CASCADE finds code-documentation mismatches by running LLM-generated tests from docs and confirming failure only when documentation-derived code succeeds on the same test.
An empirical analysis of the impact of software development problem factors on software maintainability.J
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
A paraphrase-robust duplicate-step detector for Gherkin BDD suites, built on a new 1.1M-step public corpus, reports F1 scores up to 0.906 and estimates 893k eliminable step occurrences corpus-wide.
Presents a configurable variability-based framework for LLM-assisted naming of formal concepts in FCA and RCA, illustrated on a small pizzeria relational dataset.
CodeWiki presents a unified framework for repository-level documentation across seven languages using hierarchical decomposition, recursive multi-agent processing, and multi-modal synthesis, outperforming DeepWiki by 4.73% on CodeWikiBench.
Aleena is an open-source AI agent that ingests multi-modal research software collaboration artifacts and transforms them into structured GitHub records to maintain continuous stakeholder alignment across the project lifecycle.
A data-driven 5-item subset (Q3, Q9, Q10, Q12, Q14) of QoR-15 achieves mean AUC-ROC 0.968 for predicting recovery severity, statistically comparable to the full form on one-third of items, with similar readmission tracking.
citing papers explorer
-
CASCADE: Detecting Inconsistencies between Code and Documentation with Automatic Test Generation
CASCADE finds code-documentation mismatches by running LLM-generated tests from docs and confirming failure only when documentation-derived code succeeds on the same test.
-
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
-
Reducing Maintenance Burden in Behaviour-Driven Development: A Paraphrase-Robust Duplicate-Step Detector with a 1.1M-Step Open Benchmark
A paraphrase-robust duplicate-step detector for Gherkin BDD suites, built on a new 1.1M-step public corpus, reports F1 scores up to 0.906 and estimates 893k eliminable step occurrences corpus-wide.
-
A Variability-Based Framework for Interpretable Naming in Formal and Relational Concept Analysis
Presents a configurable variability-based framework for LLM-assisted naming of formal concepts in FCA and RCA, illustrated on a small pizzeria relational dataset.
-
CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases
CodeWiki presents a unified framework for repository-level documentation across seven languages using hierarchical decomposition, recursive multi-agent processing, and multi-modal synthesis, outperforming DeepWiki by 4.73% on CodeWikiBench.
-
Aleena: Alignment Agent for Research Software Engineering Collaborations
Aleena is an open-source AI agent that ingests multi-modal research software collaboration artifacts and transforms them into structured GitHub records to maintain continuous stakeholder alignment across the project lifecycle.
-
AI-driven Optimisation of Quality of Recovery (QoR) in Remote Patient Monitoring
A data-driven 5-item subset (Q3, Q9, Q10, Q12, Q14) of QoR-15 achieves mean AUC-ROC 0.968 for predicting recovery severity, statistically comparable to the full form on one-third of items, with similar readmission tracking.