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

arXiv: https://arxiv.org/abs/2608.04355 · HTML: https://mlsanity.com/paper/2608.04355/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 23 of 23)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models](https://mlsanity.com/paper/2402.12563/) (2024)
- [Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops](https://mlsanity.com/paper/2607.07663/) (2026)
- [When are likely answers right? On Sequence Probability and Correctness in LLMs](https://mlsanity.com/paper/2606.27359/) (2026)
- [When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis](https://mlsanity.com/paper/2606.23196/) (2026)

## Built on by (most cited first, 1 of 1)

- [What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects](https://mlsanity.com/paper/2610.05533/) (2026)

## Abstract (arXiv)

Accuracy changes after language-model self-revision are usually interpreted as changes in reasoning. We show this can fail at the answer-extraction boundary, and test the failure causally rather than only observationally. Across Qwen3.5 (0.8B-9B), Gemma-4-12B, and two frontier models via API (Tencent Hy3, Nvidia Nemotron-3-Ultra-550B) in 29 primary cells plus a frontier arm, we decompose the always-revise accuracy shift into a content margin (both answers parseable) and format-recovery/loss margins (parseability changes). On 12 cells with meaningful unparseable-answer rates, format effects exceed content effects (Wilcoxon p=1.7e-3). To test this causally, we force already-generated reasoning through grammar-constrained decoding so every answer is parseable by construction: across 14 cells this closes a median 71% of the gap between the naive total effect and the content-margin estimate, with two cells converging exactly and a residual on the two largest-effect cells reported rather than dismissed. A clustered model confirms floor-scale (0.8B/2B) models have far higher odds of content-level change and harm than capable-scale models (p<1e-7). Replicating a cited confidence-gating protocol verbatim on Qwen3.5 does not reproduce its reported gain and shows the same near-zero content margin. A frontier check on much larger models shows format-dominance intensifying with scale: content margin is exactly zero in all 5 cells despite total effects up to +0.275, though this arm is lower-powered. The calibration-floor criterion on the content margin reveals a squeeze: floor-scale cells have headroom but insufficient signal, capable-scale cells have signal but little headroom; only one cell is marginally viable, with negligible sealed-holdout gain. Content is a minority share of what the field has measured as self-correction. We release the instrument, code, and derived results.