For various reasons, I left data out of the requirements because most interesting research uses data unavailable to the community. CLIP is such an example, and it's A+ science: Model, Code, Paper.

Having the model is enough to verify the paper's claims, and also to experiment with new approaches (since you can fine-tune the model).

That said, I make this concession as a "meet you halfway" compromise between hard-line positions: "We can't release models, because we trained them on private data" and "You must release both models and data."

In other words, you're technically correct, but in my estimation it would do more harm to the end goal: the whole reason the scientific method is useful, is because it makes the world more useful.

The world would be less useful if fewer commercial companies participated in the scientific method. It's an inclusive group, not an exclusive clique. All you have to do, is give me the tools to verify your claims.