MétaCan
Menu
Back to cohort
Record W6977130183 · doi:10.6084/m9.figshare.18585810

Additional file 1 of Graphical calibration curves and the integrated calibration index (ICI) for competing risk models

2022· article· en· W6977130183 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

VenueOpen MIND · 2022
Typearticle
Languageen
FieldHealth Professions
TopicSocial and Demographic Issues in Germany
Canadian institutionsInstitute for Clinical Evaluative SciencesUniversity of Toronto
Fundersnot available
KeywordsCensoring (clinical trials)CalibrationMaximum likelihoodMonte Carlo method

Abstract

fetched live from OpenAlex

Additional file 1. Figure S1. RCS: Choice of number of knots (p = 0.25). Figure S2. RCS: Choice of number of knots (p = 0.75). Figure S3. ICI/E50/E90 in simulations for selecting the optimal number of knots (p = 0.25). Figure S4. ICI/E50/E90 in simulations for selecting the optimal number of knots (p = 0.75). Figure S5. Effect of degree of censoring on estimated calibration curves (N = 2000 and p = 0.25). Figure S6. Effect of degree of censoring on estimated calibration curves (N = 2000 and p = 0.75). Figure S7. ICI/E90/E90 for correctly−specified model and censoring (N = 2000 and p = 0.25). Figure S8. ICI/E90/E90 for correctly−specified model and censoring (N = 2000 and p = 0.75). Figure S9. True model fitted with no censoring (beta1 = 0.25 & p = 0.25). Figure S10. True model fitted with no censoring (beta1 = 0.25 & p = 0.50). Figure S11. True model fitted with no censoring (beta1 = 0.25 & p = 0.75). Figure S12. True model fitted with no censoring (beta1 = 0.50 & p = 0.25). Figure S13. True model fitted with no censoring (beta1 = 0.50 & p = 0.75). Figure S14. True model fitted with no censoring (beta1 = 1 & p = 0.25). Figure S15. True model fitted with no censoring (beta1 = 1 & p = 0.50). Figure S16. True model fitted with no censoring (beta1 = 1 & p = 0.75). Figure S17. ICI/E90/E90 for correctly−specified model without censoring (p = 0.25). Figure S18. ICI/E90/E90 for correctly−specified model without censoring (p = 0.75). Figure S19. Mis−specified model (beta1 = 0.25 & p = 0.25). Figure S20. Mis−specified model (beta1 = 0.25 & p = 0.50). Figure S21. Mis−specified model (beta1 = 0.25 & p = 0.75). Figure S22. Mis−specified model (beta1 = 0.50 & p = 0.25). Figure S23. Mis−specified model (beta1 = 0.50 & p = 0.75). Figure S24. Mis−specified model (beta1 = 1 & p = 0.25). Figure S25. Mis−specified model (beta1 = 1 & p = 0.50). Figure S26. Mis−specified model (beta1 = 1 & p = 0.75). Figure S27. ICI/E90/E90 for incorrectly−specified model (p = 0.25). Figure S28. ICI/E90/E90 for incorrectly−specified model (p = 0.75). Figure S29. Mis−specified model (omission of main effect) (rho=0.25). Figure S30. Mis−specified model (omission of main effect) (rho=0.50). Figure S31. Mis−specified model (omission of main effect) (rho=0.75). :R code for constructing calibration curves and numerical metrics of calibration using restricted cubic splines.

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)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Dataset · Consensus signal: none
Teacher disagreement score0.707
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.4240.000

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 head0.065
GPT teacher head0.370
Teacher spread0.305 · 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