Dynamic estimation of evidence discounting rates based on information credibility
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Information quality is crucial to any information fusion system as combining unreliable or partially credible pieces of information may lead to erroneous results. In this paper, Dempster-Shafer theory of evidence is being used as a framework for representing and combining uncertain pieces of information. We propose a method of dynamic estimation of evidence discounting rates based on the credibility of pieces of information. The credibility of a piece of information Cre(In) is evaluated through a measure of consensus (corroboration degree) between a set of belief functions, and this measure serves as a basis for quantifying the credibility of the source (sensor or fusion node) itself, Cre(Sk), used then as a discounting factor for all further belief functions provided by Sk. The process is dynamic in the sense that the credibility of the source is revisited in the light of new incoming piece of information. The method proposed relies on a hybrid fusion topology in which the sensors are grouped according to the feature they measure (similar and dissimilar sensors), allowing to select different kinds of measure for estimating the corroboration degrees. Through simulations, we compare (a) the hybrid-combination using the source credibility and the robust combination rule (RCR-L) accounting automatically for sensors's credibility; (b) the hybrid-combination, with different membership degrees and corroboration degrees used to estimate the sources credibility. We show that the new hybrid topology together with the credibility-based evidence discounting estimation algorithm provide a faster identification of the observed object.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it