MétaCan
Menu
Back to cohort

Enhancing Adaptive Test Healing with Graph Neural Networks for Dependency-Aware Decision Making

2025· article· en· W4413319458 on OpenAlexaff
Nariman Mani, Salma Attaranasl

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSoftware System Performance and Reliability
Canadian institutionsNutrasource
Fundersnot available
KeywordsComputer scienceDependency (UML)Dependency graphArtificial intelligenceTest (biology)GraphMachine learningArtificial neural networkTheoretical computer science

Abstract

fetched live from OpenAlex

Flaky tests are a major obstacle in modern CI/CD pipelines, leading to unreliable feedback, increased reruns, and developer frustration. Our previously published adaptive healing framework combined Large Language Models (LLMs) and Reinforcement Learning (RL) to automate flaky test recovery, but it assumed test independence and failed to account for structural dependencies between tests. In this paper, we introduce a significant extension to that baseline: a Graph Neural Network (GNN)-based Test Dependency Mapping layer that models intertest relationships. By integrating GNN embeddings with LLM-classified failures, the RL agent becomes dependency-aware, enabling more precise and efficient healing decisions. We evaluate the enhanced framework on a real-world industrial platform, a social lifestyle application actively used by thousands of users for health, nutrition, and coaching. Results show a 90% reduction in flaky test-related costs and faster, autonomous resolution of dependency-induced failures.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.863
Threshold uncertainty score0.494

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.010
GPT teacher head0.265
Teacher spread0.254 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicSoftware System Performance and ReliabilityFrench-language works237,207