Multi-modal Causal RAG for Aviation Accident Analysis and Risk Prediction
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
Aviation safety analysis has traditionally relied on structured reports and expert-driven causal reasoning. Under-standing aviation accident requires a holistic approach that integrates multi-modal data, including textual reports, images, and structured knowledge representations. This paper proposes a novel multi-modal retrieval and analysis framework that integrates Natural Language Processing (NLP), Causal Relation Extraction, CLIP-based image embedding, and Latent Con-textual Modeling (LCM) with Retrieval-Augmented Generation (RAG) to link textual and visual aviation accident evidence. The system enables users to upload new incident images, such as those from newspapers or social media, and automatically match them with similar historical accidents, revealing causes and contributing factors through generative explanation. This pipeline demonstrates the feasibility of a next-generation decision-support tool for aviation safety that is interpretable, context-aware, and multi-modal. Experimental results demonstrate that our model effectively identifies and aligns latent representations across modalities, while the LLM generates coherent, contextually grounded explanations.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| 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