Abstract
If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We test this zero-shot on current commercial models. Five LLMs generate solutions to MBPP, HumanEval, and DS-1000, seven more to MBPP, and models act as evaluators in four tasks: picking their own solution from a pair, judging whether a single solution is their own, identifying which of two solutions a named model wrote, and judging quality blind. In the single-solution task, balanced accuracy is 49-58% for all 15 model-benchmark combinations, while raw accuracy (38-67%) mostly reflects how readily a model claims authorship. In the pairwise task, accuracy across 14 evaluator-opponent combinations correlates at r=0.93 with how often the evaluator's solution is longer. Attribution to a named model succeeds on some pairs and is consistently inverted on others. A rule-based normalization that strips docstrings, comments, type hints, and local names preserves Pass@1 and leaves ten of twelve re-tested results at chance; the other two follow a length difference it leaves, although a trained classifier still separates most normalized pairs. Claude Haiku's self-preference also disappears. We recommend reporting balanced accuracy, heuristic baselines, and label consistency.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Barkhordar, E., & Thapa, S. (2026). Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models. https://omanscience.com/en/articles/style-not-self-surface-cues-explain-zero-shot-code-attribution-by-large-language-models
MLA 9
Barkhordar, Ehsan, and Surendrabikram Thapa. "Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models." https://omanscience.com/en/articles/style-not-self-surface-cues-explain-zero-shot-code-attribution-by-large-language-models.
Chicago (author–date)
Barkhordar, Ehsan, and Surendrabikram Thapa. 2026. "Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models." https://omanscience.com/en/articles/style-not-self-surface-cues-explain-zero-shot-code-attribution-by-large-language-models.
Harvard
Barkhordar, E. and Thapa, S. (2026) 'Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models', Available at: https://omanscience.com/en/articles/style-not-self-surface-cues-explain-zero-shot-code-attribution-by-large-language-models.
Vancouver
Barkhordar E, Thapa S. Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models. https://omanscience.com/en/articles/style-not-self-surface-cues-explain-zero-shot-code-attribution-by-large-language-models
IEEE
E. Barkhordar, and S. Thapa, "Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models," https://omanscience.com/en/articles/style-not-self-surface-cues-explain-zero-shot-code-attribution-by-large-language-models.