Paper Citation Record · LEDGER

Backtracking Improves Generation Safety

As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 9 inbound Pith citation observations for arXiv:2409.14586.

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

pith.paper-citation-record.v1
2409.14586 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 9 of 9 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 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:57:56.116477Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T08:55:35.533570Z

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 15272f1c-e302-4d92-8a5b-8337b0449037 · inbound

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations cites this paper.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Backtracking Improves Generation Safety

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.745065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 034929b9-e38e-4cf8-a8d8-1adc5d51d3a2 · inbound

Deliberative Alignment: Reasoning Enables Safer Language Models cites this paper.

Deliberative Alignment: Reasoning Enables Safer Language Models Backtracking Improves Generation Safety

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T10:44:16.375088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94eb41f1-ff08-4f63-bbd7-722bd8b4172e · inbound

InfAlign: Inference-aware language model alignment cites this paper.

InfAlign: Inference-aware language model alignment Backtracking Improves Generation Safety

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-10T23:57:54.439796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a1754e-84ad-4dae-a433-87cf075a1006 · inbound

Disentangling Reasoning and Knowledge in Medical Large Language Models cites this paper.

Disentangling Reasoning and Knowledge in Medical Large Language Models Backtracking Improves Generation Safety

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T20:57:56.116477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a7b0b7-37ba-47da-9ea0-588d5c74fecd · inbound

Evaluating Language Model Reasoning about Confidential Information cites this paper.

Evaluating Language Model Reasoning about Confidential Information Backtracking Improves Generation Safety

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.546538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e3739b1-cbc2-4744-9184-7ec64aaa4ae8 · inbound

LLMs Should Express Uncertainty Explicitly cites this paper.

LLMs Should Express Uncertainty Explicitly Backtracking Improves Generation Safety

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:10:48.088037Z

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 b3eba9e4-6c53-4d57-b387-a711a42dc50f · inbound

LLMs Should Express Uncertainty Explicitly cites this paper.

LLMs Should Express Uncertainty Explicitly Backtracking Improves Generation Safety

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:15:11.846190Z

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 1b4c41f7-fdc2-4176-8dc5-c61747073f5a · inbound

Addressing Over-Refusal in LLMs with Competing Rewards cites this paper.

Addressing Over-Refusal in LLMs with Competing Rewards Backtracking Improves Generation Safety

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:55:35.535280Z

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 3c6167c6-8280-4ade-8adf-9ea50608b08a · inbound

Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs cites this paper.

Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs Backtracking Improves Generation Safety

Reference 33

Resolution: malformed identifier; no resolver link, observed 2026-08-01T14:53:38.598955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.