Assimilation ontological additions in convergent negotiation protocols
Bibliographic record
Abstract
We consider negotiation protocols in which each offer contains a price and a description from some given ontology. If the opposing negotiation agents do not share the same version of this ontology, for instance because not all have been made aware of the latest changes, then a fixed communication protocol may be expected to fail when one opponent is faced with an offer including a concept novel to it. However, the communication may proceed if the agent is allowed to ask for, receive and assimilate the missing information. This information may come from the other partner, a trusted source, or the human that the agent is serving. We propose a method whereby assimilation is accomplished dynamically so that existing conversations do not need to be abandoned. Our setting employs negotiation protocols that are required to be convergent, i.e. to make progress by exploring a finite negotiation space and thus terminate, either with a mutually acceptable offer or with an indication that no such offer exists. We show that existing convergent negotiation protocols, when applied in a setting that allows assimilation of monotonic additions, retain the property of convergence despite the permissibility of messages that do not meet the condition of making progress. We motivate the work within an e-marketplace where negotiation is over product features and can lead the conversation deeper into specific features, about which some fact may not be mutually known until more information is shared.
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 | 0.016 | 0.041 |
| 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 | 0.007 |
| Scholarly communication | 0.005 | 0.013 |
| Open science | 0.003 | 0.011 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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.
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".