Paper Citation Record · LEDGER

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

As of 19 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 9 inbound Pith citation observations for arXiv:2504.18415.

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

pith.paper-citation-record.v1
2504.18415 v2

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:22:24.678188Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:17:11.582287Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

14 of 14 outbound references displayed

verified exact0
verified fuzzy2
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 108c28c9-e6fb-4f31-a8ab-44bac750f846 · outbound

This paper cites QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.626982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33563ad5-77f4-4ae8-933c-8bf5281a6570 · outbound

This paper cites Training-Free Activation Sparsity in Large Language Models.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs Training-Free Activation Sparsity in Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.639464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8058c0e-5fc9-449e-9e8a-6b85a3527fe5 · outbound

This paper cites SpinQuant: LLM quantization with learned rotations.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs SpinQuant: LLM quantization with learned rotations

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.643328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972fb160-2e12-4b63-9c42-f98fe86fa71b · outbound

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

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.647509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation affe8b47-8f10-4085-bbf1-b99980e89402 · outbound

This paper cites The LAMBADA dataset: Word prediction requiring a broad discourse context.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs The LAMBADA dataset: Word prediction requiring a broad discourse context

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:22:24.856551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5e923ef8-eefe-4dda-8628-ca8a88506a42 · outbound

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

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.663102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d02018fd-1d34-4afa-be93-6257a38471b6 · outbound

This paper cites Q-Sparse: All Large Language Models can be Fully Sparsely-Activated.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs Q-Sparse: All Large Language Models can be Fully Sparsely-Activated

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.670963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c17df173-f18c-4374-9d61-9fd0f61fdf30 · outbound

This paper cites Bitnet.cpp: Efficient Edge Inference for Ternary LLMs.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs Bitnet.cpp: Efficient Edge Inference for Ternary LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.674477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 268ad104-a2c4-4efe-85a5-adeb71eda6bc · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs PIQA: Reasoning about Physical Commonsense in Natural Language

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.634955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0984557-f6c0-487a-b0b4-9b89cce3be32 · outbound

This paper cites Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.655954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7b2376-8929-4ce7-80eb-dfc0b479bc4e · outbound

This paper cites All models have 1.58-bit weights and 8-bit activations.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs All models have 1.58-bit weights and 8-bit activations

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:22:24.844400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 83731ee4-5cb9-4992-a2e7-b920b155d3a9 · outbound

This paper cites GLU Variants Improve Transformer.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs GLU Variants Improve Transformer

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.659587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e38a581-f09f-47be-bacb-1d6efc00c591 · outbound

This paper cites BitNet a4.8: 4-bit Activations for 1-bit LLMs.

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs BitNet a4.8: 4-bit Activations for 1-bit LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.667215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb28b42-5c93-42a2-89a1-12f64c4672fa · outbound

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

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T10:22:24.631231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5678a4a2-2ee3-49dd-8166-22031c443bac · inbound

Get Experience from Practice: LLM Agents with Record & Replay cites this paper.

Get Experience from Practice: LLM Agents with Record & Replay BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:29.723829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50e1376b-fe23-4b48-b5f8-6a7a9f9b03e5 · inbound

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache cites this paper.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:22.378319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 945b6c6f-c070-4bbf-a661-0c4de652805b · inbound

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization cites this paper.

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-22T13:14:53.399771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a69e8672-a83f-4a76-a92c-d1521e6afb45 · inbound

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation cites this paper.

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 91

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:46:04.939619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2a3dea04-8080-41c6-94ff-25b96a1e7f70 · inbound

UniSVQ: 2-bit Unified Scalar-Vector Quantization cites this paper.

UniSVQ: 2-bit Unified Scalar-Vector Quantization BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-06-27T13:40:57.350237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c9a3316f-369f-4e4b-86d6-92385bb88c7a · inbound

UniSVQ: 2-bit Unified Scalar-Vector Quantization cites this paper.

UniSVQ: 2-bit Unified Scalar-Vector Quantization BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:57:25.445456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 99a44317-8b15-4c8d-a0e3-82096549ec41 · inbound

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization cites this paper.

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T13:48:20.611359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 55d2d64f-ff92-4415-bd68-72975c61e5b5 · inbound

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs cites this paper.

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:19:50.572601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 06f49d2c-1f83-443f-9507-f7cf92b85e91 · inbound

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization cites this paper.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.582287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.