MétaCan
Menu
Back to cohort

How Much Confidence Do We Have for GenAI-Based Reasoningƒ A Statistical Inference Perspective for Reliability Estimation

2025· article· W7137121728 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicSoftware Reliability and Analysis Research
Canadian institutionsFuture Earth
Fundersnot available
KeywordsReliability (semiconductor)Perspective (graphical)Fiducial inferenceStatistical inferenceEstimationInferenceInterval estimationPoint estimation

Abstract

fetched live from OpenAlex

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.052
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.664
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0040.052
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0010.001
Scholarly communication0.0030.001
Open science0.0020.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.034
GPT teacher head0.378
Teacher spread0.344 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it