Paper Citation Record · LEDGER

Distributionally Robust Token Optimization in RLHF

As of 15 August 2026, this Paper Citation Record lists 3 of 3 outbound references and 0 inbound Pith citation observations for arXiv:2604.08577.

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

pith.paper-citation-record.v1
2604.08577 v2

Coverage vector

measured 3 of 3 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-14T23:19:47.586351Z

measured 3 of 3 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

3 of 3 outbound references displayed

verified exact1
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fdb5ed4b-ee3e-45cb-ad40-d7363ff7f1aa · outbound

This paper cites GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis.

Distributionally Robust Token Optimization in RLHF GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:23:16.015683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d6121785-68b6-4bd6-aa4c-7ce02724b596 · outbound

This paper cites n}and let u= (u 1.

Distributionally Robust Token Optimization in RLHF n}and let u= (u 1

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T23:23:16.733865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0314a953-b00d-4161-9372-3542c66bdc2d · outbound

This paper cites Finally, EQ⋆[Li(θ)] = ¯L(θ) +E PB[(w⋆ −1)z i(θ)] = ¯L(θ) + √ρ EPB[zi(θ)2] σ(θ) = ¯L(θ) +σ(θ) √ρ, which matches the upper bound and proves tightness.

Distributionally Robust Token Optimization in RLHF Finally, EQ⋆[Li(θ)] = ¯L(θ) +E PB[(w⋆ −1)z i(θ)] = ¯L(θ) + √ρ EPB[zi(θ)2] σ(θ) = ¯L(θ) +σ(θ) √ρ, which matches the upper bound and proves tightness

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T23:23:16.738535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.