MétaCan
Menu
Back to cohort
Record W4283521600 · doi:10.31235/osf.io/yjk3q

Embodied Conversational Agents (ECAs): Do you want them on your team?

2022· preprint· en· W4283521600 on OpenAlexaff
Jesse Hoey

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldNeuroscience
TopicEmbodied and Extended Cognition
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsArgument (complex analysis)Embodied cognitionIdentity (music)Diversity (politics)PsychologySocial psychologyEpistemologyComputer scienceSociologyArtificial intelligenceAesthetics

Abstract

fetched live from OpenAlex

If you want ECAs on your team, you'll want them to understand how you do things. You'll also want to understand how they do things. Ideally your team's actions should be synchronized, yet complementary to some degree. That is, you seek an efficient and feasible division of labour. The ``you-things'' and the ``they-things'' have to be complete (they have to cover all the sub-tasks leading to the goal), and as sound as possible (any overlap decreases efficiency). This paper argues that, due to the impenetrability of beliefs, an artificial agent will be unable to join a group with such synchronized diversity by attempting to find a balance between its own beliefs and preferences and others' beliefs and preferences (i.e., a theory of mind). Instead, successful group membership requires ignoring individual utility, and taking actions to make the world (an everyone in it) as predictable as possible. Agents will be more predictable if they not only do the ``they-things,'' but also make it clear to others what those things are. However, the group's goals are shaped by the actions of its members, and so a boundary that identifies group membership is necessary. In essence, all agents must be able to identify to which group they belong. After filling in the argument, I give a short introduction to an emotional identity theory that may provide a way forward, and attempt to convince you that you will want ECAs on your team, but only after solving this division of labour.

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)0.002
metaresearch head score (Gemma)0.007
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Other · Consensus signal: Other
Teacher disagreement score0.006
Threshold uncertainty score0.018

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.007
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0030.004
Scholarly communication0.0060.009
Open science0.0010.004
Research integrity0.0040.003
Insufficient payload (model declined to judge)0.0050.002

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 head0.115
GPT teacher head0.316
Teacher spread0.201 · 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 designNot applicable
Domainnot available
GenreOther

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
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicEmbodied and Extended CognitionFrench-language works237,207