Image–Morphometric Learning for ZooScan Object Size Classification: Source-Verified Target Auditing and Fusion Reanalysis

High classification scores are meaningful only if the prediction target is physically consistent. We audited image-only, tabular-only and fusion experiments on 9000 ZooScan objects drawn from the 1,153,507-object PELGAS collection. The archived three-class labels were tertiles of the stored equivalent spherical diameter (ESD), not biomass classes. All 893,542 records exported with version v7.26 followed the documented ESD formula, whereas all 259,965 v7.24 records equalled twice the integer part of projected area divided by π. All 2017 v7.24 objects in the subset fell in the highest archived class. Recomputing ESD consistently from area and pixel calibration changed 3430 of the 9000 labels. The subset spans 13 cruises and 697 cruise–station groups and includes 2639 objects annotated as non-living. On the corrected target, tree-based controls using all descriptors reached a macro-F1 of about 0.998 under both object-stratified and station-grouped evaluation. In preliminary single-seed neural runs without area- or length-based descriptors, tabular networks reached a macro-F1 of 0.89, a Swin-T image model 0.946 and gated fusion 0.944; the image-based runs covered three folds and retained scale cues, so they do not isolate the contribution of each modality. Target provenance should be verified before multimodal performance rankings are used in ecological monitoring.