DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains

2026-08-11

AI Summary

This study addresses the problem of selecting interventions to maximize recoverable net value under critical supply chain disruptions. It introduces CriticalSCM-Bench v1, the first synthetic benchmark that explicitly integrates causal intervention ranking with net value objectives, incorporating ground-truth causal structures and domain-specific value targets. Leveraging decision-aware learning-to-rank methods such as LambdaMART, the framework evaluates intervention strategies in controlled environments by combining causal simulation, counterfactual reasoning, and domain-informed heuristics. Experimental results demonstrate that the proposed approach improves net value by 5.7–16.2% in semiconductor and critical materials scenarios, while retaining 33–75% of full-information performance under partial observability. In digital infrastructure settings, however, simpler strategies remain competitive.

Abstract

Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present CriticalSCM-Bench v1, a controlled synthetic benchmark with causal ground truth, paired factual/counterfactual rollouts, and an explicit net-value objective. Relative to a full-information train-selected static benchmark, LambdaMART improves median normalized net value by 5.7--16.2\%, with paired statistical support on the semiconductor and critical-material archetypes but not on digital infrastructure. On digital infrastructure, a domain-informed constant-buffer policy remains stronger, showing that greater model complexity is not uniformly justified. Across partial and delayed settings, LambdaMART retains 33--75\% of full-clamp value. Stress tests further show that intervention fidelity, timing, cost, and held-out disruptions can alter policy ordering. Critical materials show the weakest out-of-distribution retention. Separately, a guarded explanation study over 540 generations preserves every fixed intervention decision after deterministic validation and template fallback, although exact wording remains unstable. Within this controlled setting, the results identify regimes in which adaptive ranking adds value and those in which simpler structural policies remain preferable.

Problem

• supply chain
• causal intervention
• net value
• intervention ranking
• critical infrastructure

Innovation

• Decision-Aware Causal Intervention
• Critical Supply Chains
• Synthetic Benchmark with Causal Ground Truth
• Counterfactual Rollouts
• Net-Value Optimization