Agent Trust Management Based on Human Plausible Reasoning: Application to Web Search
Bibliographic record
Abstract
In open systems, different service providers can join and leave at any time. Multi Agent Systems (MASs) are being used more and more as the basis of open systems. Although openness brings a huge opportunity for different systems to operate in a decoupled and autonomous manner, it can introduce untrustworthy agents into the society. For this purpose, Agent Trust Management (ATM) methods have been proposed to try to eliminate this defect. This paper presents a general framework for managing trust in MASs based on the theory of Human Plausible Reasoning (HPR). The goal of the proposed framework is to determine for each user a ranked list of trusted agents and to find newer possible trust relationships between users and agents. We use the HPR certainty parameters to define how trustworthy each agent is in the list. We measure the agent trust according to two metrics: the direct interaction rating and third-party references. For each user, a third party is any other user with whom a HPR relationship exists. We aggregate the direct interaction rating value and the reputation values of third parties to achieve a single quantitative value for the trust. This value is then used to rank the agents. We apply our HPR-based ATM framework to the domain of Web search. The resulting ATM system provides the user a list of trusted search engines ranked according to the reputation the search engine has gained by interacting with other related users as well as the retrieval precision of pages returned in response to the user's query.
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 | 0.004 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".