LATIDIA · Robótica

De los conceptos a las causas reales: Hacia el cierre de la brecha entre el concepto y el mal funcionamiento en los modelos de fundamentos robóticos

arXiv:2611.00155v1 Anuncio Tipo: nuevo Resumen: El análisis posterior al incidente de un modelo de base de robot plantea una pregunta causal singular: ¿qué componentes internos causaron esta falla y en qué grado? Interpretación mecanicista

La noticia

arXiv:2611.00155v1 Announce Type: new Abstract: Post-incident analysis of a robot foundation model poses a singular causal question: which internal components caused this failure, and to what degree? Mechanistic interpretability (MI), however, establishes general causal claims by decoding the concepts a policy has learned, yet knowing which concepts are encoded is insufficient for identifying the actual cause of a specific incident. In this position paper, we analyze this concept-malfunction gap by posing fault isolation in the framework of actual causality. Specifically, we formalize a fault-isolation query as a tuple of intervened internal components, counterfactual values, contingencies, and read-outs, and lay out conditions for it to be well-specified. Through this lens, we