SINCERITY: A New Bilingual Search engine for Image Retrieval in a Bilingual Context
Bibliographic record
Abstract
This poster presents a research project that aims todevelop an interface model for image retrieval(SINCERITY) in a bilingual (French and English)context, that is, when the query language differs fromthe indexing language. This poster will summarize theresults of the first and second phases of the projectand will present the preliminary results of the usertesting. Once fully developed, SINCERITY is intendedto be an innovative tool for image searchers who arelooking for ordinary images. The main contribution ofthis project lies in bridging a gap for unilingual imagesearchers. The bilingual search interface willconstitute a definite benefit for image searchersunfamiliar with more than one language, by givingthem user-friendly access to visual resources.Cette affiche présente un projet de recherche qui viseà développer un modèle d’interface pour la recherched’image (SINCERITY) dans un contexte bilingue(français et anglais), c’est-à-dire quand le langage derequête diffère de la langue d’indexation. Cetteaffiche résumera les résultats des première etdeuxième phases du projet et présentera les résultatspréliminaires des essais par l’utilisateur. Une foispleinement développé, SINCERITY entend devenir unoutil innovant pour les chercheurs d’image qui sont àla recherche d’images ordinaires. La contributionprincipale de ce projet est de combler une lacunepour les chercheurs unilingues. L’interface derecherche bilingue constitue un avantage certain pourles chercheurs qui ne sont familiers qu’avec uneseule langue, en leur donnant un accès convivial auxressources visuelles.
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 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 | 0.001 | 0.021 |
| 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 | 0.001 | 0.007 |
| Open science | 0.003 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".