Paper Citation Record · LEDGER

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale

As of 10 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2608.04355.

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

pith.paper-citation-record.v1
2608.04355 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T19:13:05.447852Z

measured 28 of 28 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

28 of 28 outbound references displayed

verified exact1
verified fuzzy5
unresolved21
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 251b0dd5-1f11-41e7-954a-b5fd9f7e9a59 · outbound

This paper cites Self-Refine: Iterative Refinement with Self-Feedback.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Self-Refine: Iterative Refinement with Self-Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.228565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a4309ca-8aa3-4eeb-a903-d21df0cbfae0 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Reflexion: Language agents with verbal reinforcement learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:13:06.218719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5c4ea6e0-ba34-4337-88a8-ad951046ea03 · outbound

This paper cites STaR: Bootstrapping Reasoning With Reasoning.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale STaR: Bootstrapping Reasoning With Reasoning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.247668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe8c637d-d043-43f7-8164-79cb94eb11f5 · outbound

This paper cites Self-Rewarding Language Models.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Self-Rewarding Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.256882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1acfd92-7147-4d29-ad61-4e3a95676d23 · outbound

This paper cites Large language models cannot self-correct reasoning Yet.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Large language models cannot self-correct reasoning Yet

Reference 5

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T19:13:06.188609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3e0d3294-e7d8-4e75-a364-1a9e20befa79 · outbound

This paper cites When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.270274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4efbe73-210b-440b-bb17-e147e12e215b · outbound

This paper cites When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.281469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3edcfe75-972c-435b-9a0d-84a392562412 · outbound

This paper cites Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-08T19:13:05.886833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9b207699-71a2-4f7d-bccf-ae06668faf07 · outbound

This paper cites LLMs cannot find reasoning errors, but can correct them given the error location.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale LLMs cannot find reasoning errors, but can correct them given the error location

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.294638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb28368f-8378-4a93-b219-963cfba2948b · outbound

This paper cites Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.314513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c133086c-e877-4e81-ba2d-617688511fda · outbound

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

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Language Models (Mostly) Know What They Know

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.321558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59bb5263-7d8e-4d14-964b-44b3b36af95d · outbound

This paper cites an unresolved cited work.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-08T19:13:06.154693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e03dda13-d3ee-4add-b0d5-123680bd6ac1 · outbound

This paper cites Selectiveclassificationfordeepneuralnetworks.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Selectiveclassificationfordeepneuralnetworks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:13:06.112954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ac09acb7-e4e9-48a9-85eb-cd84a89a05f4 · outbound

This paper cites When are likely answers right? On Sequence Probability and Correctness in LLMs.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale When are likely answers right? On Sequence Probability and Correctness in LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.345733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ed7ec4-e533-412c-a313-0b2ecbcadf02 · outbound

This paper cites SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.356355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5c4f2e8-d071-43b9-9af0-f2e076944223 · outbound

This paper cites Separating error structure from marginal accuracy in self-refinement, 2026.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Separating error structure from marginal accuracy in self-refinement, 2026

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:13:06.091038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation acf8bfdc-edaa-4fe0-89a6-5ce1c90ec342 · outbound

This paper cites Excess self-confirmation: Separating self-evaluation drift from the opti- mizer’s curse, 2026.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Excess self-confirmation: Separating self-evaluation drift from the opti- mizer’s curse, 2026

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:13:06.069211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f144f331-5272-49bf-a465-99cbbbd1c0cf · outbound

This paper cites Qwen3.5-Omni Technical Report.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Qwen3.5-Omni Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.376727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e8ca38-7f40-4533-b224-f75bca7ea283 · outbound

This paper cites Qwen3 Technical Report.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Qwen3 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.383086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c6ff8c7-ae36-4bf4-8806-fcc2001b4d78 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Training Verifiers to Solve Math Word Problems

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.389329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d46217a-3598-4b30-b1f3-8ec1d6426e05 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Measuring Mathematical Problem Solving With the MATH Dataset

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.395360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 723e37db-5d21-492c-91f0-4498a02bc710 · outbound

This paper cites Program Synthesis with Large Language Models.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Program Synthesis with Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.415068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8a0ce0e-e76a-4bfa-b1b6-769784c6167e · outbound

This paper cites Measuring massive multitask language understanding.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Measuring massive multitask language understanding

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:13:06.045557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 710fd35b-ae7a-42fb-b215-fd2c6b4aea2c · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.427805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c82206a-86cf-42a7-ae05-44948dbe5b19 · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.434847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f423af29-16bf-46c6-adc1-d2d6cf04c8ac · outbound

This paper cites CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.440791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cb372e7-641c-4b9f-9171-19e0aca7adc6 · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.447852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2676fd0d-b2d0-476e-aa97-7e854c6baab3 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale Evaluating Large Language Models Trained on Code

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-08T19:13:05.408848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.