Pith. sign in

Paper Citation Record · LEDGER

HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization

As of 9 August 2026, this Paper Citation Record lists 2 of 2 outbound references and 2 inbound Pith citation observations for arXiv:2605.29843.

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

pith.paper-citation-record.v1
2605.29843 v1

Coverage vector

measured 2 of 2 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T09:16:37.939055Z

measured 4 of 4 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T14:26:41.243535Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T01:46:26.837879Z

Reference resolution

2 of 2 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved1
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bc8f316e-7897-4f4a-ada1-14ead50af142 · outbound

This paper cites Extreme Compression of Large Language Models via Additive Quantization.

HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization Extreme Compression of Large Language Models via Additive Quantization

Reference 1

Resolution
malformed identifier
arxiv_id, observed 2026-06-29T13:53:29.657669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-06-29T09:16:37.939055Z digest=sha256:23af81f551cc3af2f91b4e0e3795f4d46eba310f9bd7c09ee7ad32caa29c3a29

Observation 88890f86-39ca-47c4-9ca7-029760adfa94 · outbound

This paper cites Table 12: Fine-tuning compatibility on Llama 2 7B, 2-bit, context length4096.

HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization Table 12: Fine-tuning compatibility on Llama 2 7B, 2-bit, context length4096

Reference 2

Resolution
unresolved
no resolver link, observed 2026-06-29T09:16:37.939055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T09:16:37.939055Z digest=sha256:ee982940c4facf908268e364bdaad876f7b5f0a968cef9cc1977b4c917bdf5e8

Pith citing papers

Observation 8ec5af71-faf7-4405-a299-9737ac701e8e · inbound

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery cites this paper.

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization

Reference 37

Resolution
verified exact
local_arxiv, observed 2026-07-01T23:26:21.830228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-06-28T14:26:41.243535Z digest=sha256:5c180c78c966d9803c8ff8d027dad2a6e91ae2e36ee3e236ac07210b63d92351

Observation 1cd7d7cf-0a94-4bbc-9f35-1514cd1e0c6e · inbound

Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression cites this paper.

Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization

Reference 52

Resolution
malformed identifier
local_arxiv, observed 2026-07-02T01:46:26.839835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-06-28T11:31:25.851340Z digest=sha256:170c3aad1b341dbef762ce6437158ffeb9612198078a50bb84bb88e8d1383865