aiqbench analysis
This research applies a variational autoencoder with cosine-similarity reconstruction to automatically extract causal factors from unstructured aviation safety narratives. By mapping investigation reports into a probabilistic latent space, the model achieves high semantic alignment with expert-determined probable causes while generating interpretable terms for safety analysis. The study demonstrates a viable pathway for using generative AI to assist in complex domain-specific investigations without replacing formal human oversight.
Semantic Causal-Factor Inference from Aviation Incident Narratives Using A Variational Autoencoder with Cosine-Similarity-Based Reconstruction
arXiv:2610.04472v1 Announce Type: new Abstract: Aviation accident and incident investigations generate extensive unstructured textual information containing evidence relevant to the causes and contributing factors of safety occurrences. Automatically extracting such information is challenging because causal evidence may be distributed across long and complex investigation narratives. This study proposes a semantic causal-factor inference framework combining natural language processing with a variational autoencoder (VAE) to learn the relationship between aviation investigation narratives and expert-reported probable causes. Investigation narratives and their corresponding probable causes are transformed into numerical representations, after which the encoder maps narrative representations to a probabilistic latent space. The decoder estimates representations of the corresponding probable causes and is trained using an objective that combines Kullback-Leibler divergence with cosine-similarity-based semantic reconstruction. The framework was evaluated using 20,919 finalized U.S. National Transportation Safety Board investigation reports from 2005 to 2020. On the held-out test set, the predicted and expert-reported probable-cause representations achieved a mean cosine similarity of 0.786 (SD = 0.120). The predicted representations also yielded interpretable terms associated with causal information in the reports. The results demonstrate the potential of probabilistic latent representation learning for AI-assisted extraction of causal information from aviation safety narratives while retaining expert investigation as the basis for formal causal determination.
Abstract:Aviation accident and incident investigations generate extensive unstructured textual information containing evidence relevant to the causes and contributing factors of safety occurrences. Automatically extracting such information is challenging because causal evidence may be distributed across long and complex investigation narratives. This study proposes a semantic causal-factor inference framework combining natural language processing with a variational autoencoder (VAE) to learn the relationship between aviation investigation narratives and expert-reported probable causes. Investigation narratives and their corresponding probable causes are transformed into numerical representations, after which the encoder maps narrative representations to a probabilistic latent space. The decoder estimates representations of the corresponding probable causes and is trained using an objective that combines Kullback-Leibler divergence with cosine-similarity-based semantic reconstruction. The framework was evaluated using 20,919 finalized U.S. National Transportation Safety Board investigation reports from 2005 to 2020. On the held-out test set, the predicted and expert-reported probable-cause representations achieved a mean cosine similarity of 0.786 (SD = 0.120). The predicted representations also yielded interpretable terms associated with causal information in the reports. The results demonstrate the potential of probabilistic latent representation learning for AI-assisted extraction of causal information from aviation safety narratives while retaining expert investigation as the basis for formal causal determination.
Artificial Intelligence (cs.AI)
arXiv:2610.04472 [cs.AI]
(or arXiv:2610.04472v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.04472 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 294 words
Related coverage
Advanced modelling and data analytics in aviation
arXiv · Aug 18, 2026
LiveLaw Supreme Court Half-Yearly Digest: January - June 2026 [Part 2]
livelaw.in · Sep 13, 2026
The current bottleneck is political will, not research
AI Alignment Forum · Jul 11, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026