Comment: 25 pages of main text, 13 pages of Appendix and BibliographyExisting approaches to asset-pricing under model-uncertainty adapt classical utility-maximisation frameworks and seek theoretical comprehensiveness. We move toward practice by considering binary model-uncertainties and by switching attention from 'preference' to 'constraints'. Economic asset-pricing in this setting is found to decompose into the viable pricing of model-risk and of non-model risk separately such that the former has a unique and intuitive risk-neutral equivalent formulation with convenient properties. Its parameter, a dynamically conserved constant of model-risk inference, allows an integrated representation of ex-ante risk-pricing and bias, such that their ex-post price-effects can be disentangled, through well-known price anomalies such as Momentum and Low-Risk.