Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T23:21:34.209768Z
Paper Citation Record · LEDGER
No Training Wheels: Steering Vectors for Bias Correction at Inference Time
As of 8 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2506.18598.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
18 of 18 outbound references displayed
- verified exact0
- verified fuzzy3
- unresolved15
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 6bb22b6f-f293-480d-ad29-ea262464c857 · outbound
This paper cites write newline.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time write newline
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:31.526768Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 750da7db-c23a-4cc0-a153-d6dec16b6cb6 · outbound
This paper cites Refusal in Language Models Is Mediated by a Single Direction.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Refusal in Language Models Is Mediated by a Single Direction
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:31.594561Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f6be58ab-47f8-4018-852f-6e24d53b5972 · outbound
This paper cites Diff-in-means concept editing is worst-case optimal: Explaining a result by Sam Marks and Max Tegmark , 2023.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Diff-in-means concept editing is worst-case optimal: Explaining a result by Sam Marks and Max Tegmark , 2023
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T23:21:36.134891Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e51c783d-a696-4e2a-8646-e9bd02b31344 · outbound
This paper cites Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:31.805998Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8ef136b9-5a83-4e4f-9c3a-e02393032f3b · outbound
This paper cites Discovering Latent Knowledge in Language Models Without Supervision.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Discovering Latent Knowledge in Language Models Without Supervision
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:31.897028Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0d4f3c4b-ca06-46ea-8d79-35eeef30ae6c · outbound
This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Bert: Pre-training of deep bidirectional transformers for language understanding
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:32.027162Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 21692e02-2426-43be-bfb2-d141b6a0e081 · outbound
This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:32.139438Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c6594076-7e59-4f43-80cf-5b5b66326cdb · outbound
This paper cites an unresolved cited work.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Unresolved cited work
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:32.254237Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cccf4a5c-917c-4033-a81b-f228edaa361d · outbound
This paper cites an unresolved cited work.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T23:21:35.849917Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 88b4c6a2-0167-467f-8fa3-6f2b45fa171f · outbound
This paper cites Steering Llama 2 via Contrastive Activation Addition.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Steering Llama 2 via Contrastive Activation Addition
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:32.700490Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a99bbaf2-b613-418e-8b4b-5b07e448e292 · outbound
This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time The Linear Representation Hypothesis and the Geometry of Large Language Models
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:32.928349Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c6ba4781-4a6f-4e0e-b0e8-780ac0769177 · outbound
This paper cites From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:33.015705Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6535be0-21a5-4a35-8d35-fb100bb06428 · outbound
This paper cites Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:33.126785Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 064f7a2d-a50f-4859-bb29-97c6008226f7 · outbound
This paper cites Linear Representations of Sentiment in Large Language Models.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Linear Representations of Sentiment in Large Language Models
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:33.261035Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f0e6c457-a029-44cf-b5d1-37c81bbbc7a5 · outbound
This paper cites N., Kaiser, ., and Polosukhin, I.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time N., Kaiser, ., and Polosukhin, I
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:33.375837Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b2b3c6f-eb35-4ef4-aa9c-d3a0760d7426 · outbound
This paper cites A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:21:33.504146Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 64650258-e2ee-4a14-8a20-86574bb2893b · outbound
This paper cites Celeba-spoof: Large-scale face anti-spoofing dataset with rich annotations.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Celeba-spoof: Large-scale face anti-spoofing dataset with rich annotations
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T23:21:35.621101Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cfa245c7-ee74-48a2-ba12-af6976313a18 · outbound
This paper cites Age progression/regression by conditional adversarial autoencoder.
No Training Wheels: Steering Vectors for Bias Correction at Inference Time Age progression/regression by conditional adversarial autoencoder
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T23:21:35.473703Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Pith citing papers
No inbound Pith citation observations are available.