Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-05T20:59:36.920210Z
Paper Citation Record · LEDGER
As of 8 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2508.09627.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-05T20:59:36.920210Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
37 of 37 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 309dc42d-5c34-4ea4-b840-7fbbe20d47fa · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Attention's forward pass and Frank-Wolfe
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be0693ad-f159-4275-b699-ba59d30ccd26 · outbound
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5fa23a59-cbeb-47fe-9c9a-5a63fc776f71 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs What Does BERT Look At? An Analysis of BERT's Attention
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 96c08972-70ad-4294-ae0f-2b6c2d5ef9ca · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Code available at https://github.com/borjanG/2025-transformers-frank-wolfe
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 2e3fae44-e889-45c2-ac57-1e1517f784b5 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Geometric Dynamics of Signal Propagation Predict Trainability of Transformers
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d49db9ff-bad3-421c-afac-c1727575192d · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Synchronization on circles and spheres with non- linear interactions
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 04880a75-c3bb-4696-8674-9f8d69a99d5b · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Setting the Record Straight on Transformer Oversmoothing
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2476eea6-535a-476d-a5b6-38416a280c2e · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs HashAttention: Semantic Sparsity for Faster Inference
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5e7b399b-64c1-4f3a-8ec4-f96880616beb · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Large-time asymptotics in deep learning
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a4db7592-1233-4ab9-a260-588d96f51ff7 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Dynamic metastability in the self-attention model
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 54808db1-4cb4-4349-9f62-84967e7c007f · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs When Attention Sink Emerges in Language Models: An Empirical View
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 166a3f28-2f3e-4d48-baca-9238c483fb90 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Measure-to-measure interpolation using Transformers
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3502e52c-0527-4846-9369-9a8cab6009fa · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs On the num- ber of modes of Gaussian kernel density estimators
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 184f4fac-3124-47f1-bf01-adafaa68cdad · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs OT-Transformer: A Continuous-time Transformer Architecture with Optimal Transport Regularization
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0c488601-5e03-4c95-bbd9-e12079528d8f · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Convergence Rate of Frank-Wolfe for Non-Convex Objectives
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a264f768-456a-4187-bdfd-e8c4215a6db4 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fdd1b26f-6d48-4bf0-bc57-e1cdd0bc5170 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Revisiting Over-smoothing in BERT from the Perspective of Graph
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0048375a-034c-445f-aa2a-f55b6ab1c697 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e24cac0b-f4f2-49dc-8d33-b784f73db151 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3186ff97-50f1-4c24-aa5f-f200f1d05316 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Solutions of stationary McKean-Vlasov equation on a high-dimensional sphere and other Riemannian manifolds
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e2419bc3-9a4d-446f-a74d-68c1c0a731ad · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Residual connections and normalization can provably pre- vent oversmoothing in gnns
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a2254ff4-0335-4f5c-95cc-4fb38a9bded3 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Recurrent self-attention dy- namics: An energy-agnostic perspective from Jacobians
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e6bff8e5-8ac2-47ed-ac17-06cfee5527ce · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Transformer-based Causal Language Models Perform Clustering
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 76b0351b-0473-4548-84ea-eaa5ed186703 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Learning Gaussian Mixture Models via Transformer Mea- sure Flows
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 91051fea-5921-423c-b867-6be33b69a2fd · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics
Reference 1973
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bc11a14-fda1-4ea6-8bcc-333bb7caccd9 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Finding Clustering Algorithms in the Transformer Architecture
Reference 1996
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation fee07a90-4ecf-40bd-90d4-d9cda2f960b3 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
Reference 2004
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8fe3d3f0-8c60-4bbc-929b-1897a9ec4116 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Self-attention Networks Localize When QK-eigenspectrum Concentrates
Reference 2005
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 11e8aa8d-6699-4818-ae0e-f9f8a6e8f38f · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Synchronization of mean-field models on the circle
Reference 2007
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fe4b9dc8-3e46-43ed-9d3a-6f8ce3ca128e · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Towards understanding how attention mechanism works in deep learning
Reference 2012
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ad0838aa-9c70-4d71-be19-d52d396ea4fc · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs The Geometry of Tokens in Internal Representations of Large Language Models
Reference 2015
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9e3340f0-fd96-4d64-8e81-f35743804b52 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
Reference 2016
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 210c3b96-5b53-405f-800b-56aa795a4958 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Continuum attention for neural operators
Reference 2019
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c3e72879-24cc-4739-b007-0fda49998b22 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Reference 2021
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7dca149c-b4ac-4c9e-8db8-4bdf0d50a1f1 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs A Unified Perspective on the Dynamics of Deep Transformers
Reference 2022
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 11f2bcab-7eac-4ab1-b450-47ea94c8730c · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Quantitative Clustering in Mean-Field Transformer Models
Reference 2024
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5575d3cf-34d6-46d8-980d-275027b37d83 · outbound
Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs Breaking BERT: Evaluating and Optimizing Sparsified Attention
Reference 2025
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
No inbound Pith citation observations are available.