两个黑箱，一个求解器：硬掩码和追索解码器下神经多属性车辆路径规划问题的编码器探测与解码器归因
Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders
AI总结：
研究神经自回归求解器解决多属性车辆路径规划问题，通过线性探测等方法打开编码器黑箱，用三种归因方法打开解码器黑箱，从多方面对解释进行评分，发现多种影响及特性。
摘要：
用于多属性车辆路径规划问题（MAVRP）的神经自回归求解器成本有竞争力，但无逐步骤合理性。本文在一个协议中打开两个互补黑箱。编码器端用多种方法刻画潜在表示如何在不同层级表示约束族；解码器端用三种归因方法提供不同视角。解释按多种标准评分。研究发现多种结论，如归纳偏差的作用等。
英文摘要：
Neural autoregressive solvers for the Multi-Attribute Vehicle Routing Problem (MAVRP) reach competitive cost but offer no per-step justification, a problem when dispatchers must validate, accept, or compare them. We open two complementary black boxes in one protocol. On the encoder side, linear probes, spontaneous-organization metrics, rank-based richness measures, and discovered-direction analyses with intervention validation characterize how the latent represents constraint families at the graph, node, and edge level. On the decoder side, three attribution methods (gradient, integrated gradients, DeepLIFT) feed three reading angles: abductive, contrastive against the best feasible alternative, and counterfactual (smallest input change that switches the action or restores feasibility). Explanations are scored on fidelity, concentration, stability, sanity, and actionability. Across six variants combining three encoders (Attention baseline, Unimp, UnimpMoe) with two decoders (Hard-Mask, Recourse), we find that graph inductive bias improves both representational predictability and decoder sanity, that the Mixture-of-Experts encoder represents constraints in a distributed rather than axis-aligned way, and that the Recourse training regime, not merely its softer mask, produces policies that represent infeasibility usefully, exposing make-feasible counterfactuals that Hard-Mask policies fail to produce even when fed infeasible alternatives externally.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
