Paper Citation Record · LEDGER

The Quantization Benefits of Residual-Free Transformers

As of 15 August 2026, this Paper Citation Record lists 9 of 9 outbound references and 2 inbound Pith citation observations for arXiv:2605.25880.

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

pith.paper-citation-record.v1
2605.25880 v1

Coverage vector

measured 9 of 9 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T22:52:26.612229Z

measured 11 of 11 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-30T23:38:38.639450Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

9 of 9 outbound references displayed

verified exact0
verified fuzzy0
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation e5ca9300-4218-4179-8b85-23d1d6f0fb48 · outbound

This paper cites Then each coordinate of xℓ+1 has same mean and variance as ϕ(norm(xℓ)), and its excess kurtosis γℓ+1 satisfies |γℓ+1| ≤ µℓ d |˜γℓ|.

The Quantization Benefits of Residual-Free Transformers Then each coordinate of xℓ+1 has same mean and variance as ϕ(norm(xℓ)), and its excess kurtosis γℓ+1 satisfies |γℓ+1| ≤ µℓ d |˜γℓ|

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fe5b48d-5154-47cd-9c46-8b0881275bab · outbound

This paper cites an unresolved cited work.

The Quantization Benefits of Residual-Free Transformers Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d6bca69-225b-44d0-9240-c109fbcb14fa · outbound

This paper cites Hence the excess kurtosis of a softmax coordinate is controlled only when the logits remain in a non-peaky regime.

The Quantization Benefits of Residual-Free Transformers Hence the excess kurtosis of a softmax coordinate is controlled only when the logits remain in a non-peaky regime

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d62b5584-a42f-4c8c-97e5-90b2a1d33150 · outbound

This paper cites an unresolved cited work.

The Quantization Benefits of Residual-Free Transformers Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0543442-d3e6-47c4-8513-60f70c1ec7ce · outbound

This paper cites 26 Either ingredient alone is insufficient.

The Quantization Benefits of Residual-Free Transformers 26 Either ingredient alone is insufficient

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0acd2cf-8fcd-4820-bcea-c0d51c102e99 · outbound

This paper cites This creates a self-correcting fourth-moment mechanism toward Gaussian-like activations.

The Quantization Benefits of Residual-Free Transformers This creates a self-correcting fourth-moment mechanism toward Gaussian-like activations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc8f620d-42bc-4848-a32c-13d08c174966 · outbound

This paper cites Even if the branch output were itself close to Gaussian, the sum need not become more Gaussian because the old hidden state is preserved rather than replaced.

The Quantization Benefits of Residual-Free Transformers Even if the branch output were itself close to Gaussian, the sum need not become more Gaussian because the old hidden state is preserved rather than replaced

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c246112f-ddcb-4d6f-961e-d347f0541d83 · outbound

This paper cites an unresolved cited work.

The Quantization Benefits of Residual-Free Transformers Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d1d1ff-4598-45de-b719-fa1b1d781348 · outbound

This paper cites It both promotes dense norm-preserving mixing at initialization and tends to preserve it during training.

The Quantization Benefits of Residual-Free Transformers It both promotes dense norm-preserving mixing at initialization and tends to preserve it during training

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T22:52:26.612229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7839919a-8b8a-49d0-ad14-b4a85105870e · inbound

When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation cites this paper.

When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation The Quantization Benefits of Residual-Free Transformers

Reference 102

Resolution: unresolved; no resolver link, observed 2026-07-30T23:38:38.489667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4b6fdcb-1c18-48d6-b3cf-563947f63e98 · inbound

When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation cites this paper.

When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation The Quantization Benefits of Residual-Free Transformers

Reference 154

Resolution: verified exact; local_arxiv, observed 2026-07-30T23:40:59.181246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.