Model-Sourcing Skill

Purpose

/architecture-zoo answers a literature question — which family of model suits this task. That question has a stable answer. The next question does not: which concrete artifact do I run? A repository, a revision, a checkpoint. That is a provenance question, and the two facts a careful researcher usually checks are the two that cannot answer it.

The licence tells you whether you may use it. The citation count tells you whether others did. Neither tells you whether the number you are about to report means what you will say it means.

The failure this skill exists for is the quietest one in the lane. A method developed and tuned against a benchmark family gets evaluated by the next person on that same family, and the resulting figure reads like validation while sitting much closer to a training-set score. Nothing in the repository says so. The licence is clean, the paper is peer-reviewed and highly cited, the task matches, the code runs on your GPU. The conflict lives in the relationship between two facts that are documented in different places — what the model was developed on, and what you are about to evaluate it on — and it becomes visible only when they are written down side by side.