# OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models Source: [OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models]() Collection index: [llms.txt]() Data updated: 2026-05-20T05:00:20.897Z Authors: Chiara Maria Russo, Simone Carnemolla, Simone Palazzo, Daniela Giordano, Concetto Spampinato, Matteo Pennisi Published: 2026-05-18T14:33:25.000Z ## Abstract Interpreting the decisions of deep image classifiers remains challenging, particularly in black-box settings where model internals are inaccessible. We introduce OCCAM, a framework for open-set causal concept explanation and ontology induction in vision models. OCCAM discovers visual concepts in an open-set manner, localizes them via text-guided segmentation, and performs object-level interventions by removing concepts to measure changes in class confidence, estimating each concept's causal contribution. Beyond local explanations, OCCAM aggregates interventional evidence across a dataset to induce a structured concept ontology that captures how classifiers globally organize visual concepts. Reasoning over this ontology reveals consistent dependencies between concepts, exposes latent causal relations, and uncovers systematic model biases. Experiments on Broden and ImageNet-S across multiple classifiers show that OCCAM improves explanation quality in open-set black-box settings while providing richer global insight than per-image attribution methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Concept contribution evaluation on Broden](): Concept contribution evaluation; Broden; ADP: 51.82. ## Original sources and implementation [Original paper]() [PDF]()