Evidence Hub

Audit and Statistical Reproduction Package for Translating Kansei Requirements into Product Colour Specifications for Diffusion-Assisted Conceptual Design

Hongyuan Zhang, KieSu Kim

Zenodo (CERN European Organization for Nuclear Research), 2026

Abstract

This repository contains the audit and statistical reproduction materials supporting the study “Translating Kansei Requirements into Product Colour Specifications for Diffusion-Assisted Conceptual Design.” The release includes source-traceability documentation for the retained 105-product market corpus (Amazon 20, JD.com 26, Taobao/Tmall 26, Puxiang 23, and ZCOOL 10), an exact machine-readable table of 534 raw Kansei-term occurrences transcribed from the retained source documents, derived market-colour records, de-identified participant data, independent Kansei coding data, GRA inputs, frozen generation and analysis records for Studies 2A–2E, the 12 author-generated A1–F2 fixed-stimulus concepts, Python rerun scripts, the current data-to-manuscript map, and supporting diagnostic/provenance records. The materials support recomputation of the principal reported statistical analyses and audit of frozen outputs. Third-party product/source and market-reference images are not redistributed in the public repository. The historical hythermos LoRA weight artefacts were previously audited but the five .safetensors binaries were not located among the materials available for this public-package build and are not included in this deposit. Bit-for-bit historical image regeneration is therefore not claimed from the public deposit alone.

Read the paper

Related studies

Go deeper in Evidence Hub

Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.

Open this study Sign up free