Paper Citation Record · LEDGER

JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates

As of 11 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2605.25469.

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

pith.paper-citation-record.v1
2605.25469 v1

Coverage vector

measured 4 of 4 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T22:53:39.926722Z

measured 4 of 4 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

4 of 4 outbound references displayed

verified exact0
verified fuzzy0
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 293c60bf-7875-485a-95be-bf17d08d3a73 · outbound

This paper cites PACT: Parameterized Clipping Activation for Quantized Neural Networks.

JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates PACT: Parameterized Clipping Activation for Quantized Neural Networks

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T22:54:00.677703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bb48a7fc-11c6-4098-9e74-65ce03e1795f · outbound

This paper cites DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients.

JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T22:54:00.681250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4830be8e-d92c-45e4-a83d-590f6d992fe3 · outbound

This paper cites Despite empirical success, most QAT methods inheritSTE’s bias, which ignores discrete bin geometry and can induce optimization mismatch at 2–4 bits.

JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates Despite empirical success, most QAT methods inheritSTE’s bias, which ignores discrete bin geometry and can induce optimization mismatch at 2–4 bits

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T22:53:39.926722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2ee221a-c316-4682-9d3a-7edfa48ebe94 · outbound

This paper cites an unresolved cited work.

JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates Unresolved cited work

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-06-29T22:53:39.926722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.