Paper Citation Record · LEDGER

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation

As of 20 August 2026, this Paper Citation Record lists 9 of 9 outbound references and 0 inbound Pith citation observations for arXiv:2605.25690.

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

pith.paper-citation-record.v1
2605.25690 v1

Coverage vector

measured 9 of 9 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T20:26:32.599286Z

measured 9 of 9 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

9 of 9 outbound references displayed

verified exact3
verified fuzzy0
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ef0508a5-dfca-4d67-9c24-e43c88e710dc · outbound

This paper cites Multi-behavior recommendation with cascading graph convolution networks.

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation Multi-behavior recommendation with cascading graph convolution networks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T20:26:32.599286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e473b245-1fd7-4d49-9163-bbab6590f765 · outbound

This paper cites Self-supervised graph neural networks for multi-behavior recommenda- tion.

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation Self-supervised graph neural networks for multi-behavior recommenda- tion

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T20:26:32.599286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d18df26e-8eab-4794-ac8a-1b1f9fe18255 · outbound

This paper cites Buying or browsing?: Predicting real-time purchasing intent using attention-based deep network with multiple behavior.

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation Buying or browsing?: Predicting real-time purchasing intent using attention-based deep network with multiple behavior

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T20:26:32.599286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8ee60cb-e955-4104-ba74-d1f718d17efb · outbound

This paper cites InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization.

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:24:04.588701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fa5a62b2-77c5-46de-a5e5-98280dc83873 · outbound

This paper cites Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks.

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-30T00:24:04.590870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d68a7d55-6b33-4137-b770-b32c58377fff · outbound

This paper cites Less is More: Information Bottleneck Denoised Multimedia Recommendation.

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation Less is More: Information Bottleneck Denoised Multimedia Recommendation

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:24:04.585494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7969477c-f484-4cd1-b2c7-27fea079c321 · outbound

This paper cites Related Work Graph-based Recommendation.Collaborative filtering has long been a foundational technique in recommendation systems.

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation Related Work Graph-based Recommendation.Collaborative filtering has long been a foundational technique in recommendation systems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T20:26:32.599286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68be5404-315e-428f-a7ab-8052089ceef1 · outbound

This paper cites To address noise from irrelevant graph connections, Graph Information Bottleneck (GIB) models extend the IB framework to structured graph data.

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation To address noise from irrelevant graph connections, Graph Information Bottleneck (GIB) models extend the IB framework to structured graph data

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T20:26:32.599286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74fe185a-1a2f-4bb3-abdf-ce9708a194ca · outbound

This paper cites The information bottleneck loss weight β is selected from [1, 100], and the contrastive loss weight λ is selected from [0.01, 0.5].

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation The information bottleneck loss weight β is selected from [1, 100], and the contrastive loss weight λ is selected from [0.01, 0.5]

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T20:26:32.599286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.