Retrieval Forensics: Investigating Compression Damage in the AI Retrieval Layer

EA-RFO-01 — Practice definition for Retrieval Forensics: the investigative discipline of tracing how AI retrieval systems distort, erase, or misattribute entity meaning during compression. Specifies five evidentiary levels, four diagnostic metrics (β, Δ_G⁺, Δ_G⁻, S_c), and three compression regimes (R1/R2/R3). Demonstration case: Basecamp (37signals). Related disciplines: Retrieval Architecture, Compression Diagnostics, Entity Integrity, Metadata Packet for AI Indexing. Published in Transactions of the Semantic Economy Institute, Vol. 2, No. 3.