Zero-Training Fracture Attribution via Directional Provenance Differencing

An actionable agent diagnosis must identify which write to change, the evidence for changing it, and the downstream work to replay. We introduce a zero-attribution-training framework that connects these objects through versioned artifact provenance. A bounded, directional local carrier compares fixed defect anchors against a write and its pooled parents, separating wrong-content introduction from required-content loss; confidence-aware pooling preserves anchor budgets at merges. Output ancestry determines relevance, while optional field contracts distinguish legitimate projection from deletion. On $226$ executable failures with unbalanced optimal transport (UOT) as the carrier, restricting scoring to output ancestors raises exact-write hit\@1 from $11.5\%$ to $50.9\%$, and replacing unsigned with directional local change adds a further $+21.2$ points (paired $95\%$ workflow-cluster interval $[16.3,26.9]$). With supplied contracts, an exact lexical/typed carrier reaches $100\%$ from $76.1\%$, and typed UOT gains likewise. Executed replay separates localization, repair, and regeneration cost; fixed missing-information experiments measure non-target selection, abstention, and replay-closure errors. Observation-equivalence ceilings separate what dependency structure alone can identify from what frozen defect anchors add. The result is an inspectable interface from defect evidence to testable interventions, with explicit observation requirements and no trained attribution predictor.