MétaCan
Menu
Back to cohort
Record W4393147499 · doi:10.1609/aaai.v38i9.28820

How to Evaluate Behavioral Models

2024· article· en· W4393147499 on OpenAlexafffund
Greg d'Eon, Sophie Greenwood, Kevin Leyton‐Brown, James R. Wright

Bibliographic record

VenueProceedings of the AAAI Conference on Artificial Intelligence · 2024
Typearticle
Languageen
FieldPsychology
TopicBehavioral and Psychological Studies
Canadian institutionsUniversity of AlbertaUniversity of British Columbia
FundersUniversities Space Research AssociationAlberta Machine Intelligence InstituteNatural Sciences and Engineering Research Council of CanadaDefense Advanced Research Projects AgencyCanadian Institute for Advanced Research
KeywordsPsychologyComputer science

Abstract

fetched live from OpenAlex

Researchers building behavioral models, such as behavioral game theorists, use experimental data to evaluate predictive models of human behavior. However, there is little agreement about which loss function should be used in evaluations, with error rate, negative log-likelihood, cross-entropy, Brier score, and squared L2 error all being common choices. We attempt to offer a principled answer to the question of which loss functions should be used for this task, formalizing axioms that we argue loss functions should satisfy. We construct a family of loss functions, which we dub ``diagonal bounded Bregman divergences'', that satisfy all of these axioms. These rule out many loss functions used in practice, but notably include squared L2 error; we thus recommend its use for evaluating behavioral models.

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 imitation

Not 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.

metaresearch head score (Codex)0.046
metaresearch head score (Gemma)0.260
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Evaluation · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.954
Threshold uncertainty score0.243

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0460.260
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0040.002
Science and technology studies0.0010.004
Scholarly communication0.0100.015
Open science0.0040.004
Research integrity0.0040.006
Insufficient payload (model declined to judge)0.0070.003

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 head0.522
GPT teacher head0.430
Teacher spread0.091 · 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 source (direct Gemma or distilled Codex), not a consensus.

Study designTheoretical or conceptual
DomainEvaluation
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

Citations3
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueProceedings of the AAAI Conference on Artificial IntelligenceSame topicBehavioral and Psychological StudiesFrench-language works237,207