Pith. sign in

Paper Citation Record · LEDGER

FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 15 inbound Pith citation observations for arXiv:2405.12807.

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

pith.paper-citation-record.v1
2405.12807 v11

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:15:01.106616Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T01:56:28.438782Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation f02ce2cb-a966-450d-ab87-7b6420d6c494 · inbound

High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR cites this paper.

High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-12T13:48:38.229216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T13:48:38.229216Z digest=sha256:e6c1d1d6fb2f76fd5d305c7687578e7a5052c8aa403ff1b41cb38b8f58d8882b

Observation 9ddb77ce-a62d-475a-a7f8-239610115fa8 · inbound

SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training cites this paper.

SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-11T13:28:28.812838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T13:28:28.812838Z digest=sha256:cbecff07ce24108aa8dd4dd76866e6debf63deb83a9483c8023bb5c0ff8ed6c9

Observation 7ef662b4-c5d4-45b4-a1ab-b4b5da50b20f · inbound

Fine-Tuning TransMorph with Gradient Correlation for Anatomical Alignment cites this paper.

Fine-Tuning TransMorph with Gradient Correlation for Anatomical Alignment FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-10T23:21:25.377770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:21:25.377770Z digest=sha256:71bbde577dcec43e0e3d80ab137fdfb0727277828d6312674b30ed769167b06f

Observation 05c1eb62-aff8-4045-afd3-fc7f1021728d · inbound

Grokking vs. Learning: Same Features, Different Encodings cites this paper.

Grokking vs. Learning: Same Features, Different Encodings FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.046167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.046167Z digest=sha256:55e95810ea89e48885da0850498b4a378e0c0e18f15c9852ed6b30aed91110a5

Observation 3f0ec22f-5055-46d2-a09d-78f7a9910efd · inbound

Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension cites this paper.

Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-08T11:46:47.479823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:46:47.479823Z digest=sha256:665466da9436ac61ba7622310920de9fa60ea23d70937cfaef0d54fcbc41c19c

Observation 64541f16-067b-484f-b057-2717d82b410f · inbound

Beyond the LUMIR challenge: The pathway to foundational registration models cites this paper.

Beyond the LUMIR challenge: The pathway to foundational registration models FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-07T12:39:09.533264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:39:09.533264Z digest=sha256:7786b536867e5a148fc8f58f90278eea34a25959025e15f30b85895ce0400d8e

Observation f914b36a-fff1-41dd-bc88-3abc5e3a10d2 · inbound

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks cites this paper.

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-06T20:55:06.577457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:55:06.577457Z digest=sha256:d3532ddc14e38f05a6b4bbdf35fe5d7effbda999eee8cee6ab421da2d1cdd35c

Observation e1bd8e33-7b19-4a56-87bf-08f518dbfdba · inbound

Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator cites this paper.

Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-15T18:15:01.106616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T18:15:01.106616Z digest=sha256:38671027af4c78610e3bf4443b1dc2780503458b1a4314e5ddf1c2f542e39b6c

Observation 7429b3d1-32a4-4e56-8d1c-ff82fb1e5e4c · inbound

Module-Aware Parameter-Efficient Machine Unlearning on Transformers cites this paper.

Module-Aware Parameter-Efficient Machine Unlearning on Transformers FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-05T17:06:10.224741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T17:06:10.224741Z digest=sha256:0a96b966238ac6f1b3c36694bc8ed00c7afc4a257496e820a692dfce3bd2fde5

Observation 6138ffe7-e906-4e24-bc8a-54398a9e5772 · inbound

Preconditioned Regularized Wasserstein Proximal Sampling cites this paper.

Preconditioned Regularized Wasserstein Proximal Sampling FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 22

Resolution
verified exact
arxiv_id, observed 2026-05-21T23:35:45.666978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-21T23:35:06.350853Z digest=sha256:efcbe37a006932de66fe83175762c0623873188c87a9685c212cca078f99f087

Observation 2071cd2f-8b67-4d2b-a567-7d87a2790957 · inbound

Natural Riemannian gradient for learning functional tensor networks cites this paper.

Natural Riemannian gradient for learning functional tensor networks FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:41:01.558783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-10T17:01:05.411513Z digest=sha256:5b464b4d5a1780f8593c46e8d310d5e9449c1ea1d059d02b2da7baa3c512d6bc

Observation 995d9d3b-d39f-4bd7-a8be-f42e5ad9a8d2 · inbound

Revealing Modular Gradient Noise Imbalance in LLMs: Calibrating Adam via Signal-to-Noise Ratio cites this paper.

Revealing Modular Gradient Noise Imbalance in LLMs: Calibrating Adam via Signal-to-Noise Ratio FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-05-11T16:41:05.142259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-09T15:39:51.611115Z digest=sha256:570f2df129041bb6ab8d6c4539f50ea4b5d22d5dcb83cf82d10ae87fdd91cf47

Observation ae50d6e5-d1ad-4217-a3b3-1a8a66856b7a · inbound

MAdam: Metric-Aware Multi-Objective Adam cites this paper.

MAdam: Metric-Aware Multi-Objective Adam FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 16

Resolution
verified exact
arxiv_id, observed 2026-07-02T01:56:28.441249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-28T11:21:53.393381Z digest=sha256:2ca9643d8c7bffb79eca691ab95d538b8479a872637011ee6b71dc64c41f283c

Observation a66805d2-b764-47fe-b70c-9439513a0923 · inbound

Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization cites this paper.

Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-01T22:36:56.240433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T22:36:56.240433Z digest=sha256:06e5ddea6b57ff916d551e9cb49433d68f99ba7bd014fbd4e5085681f3d65001

Observation f0398e5a-0657-47d8-a5cd-976affa008ae · inbound

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry cites this paper.

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-15T14:25:19.449857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T14:25:19.449857Z digest=sha256:a46dc5f4e26d6fabd7b1f744e48ca779f18835d8c9c8cbcfd889ec313e74709d