CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles

ArXi:2603.00523v2 Announce Type: replace-cross Every mechanistic circuit carries an invisible asterisk: it reflects not just the model's computation, but the analyst's choice of pruning threshold. Change that choice and the circuit changes, yet current practice treats a single pruned subgraph as ground truth with no way to distinguish robust structure from threshold artifacts. We which reframes circuit discovery as a problem