing methods (research design, data collection techniques) to a specific domain (marine biodiversity conservation in Ghana).	high
10.1002/aqc.901	Conservation of threatened species in the Galapagos Marine Reserve through identification and protection of marine key biodiversity areas	Abstract The Galapagos Marine Reserve provides refuge for numerous threatened marine species, including 16 mammals, birds, reptiles and fish currently recognized on the 2006 IUCN Red List of Threatened Species, plus an additional 25 endemic fish, mollusc, crustacean, echinoderm, coral and macroalgal species that comply...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods (marine zoning) to a specific domain (conservation of threatened marine species), aligning with the 'Applied' classification. It does not introduce new algorithms, datasets, or theoretical analysis, and it focuses on practical conservation measures rather than a survey or meta-analysi...	Applied	false	The abstract discusses identifying and protecting marine key biodiversity areas to conserve threatened species, which involves applying existing methods (zoning schemes) to a specific domain (marine conservation).	high
10.1002/ase.70017	The importance of science communication and public engagement to professional associations	Abstract Scientific associations exist to serve their members and advance their science. They also provide a platform for scientists to communicate their science and engage with the public, such as hosting free resources on their web pages and organizing outreach activities with local communities. His...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper presents a viewpoint on the importance of science communication and public engagement, discussing historical examples and strategic programs. It does not introduce new methodologies or datasets, nor does it provide empirical analysis. Therefore, the classification as 'Review' is appropriate.	Review	false	The abstract discusses the role of scientific associations in science communication and public engagement, providing a historical perspective and examples of strategic programs. It does not introduce a new algorithm, model architecture, training technique, or mathematical method, nor does it present a new dataset or be...	high
10.1002/asmb.2064	Monitoring change point for diffusion parameter based on discretely observed sample from stochastic differential equation models	Stochastic differential equation (SDE) models are useful in describing complex dynamical systems in science and engineering. In this study, we consider a monitoring procedure for an early detection of dispersion parameter change in SDE models. The proposed scheme provides a useful diagnostic analysis for phase I retros...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The paper applies existing methods to a specific domain (SDE modeling) and discusses practical implementation and performance evaluation. It does not introduce a new algorithm, dataset, or theoretical analysis. The abstract is clear, scientific, and provides sufficient context for the classification.	Applied	false	The abstract describes a monitoring procedure for detecting changes in dispersion parameters of SDE models, which involves applying existing methods to a specific domain (SDE modeling in science and engineering). It also mentions simulation studies and empirical examples, indicating an applied context rather than a the...	high
10.1002/asna.201211780	Protoplanetary disks and planet formation around brown dwarfs and very low‐mass stars	AbstractBrown dwarfs and very low‐mass stars are very common in the Galaxy, yet we know little about the planetary systems they may host. Here we review observational evidence emerging from comparative studies of disks around brown dwarfs and sun‐like stars. These studies show that very young brown dwarfs and very low ...	Methodology	[ { "role": "system", "content": "You are a multilingual research paper intent classifier. Given a paper title and abstract, classify its primary research intent as exactly one of: Methodology, Dataset, Review, Applied, Theoretical, Unclassifiable." }, { "role": "user", "content": "Classify the re...	The abstract clearly outlines a systematic review of observational studies, focusing on the frequency of disks, disk lifetime, dust processing, and chemical composition around brown dwarfs and very low-mass stars. It does not introduce new methodologies, datasets, or theoretical analysis, confirming the classification ...	Review	false	The abstract provides a comprehensive review of observational evidence related to protoplanetary disks and planet formation around brown dwarfs and very low-mass stars. It discusses existing studies, their findings, and the implications for formation processes without introducing new empirical data or methods.	high

End of preview. Expand in Data Studio

Research Intent — LLM-as-Judge

LLM-as-Judge annotations for research paper intent classification, collected through the Echo-DSRN collaborative platform during the OpenAIRE AI Hackathon 2026.

The dataset has one split per judge model (Gemma_4_E4B_it_GGUF, Qwen3.6_35B_A3B_GGUF, Bonsai_8B_gguf, ...) plus a human_annotations split with curator annotations. Split names use underscores in place of the dashes in model names (HF does not allow dashes in split names).

Each record is a single judge verdict from one model on one paper, in ChatML conversation format with the judge's reasoning (rationale) included both inline in the assistant message and as a separate reasoning field.

Labels

Methodology — introduces a new algorithm, model architecture, or method
Dataset — primarily contributes a new dataset, benchmark, or annotation scheme
Review — survey, systematic review, or position paper
Applied — applies existing methods to a domain problem
Theoretical — mathematical or formal analysis
Unclassifiable — garbled, non-English, or non-academic content

Data structure

{
  "doi": "10.48550/arXiv.2106.01345",
  "title": "...",
  "description": "abstract text",
  "initial_intent": "Methodology",
  "messages": [
    {"role": "system", "content": "You are a multilingual research paper intent classifier..."},
    {"role": "user", "content": "Classify the research intent of this paper:\n\nTitle: ...\nAbstract: ..."},
    {"role": "assistant", "content": "The paper introduces a novel...\n\nDataset"}
  ],
  "reasoning": "The paper introduces a novel...",
  "model_prediction": "Dataset",
  "is_flagged": false,
  "flag_reason": null,
  "confidence": "high"
}

messages — ChatML conversation with inline reasoning in the assistant turn
reasoning — the judge's rationale as a standalone field
model_prediction — the label proposed by the judge
is_flagged / flag_reason — quality-issue signal (garbled text, language mismatch)
confidence — high / medium / low

Splits

One split per judge model (21 models, ~10k records each) plus human_annotations (46 curator annotations). Records within a split are per-paper single verdicts; a paper appears in every model split that judged it.

Provenance

Papers were collected from arXiv and OpenAIRE via the OpenAIRE Graph and judged by 20+ open-weight LLMs. Underperforming models (e.g. DeepSeek-Qwen3-8B, Kurtis-E1.1, Ministral-3-3B, Jan-v1-4B) are excluded. MTP and non-MTP variants of the same model are merged (they produce identical predictions).

Export tooling: scripts/export_llm_judge_dataset.py in the OpenAIRE-AI-Research-Evaluator repository.

License

CC-BY 4.0. Paper metadata originates from OpenAIRE Graph (CC BY 4.0).

Citation

If you reuse this work, please cite:

@software{echo_dsrn_research_intent_clf,
  author = {Massimo Roberto Scamarcia},
  title = {OpenAIRE Graph Evaluator: Research paper classifier and LLM-as-Judge pipeline},
  year = {2026},
  url = {https://huggingface.co/collections/ethicalabs/openaire-ai-hackathon-2026}
}

Downloads last month: 53

Collection including ethicalabs/Research-Intent-Judge

OpenAIRE AI Hackathon 2026

Collection

ethicalabs.ai's entry in the OpenAIRE AI Hackathon 2026, co-organised by OpenAIRE and Alien Intelligence — a 12-week open science build challenge • 6 items • Updated about 11 hours ago • 1