Read next because FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models overlaps with clean result "A pretraining-data-poisoned Qwen3-4B backdoor only fires on the exact trigger tokens — paraphrases don't activate it, and base-model similarity to the trigger doesn't predict which inputs fire (MODERATE confidence)", clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)", experiment "Add C2 control arm (donor sees marker_B without marker_A) to disambiguate paired-marker binding from marker_B leaking alone". Matching terms: token, line, without, full, stage, position, language, model. Source: arxiv cs.LG (Machine Learning).