DEpendable and ExpLainable Learning: from Research to Industry
Bibliographic record
Abstract
This paper presents the outcomes of the DEEL (DEpendable and Explainable Learning) program-an innovative Franco-Québec collaboration focused on enabling the safe and certifiable use of AI in safety-critical systems. Drawing on the experience and insights of the DEEL project, this paper examines key questions concerning the advancement of AI systems in safety-critical domains, focusing on their operational capabilities and the challenges associated with certification. We explore major challenges such as explainability, robustness, statistical guarantees, out-of-distribution detection, and fairness, and critically assess both the advances made and the limitations that remain-offering guidance for the continued development and certification of safety-critical AI systems. The DEEL program has not only produced novel and advanced research methodologies but has also resulted in multiple open-source libraries and datasets that bridge the gap between theoretical AI research and practical real-world applications. The insights and tools developed through the DEEL program demonstrate the potential for creating safer, more reliable, and more understandable AI systems, paving the way for further research in this important field.
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 | 0.021 | 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 | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 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".