FORGEry: A Multi-Model Adversarial Research Methodology for Independent AI Researchers

We present FORGEry, a multi-model adversarial research methodology enabling independent researchers to produce credible, reproducible AI research results without institutional infrastructure. FORGEry structures collaboration between large language models in strictly separated roles — execution substrate and architectural interrogator — with the human researcher as the sole cross-model routing node. Version 1.1 adds a Scorecard Layer — three orthogonal maturity scales (Bathtub to Blueprint, Today to Terminator, Nuts to Nobel) — applied before any irreversible Act, so "forge" does not become "forgery." We demonstrate validity through a concrete result: structural weight mapping from Mamba2-2.7B to Mamba3 (CE ratio 1.0016 on random tokens), prior to the Mamba team's reference model release. The nine-point weight mapping is open-sourced at https://github.com/Rta-Forge/heists-galore. The reference checkpoint is at https://huggingface.co/RtaForge/Mamba3-2.7B. The structural mapping was produced using the FORGEry adversarial methodology. All architectural decisions and validation were performed by the author; execution substrate and interrogator roles were filled by frontier LLMs under strict role separation.