Separating What from When: Stage-Specialised Credit Assignment for Auditable Foreground Sound Evidence

Audio–language models can recognise a foreground sound while failing to show when it occurs. A tool-assisted system can also change a correct class label even when its timing tool supplies no new class evidence. We study these as separate fields of structured audio prediction. Our fixed protocol has three auditable stages: the model proposes a class, a frozen label-free tool inspects the waveform and returns an interval, and a finalisation rule retains the proposed class unless the new observation contains class evidence. A proposal-only adapter changes semantic behaviour while the temporal tool and the finalisation stage remain fixed. Across source-disjoint evaluation splits, stage specialisation improves answer exact match from $0.639$ to $0.736$ on the primary split without changing any predicted interval. The direction recurs on a later split and on new recordings of the classes used for adaptation. It reverses for an unseen class, which makes the transfer boundary explicit. Holding the semantic stage fixed, a frozen spectral-contrast localiser improves temporal IoU from $0.293$ to $0.464$ over an energy-based tool. Comparisons with three external audio–language models and the unadapted backbone use a shared tool and answer contract, so they measure semantic recognition under the evaluated protocol rather than native end-to-end system performance. Independent retraining preserves the direction of the semantic effect, whereas learned routing does not improve localisation. The evidence supports stage-specific credit assignment within this protocol and identifies low-SNR localisation and unseen-class transfer as open limits. It does not establish general state-of-the-art performance.