How Much Confidence Do We Have for GenAI-Based Reasoningƒ A Statistical Inference Perspective for Reliability Estimation
Bibliographic record
Abstract
This paper investigates the confidence of using GenAI-based models in performing quantitative reliability reasoning, specifically focusing on estimating the shape and scale parameters of Weibull distributions. By using synthetic datasets generated from Weibull models, we design multiple experimental factors, including sample sizes, shape parameters, prompts, and five GenAI models (Claude, DeepSeek, Gemini, ChatGPT, and xAI) to see how various factors impact parameter estimations in the Weibull reliability model. The confidence levels and robustness of each GenAI model’s estimates are assessed through a factorial experimental design framework. Notably, the estimates of unknown parameters for Weibull model do not converge over increasing sample size as commonly observed in the traditional pure statistics-based inference. We also observe that ChatGPT and DeepSeek perform the best for both shape and scale parameters’ estimation compared with other GenAI models. ChatGPT and DeepSeek also show robustness in estimating parameters regardless of the types of prompts being used. The findings of this paper highlight the reliability and confidence of using GenAI models for unknown parameter estimation in quantitative reliability engineering analysis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.103 | 0.484 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.006 |
| Scholarly communication | 0.009 | 0.015 |
| Open science | 0.005 | 0.004 |
| Research integrity | 0.004 | 0.008 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".