A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels
Abstract
Reconstructing who infected whom often relies on case timing and published transmission links. However, two important questions remain: can a temporal pattern learned from other diseases transfer to a new outbreak, and how reliable are the transmission links used as ground truth? We learned a temporal prior from eleven disease groups using logistic regression. The model was locked before any target-outbreak data were accessed and was then tested without refitting on 29 Andes virus (ANDV) parent-ranking tasks. The locked prior achieved a mean reciprocal rank (MRR) of 0.571, compared with 0.274 for the strongest fair source-trained temporal baseline (permutation p<0.001). Its Top-1 accuracy was 37.9%, compared with 13.8%. The MRR advantage remained significant unless 7-8 favorable task outcomes were reversed. We separately examined the reliability of published transmission links. Among 75 epidemiologically linked inter-host pairs from the 2022 New York City mpox outbreak, 54.67% were genomically unresolved or unsupported as direct transmission links (exact 95% CI: 42.75-66.21%). We also tested whether retaining uncertain transmission edges changed source prioritization. In ANDV and Guangdong Delta outbreak graphs, the top-5 priority sets changed, with Jaccard similarity ranging from 0.429 to 0.667. These results show that temporal information learned across diseases can provide a useful ranking signal without target-specific refitting. They also show that uncertainty in published transmission links can affect which source cases are prioritized for investigation.
Related
- Uncertainty-Guided Decision-Making in Bumble Bees
- Contact heterogeneity in network reconstruction: evaluating synthetic graph generators for rabies transmission modeling
- Proactive early invisible spoilage-risk prediction through uncertainty-quantified temporal microbial growth intelligence
- Spatio-temporal dynamics, transmission hotspots, and vaccination gaps driving measles persistence in Nigeria, 2006–2025
- Dynamic interactions between sensory and decision-making circuits shape temporal evidence weighting
BibTeX
@misc{karim2026transferable,
title = {{A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels}},
author = {Md Ahsan Karim},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.30842},
eprint = {2606.30842},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.30842},
}
RIS
TY - UNPB
TI - A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels
AU - Md Ahsan Karim
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2606.30842
UR - https://arxiv.org/abs/2606.30842
AB - Reconstructing who infected whom often relies on case timing and published transmission links. However, two important questions remain: can a temporal pattern learned from other diseases transfer to a new outbreak, and how reliable are the transmission links used as ground truth? We learned a temporal prior from eleven disease groups using logistic regression. The model was locked before any target-outbreak data were accessed and was then tested without refitting on 29 Andes virus (ANDV) parent-ranking tasks. The locked prior achieved a mean reciprocal rank (MRR) of 0.571, compared with 0.274 for the strongest fair source-trained temporal baseline (permutation p<0.001). Its Top-1 accuracy was 37.9%, compared with 13.8%. The MRR advantage remained significant unless 7-8 favorable task outcomes were reversed. We separately examined the reliability of published transmission links. Among 75 epidemiologically linked inter-host pairs from the 2022 New York City mpox outbreak, 54.67% were genomically unresolved or unsupported as direct transmission links (exact 95% CI: 42.75-66.21%). We also tested whether retaining uncertain transmission edges changed source prioritization. In ANDV and Guangdong Delta outbreak graphs, the top-5 priority sets changed, with Jaccard similarity ranging from 0.429 to 0.667. These results show that temporal information learned across diseases can provide a useful ranking signal without target-specific refitting. They also show that uncertainty in published transmission links can affect which source cases are prioritized for investigation.
ER -