Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective | Paper Citation Record

Observation c91fc1ca-4ea5-40ac-9448-e45d6ba2d816 · outbound

This paper cites Mixhop : Higher-order graph convolutional architectures via sparsified neighborhood mixing.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Mixhop : Higher-order graph convolutional architectures via sparsified neighborhood mixing

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.125450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a52379f8-dc21-4993-830f-0988e8c5d4f6 · outbound

This paper cites On the bottleneck of graph neural networks and its practical implications.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective On the bottleneck of graph neural networks and its practical implications

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.130809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd969f21-f063-4ef4-a6bc-f2c6d66d49a5 · outbound

This paper cites A machine learning-based approximation of strong branching.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective A machine learning-based approximation of strong branching

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.135531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e828d5d-d28b-4df0-a410-c057ec0dff3a · outbound

This paper cites Label propagation across graphs: Node classification using graph neural tangent kernels.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Label propagation across graphs: Node classification using graph neural tangent kernels

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.140228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f68589fe-2721-4a7f-b982-8e87edd73a6c · outbound

This paper cites Machine learning for combinatorial optimization: a methodological tour d’horizon.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Machine learning for combinatorial optimization: a methodological tour d’horizon

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.144838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a04667d6-c75c-4feb-a006-d98c8a2f6655 · outbound

This paper cites Decision diagrams for optimization, volume 1.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Decision diagrams for optimization, volume 1

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.148857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ea5bf44-2c9c-4e1c-9040-9c01e1010c1e · outbound

This paper cites The maximum clique problem.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective The maximum clique problem

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.152982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e053edc7-435d-4efa-98a7-77ba6f07dadb · outbound

This paper cites Can graph neural networks go deeper without over-smoothing? yes, with a randomized path exploration! In IEEE Transactions on Emerging Topics in Computational Intelligence.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Can graph neural networks go deeper without over-smoothing? yes, with a randomized path exploration! In IEEE Transactions on Emerging Topics in Computational Intelligence

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.157230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 885cb1ff-2ffa-4961-99ab-793aa64adfc7 · outbound

This paper cites Reconnaissance de la parole par reseaux connexionnistes.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Reconnaissance de la parole par reseaux connexionnistes

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.161303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 722919a5-1b5d-4a2a-9543-99b1138aa357 · outbound

This paper cites A survey on optimization metaheuristics.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective A survey on optimization metaheuristics

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.165310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dc6f21a-f8a1-4ad6-9540-98f22304748e · outbound

This paper cites A note on over-smoothing for graph neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective A note on over-smoothing for graph neural networks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.169064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 836d7a64-8228-41f0-ab1e-5dfc691939dd · outbound

This paper cites Measuring and relieving the over-smoothing problem for graph neural networks from the topological view.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Measuring and relieving the over-smoothing problem for graph neural networks from the topological view

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.173370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33613da8-c84f-4000-81c1-b09d091f8048 · outbound

This paper cites Dirichlet energy enhancement of graph neural networks by framelet augmentation.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Dirichlet energy enhancement of graph neural networks by framelet augmentation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.178559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 965abd38-b443-4293-9d68-374e3f5f63cf · outbound

This paper cites Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.183603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79c4674c-593e-475d-96e1-95e868a8d056 · outbound

This paper cites Simple and deep graph convolutional networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Simple and deep graph convolutional networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.188886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e9afcfb-5412-48e8-9353-a5f627c57b31 · outbound

This paper cites Dynamical isometry and a mean field theory of rnns: Gating enables signal propagation in recurrent neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Dynamical isometry and a mean field theory of rnns: Gating enables signal propagation in recurrent neural networks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.193479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dfdf6cc-0ddc-4e71-b30b-c4f54f7ff572 · outbound

This paper cites Bag of tricks for training deeper graph neural networks: A comprehensive benchmark study.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Bag of tricks for training deeper graph neural networks: A comprehensive benchmark study

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.198105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fbbb7bd-41eb-44be-917b-88e0c5acc06e · outbound

This paper cites On representing linear programs by graph neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective On representing linear programs by graph neural networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.203774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41affb3d-1773-4747-ae36-d81d325aa57f · outbound

This paper cites Expressive power of graph neural networks for (mixed-integer) quadratic programs.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Expressive power of graph neural networks for (mixed-integer) quadratic programs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.208555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d434ef5-ebd9-49b9-89bd-d47077b03b58 · outbound

This paper cites Adaptive universal generalized pagerank graph neural network.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Adaptive universal generalized pagerank graph neural network

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.212766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c0385a8-57e2-49f1-9d77-398696756b45 · outbound

This paper cites Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-15T19:24:58.371978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7e08e607-16ac-4cb2-ac43-b0da85090cb6 · outbound

This paper cites Approximation algorithms for bin-packing—an updated survey.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Approximation algorithms for bin-packing—an updated survey

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.221394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a89a58c-630a-4322-ac15-49342cf95d16 · outbound

This paper cites On provable benefits of depth in training graph convolutional networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective On provable benefits of depth in training graph convolutional networks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.225961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac92d969-592b-4c31-80e1-5b4af06ca604 · outbound

This paper cites Metainit: Initializing learning by learning to initialize.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Metainit: Initializing learning by learning to initialize

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.229567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60be6f7d-6686-4b3f-9be8-10d200ce0028 · outbound

This paper cites Understanding convolution on graphs via energies.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Understanding convolution on graphs via energies

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.233344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45e510d2-0f93-48ca-8eb6-7ad1df7b5c5c · outbound

This paper cites Adagnn: Graph neural networks with adaptive frequency response filter.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Adagnn: Graph neural networks with adaptive frequency response filter

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.237971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31e9114a-7cf5-420d-a082-f2f9cd8d781f · outbound

This paper cites Graph neural tangent kernel: Fusing graph neural networks with graph kernels.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Graph neural tangent kernel: Fusing graph neural networks with graph kernels

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.241791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac014f7d-d628-4c96-824c-075533f6ac38 · outbound

This paper cites Learning from the dark: boosting graph convolutional neural networks with diverse negative samples.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Learning from the dark: boosting graph convolutional neural networks with diverse negative samples

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.245697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c1ad13c-9d26-4553-b872-484b09b846fb · outbound

This paper cites Graph convolutional neural networks with diverse negative samples via decomposed determinant point processes.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Graph convolutional neural networks with diverse negative samples via decomposed determinant point processes

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.249396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 621c0bb0-0d8d-45ec-bae7-84e219b48b18 · outbound

This paper cites Layer-diverse negative sampling for graph neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Layer-diverse negative sampling for graph neural networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.253225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3656e498-d58b-495e-a0e8-dc9caaab6ca5 · outbound

This paper cites The power of depth for feedforward neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective The power of depth for feedforward neural networks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.257176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ba5654-c20a-4c5a-8873-961247db9537 · outbound

This paper cites DropMessage : Unifying random dropping for graph neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective DropMessage : Unifying random dropping for graph neural networks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.260990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9adbaf49-5938-46a4-bcc1-b51b825b70cd · outbound

This paper cites Grato: Graph neural network framework tackling over-smoothing with neural architecture search.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Grato: Graph neural network framework tackling over-smoothing with neural architecture search

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.265198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b86f95be-218a-49dc-8f7e-acd537e9302e · outbound

This paper cites an unresolved cited work.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.270059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e108765b-40d5-4578-a6e0-39189c8262e9 · outbound

This paper cites Cooperative Graph Neural Networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Cooperative Graph Neural Networks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.274279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09068c51-fd1a-46a4-8809-1e63687ecab6 · outbound

This paper cites Exact combinatorial optimization with graph convolutional neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Exact combinatorial optimization with graph convolutional neural networks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.278366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3651b512-aec5-43ea-af88-41d225370c0f · outbound

This paper cites Predict then propagate: Graph neural networks meet personalized pagerank.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Predict then propagate: Graph neural networks meet personalized pagerank

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.283704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac9e7fe6-52a9-4fac-a681-e6763f020b7c · outbound

This paper cites The travelling salesman problem and related problems.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective The travelling salesman problem and related problems

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.287779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb00f4a-6ef1-484d-b288-3dddf1fdc8cd · outbound

This paper cites Graph convolutional networks from the perspective of sheaves and the neural tangent kernel.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Graph convolutional networks from the perspective of sheaves and the neural tangent kernel

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.291486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6db5fc30-5048-4951-8af5-dbf317370da1 · outbound

This paper cites Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.295398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca7c281-f2a1-46b2-a255-f18ecc47f2a6 · outbound

This paper cites Understanding the difficulty of training deep feedforward neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Understanding the difficulty of training deep feedforward neural networks

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.299939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16ee122a-9cbd-4e15-a6bc-0351ecea1e7f · outbound

This paper cites Orthogonal graph neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Orthogonal graph neural networks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.304468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef33b669-d633-4d61-a10f-4f30e59efe82 · outbound

This paper cites Contranorm: A contrastive learning perspective on oversmoothing and beyond.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Contranorm: A contrastive learning perspective on oversmoothing and beyond

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.308345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97ebbe23-c890-47a8-8329-806df2307d54 · outbound

This paper cites Structure-aware dropedge toward deep graph convolutional networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Structure-aware dropedge toward deep graph convolutional networks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.312707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c34132f-96b4-477f-b447-9a0317465f16 · outbound

This paper cites A gnn-guided predict-and-search framework for mixed-integer linear programming.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective A gnn-guided predict-and-search framework for mixed-integer linear programming

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.316760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccbb12d0-971d-4dde-a8c3-234a8923b746 · outbound

This paper cites Mlpinit: Embarrassingly simple gnn training acceleration with mlp initialization.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Mlpinit: Embarrassingly simple gnn training acceleration with mlp initialization

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.320668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64449fb6-085d-422e-ae78-fe0b6fdf0e2a · outbound

This paper cites Which neural net architectures give rise to exploding and vanishing gradients? Advances in Neural Information Processing Systems, 31, 2018.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Which neural net architectures give rise to exploding and vanishing gradients? Advances in Neural Information Processing Systems, 31, 2018

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.325302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 715c994a-279b-46f7-a3d0-be6cb559b44d · outbound

This paper cites Inequalities.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Inequalities

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.329349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311bf995-afa0-4120-b21f-6564f9b3c9eb · outbound

This paper cites On the impact of the activation function on deep neural networks training.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective On the impact of the activation function on deep neural networks training

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.333143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c48ed9-fde9-4ac0-acd4-17611cabe764 · outbound

This paper cites The curse of depth in kernel regime.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective The curse of depth in kernel regime

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.337985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b8e1b15-bc81-4c63-a620-c8d7907dac51 · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.342413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52bb6147-a673-4cf7-b1d1-0a4db78ae4a4 · outbound

This paper cites Deep residual learning for image recognition.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Deep residual learning for image recognition

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.346176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccb84385-0851-4a09-97b2-452c0dcc1451 · outbound

This paper cites Open graph benchmark: Datasets for machine learning on graphs.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Open graph benchmark: Datasets for machine learning on graphs

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.349790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 971efa90-5585-45fa-ba8f-036325a644c2 · outbound

This paper cites Towards deepening graph neural networks: A gntk-based optimization perspective.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Towards deepening graph neural networks: A gntk-based optimization perspective

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.353217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdde0d09-08a9-4540-a33c-9b1ec448fe64 · outbound

This paper cites Tackling Over-Smoothing for General Graph Convolutional Networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Tackling Over-Smoothing for General Graph Convolutional Networks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.356848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a3b771d-48b2-48ef-a254-280b2b2710c5 · outbound

This paper cites Batch normalization: Accelerating deep network training by reducing internal covariate shift.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Batch normalization: Accelerating deep network training by reducing internal covariate shift

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.360839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eacffcf3-3007-4e26-84ea-a62f40ed271f · outbound

This paper cites Old can be gold: Better gradient flow can make vanilla-gcns great again.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Old can be gold: Better gradient flow can make vanilla-gcns great again

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.364607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 991eda1c-260d-41c0-8d87-d9d96af0ebd1 · outbound

This paper cites Fast graph neural tangent kernel via kronecker sketching.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Fast graph neural tangent kernel via kronecker sketching

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.368784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5ee31b8-3afb-45ae-b717-7671c4337684 · outbound

This paper cites Towards feature overcorrelation in deeper graph neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Towards feature overcorrelation in deeper graph neural networks

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.372827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7af2a450-8f55-4c1d-a80b-f016c51c3ad6 · outbound

This paper cites Reducing oversmoothing in graph neural networks by changing the activation function.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Reducing oversmoothing in graph neural networks by changing the activation function

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.377012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fd4e461-85c4-4018-99a1-9e3513db3c19 · outbound

This paper cites Reducing Oversmoothing through Informed Weight Initialization in Graph Neural Networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Reducing Oversmoothing through Informed Weight Initialization in Graph Neural Networks

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-08-15T19:24:58.301670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 055a1984-9a77-40b8-bbe3-878948aebd87 · outbound

This paper cites Not too little, not too much: a theoretical analysis of graph (over)smoothing.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Not too little, not too much: a theoretical analysis of graph (over)smoothing

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.385708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b8f2f51-81a8-4324-afa9-4f2892898b60 · outbound

This paper cites Learning to branch in mixed integer programming.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Learning to branch in mixed integer programming

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.389779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e52646-e61d-4d99-8a55-0379419e2458 · outbound

This paper cites Learning to run heuristics in tree search.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Learning to run heuristics in tree search

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.393959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 449a0644-2b50-4eed-aa7b-94cc8762dac8 · outbound

This paper cites Semi-supervised classification with graph convolutional networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Semi-supervised classification with graph convolutional networks

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.398296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ea9943b-5fd6-4908-91c6-4c765923f509 · outbound

This paper cites Goat: A global transformer on large-scale graphs.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Goat: A global transformer on large-scale graphs

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.402705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f48d6f55-59c6-4c3f-8c85-382115fb30ee · outbound

This paper cites Graph Neural Tangent Kernel: Convergence on Large Graphs.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Graph Neural Tangent Kernel: Convergence on Large Graphs

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-08-15T19:24:58.272797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d584834c-e796-4a60-869f-a899c0391e67 · outbound

This paper cites Imagenet classification with deep convolutional neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Imagenet classification with deep convolutional neural networks

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.411653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98cf3d30-fa0c-4697-a8e8-06282af42d26 · outbound

This paper cites Efficient backprop.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Efficient backprop

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.415906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e485507-1026-48fb-8827-8f99a8b9143a · outbound

This paper cites Deep neural networks as gaussian processes.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Deep neural networks as gaussian processes

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.419621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b0ae74-eba1-43c8-b21b-d8d2188dd870 · outbound

This paper cites PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.423732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7d31d6d-eb62-4b9d-b16f-a2b5cdf8962a · outbound

This paper cites Deepgcns: Can gcns go as deep as cnns? In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Deepgcns: Can gcns go as deep as cnns? In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.427844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae96fa72-2d7c-4998-9627-6c52ce3475da · outbound

This paper cites Deepergcn: All you need to train deeper gcns, 2020.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Deepergcn: All you need to train deeper gcns, 2020

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.431574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5fdfd23-0b97-4ceb-bb15-4ad4704d2cfc · outbound

This paper cites Training graph neural networks with 1000 layers.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Training graph neural networks with 1000 layers

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.435829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39d3aa15-7d9a-4622-83de-2c5806560381 · outbound

This paper cites On the initialization of graph neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective On the initialization of graph neural networks

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.439693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 464cce68-f87e-40bb-b6e2-5d73449364d0 · outbound

This paper cites On random deep weight-tied autoencoders: Exact asymptotic analysis, phase transitions, and implications to training.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective On random deep weight-tied autoencoders: Exact asymptotic analysis, phase transitions, and implications to training

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.443456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76dd95d7-44b1-4174-ba0a-cb8c4598a906 · outbound

This paper cites On the power of small-size graph neural networks for linear programming.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective On the power of small-size graph neural networks for linear programming

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.447304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05845693-62fe-47d8-92c7-ddde24a04d1d · outbound

This paper cites Deeper insights into graph convolutional networks for semi-supervised learning.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Deeper insights into graph convolutional networks for semi-supervised learning

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.178707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 919b764a-b3c9-46e2-a4d2-087d0d23dbe8 · outbound

This paper cites Why deep neural networks for function approximation? In 5th International Conference on Learning Representations, ICLR 2017, 2017.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Why deep neural networks for function approximation? In 5th International Conference on Learning Representations, ICLR 2017, 2017

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.166244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 69bc9f17-2224-4cdf-ab73-5bc399db6164 · outbound

This paper cites Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.152768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0aa74f5b-072e-432d-b9ee-2f58686f81d4 · outbound

This paper cites Towards deeper graph neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Towards deeper graph neural networks

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.140210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3c0f2f8f-95bf-4cfc-9315-b7a261e72da5 · outbound

This paper cites SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.469947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55bff787-074d-4497-8d87-48a17e2c6dc2 · outbound

This paper cites Break the ceiling: Stronger multi-scale deep graph convolutional networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Break the ceiling: Stronger multi-scale deep graph convolutional networks

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.127095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 97072f62-184b-4773-8dc4-803cd817ed81 · outbound

This paper cites Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks

Reference 84

Resolution: verified exact; local_arxiv, observed 2026-08-15T19:24:58.225419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ef6dcf14-ddb0-4c6a-8159-5e464006715c · outbound

This paper cites Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.483700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e48f098-bc44-4680-bb26-853e79e69d74 · outbound

This paper cites A fractional graph laplacian approach to oversmoothing.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective A fractional graph laplacian approach to oversmoothing

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.113803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e773b079-42aa-4181-8859-1c0d318ec46a · outbound

This paper cites Gaussian process behaviour in wide deep neural networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Gaussian process behaviour in wide deep neural networks

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.099939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3ba60682-76e3-47f0-b552-2ade60841c2d · outbound

This paper cites Scattering gcn: Overcoming oversmoothness in graph convolutional networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Scattering gcn: Overcoming oversmoothness in graph convolutional networks

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.085480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0861386b-bead-4f09-927c-a1a06e218e10 · outbound

This paper cites Solving Mixed Integer Programs Using Neural Networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Solving Mixed Integer Programs Using Neural Networks

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.500704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d56b641-d36f-4fd3-bbb5-783773e5d91a · outbound

This paper cites Bayesian learning for neural networks, volume 118.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Bayesian learning for neural networks, volume 118

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.070836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0ffdf19a-14d5-45ae-bb38-b5a372448059 · outbound

This paper cites Random gradient-free minimization of convex functions.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Random gradient-free minimization of convex functions

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.510675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1029184-dd79-4dfc-9fbf-c5cb31389c97 · outbound

This paper cites Revisiting over-smoothing and over-squashing using ollivier-ricci curvature.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Revisiting over-smoothing and over-squashing using ollivier-ricci curvature

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.516955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a39ea9-c899-495c-b66e-7e8fb88b1524 · outbound

This paper cites Graph neural networks exponentially lose expressive power for node classification.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Graph neural networks exponentially lose expressive power for node classification

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.040403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2a243edb-a5e1-4e6d-b4ef-4aa14094aac5 · outbound

This paper cites Applications of combinatorial optimization.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Applications of combinatorial optimization

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.026991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation acf57eee-1117-4469-8360-e89e9ab3e866 · outbound

This paper cites Resurrecting the sigmoid in deep learning through dynamical isometry: Theory and practice.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Resurrecting the sigmoid in deep learning through dynamical isometry: Theory and practice

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:59.013044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation caece68e-d163-45a7-b450-4279ce076e23 · outbound

This paper cites The emergence of spectral universality in deep networks.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective The emergence of spectral universality in deep networks

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:58.998997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 79abcf6a-45fc-494f-8f69-f65c71132e3a · outbound

This paper cites A critical look at the evaluation of GNNs under heterophily: Are we really making progress?.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective A critical look at the evaluation of GNNs under heterophily: Are we really making progress?

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-15T19:24:57.540519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64916308-d86e-4cb9-9ca8-94efebc62be7 · outbound

This paper cites Exponential expressivity in deep neural networks through transient chaos.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Exponential expressivity in deep neural networks through transient chaos

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:58.983544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8c0266ee-4fec-4b6c-8afa-2482d1c8af11 · outbound

This paper cites Exploring the power of graph neural networks in solving linear optimization problems.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Exploring the power of graph neural networks in solving linear optimization problems

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:58.961682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3f34df87-c140-425a-b4e8-f5be47f3f8a6 · outbound

This paper cites Dropedge: Towards deep graph convolutional networks on node classification.

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective Dropedge: Towards deep graph convolutional networks on node classification

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:24:58.947191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers