Paper Citation Record · LEDGER

First-order Methods Almost Always Avoid Saddle Points

As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:1710.07406.

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

pith.paper-citation-record.v1
1710.07406 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 5 of 5 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:43:39.672597Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-14T10:36:30.762220Z

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 50aaf26f-96d6-42ba-a530-eb26bbd29da0 · inbound

Extending the step-size restriction for gradient descent to avoid strict saddle points cites this paper.

Extending the step-size restriction for gradient descent to avoid strict saddle points First-order Methods Almost Always Avoid Saddle Points

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-14T15:14:53.411614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27484ef9-3f47-4fb7-8b89-b2a93a6833dc · inbound

Distributed Stochastic Gradient Method for Non-Convex Problems with Applications in Supervised Learning cites this paper.

Distributed Stochastic Gradient Method for Non-Convex Problems with Applications in Supervised Learning First-order Methods Almost Always Avoid Saddle Points

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-14T12:47:24.833526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207f2e1d-7f74-4a91-b4c6-7071eda18cd5 · inbound

Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective cites this paper.

Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective First-order Methods Almost Always Avoid Saddle Points

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-14T10:36:30.766648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 24952eca-8571-4f68-ba10-c84e72b6ed57 · inbound

Learning based convex approximation for constrained parametric optimization cites this paper.

Learning based convex approximation for constrained parametric optimization First-order Methods Almost Always Avoid Saddle Points

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T23:43:39.672597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aff3332f-ccb3-49cc-ad0a-c49c1bf8b27d · inbound

Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting cites this paper.

Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting First-order Methods Almost Always Avoid Saddle Points

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:26:51.797163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.