Preregistered placebo-controlled decomposition shows external executable counterexamples drive self-repair gains in small code models more than re-exposure or self-critique.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.SE 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Introduces evaluation of LLMs' implicit software world models via prediction of execution resources on real software tasks, finding modest and brittle performance across models including frontier ones.
RepoMirage uses semantics-preserving perturbations on SWE-Bench to show code agents lack repository context reasoning, with performance falling sharply on extended structure tasks, and introduces RepoAnchor as a structure-first fix.
citing papers explorer
-
Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models
Preregistered placebo-controlled decomposition shows external executable counterexamples drive self-repair gains in small code models more than re-exposure or self-critique.
-
Towards Evaluation of Implicit Software World Models in Coding LLMs
Introduces evaluation of LLMs' implicit software world models via prediction of execution resources on real software tasks, finding modest and brittle performance across models including frontier ones.
-
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
RepoMirage uses semantics-preserving perturbations on SWE-Bench to show code agents lack repository context reasoning, with performance falling sharply on extended structure tasks, and introduces RepoAnchor as a structure-first fix.