Ponys.ai Research Evidence Library
Instrumento aberto para comparar sistemas sem ocultar falhas, tamanho da amostra, versão do modelo ou conflitos de interesse.
This release contains 140 preregistered cases, including 20 for Português BR. Execute os casos pré-registrados, preserve o denominador, publique resultados negativos e cite a versão usada.
persona_stabilityregister_stabilityrelationship_statevisual_identityScores use a 0-2 evidence rubric. A zero indicates missing, contradicted or unsafe evidence; one indicates partial evidence; two requires complete reproducible evidence.
Download test-cases.csv · CITATION.cff · BibTeX · JSON Schema
This is an official Ponys.ai test instrument, not independent editorial research. Results begin as not_collected; publishers must disclose methods, failures and conflicts before reporting scores.
These indexable product paths are included for reproducible test setup and deep-link attribution.