MétaCan
Menu
Back to cohort
Record W4404471047 · doi:10.31234/osf.io/a7kdx

The Forecasting Proficiency Test: A General Use Assessment of Forecasting Ability

2024· preprint· en· W4404471047 on OpenAlexaff
Mark Himmelstein, Sophie Ma Zhu, Ezra Karger, Jessica Helmer, Sivan Livnat, A. I. Bennett, Page Hedley, Phil Tetlock

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldDecision Sciences
TopicForecasting Techniques and Applications
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsTest (biology)Probabilistic forecastingComputer scienceEconometricsArtificial intelligenceEconomics

Abstract

fetched live from OpenAlex

How can we identify accurate forecasters? Current gold standard approaches draw from two sources of information: simple cognitive assessments of reasoning ability and past forecasting accuracy. Cognitive assessments are well-studied and normed psychometric instruments, but have lower predictive value. Real-world forecasting problems are more challenging to norm a priori: they typically require a large comparison sample of forecasters to make predictive inferences. This paper develops the Forecasting Proficiency Test (FPT): a one-hour test that predicts more than 60% of the variation in out-of-sample forecasting accuracy, double the predictive utility of prior work. We highlight several key results: (1) Eliciting forecasts in a quantile format is considerably more psychometrically reliable, meaning it is more efficient at reducing measurement error about forecasters' expected accuracy with fewer items, than forecasts elicited using the standard probability format common to most judgmental forecasting tournaments. (2) Several cognitive tasks, novel to forecasting research, are highly predictive of forecasting ability. These include denominator neglect, Bayesian updating, and adherence to decision rules. (3) Although our methods do best at separating out the worst forecasters from the population, they are also remarkably effective at identifying elite talent in the upper range of the skill distribution.

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)0.009
metaresearch head score (Gemma)0.013
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.643
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0090.013
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0020.000
Open science0.0020.006
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 head0.358
GPT teacher head0.464
Teacher spread0.106 · 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.

Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

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
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicForecasting Techniques and ApplicationsFrench-language works237,207