Paper Citation Record · LEDGER

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models

As of 17 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2505.23848.

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

pith.paper-citation-record.v1
2505.23848 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:03:47.041540Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

14 of 14 outbound references displayed

verified exact1
verified fuzzy3
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e0ddc226-decf-4f84-ba19-0708e4af53c3 · outbound

This paper cites write newline.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:45.980612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c39aefa8-d924-4707-8109-808146d524b4 · outbound

This paper cites an unresolved cited work.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:48.398558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c3ea496a-5d97-4c03-abf6-9e4b01f4d6d3 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Refusal in Language Models Is Mediated by a Single Direction

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:46.199051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d2fa7d-8e81-4141-8722-ba0624a7a5d3 · outbound

This paper cites F., Choquette-Choo, C.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models F., Choquette-Choo, C

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:46.283063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db73d0d4-39be-4e70-bdfb-1c46b48afac5 · outbound

This paper cites Deepseek-r1 technical report.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Deepseek-r1 technical report

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:48.276316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ee66c62b-36a4-476d-8a76-c3032a5e2c42 · outbound

This paper cites Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:46.414487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f90695a-20cc-4d63-a1e6-f203562b49a1 · outbound

This paper cites s1: Simple test-time scaling.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models s1: Simple test-time scaling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:46.504667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeb1ba44-158f-4dd8-9a2b-48555e675a92 · outbound

This paper cites R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:46.603474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e4b8aaf-a78b-4ca9-b52b-dce9da988cb2 · outbound

This paper cites Using logit bias to alter token probability.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Using logit bias to alter token probability

Reference 9

Resolution: verified exact; raw_fallback, observed 2026-08-07T13:03:47.498322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c916b80e-3370-448d-8ca6-18a8d4ba30a7 · outbound

This paper cites Ccp-sensitive-prompts.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Ccp-sensitive-prompts

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:48.174607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 35a1f9f0-aae3-4f87-8542-5bfd1fd1e306 · outbound

This paper cites Qwq: Reflect deeply on the boundaries of the unknown, November 2024.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Qwq: Reflect deeply on the boundaries of the unknown, November 2024

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:48.052222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 65f3e038-b85a-4f19-bad6-adc47acf9889 · outbound

This paper cites Iteratively Prompt Pre-trained Language Models for Chain of Thought.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Iteratively Prompt Pre-trained Language Models for Chain of Thought

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:46.877533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54febf91-7b01-4851-9e92-e1ec99fa8183 · outbound

This paper cites L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:46.949139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c766c2b2-dd79-47a3-938f-a8d48cf70a05 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:47.041540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.