Comprehensive Content Analysis Dataset of the Iranian Junior High School "Social Studies" Textbook(Grade 9)(Lesson 9-12): A Multi-Agent Adjudicated Protocol (CAP) Based on the William Romey Method

This dataset provides a highly structured, empirical, and multi-agent adjudicated content analysis of Lessons 9 to 12 of the Iranian National Middle School textbook, "Social Studies" (Grade 9), using an advanced extension of the William Romey Method. Developed as an open-science initiative at Farhangian University (Nasiabeh Campus, Tehran), this project shifts the operational paradigm of pre-service teachers from curriculum consumers to Intelligent Supervisors. The analytical matrix conducts a granular evaluation across four critical textbook components: textual narratives, visual illustrations, integrated classroom activities, and sample questions. This systematic boundary isolates civic, socio-political, and constitutional learning pillars. To mitigate individual human biases and potential generative AI hallucination, the generation pipeline adhered strictly to the 4-stage Collaborative Adjudication Protocol (CAP): (1) Methodological training on active/passive content dynamic factors; (2) Baseline AI-assisted auditing via structurally validated prompt sequences; (3) Double-blind peer human-AI cross-auditing deploying four distinct professional roles (First Auditor, Second Auditor, Prompt Engineer, and Documentation Manager); and (4) Final CAP reconciliation and multi-agent text/image adjudication. This benchmark corpus stands as Volume 8 of the Iranian School Textbook Auditing Repository.