Replication Data: Vocabulary-Activation Correspondence in Self-Referential LLM Processing

Data and code for a replication study of Dadfar (2026) "Vocabulary-Activation Correspondence in Self-Referential LLM Processing"(arXiv:2602.11358). The replication fails: VAC as reported does not survive length correction or cross-model validation. The underlying autoregressive dynamics (limit cycles, vocabulary narrowing) are real and reproducible, but they are properties of extended generation, not of self-referential processing specifically.本数据集包含针对Dadfar（2026）发表于arXiv:2602.11358的论文《自指式大语言模型（Large Language Model，LLM）处理中的词汇激活对应关系》开展重复研究所用的数据与代码。本次重复研究未达预期：原论文所报道的词汇激活对应关系（Vocabulary-Activation Correspondence，VAC）无法通过长度校正或跨模型验证得以保留。其底层的自回归动态特性（极限环、词汇收缩现象）确实存在且可复现，但这些特性仅属于扩展生成过程的通用属性，并非特指自指式处理。