Supplemental materials for "A Result-Auditable Protocol for Low-Data Classification of Blue-and-White Porcelain Botanical Motifs Using Frozen Chinese-CLIP Features"

Abstract

This record contains Supplemental File 1 for the revised manuscript, “A Result-Auditable Protocol for Low-Data Classification of Blue-and-White Porcelain Botanical Motifs Using Frozen Chinese-CLIP Features,” by Jingyun Hu, Jia Zhan, and Chenghao Yu. The image-free result-verification package contains de-identified internal and external image indices, five fixed train-test splits, per-image predictions, per-seed performance summaries, few-shot learning outputs, metadata audit results, retained 64-bit pHash values and distance audits, Chinese designed semantic prompts, extracted feature arrays, software and model configuration records, verification scripts, Docker and Conda environment definitions, retrospective external-label analyses, the pHash candidate-exclusion sensitivity analysis, a de-identified summary of the 11-pair blinded expert review, and SHA-256 checksums. The package supports result-level verification and classifier refitting from retained derived data. It does not reproduce pixel-level preprocessing, feature extraction, historical pHash generation, or exploratory fine-tuning from source pixels. Original catalog and museum images are not included because of copyright and reuse restrictions. Original crop files used for revision-stage inspection are also excluded from this public package.