Paper Citation Record · LEDGER

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs

As of 8 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 3 inbound Pith citation observations for arXiv:2604.01457.

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

pith.paper-citation-record.v1
2604.01457 v3

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T16:59:55.511627Z

measured 23 of 23 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 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:24:38.335417Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T03:06:29.186667Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy0
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1f6e6904-56a7-46de-9d21-d671444b9ad5 · outbound

This paper cites Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:54.448597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e097604c-a002-4a6e-ba54-3ee2fe4f8b4a · outbound

This paper cites Teaching Models to Express Their Uncertainty in Words.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Teaching Models to Express Their Uncertainty in Words

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.118772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82a543d1-b707-47e0-bfc9-0e90eb47d197 · outbound

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

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.251035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e24aced5-856e-439c-81d2-e890eb057852 · outbound

This paper cites Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE).

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.297709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e2aec1-41b7-44ae-a65d-2171f6ba81a4 · outbound

This paper cites A practical review of mechanistic interpretability for transformer-based language models.arXiv preprint arXiv:2407.02646,.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs A practical review of mechanistic interpretability for transformer-based language models.arXiv preprint arXiv:2407.02646,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.344455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f3a60c8-00ca-429f-82f6-9749622183af · outbound

This paper cites Carter Teplica, Yixin Liu, Arman Cohan, and Tim GJ Rudner.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Carter Teplica, Yixin Liu, Arman Cohan, and Tim GJ Rudner

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.455482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac668261-cf7d-4537-ad1b-b31a716b6106 · outbound

This paper cites Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.493552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb22fcdc-9130-478d-995c-dfdbbe5d6e62 · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.496930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f4d0c16-b4f0-4825-be24-bea381fd0069 · outbound

This paper cites Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.500112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dd618b5-efee-41fb-8f1e-830644ba7991 · outbound

This paper cites Can large language models faithfully express their intrinsic uncertainty in words? InProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Can large language models faithfully express their intrinsic uncertainty in words? InProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.503212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b600cc46-705f-4d36-a0c9-58d944cff8e9 · outbound

This paper cites To balance fidelity and efficiency, we employ Edge Attribution Patching with Integrated Gradients (EAP-IG) (Hanna et al., 2024).

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs To balance fidelity and efficiency, we employ Edge Attribution Patching with Integrated Gradients (EAP-IG) (Hanna et al., 2024)

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.505910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b22874a2-232a-4930-8171-43c43aa783d5 · outbound

This paper cites Let xe denote the activation along edgee.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Let xe denote the activation along edgee

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.508447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 138ba225-fe9b-4afe-a507-904c68e012cf · outbound

This paper cites the stronger, the better.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs the stronger, the better

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.511627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c415eab-b911-4d35-ab34-824900eeb823 · outbound

This paper cites The Llama 3 Herd of Models.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs The Llama 3 Herd of Models

Reference 1950

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:54.282601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44695dcf-2dd1-448e-b336-c1005cf59ae7 · outbound

This paper cites doi: 10.18653/v1/P19-1612.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs doi: 10.18653/v1/P19-1612

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.006395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9529e23-b866-4c62-8a1a-9e0723b60c88 · outbound

This paper cites Calibrating verbal uncertainty as a linear feature to reduce hallucinations.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Calibrating verbal uncertainty as a linear feature to reduce hallucinations

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:54.672370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 917d2708-72ca-4af2-8611-9e7cfb4de52e · outbound

This paper cites How do LLMs Compute Verbal Confidence.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs How do LLMs Compute Verbal Confidence

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:54.843386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159acf68-bc10-428c-bb9a-29be41de2f50 · outbound

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

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:54.157676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ec7e450-71b1-4bc4-9127-d2bbd044472b · outbound

This paper cites Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:54.616589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e92beed8-26c2-41fb-8864-94d7a84727b0 · outbound

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

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Language Models (Mostly) Know What They Know

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:54.743554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bb4879f3-314a-4672-9137-0eadbfc8a707 · inbound

Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen cites this paper.

Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-21T02:20:37.021155Z

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 a5db85f6-35ec-4e22-9d3e-cc3c996ceb8e · inbound

Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B cites this paper.

Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-21T02:20:37.021155Z

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 fc212bdb-10c3-447b-849f-81a429f78a25 · inbound

Quantifying Faithful Confidence Expression in Large Reasoning Models cites this paper.

Quantifying Faithful Confidence Expression in Large Reasoning Models Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-07-21T02:20:37.021155Z

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.