Paper Citation Record · LEDGER

Singular Bayesian Neural Networks

As of 11 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2602.00387.

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

pith.paper-citation-record.v1
2602.00387 v4

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T06:09:36.403226Z

measured 29 of 29 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:09:20.996255Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ee17cf46-ae48-4e4e-9312-a45e964fa611 · outbound

This paper cites This depends on optimization quality and can be reduced with better training procedures.

Singular Bayesian Neural Networks This depends on optimization quality and can be reduced with better training procedures

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:33.541907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17ba7a08-f7e6-4225-acbf-830e1a626a2e · outbound

This paper cites ln QD i=1 qi(θi) QD i=1 pi(θi) # =E θ∼Q.

Singular Bayesian Neural Networks ln QD i=1 qi(θi) QD i=1 pi(θi) # =E θ∼Q

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:33.666588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e5ddbe4-93d7-4879-a9db-fd1ac6e90723 · outbound

This paper cites an unresolved cited work.

Singular Bayesian Neural Networks Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:33.960629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 587d740b-1b08-4a43-a8a7-0a1a6676466b · outbound

This paper cites original class).

Singular Bayesian Neural Networks original class)

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:33.780351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbe152c0-5c45-4b25-9413-0e9ff5c716e7 · outbound

This paper cites an unresolved cited work.

Singular Bayesian Neural Networks Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:33.886356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea7e879-725d-420e-b34a-8e01e878457d · outbound

This paper cites an unresolved cited work.

Singular Bayesian Neural Networks Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.036326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca1229fa-7843-463e-8163-0f0d1c52a55f · outbound

This paper cites We cite it in this combined form to avoid re-deriving technical constants.

Singular Bayesian Neural Networks We cite it in this combined form to avoid re-deriving technical constants

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.110142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c14694b0-61ca-43e0-aeb5-265e3b90631a · outbound

This paper cites 3.Depth dependence: The product QD i=j+1 C0Ci shows how spectral norms accumulate through the network depth.

Singular Bayesian Neural Networks 3.Depth dependence: The product QD i=j+1 C0Ci shows how spectral norms accumulate through the network depth

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.229274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dc2c5ec-da0f-403d-bed3-ccc1a6b784c4 · outbound

This paper cites This is an artifact of the layer-peeling proof technique (specifically, how the chaining argument handles the input layer), not a reflection of a missing rank constraint.

Singular Bayesian Neural Networks This is an artifact of the layer-peeling proof technique (specifically, how the chaining argument handles the input layer), not a reflection of a missing rank constraint

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.356028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0095ca9a-ac89-4bcb-ae5c-b549a005f04a · outbound

This paper cites In the extreme case of a near-deterministic posterior, the PAC-Bayes gap approaches zero while the Gaussian complexity bound remains fixed by the class geometry.

Singular Bayesian Neural Networks In the extreme case of a near-deterministic posterior, the PAC-Bayes gap approaches zero while the Gaussian complexity bound remains fixed by the class geometry

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.414493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb4e5776-09b4-46be-8752-99f9711f7231 · outbound

This paper cites The Gaussian complexity bound’s leading term grows linearly in∥X∥ F.

Singular Bayesian Neural Networks The Gaussian complexity bound’s leading term grows linearly in∥X∥ F

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.494297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 505d7101-7d3c-4cf3-8e6d-b63d5e8df1b6 · outbound

This paper cites When din ≫d out and C 2 0 C 4 1 R2 is large, PAC-Bayes can still be favorable despite thedin term, because it avoids the spectral norm constants entirely.

Singular Bayesian Neural Networks When din ≫d out and C 2 0 C 4 1 R2 is large, PAC-Bayes can still be favorable despite thedin term, because it avoids the spectral norm constants entirely

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.606589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1068b379-e040-494d-8365-3060e6fbf82b · outbound

This paper cites an unresolved cited work.

Singular Bayesian Neural Networks Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.721361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87af22f4-34bf-432f-9eca-a78d31fa2903 · outbound

This paper cites This is the regime where the Gaussian complexity bound is numerically tighter.

Singular Bayesian Neural Networks This is the regime where the Gaussian complexity bound is numerically tighter

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.815773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba0b94f-d768-4d4c-9351-636af53aed25 · outbound

This paper cites This makes them valuable as aprior-free sanity check.

Singular Bayesian Neural Networks This makes them valuable as aprior-free sanity check

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:34.924325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b5e6743-89ff-44b2-b2e8-30f6d473be88 · outbound

This paper cites good event.

Singular Bayesian Neural Networks good event

Reference 17

Resolution: malformed identifier; no resolver link, observed 2026-08-03T06:09:35.004978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d7e5f19-3e32-4da6-b584-a5645ae8400b · outbound

This paper cites In reparameterized variational inference, the same clipping can be applied to sampled factors.

Singular Bayesian Neural Networks In reparameterized variational inference, the same clipping can be applied to sampled factors

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:35.119495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f36a822-d35f-437e-b407-e083025fb937 · outbound

This paper cites For example, a truncated Gaussian with support {A:∥A∥ 2 ≤C A} naturally satisfies the assumption.

Singular Bayesian Neural Networks For example, a truncated Gaussian with support {A:∥A∥ 2 ≤C A} naturally satisfies the assumption

Reference 19

Resolution: malformed identifier; no resolver link, observed 2026-08-03T06:09:35.236625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 405a35b1-3efd-448b-9356-c48c0101e5c2 · outbound

This paper cites Biases are either stochastic Gaussians or deterministic (both tested); we report the deterministic-bias variant for parameter efficiency.

Singular Bayesian Neural Networks Biases are either stochastic Gaussians or deterministic (both tested); we report the deterministic-bias variant for parameter efficiency

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:35.311756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a13b4b99-de54-4386-a882-0d2514d2a771 · outbound

This paper cites Each entry of A and B has a diagonal Gaussian posterior: q(Aik) =N(µ A ik,(σ A ik)2) and similarly for B.

Singular Bayesian Neural Networks Each entry of A and B has a diagonal Gaussian posterior: q(Aik) =N(µ A ik,(σ A ik)2) and similarly for B

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:35.398014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12221045-023b-4fc9-b293-1fa07b9cb3af · outbound

This paper cites an unresolved cited work.

Singular Bayesian Neural Networks Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:35.470903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce392c85-93ea-44fe-8f3d-684090a1e6a4 · outbound

This paper cites This prior encourages sparsity by placing probability mass on both a standard Gaussian and a narrow Gaussian; it is identical across all four models to ensure fair comparison.

Singular Bayesian Neural Networks This prior encourages sparsity by placing probability mass on both a standard Gaussian and a narrow Gaussian; it is identical across all four models to ensure fair comparison

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:35.625339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdb79893-7870-41ee-887c-eb6b763d8144 · outbound

This paper cites Prior: mixturep(w) = 0.5N(0,2.0 2) + 0.5N(0, e−6).

Singular Bayesian Neural Networks Prior: mixturep(w) = 0.5N(0,2.0 2) + 0.5N(0, e−6)

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:35.768072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80e04a66-d74b-4fef-b955-2c0805e01d6e · outbound

This paper cites Input (1→100 ) and output (100→1 ) layers remain full-rank.

Singular Bayesian Neural Networks Input (1→100 ) and output (100→1 ) layers remain full-rank

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:35.946967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ba2113-7604-44d0-8552-9271546e643f · outbound

This paper cites This is a desirable property for safe prediction.

Singular Bayesian Neural Networks This is a desirable property for safe prediction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:36.072221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b579a411-eb80-499b-924e-28bf83b6c99a · outbound

This paper cites This shows low-rank preserves the qualitative epistemic sensitivity: uncertainty grows when leaving the training domain.

Singular Bayesian Neural Networks This shows low-rank preserves the qualitative epistemic sensitivity: uncertainty grows when leaving the training domain

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:36.280769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74857da9-2a36-47b0-8509-42fb5e9189ea · outbound

This paper cites Rather than under-confident (overfitting) predictions, the low-rank posterior spreads mass more broadly, yielding conservative predictions even in-domain.

Singular Bayesian Neural Networks Rather than under-confident (overfitting) predictions, the low-rank posterior spreads mass more broadly, yielding conservative predictions even in-domain

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:36.403226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7558ad22-e299-4a74-a342-e4de1a827ccc · outbound

This paper cites Pathologies in priors and inference for Bayesian transformers.

Singular Bayesian Neural Networks Pathologies in priors and inference for Bayesian transformers

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-03T06:09:33.403710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 89eaa672-0f80-4c90-a40e-39a0381e415e · inbound

Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions cites this paper.

Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions Singular Bayesian Neural Networks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T21:09:20.996255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.