Paper Citation Record · LEDGER

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models

As of 21 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2607.02893.

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

pith.paper-citation-record.v1
2607.02893 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-12T06:20:07.112455Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

39 of 39 outbound references displayed

verified exact0
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9c430808-cf45-4e16-8007-892318372983 · outbound

This paper cites Introducing apple’s on-device and server foundation models.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Introducing apple’s on-device and server foundation models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e085793-e60d-4b85-8ee5-cebd0e1123dc · outbound

This paper cites an unresolved cited work.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abb8d770-be34-4ed0-a0c8-61a31fe30368 · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 949dd14f-7af8-4634-8afc-ee5d7a3cb541 · outbound

This paper cites Rethinking differentiable search for mixed-precision neural networks.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Rethinking differentiable search for mixed-precision neural networks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9d03994-6431-4cee-842a-b956f5d8db66 · outbound

This paper cites Scaling Laws For Mixed Quantization.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Scaling Laws For Mixed Quantization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 801f5d72-5310-41b7-b251-867a73c40618 · outbound

This paper cites GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af44db72-7cb6-4a08-a63b-4177888d8a42 · outbound

This paper cites The case for 4-bit precision: k-bit inference scaling laws.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models The case for 4-bit precision: k-bit inference scaling laws

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e728a3a-de8d-4aca-b012-00ae616d276d · outbound

This paper cites LLM.int8(): 8-bit matrix multiplication for transformers at scale.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models LLM.int8(): 8-bit matrix multiplication for transformers at scale

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8558b211-2862-4c5c-973d-8ae8e7e7faae · outbound

This paper cites Mahoney, and Kurt Keutzer.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Mahoney, and Kurt Keutzer

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d004b53-0b49-480b-ab1b-681f1022046d · outbound

This paper cites Accuracy is Not All You Need.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Accuracy is Not All You Need

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e288edd0-1a2f-4c34-8485-0b42eabb054b · outbound

This paper cites Extreme compression of large language models via additive quantization.International Conference on Machine Learning (ICML), 2024.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Extreme compression of large language models via additive quantization.International Conference on Machine Learning (ICML), 2024

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaf3d5c4-31e7-4dfe-ad78-39b92fa53efc · outbound

This paper cites TinyStories: How Small Can Language Models Be and Still Speak Coherent English?.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models TinyStories: How Small Can Language Models Be and Still Speak Coherent English?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f96a24be-7752-4512-886e-858bc8952ebf · outbound

This paper cites dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a262b0-6465-4ab1-be80-6e39b3155bd0 · outbound

This paper cites GPTQ: Accurate post-training quantization for generative pre-trained transformers.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models GPTQ: Accurate post-training quantization for generative pre-trained transformers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fa2381c-37b7-4ac1-af0d-4609dbd2a7a5 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Distilling the Knowledge in a Neural Network

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 269cae30-78e8-46b2-963d-9db092a59491 · outbound

This paper cites SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad9a1d15-c8f4-41b3-9258-40ccfbe98fbf · outbound

This paper cites Categorical reparameterization with Gumbel-Softmax.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Categorical reparameterization with Gumbel-Softmax

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 992beea6-92ca-4667-9ac0-11d039a87158 · outbound

This paper cites Spector, Blake Bordelon, Niklas Muennighoff, Mansheej Paul, Cengiz Pehlevan, Christopher Ré, and Aditi Raghunathan.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Spector, Blake Bordelon, Niklas Muennighoff, Mansheej Paul, Cengiz Pehlevan, Christopher Ré, and Aditi Raghunathan

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b2591f5-5c86-4cd8-af98-aafadbeb9c20 · outbound

This paper cites AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06c75d7d-8003-4f87-83b2-2d7f07095458 · outbound

This paper cites DARTS: Differentiable architecture search.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models DARTS: Differentiable architecture search

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f14718cf-a609-4c94-8c2b-6104313d3f42 · outbound

This paper cites ParetoQ: Improving scaling laws in extremely low-bit LLM quantization.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models ParetoQ: Improving scaling laws in extremely low-bit LLM quantization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0b92520-541d-4826-998f-2acfe0ed7675 · outbound

This paper cites The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5af0ec40-ac71-4445-aeca-0d80212e9a20 · outbound

This paper cites Maddison, Andriy Mnih, and Yee Whye Teh.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Maddison, Andriy Mnih, and Yee Whye Teh

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64b1651d-ea0f-4cd4-8300-a369da0b205f · outbound

This paper cites Introducing NVFP4 for efficient and accurate low-precision in- ference.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Introducing NVFP4 for efficient and accurate low-precision in- ference

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83e12407-03ff-47af-aee0-6e8fa9066c6a · outbound

This paper cites Pretraining large language models with NVFP4.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Pretraining large language models with NVFP4

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14d41e4d-5a88-4599-ac44-8f14fefca371 · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e19aea9f-d1c4-4e83-8a55-720c0c0930b5 · outbound

This paper cites Bonsai: 1-bit and ternary (1.58-bit) language models for on-device inference.https: //prismml.com/news/ternary-bonsai, 2026.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Bonsai: 1-bit and ternary (1.58-bit) language models for on-device inference.https: //prismml.com/news/ternary-bonsai, 2026

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afe9501a-4b5c-41c2-8cf1-c9eafe0cc659 · outbound

This paper cites Qwen3 Technical Report.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Qwen3 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 868adaf7-cb4b-41de-9257-d11f7009c54c · outbound

This paper cites Language models are unsupervised multitask learners.OpenAI Technical Report, 2019.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Language models are unsupervised multitask learners.OpenAI Technical Report, 2019

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 981a02bd-6b5d-4975-aadb-7255857c6682 · outbound

This paper cites Neural hashing: The future of search.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Neural hashing: The future of search

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e283b8ec-65f9-449b-b47d-b87b96e48e7c · outbound

This paper cites GLU Variants Improve Transformer.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models GLU Variants Improve Transformer

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a24a10cb-9ae6-49a7-849f-b5162bde7830 · outbound

This paper cites RoFormer: Enhanced transformer with rotary position embedding.Neurocomputing, 568, 2024.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models RoFormer: Enhanced transformer with rotary position embedding.Neurocomputing, 568, 2024

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc47bd7f-209c-4fdb-872c-96e49ec5373e · outbound

This paper cites QuIP#: Even better LLM quantization with hadamard incoherence and lattice codebooks.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models QuIP#: Even better LLM quantization with hadamard incoherence and lattice codebooks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 366a9eea-fd33-4558-9870-fb271f324b47 · outbound

This paper cites Unsloth dynamic GGUF quants.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Unsloth dynamic GGUF quants

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a938dd76-9e7a-4734-8305-a0b0382df0da · outbound

This paper cites BitNet: Scaling 1-bit Transformers for Large Language Models.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfb8442f-00c8-45aa-9e58-f01af8a88415 · outbound

This paper cites HAQ: Hardware-aware automated quantization with mixed precision.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models HAQ: Hardware-aware automated quantization with mixed precision

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6848eb2-332b-4dc4-ad76-1a9d9bd7444b · outbound

This paper cites Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd88fe1c-a4f4-46c8-8f7e-f1268e9fd667 · outbound

This paper cites SmoothQuant: Accurate and efficient post-training quantization for large language models.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models SmoothQuant: Accurate and efficient post-training quantization for large language models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58e27d8e-bafb-43ad-9522-5e1bd0616350 · outbound

This paper cites MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design.

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-12T06:20:07.112455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.