Using a performative subsumption lattice to support commitment-based conversations
Bibliographic record
Abstract
In this paper, we arrange FIPA's ACL performatives to form a sub-sumption lattice (ontology) and apply a theory of social commitments to achieve a simplified and observable model of agent behaviour. Using this model, it is straight forward to model agents' social commitments (obligations) based solely on observation of messages passed between the agents (such observation is supported by our agent infrastructure system). Furthermore, owing to the performatives being in a subsumption lattice, it is relatively easy for an observer to infer social commitment relationships even if the observer does not understand the details of messages or even the exact performatives used (so long as the observer has access to the performatives ontology).Although social commitment modelling of agent behaviour does not demand that agents are implemented using the social commitment model, our model nonetheless can be used in agent implementation to simplify the specification of agent behaviour through the use of "commitment operators" attached to the performatives (as policies) in the subsumption lattice.The primary contribution of this paper is to show how FIPA's performatives can be mapped onto a theory of social commitment to allow observable social behaviour and conformance to social norms.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.004 | 0.006 |
| Scholarly communication | 0.006 | 0.013 |
| Open science | 0.004 | 0.006 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".