Paper Citation Record · LEDGER

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs

As of 4 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2607.04371.

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

pith.paper-citation-record.v1
2607.04371 v2

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T19:41:48.225019Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+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

12 of 12 outbound references displayed

verified exact1
verified fuzzy0
unresolved10
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 481f871b-300d-4b8d-b7dd-58aa949534f8 · outbound

This paper cites SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9445dc3-3ed0-4734-af37-6118be652910 · outbound

This paper cites Venmugil Elango, Nidhi Bhatia, Roger Waleffe, Rasoul Shafipour, Tomer Asida, Abhinav Khattar, Nave Assaf, Maximilian Golub, Joey Guman, Tiyasa Mitra, et al.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Venmugil Elango, Nidhi Bhatia, Roger Waleffe, Rasoul Shafipour, Tomer Asida, Abhinav Khattar, Nave Assaf, Maximilian Golub, Joey Guman, Tiyasa Mitra, et al

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c1feb8a-e9cf-41d4-88fa-e0d554fcd4a7 · outbound

This paper cites Yaniv Leviathan, Matan Kalman, and Yossi Matias.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Yaniv Leviathan, Matan Kalman, and Yossi Matias

Reference 3

Resolution: verified exact; doi, observed 2026-07-11T19:48:13.157049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b4c6027c-a690-466f-8a28-fdc5b9ba75e1 · outbound

This paper cites Compact Language Models via Pruning and Knowledge Distillation.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Compact Language Models via Pruning and Knowledge Distillation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34c2917f-6c0a-4939-a47e-53946387a420 · outbound

This paper cites org/CorpusID:271328221.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs org/CorpusID:271328221

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05212816-e4fc-40cd-819c-7773a08d16cd · outbound

This paper cites URL https://doi.org/10.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs URL https://doi.org/10

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe49c38d-1044-44ea-94c9-9c1697f51c5f · outbound

This paper cites Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 052a5d1a-d075-4b19-927d-2ba205bc81ed · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75c94ad7-f8fb-4c72-932e-a3b685627ad8 · outbound

This paper cites Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69f43dcf-873f-48ff-bbd2-d6eed2f11802 · outbound

This paper cites 17 Appendix A Mamba SSM Pruning A.1 Method We chose which SSM channels to prune by estimating their contribution to the Mamba layer output in the following manner.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs 17 Appendix A Mamba SSM Pruning A.1 Method We chose which SSM channels to prune by estimating their contribution to the Mamba layer output in the following manner

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b264ea6-46b9-4a6d-964f-1577307d0d34 · outbound

This paper cites Per-request prefill of the 990K-token prompt is roughly1.2×faster on Super Turbo than on Super.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Per-request prefill of the 990K-token prompt is roughly1.2×faster on Super Turbo than on Super

Reference 11

Resolution: malformed identifier; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 319c2fb7-d39b-4070-beca-7544883b3811 · outbound

This paper cites The projection-based method outperforms the coordinate-selection baselines at each tested latent size.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs The projection-based method outperforms the coordinate-selection baselines at each tested latent size

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.