Paper Citation Record · LEDGER

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders

As of 9 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2607.04487.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.04487 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T18:45:31.095808Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 94f10ea7-5222-49e8-ab40-ee2501192e9a · outbound

This paper cites Quantifying attention flow in transformers.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Quantifying attention flow in transformers

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad7cd4e6-7bfb-448b-8289-23adfaad61d1 · outbound

This paper cites Sanity checks for saliency maps.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Sanity checks for saliency maps

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe6528d2-40fd-495c-bcda-8573834099f9 · outbound

This paper cites Understanding intermediate layers using linear classi- fier probes.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Understanding intermediate layers using linear classi- fier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1885cdd-529a-42d1-a34c-d288c9a0e9b9 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05d7f26d-3785-437d-9c3f-ed256326cc51 · outbound

This paper cites Comparing partitions.Journal of Classification, 2:193–218,.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Comparing partitions.Journal of Classification, 2:193–218,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8d13caa-5ebe-4fe5-b8bc-b40863f36cc6 · outbound

This paper cites G-UniRouting: A graph-based unified neural model for solving multi-attribute vehicle routing problems.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders G-UniRouting: A graph-based unified neural model for solving multi-attribute vehicle routing problems

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd95cc2-1897-4b00-9aeb-fd6094cdf015 · outbound

This paper cites Captum: A unified and generic model interpretability library for PyTorch.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Captum: A unified and generic model interpretability library for PyTorch

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46109bc4-1c3e-4f6a-9aaf-d8c3a917d2c0 · outbound

This paper cites Attention, learn to solve routing problems! In ICLR,.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Attention, learn to solve routing problems! In ICLR,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6817235b-98d6-4877-bb2a-175e08fb8bbe · outbound

This paper cites Rousseeuw.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Rousseeuw

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9263144-8989-4939-8184-4a225890a216 · outbound

This paper cites The effective rank: A measure of effective dimensional- ity.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders The effective rank: A measure of effective dimensional- ity

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b79ced-81d8-4645-bd7a-367fc5c3c77f · outbound

This paper cites Outrageously large neural networks: The sparsely-gated mixture-of-experts layer.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Outrageously large neural networks: The sparsely-gated mixture-of-experts layer

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a27b6916-73c6-438e-b0ff-42b48d4b7295 · outbound

This paper cites Masked label prediction: Unified message passing model for semi- supervised classification.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Masked label prediction: Unified message passing model for semi- supervised classification

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 302c68aa-7516-426b-9915-f6f30b879707 · outbound

This paper cites Learning important features through propagating activation differences.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Learning important features through propagating activation differences

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cb020e6-2462-40ae-989c-ac977f7a02bd · outbound

This paper cites Axiomatic attribution for deep net- works.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Axiomatic attribution for deep net- works

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bee83a8-56bf-4451-8401-8e8919e7c632 · outbound

This paper cites Visualizing data using t-SNE.Jour- nal of Machine Learning Research, 9:2579–2605,.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Visualizing data using t-SNE.Jour- nal of Machine Learning Research, 9:2579–2605,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4423cc23-d034-4cf9-990e-d87fbe0e3352 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b2b2371-9c86-4d66-b763-b88aa694fc60 · outbound

This paper cites Information theoretic measures for cluster- ings comparison: Variants, properties, normalization and correction for chance.Journal of Machine Learning Re- search, 11:2837–2854,.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders Information theoretic measures for cluster- ings comparison: Variants, properties, normalization and correction for chance.Journal of Machine Learning Re- search, 11:2837–2854,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e295396-766d-41b8-b3cd-750112895ba6 · outbound

This paper cites GNNExplainer: Generating explanations for graph neural networks.

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders GNNExplainer: Generating explanations for graph neural networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T18:45:31.095808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.