1 - Contribution des mesures d'information à la modélisation crédibiliste de connaissances
Bibliographic record
Abstract
Dans le cadre de la reconnaissance de formes, plusieurs methodes de classification ont ete developpees. Plus recemment, des methodes utilisant la theorie de Dempster-Shafer ont ete mises au point afin de gerer les problemes lies a la fusion d'informations imparfaites. Nous proposons ici une methode de discrimination fondee sur l'utilisation de structures de croyance. L'une des principales difficultes de la theorie de l'evidence reside dans la modelisation des connaissances. Afin de pallier ce probleme, plusieurs methodes de modelisation des connaissances a l'aide de fonctions de croyance ont vu le jour, dont celle proposee par A. Appriou [1, 2]. Afin de respecter l'inference bayesienne dans le cas de la connaissance parfaite des probabilites a priori, nous utilisons cette methode pour initialiser nos fonctions de croyance. Notre contribution reside dans l'utilisation de coefficients de fiabilite attribues a chaque source d'information selon chaque hypothese afin de modeliser le plus precisement possible l'information disponible. Ces coefficients sont definis par l'intermediaire d'une mesure de ressemblance entre des approximations de lois de probabilites a priori inconnues. Celles-ci sont determinees par des histogrammes construits a l'aide de criteres d'information. Les structures de croyance issues des sources les moins fiables sont alors affaiblies. Ensuite, les informations sont fusionnees a l'aide de l'operateur de combinaison de Dempster. Des resultats sur des donnees synthetiques sont proposes afin d'illustrer la methode.
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 | 0.005 | 0.031 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.005 | 0.006 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| 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".