Paper Citation Record · LEDGER

The Geometry of Self-Verification in a Task-Specific Reasoning Model

As of 17 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 2 inbound Pith citation observations for arXiv:2504.14379.

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

pith.paper-citation-record.v1
2504.14379 v2

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:53:47.506728Z

measured 45 of 45 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T10:36:09.211639Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T08:57:48.152681Z

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy14
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2f6e4900-ca75-41d5-a8f4-d3b01eb69a46 · outbound

This paper cites an unresolved cited work.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.338083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d52b7fd0-23c5-45c1-8d34-96ed7255fd0c · outbound

This paper cites Chain-of-Thought Reasoning In The Wild Is Not Always Faithful.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.342485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b88ff8-550c-47f4-a64b-cb48c479503e · outbound

This paper cites Refusal in language models is mediated by a single direction.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Refusal in language models is mediated by a single direction

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.347290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60fa3c90-13cd-4273-a990-b5f103d9aa3f · outbound

This paper cites Discovering latent knowledge in language models without supervision.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Discovering latent knowledge in language models without supervision

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:48.014261Z

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 a01dac76-b5c6-44b1-854c-40ce431965a4 · outbound

This paper cites Designing a Dashboard for Transparency and Control of Conversational AI.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Designing a Dashboard for Transparency and Control of Conversational AI

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.355644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef13720e-0a2f-4779-bcc2-47542e525312 · outbound

This paper cites Transcoders find interpretable llm feature circuits.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Transcoders find interpretable llm feature circuits

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:48.001841Z

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 389909d4-d244-45c7-99dd-5169ec699cf4 · outbound

This paper cites A mathematical framework for transformer circuits.

The Geometry of Self-Verification in a Task-Specific Reasoning Model A mathematical framework for transformer circuits

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.364017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d07a65a5-12ba-4ca0-a593-60298d1e3f4b · outbound

This paper cites Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.371602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baf66378-3f31-4c75-9d58-bcc9c0b78e61 · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.375711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 616ccbc1-282f-44ee-859a-17d02d485cbf · outbound

This paper cites Stream of Search (SoS): Learning to Search in Language.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Stream of Search (SoS): Learning to Search in Language

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.379970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c65f562-47b7-45f7-815b-d826901b3eb8 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

The Geometry of Self-Verification in a Task-Specific Reasoning Model DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.384334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a1ac98-ed4f-4f6a-bf4c-768185bb2a8a · outbound

This paper cites Gaussian Error Linear Units (GELUs).

The Geometry of Self-Verification in a Task-Specific Reasoning Model Gaussian Error Linear Units (GELUs)

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.389245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df6b2f85-0396-4d38-90e5-cecbfa976058 · outbound

This paper cites Understanding the effects of rlhf on llm generalisation and diversity.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Understanding the effects of rlhf on llm generalisation and diversity

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.976794Z

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 fa3bc5c0-54d7-4156-b261-9be4965254b4 · outbound

This paper cites Measuring Faithfulness in Chain-of-Thought Reasoning.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.397673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31082ea8-c38b-4089-985d-372668a9e817 · outbound

This paper cites A mechanistic understanding of alignment algorithms: A case study on dpo and toxicity.

The Geometry of Self-Verification in a Task-Specific Reasoning Model A mechanistic understanding of alignment algorithms: A case study on dpo and toxicity

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.964834Z

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 e6857bfc-e133-47eb-bc4b-af5aa067c455 · outbound

This paper cites Shared Global and Local Geometry of Language Model Embeddings.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Shared Global and Local Geometry of Language Model Embeddings

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.405225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80d9d2cc-0d43-45d8-8baf-c0a54f3ac1b0 · outbound

This paper cites Inference- time intervention: Eliciting truthful answers from a language model.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Inference- time intervention: Eliciting truthful answers from a language model

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.409295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba73a0e-e55b-42b7-b1b1-a5da7551152b · outbound

This paper cites an unresolved cited work.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.412786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc06920-49f8-47e4-a024-50ac2427cc92 · outbound

This paper cites Talking heads: Understanding inter-layer communication in transformer language models.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Talking heads: Understanding inter-layer communication in transformer language models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.940160Z

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 6ebe2e01-62bc-4ec1-81f7-a5704f7c19f0 · outbound

This paper cites Efficient Estimation of Word Representations in Vector Space.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Efficient Estimation of Word Representations in Vector Space

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.420315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f1f6ab9-6d3b-492f-94a9-df2f0582e431 · outbound

This paper cites One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity.

The Geometry of Self-Verification in a Task-Specific Reasoning Model One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.424568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29151898-cf60-4ebb-a5b3-5fc31abc85c9 · outbound

This paper cites Emergent linear representations in world models of self-supervised sequence models.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Emergent linear representations in world models of self-supervised sequence models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.929286Z

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 d5acc087-73cf-4099-b95c-868917e84f91 · outbound

This paper cites Interpreting gpt: The logit lens, 2020.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Interpreting gpt: The logit lens, 2020

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.915914Z

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 4dd43f55-466c-47f8-beb2-feeb74a7282d · outbound

This paper cites Zoom in: An introduction to circuits.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Zoom in: An introduction to circuits

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.435489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23ee7f44-ba05-4b01-a032-592ec1ecb52e · outbound

This paper cites Olshausen and David J.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Olshausen and David J

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.896567Z

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 4eab2395-ea62-49ea-9ab7-1e74c609e9fd · outbound

This paper cites In-context learning and induction heads.

The Geometry of Self-Verification in a Task-Specific Reasoning Model In-context learning and induction heads

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.442570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d2f5af4-a7b2-46c3-9f07-ef0eb1bd10f5 · outbound

This paper cites Learning to reason with llms.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Learning to reason with llms

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.876043Z

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 3dad8602-e9ec-4a4d-89af-f481cf03ad48 · outbound

This paper cites LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations.

The Geometry of Self-Verification in a Task-Specific Reasoning Model LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.450055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a92d2494-e3cf-4a5e-a5bd-56e65d362a45 · outbound

This paper cites Does writing with language models reduce content diversity? In The Twelfth International Conference on Learning Representations, 2024.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Does writing with language models reduce content diversity? In The Twelfth International Conference on Learning Representations, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.862824Z

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 e899e95e-1081-467c-b00e-a06317ca2715 · outbound

This paper cites The linear representation hypothesis and the geometry of large language models.

The Geometry of Self-Verification in a Task-Specific Reasoning Model The linear representation hypothesis and the geometry of large language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.848638Z

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 89222cb1-d9ab-4cad-8ba2-897f04b904ef · outbound

This paper cites Fine-tuning enhances existing mechanisms: A case study on entity tracking.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Fine-tuning enhances existing mechanisms: A case study on entity tracking

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.836306Z

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 efc37895-e9bb-434d-afbd-202aa3ab9f17 · outbound

This paper cites To backtrack or not to backtrack: When sequential search limits model reasoning.

The Geometry of Self-Verification in a Task-Specific Reasoning Model To backtrack or not to backtrack: When sequential search limits model reasoning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.465370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03fc990b-8040-4596-b3dd-fabbbf8418af · outbound

This paper cites Steering llama 2 via contrastive activation addition.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Steering llama 2 via contrastive activation addition

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.469230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07df36c7-eb31-4b6d-9d35-5317d3fc9ed0 · outbound

This paper cites GLU Variants Improve Transformer.

The Geometry of Self-Verification in a Task-Specific Reasoning Model GLU Variants Improve Transformer

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.473166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a30d986b-f441-48c5-b9ba-9e7b2d84b1a2 · outbound

This paper cites Diverse preference learn- ing for capabilities and alignment.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Diverse preference learn- ing for capabilities and alignment

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.815846Z

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 070207e4-ba60-4fab-bd9f-575fd98e02a4 · outbound

This paper cites Language models don’t always say what they think: Unfaithful explanations in chain-of-thought prompting.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Language models don’t always say what they think: Unfaithful explanations in chain-of-thought prompting

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.481108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac902cec-9cd2-413a-911a-e2916290087a · outbound

This paper cites Understanding reasoning in thinking language models via steering vectors.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Understanding reasoning in thinking language models via steering vectors

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:47.797666Z

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 b801aff0-6a6c-448c-9185-4a9afa233710 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Chain-of-thought prompting elicits reasoning in large language models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.488972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83b74323-6da2-41f3-bb1b-6029f0b16903 · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Tree of thoughts: Deliberate problem solving with large language models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.493037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1694bfd1-90c0-4389-9568-d65fafbaf265 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.497301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd9a1fa-60ae-4eba-b399-349e334e2ecf · outbound

This paper cites Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.502158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 710f8f3e-4c4e-4e95-bdd5-29be6afdd0b4 · outbound

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

The Geometry of Self-Verification in a Task-Specific Reasoning Model Representation Engineering: A Top-Down Approach to AI Transparency

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.506728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11e587e7-ffec-4ad5-ba60-81be05eddb0d · outbound

This paper cites an unresolved cited work.

The Geometry of Self-Verification in a Task-Specific Reasoning Model Unresolved cited work

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:47.367850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 783711c7-5ce7-41b7-a170-522fd284643f · inbound

Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions cites this paper.

Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions The Geometry of Self-Verification in a Task-Specific Reasoning Model

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:16:30.194354Z

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 abb62747-5e2c-4ffa-9216-88db3019bfe9 · inbound

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier cites this paper.

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier The Geometry of Self-Verification in a Task-Specific Reasoning Model

Reference 108

Resolution: verified exact; arxiv_id, observed 2026-07-03T08:57:48.154799Z

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.