@article{l0reasoningbenchevaluatingprocedural, title = {L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution}, author = {Simeng Sun and Cheng-Ping Hsieh and Faisal Ladhak and Erik Arakelyan and Santiago Akle Serano and Boris Ginsburg}, year = {2025}, eprint = {2503.22832}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.22832v2}, }