# Decision Readouts for Text-Mediated Video Anomaly Detection: An Exploratory Evaluation of Jev and Qwen

arXiv: https://arxiv.org/abs/2609.34180 · HTML: https://mlsanity.com/paper/2609.34180/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Harnessing Large Language Models for Training-free Video Anomaly Detection](https://mlsanity.com/paper/2404.01014/) (2024)
- [Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection](https://mlsanity.com/paper/2505.15205/) (2025)
- [A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection](https://mlsanity.com/paper/2608.21244/) (2026)
- [Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection](https://mlsanity.com/paper/2609.17211/) (2026)

## Built on by (most cited first, 1 of 1)

- [VideoJev: System One Model for Video Understanding and Interaction](https://mlsanity.com/paper/2610.18615/) (2026)

## Abstract (arXiv)

How much does the decision readout matter when video-derived textual evidence is held fixed? We evaluate Jev typed decisions and three Qwen readouts on a sparse development sample of 40 videos and 400 target anchors from UCF-Crime and XD-Violence, each presented as a summary and ordered captions. Each dataset contributes 20 source groups and 200 anchors, including only 10 and 37 positives, respectively. The original five-backend pilot requested 4,000 predictions; Jev Choice returned 776 valid responses out of 800 under the study's strict numerical policy, blocking its full-coverage quality comparison. On XD captions, Jev Noul achieved 75.99% average precision versus 48.47% for Qwen generated probability and 57.81% for the stronger local ordinal-likelihood expectation. The latter paired difference was 18.18 percentage points (95% source-group bootstrap interval 5.53-31.50). UCF did not show a corresponding advantage: caption ROC-AUC was 52.26% for Noul and 65.95% for ordinal likelihood. Both probability readouts had higher, hence worse, UCF Brier scores than the evaluation-prevalence reference of 0.0475. We additionally audit historical LAVAD scores at exactly matched anchors and distinguish response structure from numerical consistency. A binary-likelihood control is missing. These exploratory offline results characterize ranking, probability quality and interface failures; they establish neither a causal typed-interface benefit nor general superiority, calibration or end-to-end acceleration.