What Should a Finite World Model Preserve? Learning Consequences for Decision-Weighted Capacity Allocation

Finite world models must decide which distinctions deserve limited representational resolution. We formulate this as context-conditioned allocation under observational support, decision relevance, and finite capacity. Our Learn–then–Allocate factorization predicts rate-conditioned representational consequences and solves the current budget explicitly. Uniform consequence error bounds allocation regret and yields exact recovery below the oracle margin; measured distortion curves reproduce $98.61\%$ of brute-force optima. A representation-specific ablation shows that the essential structure is rate-dependent marginal consequence: static importance and constant-marginal surrogates cannot reproduce scarcity-sensitive allocation, while a generic rate model captures only part of it. Under joint $(d,o,B)$ OOD, Learned-DP reaches $97.22\pm 1.75\%$ exact match and $0.00087$ regret versus $56.22\pm 1.75\%$ and $1.782$ for Direct-MLP+Slack. In learned-latent control, one-step regret is halved relative to Uniform, but freezing one allocation over longer rollouts erodes and eventually reverses that advantage. Finite representation allocation is therefore context-conditioned: learn rate-dependent consequences, optimize current scarcity, and do not treat one allocation as permanent.