Vladimir Filkov

Raiyan Jahangir, Nafiz Imtiaz Khan, Amritanand Sudheerkumar et al.

Screening mammography is high volume, time sensitive, and documentation heavy. Radiologists must translate subtle visual findings into consistent BI-RADS assessments, breast density categories, and structured narrative reports. While recent Vision Language Models (VLMs) enable image-to-text reporting, many rely on closed cloud systems or tightly coupled architectures that limit privacy, reproducibility, and adaptability. We present MammoWise, a local multi-model pipeline that transforms open source VLMs into mammogram report generators and multi-task classifiers. MammoWise supports any Ollama-hosted VLM and mammography dataset, and enables zero-shot, few-shot, and Chain-of-Thought prompting, with optional multimodal Retrieval Augmented Generation (RAG) using a vector database for case-specific context. We evaluate MedGemma, LLaVA-Med, and Qwen2.5-VL on VinDr-Mammo and DMID datasets, assessing report quality (BERTScore, ROUGE-L), BI-RADS classification, breast density, and key findings. Report generation is consistently strong and improves with few-shot prompting and RAG. Classification is feasible but sensitive to model and dataset choice. Parameter-efficient fine-tuning (QLoRA) of MedGemma improves reliability, achieving BI-RADS accuracy of 0.7545, density accuracy of 0.8840, and calcification accuracy of 0.9341 while preserving report quality. MammoWise provides a practical and extensible framework for deploying local VLMs for mammography reporting within a unified and reproducible workflow.

Weiwei Xu, Hengzhi Ye, Haoran Ye et al.

Ethical constraints on open-weight AI models are both a reflection of societal concerns and a foundation for AI governance policy. They are expected to propagate to downstream derivatives while implemented as voluntary metadata disclosures that must be restated at each generation of reuse. We audit 2,142,823 model repositories on Hugging Face Hub to test whether this disclosure-based governance infrastructure can sustain traceability across deep model lineages. Restriction evidence decays with a half-life of 1.31 derivation steps ($R^2$=0.98), and beyond seven downstream generations at least 80% of descendant models lack sufficient public evidence for a governance determination, a depth boundary we formalize as the governance horizon. Platform-level interventions to restore missing licence metadata reveal that policy design (not enforcement alone) is the binding factor: inheritance-only designs require near-complete enforcement to move the horizon, whereas a mandatory-declaration design that explicitly resolves orphan lineage components shifts the horizon already at moderate enforcement. The structural bottleneck is lineages with no inheritable upstream intent: such orphan components remain undecidable under any inheritance-only policy regardless of enforcement rate, and unresolved upstream nodes additionally create direct downstream undecidability bottlenecks that inheritance rules alone cannot recover. Comparison with PyPI, where governance signals are carried by explicit machine-readable declarations, corroborates that the collapse is topology-specific to open-weight derivation rather than inherent to open ecosystems. These results establish that disclosure-based governance has a shallow, structurally determined reach in open-weight AI, and that achieving deep supply-chain accountability requires provenance mechanisms propagating governance signals through derivation itself.

David Kavaler, Premkumar Devanbu, Vladimir Filkov

Open Source Software (OSS) project success relies on crowd contributions. When an issue arises in pull-request based systems, @-mentions are used to call on people to task; previous studies have shown that @-mentions in discussions are associated with faster issue resolution. In most projects there may be many developers who could technically handle a variety of tasks. But OSS supports dynamic teams distributed across a wide variety of social and geographic backgrounds, as well as levels of involvement. It is, then, important to know whom to call on, i.e., who can be relied or trusted with important task-related duties, and why. In this paper, we sought to understand which observable socio-technical attributes of developers can be used to build good models of them being future @-mentioned in GitHub issues and pull request discussions. We built overall and project-specific predictive models of future @-mentions, in order to capture the determinants of @-mentions in each of two hundred GitHub projects, and to understand if and how those determinants differ between projects. We found that visibility, expertise, and productivity are associated with an increase in @-mentions, while responsiveness is not, in the presence of a number of control variables. Also, we find that though project-specific differences exist, the overall model can be used for cross-project prediction, indicating its GitHub-wide utility.

Qi Xuan, Premkumar T Devanbu, Vladimir Filkov

Much of what we do is accomplished by working collaboratively with others, and a large portion of our lives are spent working and talking; the patterns embodied in the alternation of working and talking can provide much useful insight into task-oriented social behaviors. The available electronic traces of the different kinds of human activities in online communities are an empirical goldmine that can enable the holistic study and understanding of these social systems. Open Source Software projects are prototypical examples of collaborative, task-oriented communities, depending on volunteers for high-quality work. Here, we use sequence analysis methods to identify the work-talk patterns of software developers in these online communities. We find that software developers prefer to persist in same kinds of activities, i.e., a string of work activities followed by a string of talk activities and so forth, rather than switch them frequently; this tendency strengthens with time, suggesting that developers become more efficient, and can work longer with fewer interruptions. This process is accompanied by the formation of community culture: developers' patterns in the same communities get closer with time while different communities get relatively more different. The emergence of community culture is apparently driven by both "talk" and "work". Finally, we also find that workers with good balance between "work" and "talk" tend to produce just as much work as those that focus strongly on "work"; however, the former appear to be more likely to continue to be active contributors in the communities.

Saisha Pradeep Shetty, Roger Eric Goldman, Vladimir Filkov

Radiology report annotation is essential for clinical NLP, yet manual labeling is slow and costly. We present RadAnnotate, an LLM-based framework that studies retrieval-augmented synthetic reports and confidence-based selective automation to reduce expert effort for labeling in RadGraph. We study RadGraph-style entity labeling (graph nodes) and leave relation extraction (edges) to future work. First, we train entity-specific classifiers on gold-standard reports and characterize their strengths and failure modes across anatomy and observation categories, with uncertain observations hardest to learn. Second, we generate RAG-guided synthetic reports and show that synthetic-only models remain within 1-2 F1 points of gold-trained models, and that synthetic augmentation is especially helpful for uncertain observations in a low-resource setting, improving F1 from 0.61 to 0.70. Finally, by learning entity-specific confidence thresholds, RadAnnotate can automatically annotate 55-90% of reports at 0.86-0.92 entity match score while routing low-confidence cases for expert review.

Nafiz Imtiaz Khan, Kylie Cleland, Vladimir Filkov et al.

Procedural case logs are a core requirement in radiology training, yet they are time-consuming to complete and prone to inconsistency when authored manually. This study investigates whether large language models (LLMs) can automate procedural case log documentation directly from free-text radiology reports. We evaluate multiple local and commercial LLMs under instruction-based and chain-of-thought prompting to extract structured procedural information from 414 curated interventional radiology reports authored by nine residents between 2018 and 2024. Model performance is assessed using sensitivity, specificity, and F1-score, alongside inference latency and token efficiency to estimate operational cost. Results show that both local and commercial models achieve strong extraction performance, with best F1-scores approaching 0.87, while exhibiting different trade-offs between speed and cost. Automation using LLMs has the potential to substantially reduce clerical burden for trainees and improve consistency in case logging. These findings demonstrate the feasibility of AI-assisted documentation in medical education and highlight the need for further validation across institutions and clinical workflows.

Xiaoguang Zhu, Lianlong Sun, Yang Liu et al.

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.

Likang Yin, Zhunagzhi Chen, Qi Xuan et al.

Although OSS development is very popular, ultimately more than 80 percent of OSS projects fail. Identifying the factors associated with OSS success can help in devising interventions when a project takes a downturn. OSS success has been studied from a variety of angles, more recently in empirical studies of large numbers of diverse projects, using proxies for sustainability, e.g., internal metrics related to productivity and external ones, related to community popularity. The internal socio-technical structure of projects has also been shown important, especially their dynamics. This points to another angle on evaluating software success, from the perspective of self-sustaining and self-governing communities. To uncover the dynamics of how a project at a nascent development stage gradually evolves into a sustainable one, here we apply a socio-technical network modeling perspective to a dataset of Apache Software Foundation Incubator (ASFI), sustainability-labeled projects. To identify and validate the determinants of sustainability, we undertake a mix of quantitative and qualitative studies of ASFI projects' socio-technical network trajectories. We develop interpretable models which can forecast a project becoming sustainable with more than 93 percent accuracy, within 8 months of incubation start. Based on the interpretable models we describe a strategy for real-time monitoring and suggesting actions, which can be used by projects to correct their sustainability trajectories.

Baishakhi Ray, Prem Devanbu, Vladimir Filkov

Berger et al., published in TOPLAS 2019, is a critique of our 2014 FSE conference abstract and its archival version, the 2017 CACM paper: A Large-Scale Study of Programming Languages and Code Quality in Github. In their paper Berger et al. make academic claims about the veracity of our work. Here, we respond to their technical and scientific critiques aimed at our work, attempting to stick with scientific discourse. We find that Berger et al. largely replicated our results, and agree with us in their conclusion: that the effects (in a statistical sense) found in the data are small, and should be taken with caution, and that it is possible that an absence of effect is the correct interpretation. Thus, our CACM paper's conclusions still hold, even more so now that they have been reproduced, and our paper is eminently citable.

Yue Yu, Bogdan Vasilescu, Huaimin Wang et al.

The constant demand for new features and bug fixes are forcing software projects to shorten cycles and deliver updates ever faster, while sustaining software quality. The availability of inexpensive, virtualized, cloud-computing has helped shorten schedules, by enabling continuous integration (CI) on demand. Platforms like GitHub support CI in-the-cloud. In projects using CI, a user submitting a pull request triggers a CI step. Besides speeding up build and test, this fortuitously creates voluminous archives of build and test successes and failures. CI is a relatively new phenomenon, and these archives allow a detailed study of CI. How many problems are exposed? Where do they occur? What factors affect CI failures? Does the "initial quality" as ascertained by CI predict how many bugs will later appear ("eventual quality") in the code? In this paper, we undertake a large-scale, fine resolution study of these records, to better understand CI processes, the nature, and predictors of CI failures, and the relationship of CI failures to the eventual quality of the code. We find that: a) CI failures appear to be concentrated in a few files, just like normal bugs; b) CI failures are not very highly correlated with eventual failures; c) The use of CI in a pull request doesn't necessarily mean the code in that request is of good quality.