Paper Citation Record · LEDGER

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling

As of 8 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2505.21399.

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

pith.paper-citation-record.v1
2505.21399 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:41:58.026877Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T12:41:48.620040Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T12:42:36.874577Z

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy16
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5045ac70-1ca4-4d74-adf5-f1fe8fc5d34f · outbound

This paper cites an unresolved cited work.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:54.922013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95079b00-4a11-42cb-8cd0-f88c89075457 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.019084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a799c9cc-f703-4a9c-9463-6c22227b0610 · outbound

This paper cites Language Models (Mostly) Know What They Know.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Language Models (Mostly) Know What They Know

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.083026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee4d5712-796c-4981-ac20-c75b398bf2f5 · outbound

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

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Inference-time intervention: Eliciting truthful answers from a language model

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:02.264258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f84fe498-cc02-4d7f-b284-b1aabbf0e920 · outbound

This paper cites Mitchell.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Mitchell

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.252095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83f3f301-d68e-4604-bb25-815b443768cd · outbound

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

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Discovering latent knowledge in language models without supervision

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.342908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f56b94f2-4d88-4257-8611-1a08d462c34b · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Self-refine: Iterative refinement with self-feedback

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:02.066993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4045bb5e-1fa8-4628-a079-aaba7a2b878c · outbound

This paper cites Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.503652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a76768c2-2c51-4a51-9972-26e4b63a0a21 · outbound

This paper cites On the self-verification limitations of large language models on reasoning and planning tasks.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling On the self-verification limitations of large language models on reasoning and planning tasks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:01.866647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5c728957-0b90-44ff-a5be-e5dca66e38c2 · outbound

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

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.687389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b5ccc3e-88c8-4cbf-abce-a2b5428b5c0d · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Gemma 2: Improving Open Language Models at a Practical Size

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.766792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46919ae5-1328-4c8f-bc5b-e61b9faef080 · outbound

This paper cites Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.859164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3d9f668-9bfd-4716-8cc8-22f4b6bdd7e4 · outbound

This paper cites Do large language models know what they don't know? In Anna Rogers, Jordan L.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Do large language models know what they don't know? In Anna Rogers, Jordan L

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:55.934804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1435aefa-5906-41c2-9302-88904de0310f · outbound

This paper cites Can llms replace neil degrasse tyson? evaluating the reliability of llms as science communicators.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Can llms replace neil degrasse tyson? evaluating the reliability of llms as science communicators

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:01.722803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d0d69705-22b9-400f-9c5b-10aa758c6c34 · outbound

This paper cites Tell me about yourself: LLMs are aware of their learned behaviors.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Tell me about yourself: LLMs are aware of their learned behaviors

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:56.079078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74ac85e9-4d5a-4ec5-8eab-ff3a8220d745 · outbound

This paper cites Large language models must be taught to know what they don't know.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Large language models must be taught to know what they don't know

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:01.535613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b0c82315-5687-4828-ac7c-c2605c140cdc · outbound

This paper cites Self-contrast: Better reflection through inconsistent solving perspectives.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Self-contrast: Better reflection through inconsistent solving perspectives

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:56.211670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39c096e-4c3d-465c-8d3b-2320e0d0e305 · outbound

This paper cites Le, Ed H.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Le, Ed H

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:56.322903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b70064-f8b2-4784-a08a-9267955e4055 · outbound

This paper cites INSIDE: llms' internal states retain the power of hallucination detection.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling INSIDE: llms' internal states retain the power of hallucination detection

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:01.364663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3a49852b-fe53-4d74-bed8-9d2c72b837df · outbound

This paper cites LLM Internal States Reveal Hallucination Risk Faced With a Query.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling LLM Internal States Reveal Hallucination Risk Faced With a Query

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:56.531343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8969fa5-38c4-4dee-8492-0f0e4b1c466e · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Towards monosemanticity: Decomposing language models with dictionary learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:01.064969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 18e1fe59-6afe-43e3-ad00-56cc4f4ddfbb · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Sparse autoencoders find highly interpretable features in language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:00.814319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c2605246-cce2-4e1f-b418-c1bc61096cce · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:56.759530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80809f29-14ec-41f4-8724-15384c72dda1 · outbound

This paper cites Distributed representations of words and phrases and their compositionality.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Distributed representations of words and phrases and their compositionality

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:00.486762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2de16871-de4d-4537-92f0-386ec1ca6cf2 · outbound

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

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Inference-time intervention: Eliciting truthful answers from a language model

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:42:00.205306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fca1fa49-5ef5-4762-a9dd-a33bef740c6e · outbound

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

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Representation Engineering: A Top-Down Approach to AI Transparency

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:56.958567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02af764a-c886-4edf-b031-c47dbbe9f001 · outbound

This paper cites Saes are highly dataset dependent: A case study on the refusal direction.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Saes are highly dataset dependent: A case study on the refusal direction

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:41:59.918261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 44b7442f-32c0-4d6c-94e5-e38f4619f4be · outbound

This paper cites Open Problems in Mechanistic Interpretability.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Open Problems in Mechanistic Interpretability

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:57.279860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac1a8290-6e72-4e91-b7c7-0be9661cf1d1 · outbound

This paper cites Learning Multi-Level Features with Matryoshka Sparse Autoencoders.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:57.359666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bd34682-fb12-48c0-9375-f95742b16791 · outbound

This paper cites Wikidata.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Wikidata

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:41:59.592995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0ef15772-cb0b-4702-99c0-973fe07912dd · outbound

This paper cites Locating and editing factual associations in gpt.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Locating and editing factual associations in gpt

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:57.483957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9ddcc0a-8290-4535-943c-e19cc527156b · outbound

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

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Dissecting recall of factual associations in auto-regressive language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:57.563000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab8ae9d-8d99-4149-a193-745371acf754 · outbound

This paper cites Fact finding: Attempting to reverse-engineer factual recall on the neuron level.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Fact finding: Attempting to reverse-engineer factual recall on the neuron level

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:41:59.304081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 43462163-784f-44bf-9fc6-bb51c38f0bd3 · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:57.703508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aae4ff6-b5b1-447c-81c9-52862d1dc857 · outbound

This paper cites Demystifying prompts in language models via perplexity estimation.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Demystifying prompts in language models via perplexity estimation

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:41:59.060236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c2c99ab0-6d7d-46bd-aecb-c24bcdb66f87 · outbound

This paper cites Quantifying lms’ sensitivity to spurious prompt formatting.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Quantifying lms’ sensitivity to spurious prompt formatting

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:41:58.791245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d79d578e-579d-48af-9254-5a36e8241f4a · outbound

This paper cites Large language models are zero-shot reasoners.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Large language models are zero-shot reasoners

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:57.969695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b5bb3c-52ef-42c6-ae7b-52705c704dba · outbound

This paper cites State of what art? a call for multi-prompt llm evaluation.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling State of what art? a call for multi-prompt llm evaluation

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:41:58.547664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation ac32da1d-3dcd-44ee-8fef-00aa028b7c9d · inbound

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models cites this paper.

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:42:36.877686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.