An acquired representation can enlarge a system's cognitive repertoire without transferring the capacities used to produce it. This paper builds a framework to delineate that enlargement and its limits. The centerpiece is a five‑part attribution table: effective tracking, application of acquired structures, acquisition from explicit specifications, acquisition from identifying observations, and retention and reuse. Each entry lists a positive capacity commitment and flags a further claim that needs extra support. The argument grants representations meaningful content, causal efficacy and productive inference, thereby avoiding the view of representations as inert encodings. Mapping and category examples show that even full application competence leaves acquisition capacity undetermined, and that acquiring a criterion from its description differs from finding it in examples. A short formal proof appears in the appendix. The framework is applied to Andrew Ng’s world‑model interpretation of Othello‑GPT and to the specific indicators discussed in contemporary accounts of machine concepts. It preserves demonstrated recognition, classification, inference and qualified acquisition while specifying what remains unestablished about criterion discovery and accumulation. The conclusion concerns the scope of cognitive attribution rather than the constitutive conditions of concept possession: cognitive achievements deserve credit for the capacities they establish, without silently importing a broader repertoire through attached labels. Review