Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-08T14:04:41.456059Z
Paper Citation Record · LEDGER
Normalized Architectures are Natively 4-Bit
As of 7 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 2 inbound Pith citation observations for arXiv:2605.06067.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T10:14:06.287259Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-04T20:30:07.713045Z
Reference resolution
17 of 17 outbound references displayed
- verified exact5
- verified fuzzy9
- unresolved1
- parse uncertain0
- malformed identifier1
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 5d1fe4f9-c63b-4969-92e9-1b9a33532821 · outbound
This paper cites URLhttps://huggingface.co/collections/ nvidia/nemotron-pre-training-datasets.
Normalized Architectures are Natively 4-Bit URLhttps://huggingface.co/collections/ nvidia/nemotron-pre-training-datasets
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.113684Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3e325710-cef4-4ffc-8c28-7bde8f9a5a02 · outbound
This paper cites URLhttps://resources.nvidia.com/ en-us-blackwell-architecture.
Normalized Architectures are Natively 4-Bit URLhttps://resources.nvidia.com/ en-us-blackwell-architecture
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.123604Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 967d8994-9803-4a8d-9134-bf628c7603cc · outbound
This paper cites Pretraining large language models with NVFP4.
Normalized Architectures are Natively 4-Bit Pretraining large language models with NVFP4
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T18:46:09.283764Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7c68c0d4-aef3-4196-86ad-b59eb7335eb9 · outbound
This paper cites Nemotron 3 nano: Open, efficient mixture-of- experts hybrid mamba-transformer model for agentic reasoning.
Normalized Architectures are Natively 4-Bit Nemotron 3 nano: Open, efficient mixture-of- experts hybrid mamba-transformer model for agentic reasoning
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T18:46:09.277274Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0314bab5-9c38-4d78-b56d-ed8f792133f2 · outbound
This paper cites Castro, Andrei Panferov, Soroush Tabesh, Oliver Sieberling, Jiale Chen, Mahdi Nikdan, Saleh Ashkboos, and Dan Alistarh.
Normalized Architectures are Natively 4-Bit Castro, Andrei Panferov, Soroush Tabesh, Oliver Sieberling, Jiale Chen, Mahdi Nikdan, Saleh Ashkboos, and Dan Alistarh
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.100922Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 21a5ade8-9ace-4a8d-9c6e-5e2cfc0e2143 · outbound
This paper cites Fp4 all the way: Fully quantized training of llms.
Normalized Architectures are Natively 4-Bit Fp4 all the way: Fully quantized training of llms
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.091401Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e38a84a5-3dad-4bec-905c-0de29ee5a02a · outbound
This paper cites Robust implicit regularization via weight normalization.Information and Inference: A Journal of the IMA, 13(3):iaae022.
Normalized Architectures are Natively 4-Bit Robust implicit regularization via weight normalization.Information and Inference: A Journal of the IMA, 13(3):iaae022
Reference 7
- Resolution
- verified exact
- doi, observed 2026-05-08T21:19:12.041551Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 80af715d-d82e-4c20-a1a1-ca0add8d0ef8 · outbound
This paper cites Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling.
Normalized Architectures are Natively 4-Bit Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T18:46:09.293385Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a77bac30-65fc-47dd-a798-654c39e28cac · outbound
This paper cites nanogpt.https://github.com/karpathy/nanoGPT.
Normalized Architectures are Natively 4-Bit nanogpt.https://github.com/karpathy/nanoGPT
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.120623Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1449fd11-4fcd-4a73-a019-414ce9e981f2 · outbound
This paper cites ngpt: Normalized trans- former with representation learning on the hypersphere.
Normalized Architectures are Natively 4-Bit ngpt: Normalized trans- former with representation learning on the hypersphere
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.097687Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5af9fb46-0987-49d6-9f53-5ce898c596f3 · outbound
This paper cites Ramaswamy.
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.094307Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation fa5ce5c8-89e5-4aa2-9977-8767439dabb5 · outbound
This paper cites an unresolved cited work.
Normalized Architectures are Natively 4-Bit Unresolved cited work
Reference 12
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T11:52:16.104121Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 64c76a18-bd3b-4a40-afe1-dae9f9e0d4fe · outbound
This paper cites Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation.
Normalized Architectures are Natively 4-Bit Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-06-02T03:04:37.455094Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f3c133d8-9c3e-4399-915e-8eb570a81e92 · outbound
This paper cites Rethinking language model scaling under transferable hypersphere optimization.
Normalized Architectures are Natively 4-Bit Rethinking language model scaling under transferable hypersphere optimization
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.117098Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8947eb1f-c81f-48ce-84db-7ab6fce40f38 · outbound
This paper cites Optimizing Large Language Model Training Using FP4 Quantization.
Normalized Architectures are Natively 4-Bit Optimizing Large Language Model Training Using FP4 Quantization
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T00:00:17.330307Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9293268c-7bf0-49d0-999e-7aa3732a940b · outbound
This paper cites MEMEM*EMEMEM.
Normalized Architectures are Natively 4-Bit MEMEM*EMEMEM
Reference 16
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-26T11:52:16.110593Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8c88987f-9db3-436c-b902-fdc680dfce11 · outbound
This paper cites MEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEMEM*EMEMEMEME.
Normalized Architectures are Natively 4-Bit MEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEMEM*EMEMEMEME
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T11:52:16.107471Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
Observation c1a4eaf6-4278-4192-8d62-cca8467235ac · inbound
Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors cites this paper.
Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors Normalized Architectures are Natively 4-Bit
Reference 183
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-04T20:30:07.714565Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4ea6b14f-06fe-4ddf-a507-5500ed9bac6b · inbound
Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors cites this paper.
Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors Normalized Architectures are Natively 4-Bit
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T10:14:06.287259Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.