3 papers
cs.SE2026
Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair
Anik Jha
Fault localization can focus a code model's repair on the statements a failing test implicates, but a targeted edit may succeed merely because it is small, and a second model call…
cs.CR2026
Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles
Anik Jha
Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monitor at matched cost. They are b…
cs.CL2026
Whose Gold? Annotator-Pool Disagreement Is Large at the Item Level, and Hidden by Small Leaderboards
Anik Jha
Preference benchmarks are built by hiring annotators, and the identity of those annotators is treated as an implementation detail. We measure what that detail buys. On the 2,885 Mu…