MétaCan
Menu
← Back to cohort

AI-Assisted System Design: Improving Sequence Diagrams Through Use Case Scenarios

2025· article· W7127277507 on OpenAlexaff
Harsh Sarvaiya, Munima Jahan

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicSoftware Engineering Research
Canadian institutionsThompson Rivers University
Fundersnot available
KeywordsWorkflowSequence diagramLeverage (statistics)Pipeline (software)Pipeline transportSoftwareConsistency (knowledge bases)Sequence (biology)

Abstract

fetched live from OpenAlex

This paper explores two AI-driven approaches for transforming user stories (USs) into sequence diagrams (SDs). Pipeline A directly converts USs into SDs, while Pipeline B introduces an intermediate step of generating use case scenarios. Both pipelines leverage OpenAI’s GPT-4 model to automate these tasks. Ten user stories were processed through both pipelines and evaluated for accuracy, clarity, efficiency, and scalability. Pipeline B’s use of intermediate use case scenarios significantly improved the quality and detail of SDs while maintaining logical consistency and reducing ambiguity. These findings demonstrate the potential of AI-assisted tools to streamline software development, enhance collaboration, and make technical workflows accessible to non-technical stakeholders. While promising, challenges such as computational overhead and reliance on language models require further research. This study lays the groundwork for integrating AI into model-driven engineering, advancing efficiency and collaboration in software design.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.013
metaresearch head score (Gemma)0.070
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.013
Threshold uncertainty score0.071

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0130.070
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0040.002
Science and technology studies0.0010.002
Scholarly communication0.0040.007
Open science0.0030.004
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0040.001

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 head0.078
GPT teacher head0.316
Teacher spread0.238 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreEmpirical

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 Engineering Research→French-language works237,207→