Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-16T00:38:29.713872Z
Paper Citation Record · LEDGER
As of 23 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2608.11612.
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 2026-08-16T00:38:29.713872Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+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
46 of 46 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 81114db0-6da8-4eaf-ac05-79ffce472745 · outbound
Dion3: Full-Stack Orthogonal Updates Laguna M.1/XS.2 Technical Report
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3156684f-6e66-4c0a-aeb1-24c6f4a098d2 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1c84dee9-c2f0-4087-b8e8-ae3d9e5c37a1 · outbound
Dion3: Full-Stack Orthogonal Updates The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon Algorithm
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation d1aaa74c-794d-4e47-b23f-d0878aa2417e · outbound
Dion3: Full-Stack Orthogonal Updates Google DeepMind, 2025.https://jax-ml.github.io/scaling-book/
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation c28cf9d9-96c5-4861-a870-65667fa1c2fc · outbound
Dion3: Full-Stack Orthogonal Updates Deriving Muon
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 247a6308-c481-4fd1-bcc4-1c7eff8540c0 · outbound
Dion3: Full-Stack Orthogonal Updates Turbo-Muon: Almost-Orthogonal Pre-Conditioning for Fast Muon Updates
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6e3f798-2f5a-4a8d-8e8d-a73270685989 · outbound
Dion3: Full-Stack Orthogonal Updates Towards understanding of orthogonalization in Muon
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation f18bd7b0-6a75-45d1-afa3-e51d494057ae · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 5b0f9dd9-ace9-4482-b97c-8f16bc71070e · outbound
Dion3: Full-Stack Orthogonal Updates DeepSeek-V3 Technical Report
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a985daa5-8ff4-4c87-8094-44dc2db0c780 · outbound
Dion3: Full-Stack Orthogonal Updates Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre- training
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation a9343e0a-a92c-4dff-a1e5-fd4dff950249 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 630b6042-0016-44ea-b1fd-dd9c22b952fc · outbound
Dion3: Full-Stack Orthogonal Updates Gemma 3 Technical Report
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7dfee4a9-3575-451a-b223-cbc69e9c7e73 · outbound
Dion3: Full-Stack Orthogonal Updates GLM-5: from Vibe Coding to Agentic Engineering
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cca2198a-b058-4487-8039-5d91d44e1d27 · outbound
Dion3: Full-Stack Orthogonal Updates The Llama 3 Herd of Models
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 08c989f2-85c0-4746-a357-d96de9d0ad4f · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e1db63f2-32eb-4299-84c2-1c2258555041 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e7b3ed4c-c578-4fdc-ac2b-2d1ace7e9bb4 · outbound
Dion3: Full-Stack Orthogonal Updates Higham.Functions of Matrices: Theory and Computation
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1ff10930-8c9d-4890-afc1-4634d1549ea1 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 0a52da0b-8c18-4518-9572-dfad7fc32383 · outbound
Dion3: Full-Stack Orthogonal Updates Muon: An optimizer for hidden layers in neural networks
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 1da1f387-8262-4ddb-9266-3a124b66e2d6 · outbound
Dion3: Full-Stack Orthogonal Updates MuonBP: Faster Muon via Block-Periodic Orthogonalization
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 3c9c39f3-8230-46b5-9f09-4ceb7585854a · outbound
Dion3: Full-Stack Orthogonal Updates Kimi K2: Open Agentic Intelligence
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d00e529c-71e2-48b7-9dd4-408f88cf66a9 · outbound
Dion3: Full-Stack Orthogonal Updates On the Computation of the Matrix k-th Root
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation b032cb0e-88f5-47f7-aace-44d36ff16c95 · outbound
Dion3: Full-Stack Orthogonal Updates NorMuon: Making Muon more efficient and scalable
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 9f3e6526-5cb5-4eef-b4bb-45b119134d92 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 33938041-27c7-4bc8-8498-928a9af941f4 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 6cf4a60e-2373-42b9-bf13-43f5dcd4626b · outbound
Dion3: Full-Stack Orthogonal Updates Pull Request #1428, NVIDIA/Megatron-LM
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 3f2dd4d1-38f9-474f-a477-b07f803e86cb · outbound
Dion3: Full-Stack Orthogonal Updates Muon is Scalable for LLM Training
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 966dae4d-2ed2-43d2-a1bc-9cb41b306d0e · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 45d465e0-b136-46c1-9edd-a6b51d574a85 · outbound
Dion3: Full-Stack Orthogonal Updates Trion: FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of LLMs
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 5acd166c-8285-46e9-9510-92b5a5a934d2 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 30
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 852f15eb-4b73-47fc-b6ae-fcb30b0d00c1 · outbound
Dion3: Full-Stack Orthogonal Updates gpt-oss-120b & gpt-oss-20b Model Card
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8d7dc421-313d-453a-a573-b0891ca11438 · outbound
Dion3: Full-Stack Orthogonal Updates Hierarchical Muon: Tiled Newton-Schulz Updates for Efficient Muon Optimization
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation dc207fcd-05b6-4d17-9d86-1dc8b4309016 · outbound
Dion3: Full-Stack Orthogonal Updates Transpose one of the MLP matrices + add Triton kernel for symmetric matmul
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation f008b20b-ff23-4b42-8bba-6148af51ad09 · outbound
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78ab6d13-f9f3-4813-be43-9a26ae618371 · outbound
Dion3: Full-Stack Orthogonal Updates PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation ed37af50-8204-4cbf-b5f9-a97a83ce7b4e · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 19b1dfd4-cfd3-4c2d-a6e8-fe88fae6286d · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation e244ebac-17cc-4b31-a068-db26b0c98ea8 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation a3d4cfe2-577d-4a47-b787-298ae14d90db · outbound
Dion3: Full-Stack Orthogonal Updates Fused GEMM + Add
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation c0ec1233-d25d-4743-98e2-c58047b033f7 · outbound
Dion3: Full-Stack Orthogonal Updates This is the size of the cluster used to train DeepSeek-V3, with upgraded hardware [9]
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 5907a4e7-d2da-4f08-a977-9e2bccf596be · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 41
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 4777f75e-9470-4719-b6a4-f3a595acc4a1 · outbound
Dion3: Full-Stack Orthogonal Updates The optimizer steps of pipeline stages2 to 16 are fully hidden behind the backwards of stages1 to 15
Reference 42
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 6d55a396-36f0-4fe1-9b00-393e771e7952 · outbound
Dion3: Full-Stack Orthogonal Updates Under these assumptions, the optimal way to partition the Newton-Schulz work of pipeline stage1 is as follows
Reference 43
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation ba735996-3d3b-432a-be55-c51c96947997 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 44
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 82e8d711-b021-4e16-a52e-acb826a1bf12 · outbound
Dion3: Full-Stack Orthogonal Updates Unresolved cited work
Reference 45
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 13d18c84-be12-4a74-92fc-1403be71c0ce · outbound
Dion3: Full-Stack Orthogonal Updates Each layer has3 MLP weights (up, gate, down), and the attention weights WQ, WK, WV, and WO
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
No inbound Pith citation observations are available.