Vladimir Filkov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Vladimir Filkov has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Nafiz Imtiaz Khan
Department of Computer Science, University of California, Davis
5 shared publications - Seth Frey
University of California Davis
5 shared publications - Likang Yin
Google, Mountain View, CA, USA
4 shared publications - Arjun Ashok
Department of Computer Science, University of California, Davis
2 shared publications - Curtis Atkisson
University of Washington, Seattle, WA, USA
2 shared publications - Mahasweta Chakraborti
Communication, University of California Davis, United States
2 shared publications
Latest Publications
- 6 October 2026
- Published by Springer Nature
- p. 268-288
RepoWise: A Conversational Framework for Open Source Repository Analysis with Retrieval-Augmented Generation and Structured Analytics
- 6 October 2026
- Published by Springer Nature
- p. 268-288
RepoWise: A Conversational Framework for Open Source Repository Analysis with Retrieval-Augmented Generation and Structured Analytics
- 13 July 2026
- Published by Elsevier in Journal of Systems and Software
- Vol. 242
Governing the digital commons at scale: Detecting Ostrom rule types in OSS
- 13 July 2026
- Published by Elsevier in Journal of Systems and Software
- Vol. 242
Governing the digital commons at scale: Detecting Ostrom rule types in OSS
- Open Access
- 21 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open-Source Software Sustainability: Defining and Measuring a Multifaceted Concept
Context: Open-source software (OSS) has become foundational to modern digital infrastructure, yet its long-term sustainability remains inadequately understood. Researchers and practitioners frequently conflate OSS sustainability with related but distinct concepts—success and health—leading to conceptual ambiguity and measurement challenges. Moreover, existing sustainability metrics often rely on static snapshots that fail to capture temporal dynamics and overlook the diversity of project types and stakeholder perspectives.Objectives: This paper aims to (1) establish clear conceptual distinctions between OSS sustainability, success, and health, and (2) develop a systematic metrics framework that incorporates dynamic, temporal measures and accounts for diverse project contexts and stakeholder perspectives.Methods: We conduct a conceptual analysis to delineate OSS sustainability (long-term adaptive capacity), success (milestone achievement), and health (current activity levels) as interconnected yet fundamentally different dimensions. We then develop the OSS Sustainability Metrics Framework organized across social and technical dimensions, incorporating both static indicators and dynamic trend-based measures. We demonstrate its applicability through empirical case studies across foundation-backed projects (Apache Software Foundation, Eclipse Foundation) and independent GitHub repositories, using a computational model called "OSSPREY."Results: Our framework reveals how sustainability trajectories emerge from evolving socio-technical equilibria rather than static attributes, enabling earlier identification of decline patterns. We further show how different stakeholders—core developers, new contributors, corporate adopters, and foundations—prioritize different sustainability dimensions based on their goals and dependencies.Conclusion: This work provides a foundation for developing nuanced sustainability assessment approaches that serve the varied needs of OSS ecosystem participants and supports future research on governance integration and stakeholder-specific indicator weighting.
- 21 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessOpen-Source Software Sustainability: Defining and Measuring a Multifaceted Concept
Context: Open-source software (OSS) has become foundational to modern digital infrastructure, yet its long-term sustainability remains inadequately understood. Researchers and practitioners frequently conflate OSS sustainability with related but distinct concepts—success and health—leading to conceptual ambiguity and measurement challenges. Moreover, existing sustainability metrics often rely on static snapshots that fail to capture temporal dynamics and overlook the diversity of project types and stakeholder perspectives.Objectives: This paper aims to (1) establish clear conceptual distinctions between OSS sustainability, success, and health, and (2) develop a systematic metrics framework that incorporates dynamic, temporal measures and accounts for diverse project contexts and stakeholder perspectives.Methods: We conduct a conceptual analysis to delineate OSS sustainability (long-term adaptive capacity), success (milestone achievement), and health (current activity levels) as interconnected yet fundamentally different dimensions. We then develop the OSS Sustainability Metrics Framework organized across social and technical dimensions, incorporating both static indicators and dynamic trend-based measures. We demonstrate its applicability through empirical case studies across foundation-backed projects (Apache Software Foundation, Eclipse Foundation) and independent GitHub repositories, using a computational model called "OSSPREY."Results: Our framework reveals how sustainability trajectories emerge from evolving socio-technical equilibria rather than static attributes, enabling earlier identification of decline patterns. We further show how different stakeholders—core developers, new contributors, corporate adopters, and foundations—prioritize different sustainability dimensions based on their goals and dependencies.Conclusion: This work provides a foundation for developing nuanced sustainability assessment approaches that serve the varied needs of OSS ecosystem participants and supports future research on governance integration and stakeholder-specific indicator weighting.
- Open Access
- 3 March 2026
- Published by Elsevier in SSRN Electronic Journal
Multi-Ecosystem Modeling of OSS Project Sustainability
OSS projects join software foundations like Apache, Eclipse, and OSGeo to get help with their immediate development plans and to improve long-term sustainability prospects. Once inside, they receive governance advice, incubation support, and community-building mechanisms. But foundations differ in their policies, funding models, and support strategies, and thus, outcomes can vary across them. Moreover, since projects have diverse needs and join these foundations at different lifecycle stages, it can be challenging to decide on the appropriate project-foundation match and on the project-specific plan for sustainability.Here, we present an empirical study and quantitative modeling analysis of the sustainability of incubator projects in the Apache, Eclipse, and OSGeo foundations, and, additionally, of GitHub projects from outside of the foundations. We develop sustainability models based on projects' sociotechnical traces and demonstrate their effectiveness within and across the foundations. We show that our best model, which uses a project-foundation router, OSS-ProF, can effectively forecast sustainability outcomes not only within but across foundations. In addition, the generalizability of the framework allows us to effectively apply the approach to GitHub projects outside the foundations. Our study highlights the value of sociotechnical networks as a generalizable framework for characterizing and addressing software project sustainability issues.
- 3 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMulti-Ecosystem Modeling of OSS Project Sustainability
OSS projects join software foundations like Apache, Eclipse, and OSGeo to get help with their immediate development plans and to improve long-term sustainability prospects. Once inside, they receive governance advice, incubation support, and community-building mechanisms. But foundations differ in their policies, funding models, and support strategies, and thus, outcomes can vary across them. Moreover, since projects have diverse needs and join these foundations at different lifecycle stages, it can be challenging to decide on the appropriate project-foundation match and on the project-specific plan for sustainability.Here, we present an empirical study and quantitative modeling analysis of the sustainability of incubator projects in the Apache, Eclipse, and OSGeo foundations, and, additionally, of GitHub projects from outside of the foundations. We develop sustainability models based on projects' sociotechnical traces and demonstrate their effectiveness within and across the foundations. We show that our best model, which uses a project-foundation router, OSS-ProF, can effectively forecast sustainability outcomes not only within but across foundations. In addition, the generalizability of the framework allows us to effectively apply the approach to GitHub projects outside the foundations. Our study highlights the value of sociotechnical networks as a generalizable framework for characterizing and addressing software project sustainability issues.
- Open Access
- 3 March 2026
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 205, 111599
Natural language processing of biomedical text to map and prioritize protein–disease associations in HFpEF
- 3 March 2026
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 205, 111599
Open AccessNatural language processing of biomedical text to map and prioritize protein–disease associations in HFpEF
- 2 January 2026
- Published by Springer Nature
- p. 446-463
Mammo-Find: An LLM-Based Multi-channel Tool for Recommending Public Mammogram Datasets
- 2 January 2026
- Published by Springer Nature
- p. 446-463
Mammo-Find: An LLM-Based Multi-channel Tool for Recommending Public Mammogram Datasets
- Open Access
- 15 October 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Vol. 8 (1) , 513-527
Responsible AI in the OSS: Reconciling Innovation with Risk Assessment and Disclosure
Ethical concerns around AI have increased emphasis on model auditing and reporting requirements. We thoroughly review the current state of governance and evaluation practices to identify specific challenges to responsible AI development in OSS. We then analyze OSS projects to understand if model evaluation is associated with safety assessments, through documentation of limitations, biases, and other risks. Our analysis of 7902 Hugging Face projects found that while risk documentation is strongly associated with evaluation practices, high performers from the platform’s largest competitive leaderboard (N=789) were less accountable. Recognizing these delicate tensions from performance incentives may guide providers in revisiting the objectives of evaluation and legal scholars in formulating platform interventions and policies that balance innovation and responsibility.
- 15 October 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Vol. 8 (1) , 513-527
Open AccessResponsible AI in the OSS: Reconciling Innovation with Risk Assessment and Disclosure
Ethical concerns around AI have increased emphasis on model auditing and reporting requirements. We thoroughly review the current state of governance and evaluation practices to identify specific challenges to responsible AI development in OSS. We then analyze OSS projects to understand if model evaluation is associated with safety assessments, through documentation of limitations, biases, and other risks. Our analysis of 7902 Hugging Face projects found that while risk documentation is strongly associated with evaluation practices, high performers from the platform’s largest competitive leaderboard (N=789) were less accountable. Recognizing these delicate tensions from performance incentives may guide providers in revisiting the objectives of evaluation and legal scholars in formulating platform interventions and policies that balance innovation and responsibility.
- Open Access
Causal Debiasing Medical Multimodal Representation Learning with Missing Modalities
Medical multimodal representation learning aims to integrate heterogeneous clinical data into unified patient representations to support predictive modeling, which remains an essential yet challenging task in the medical data mining community. However, real-world medical datasets often suffer from missing modalities due to cost, protocol, or patient-specific constraints. Existing methods primarily address this issue by learning from the available observations in either the raw data space or feature space, but typically neglect the underlying bias introduced by the data acquisition process itself. In this work, we identify two types of biases that hinder model generalization: missingness bias, which results from non-random patterns in modality availability, and distribution bias, which arises from latent confounders that influence both observed features and outcomes. To address these challenges, we perform a structural causal analysis of the data-generating process and propose a unified framework that is compatible with existing direct prediction-based multimodal learning methods. Our method consists of two key components: (1) a missingness deconfounding module that approximates causal intervention based on backdoor adjustment and (2) a dual-branch neural network that explicitly disentangles causal features from spurious correlations. We evaluated our method in real-world public and in-hospital datasets, demonstrating its effectiveness and causal insights.
Open AccessCausal Debiasing Medical Multimodal Representation Learning with Missing Modalities
Medical multimodal representation learning aims to integrate heterogeneous clinical data into unified patient representations to support predictive modeling, which remains an essential yet challenging task in the medical data mining community. However, real-world medical datasets often suffer from missing modalities due to cost, protocol, or patient-specific constraints. Existing methods primarily address this issue by learning from the available observations in either the raw data space or feature space, but typically neglect the underlying bias introduced by the data acquisition process itself. In this work, we identify two types of biases that hinder model generalization: missingness bias, which results from non-random patterns in modality availability, and distribution bias, which arises from latent confounders that influence both observed features and outcomes. To address these challenges, we perform a structural causal analysis of the data-generating process and propose a unified framework that is compatible with existing direct prediction-based multimodal learning methods. Our method consists of two key components: (1) a missingness deconfounding module that approximates causal intervention based on backdoor adjustment and (2) a dual-branch neural network that explicitly disentangles causal features from spurious correlations. We evaluated our method in real-world public and in-hospital datasets, demonstrating its effectiveness and causal insights.
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1188-1192
EvidenceBot: A Privacy-Preserving, Customizable RAG-Based Tool for Enhancing Large Language Model Interactions
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1188-1192
Open AccessEvidenceBot: A Privacy-Preserving, Customizable RAG-Based Tool for Enhancing Large Language Model Interactions
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 457-461
From Models to Practice: Enhancing OSS Project Sustainability with Evidence-Based Advice
Sustainability in Open Source Software (OSS) projects is crucial for long-term innovation, community support, and the enduring success of open-source solutions. Although multitude of studies have provided effective models for OSS sustainability, their practical implications have been lacking because most identified features are not amenable to direct tuning by developers (e.g., levels of communication, number of commits per project). In this paper, we report on preliminary work toward making models more actionable based on evidence-based findings from prior research. Given a set of identified features of interest to OSS project sustainability, we performed comprehensive literature review related to those features to uncover practical, evidence-based advice, which we call Researched Actionables (ReACTs). The ReACTs are practical advice with specific steps, found in prior work to associate with tangible results. Starting from a set of sustainability-related features, this study contributes 105 ReACTs to the SE community by analyzing 186 published articles. Moreover, this study introduces a newly developed tool (ReACTive) designed to enhance the exploration of ReACTs through visualization across various facets of the OSS ecosystem. The ReACTs idea opens new avenues for connecting SE metrics to actionable research in SE in general.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 457-461
Open AccessFrom Models to Practice: Enhancing OSS Project Sustainability with Evidence-Based Advice
Sustainability in Open Source Software (OSS) projects is crucial for long-term innovation, community support, and the enduring success of open-source solutions. Although multitude of studies have provided effective models for OSS sustainability, their practical implications have been lacking because most identified features are not amenable to direct tuning by developers (e.g., levels of communication, number of commits per project). In this paper, we report on preliminary work toward making models more actionable based on evidence-based findings from prior research. Given a set of identified features of interest to OSS project sustainability, we performed comprehensive literature review related to those features to uncover practical, evidence-based advice, which we call Researched Actionables (ReACTs). The ReACTs are practical advice with specific steps, found in prior work to associate with tangible results. Starting from a set of sustainability-related features, this study contributes 105 ReACTs to the SE community by analyzing 186 published articles. Moreover, this study introduces a newly developed tool (ReACTive) designed to enhance the exploration of ReACTs through visualization across various facets of the OSS ecosystem. The ReACTs idea opens new avenues for connecting SE metrics to actionable research in SE in general.