Paper Citation Record · LEDGER

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing

As of 9 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2603.13259.

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

pith.paper-citation-record.v1
2603.13259 v3

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:01:58.418218Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

13 of 13 outbound references displayed

verified exact0
verified fuzzy0
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 72b1fe07-3fdb-4d20-a9b7-078fa10bf59e · outbound

This paper cites Jump to Conclusions: Short-Cutting Transformers With Linear Transformations.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Jump to Conclusions: Short-Cutting Transformers With Linear Transformations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:57.338265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc74046-aa24-4aa4-b600-35633b4f30aa · outbound

This paper cites Dissecting recall of factual as- sociations in auto-regressive language models.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Dissecting recall of factual as- sociations in auto-regressive language models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:57.678012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 228fac9d-dc80-42c8-9bd6-5c2583aef3fa · outbound

This paper cites A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:57.873002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f995a17-80b7-4f49-9ce8-eb75429eaac9 · outbound

This paper cites Mistral 7B.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Mistral 7B

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:57.972567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ae93648-8564-434c-948f-fe644b17d484 · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:58.059445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fee57e1e-7817-4945-a4a6-e02caf651f88 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing LLaMA: Open and Efficient Foundation Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:58.160603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb8c5413-8ddc-42d6-890f-4d27bededb4c · outbound

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

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Representation Engineering: A Top-Down Approach to AI Transparency

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:58.418218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a88efd19-9fa2-4af7-847b-52044d1e2c52 · outbound

This paper cites Transformer feed-forward layers are key-value memories.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Transformer feed-forward layers are key-value memories

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:57.553434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ebcb12a-4ba8-4d43-a7c9-bd9102438ae4 · outbound

This paper cites Qwen2 Technical Report.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Qwen2 Technical Report

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:58.323791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a1a6e0-9b30-40e2-b273-017f42c4a90b · outbound

This paper cites How contextual are contextualized word representations? comparing the ge- ometry of BERT, ELMo, and GPT-2 representations.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing How contextual are contextualized word representations? comparing the ge- ometry of BERT, ELMo, and GPT-2 representations

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:57.426132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c0e57ef-9ab9-48b4-99f9-d5876b9372be · outbound

This paper cites Transformers: State-of-the-art natural language processing.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Transformers: State-of-the-art natural language processing

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:58.252582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 133624e8-0c3d-4db5-b73f-01c34ea81e78 · outbound

This paper cites Stable LM 2 1.6B Technical Report.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Stable LM 2 1.6B Technical Report

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:57.284733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afe11057-c60b-44a7-ab80-ff913a15c3aa · outbound

This paper cites Designing and interpreting probes with control tasks.

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Designing and interpreting probes with control tasks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T21:01:57.795306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.