activity
20212026
most citedThe impact of feature importance methods on the interpretation of defect classifiers

132 citations · 469 across the 30 of their papers we have counts for

collaborators

33 papers

cs.SE2026

LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering

Gopi Krishnan Rajbahadur, Amir M. Ebrahimi, Boyuan Chen +1

Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing…

cs.SE2026

To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing

Amir M. Ebrahimi, Mohammed Mehedi Hasan, Aaditya Bhatia +2

Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder to maintain. We identify one co…

cs.SE2026

Don't Trust the Label: License Laundering in AI Supply Chains

James Jewitt, Hao Li, Gopi Krishnan Rajbahadur +2

AI artifacts move through a multi-platform supply chain, spanning datasets and models on Hugging Face and applications on GitHub. While each artifact carries a license whose obliga…

cs.SE2026

From Failure to Alignment: A Requirements Engineering Framework for Machine Learning Systems

Amel Bennaceur, Gopi Krishnan Rajbahadur, Prince Mercy +2

Organisations designing, developing, and deploying machine learning systems (MLS) need to be able to check that these systems are trustworthy, and communicate this clearly to their…

cs.SE2026

Edit, But Verify: An Empirical Audit of Instructed Code-Editing Benchmarks

Amir M. Ebrahimi, Gopi Krishnan Rajbahadur

Instructed code editing, where an LLM modifies existing code based on a natural language instruction, accounts for roughly 19% of real-world coding assistant interactions. Yet very…

cs.LG2026

Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity

James Jewitt, Gopi Krishnan Rajbahadur, Hao Li +2

Permissive licenses like MIT, Apache-2.0, and BSD-3-Clause dominate open-source AI, signaling that artifacts like models, datasets, and code can be freely used, modified, and redis…