MétaCan
Menu
Back to cohort
Record W1554661716 · doi:10.48550/arxiv.1206.3261

Learning When to Take Advice: A Statistical Test for Achieving A Correlated Equilibrium

2012· article· en· W1554661716 on OpenAlexaff
Greg Hines, Kate Larson

Bibliographic record

VenuearXiv (Cornell University) · 2012
Typearticle
Languageen
FieldDecision Sciences
TopicGame Theory and Applications
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsAdvice (programming)MediatorTest (biology)Computer scienceRelation (database)Artificial intelligenceMachine learningData miningMedicine

Abstract

fetched live from OpenAlex

We study a multiagent learning problem where agents can either learn via repeated interactions, or can follow the advice of a mediator who suggests possible actions to take. We present an algorithmthat each agent can use so that, with high probability, they can verify whether or not the mediator's advice is useful. In particular, if the mediator's advice is useful then agents will reach a correlated equilibrium, but if the mediator's advice is not useful, then agents are not harmed by using our test, and can fall back to their original learning algorithm. We then generalize our algorithm and show that in the limit it always correctly verifies the mediator's advice.

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)0.025
metaresearch head score (Gemma)0.159
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.025
Threshold uncertainty score0.130

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0250.159
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0030.001
Bibliometrics0.0010.001
Science and technology studies0.0010.007
Scholarly communication0.0020.005
Open science0.0040.003
Research integrity0.0040.005
Insufficient payload (model declined to judge)0.0030.001

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 head0.148
GPT teacher head0.281
Teacher spread0.133 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
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

Citations5
Published2012
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicGame Theory and ApplicationsFrench-language works237,207