Paper Citation Record · LEDGER

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models

As of 18 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2412.19821.

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

pith.paper-citation-record.v1
2412.19821 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T15:07:15.153580Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:54:30.816676Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T10:54:31.239932Z

Reference resolution

35 of 35 outbound references displayed

verified exact1
verified fuzzy20
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3b3c2a16-66dc-49c1-8993-d70acc83da4c · outbound

This paper cites write newline.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.018824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18110881-5841-4a97-9512-d0edc7b816b2 · outbound

This paper cites A., Awan, A.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models A., Awan, A

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.996661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5e15c781-cb8e-4eb4-964f-e13e5fcc1945 · outbound

This paper cites Language Models are Few-Shot Learners.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Language Models are Few-Shot Learners

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.028073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3888b70-56c0-420a-b5fb-19dc4f01a8fe · outbound

This paper cites Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.986125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0d2701d2-b11e-4195-9589-79d87cd54c45 · outbound

This paper cites S., Naghshineh, S., Park, J., and Naumov, M.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models S., Naghshineh, S., Park, J., and Naumov, M

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.037771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ecb3caf-ef99-4dcf-a2d4-d0c303b6ae05 · outbound

This paper cites The Llama 3 Herd of Models.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.041392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d24d47c-722b-44da-9ed9-1064805b8ead · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.975476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4fb3f5b5-37d6-48a1-a59d-ee1331fa31a8 · outbound

This paper cites A framework for few-shot language model evaluation, 07 2024.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models A framework for few-shot language model evaluation, 07 2024

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.049136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3492629-1d75-429e-9f39-f19db6dfaa81 · outbound

This paper cites W., and Keutzer, K.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models W., and Keutzer, K

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.053141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f585db-1f74-42ae-84bd-3d472420d805 · outbound

This paper cites A., Welbl, J., Clark, A., et al.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models A., Welbl, J., Clark, A., et al

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.965139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8685261d-13d6-4220-97f3-1b40b9510a31 · outbound

This paper cites W., Shao, Y.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models W., Shao, Y

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.952934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e63849f1-c0bd-438e-9bfd-fc81cb5fd9dd · outbound

This paper cites Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.941905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cc0f5156-fd88-4a40-b77f-45834615bd29 · outbound

This paper cites B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.931082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f10b2a27-b317-4a1b-b3c4-38f632a27e9b · outbound

This paper cites J., Wang, X., Nassar, M., Bansal, A.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models J., Wang, X., Nassar, M., Bansal, A

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.920175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3f4e25aa-021c-4829-a9f1-0579f668bb34 · outbound

This paper cites B., Zi, Y., Muennighoff, N., Kocetkov, D., Mou, C., Marone, M., Akiki, C., Li, J., Chim, J., Liu, Q., Zheltonozhskii, E., Zhuo, T.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models B., Zi, Y., Muennighoff, N., Kocetkov, D., Mou, C., Marone, M., Akiki, C., Li, J., Chim, J., Liu, Q., Zheltonozhskii, E., Zhuo, T

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.910113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 60336d6a-f5f2-49a4-831f-23b32f20eda8 · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.899502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 04312f69-af70-4e42-8071-c64d58fa026c · outbound

This paper cites and Liu, R.-S.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models and Liu, R.-S

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.083427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f2469d-6d8d-455d-9035-6cf903d66ba0 · outbound

This paper cites Block and subword-scaling floating-point ( BSFP ) : An efficient non-uniform quantization for low precision inference.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Block and subword-scaling floating-point ( BSFP ) : An efficient non-uniform quantization for low precision inference

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.889084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fc762c23-1641-4367-a3a7-c482df4ed483 · outbound

This paper cites Lv: Latency-versatile floating-point engine for high-performance deep neural networks.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Lv: Latency-versatile floating-point engine for high-performance deep neural networks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.091124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f77f9c95-9e52-4f56-ae23-a0a84e321a76 · outbound

This paper cites P., Mallick, R., Wollaber, A.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models P., Mallick, R., Wollaber, A

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.095001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f06c684-8754-4bcf-9dc1-d2ad0376fb90 · outbound

This paper cites Intel Unleashes Enterprise AI with Gaudi 3, AI Open Systems Strategy and New Customer Wins.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Intel Unleashes Enterprise AI with Gaudi 3, AI Open Systems Strategy and New Customer Wins

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.877503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 04733370-e452-4e34-b4f8-c154b01b73a4 · outbound

This paper cites Pointer sentinel mixture models.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Pointer sentinel mixture models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.866101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1bc2d6b2-ceb3-4125-b0a0-1a38903ba942 · outbound

This paper cites Introducing Meta Llama 3: The most capable openly available LLM to date , 2024.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Introducing Meta Llama 3: The most capable openly available LLM to date , 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.853935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7762bdee-58fa-4694-9342-c45f48f5c7e6 · outbound

This paper cites NVIDIA Blackwell Architecture Technical Brief.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models NVIDIA Blackwell Architecture Technical Brief

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.841018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ed3168e4-ce56-4101-9dbc-99ee8b783333 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.114160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 267e194d-5e2d-44c1-983e-4718e1e8edb5 · outbound

This paper cites D., Garegrat, N., Savell, T., More, A., Han, K.-N., Zhao, R., Mathew Hall, J.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models D., Garegrat, N., Savell, T., More, A., Han, K.-N., Zhao, R., Mathew Hall, J

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.829095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b9296a21-9081-4672-a303-2d3d44187bd4 · outbound

This paper cites an unresolved cited work.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-11T15:07:15.817015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dbb0c251-fb08-465a-91bd-8e1a822fc2c4 · outbound

This paper cites Algorithm-Hardware Co-Design of Adaptive Floating-Point Encodings for Resilient Deep Learning Inference.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Algorithm-Hardware Co-Design of Adaptive Floating-Point Encodings for Resilient Deep Learning Inference

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.126442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9305df71-5818-458b-9765-1992dfc1b5f3 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.805672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8d275a21-5971-4ade-9133-e96d894178c3 · outbound

This paper cites an unresolved cited work.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T15:07:15.134083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4102f3b-1cb5-4f9c-9313-bd6091efc4e4 · outbound

This paper cites How to Quadruple LLM Decoding Performance with Speculative Decoding (SpD) and Microscaling (MX) Formats on Qualcomm Cloud AI 100.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models How to Quadruple LLM Decoding Performance with Speculative Decoding (SpD) and Microscaling (MX) Formats on Qualcomm Cloud AI 100

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.785722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5d11f7c8-5ac0-468f-9de7-7d5a79aee403 · outbound

This paper cites GPTVQ: The Blessing of Dimensionality for LLM Quantization.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models GPTVQ: The Blessing of Dimensionality for LLM Quantization

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.773784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c6b1e348-98b5-4756-9f79-2a42c40efa11 · outbound

This paper cites Sg-float: Achieving memory access and computing power reduction using self-gating float in cnns.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Sg-float: Achieving memory access and computing power reduction using self-gating float in cnns

Reference 33

Resolution: verified exact; doi, observed 2026-08-11T15:07:15.187085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 199b1854-cbdc-4e42-af08-0edffc97e204 · outbound

This paper cites an unresolved cited work.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-11T15:07:15.762496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 372c4e47-7429-4808-b478-5740c607a5a3 · outbound

This paper cites BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization.

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:07:15.752504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation fe303a0a-7967-48ef-bba0-6916b10b4dd8 · inbound

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference cites this paper.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-05T10:54:31.243463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.