MétaCan
Menu
Back to cohort
Record W4415234144 · doi:10.1080/03610918.2025.2574482

Power-controlled reliability tests for assessing probabilistic classifier calibration

2025· article· en· W4415234144 on OpenAlexafffund
Hyukjun Gweon, Yu Hao, Reg Kulperger

Bibliographic record

VenueCommunications in Statistics - Simulation and Computation · 2025
Typearticle
Languageen
FieldEngineering
TopicFault Detection and Control Systems
Canadian institutionsWestern University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsProbabilistic logicCalibrationReliability (semiconductor)Classifier (UML)Pattern recognition (psychology)

Abstract

fetched live from OpenAlex

In supervised classification, a reliability diagram can be used to assess the quality of class probability estimates. Based on data binning, the reliability diagram visualizes the level of calibration of the probability outcomes. However, despite its visual appeal, it lacks statistical rigor. Efforts to add a statistical inference to a reliability diagram often encounter issues with sample size dependency, as in other statistical tests, where the statistical power increases with sample size. In this paper, we propose power-controlled reliability tests for the assessment of binary probabilistic classifiers. Our method provides consistent statistical power across different ranges of probability estimates. For each bin, the proposed method tests the reliability using a local alternative. We obtain uniform power for individual tests by allowing bins to have different sizes. Our iterative algorithm effectively determines the appropriate bin sizes as well as the total number of bins. A simulation study was conducted to investigate the performance of the proposed method across different models. We also illustrate a practical use of the proposed method with two real data sets.

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 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)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.960
Threshold uncertainty score0.594

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.060
GPT teacher head0.395
Teacher spread0.336 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueCommunications in Statistics - Simulation and ComputationSame topicFault Detection and Control SystemsFrench-language works237,207