- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes verifiable meta-detection for AI-generated video detection: beyond label-level rewards, the VLM detector (built on Qwen3.5-9B) outputs evidence in the form of temporal grounding, i.e., intervals where forgery artifacts occur, and is trained with reinforcement learning under EGRR. Evidence verification is rule-based computation (tIoU ≥ 0.7 against ground-truth intervals created by controlled construction); no reference model is needed at reward time, although the textual-evidence training subset is filtered by Gemini-3.1-Pro. Experiments cover held-out tests on five in-domain generators (ViF-Bench) and the external GenBuster-Bench. On ViF-Bench, Label-Tem-RL improves over Label-RL by 10.38% accuracy and over the textual-evidence route (Label-Exp-RL) by 7.06% accuracy; temporal grounding success rate rises e.g. from 26.5 to 79.5 on the LTX-Video-2B column (a 3.0–3.7x ratio across generators, range 61.5–79.5); on the fake-only GenBuster-Bench subset the paper reports Recall improvements of 7.0% (OOD) and 11.4% (Wild).
Critical strengths
- The problem framing is clear and valuable. Many prior explanation-producing detectors rely on teacher- or annotator-derived evidence that cannot be verified by rule; recasting detection supervision as "evidence that can be mechanically verified" is directly relevant to AI-generated content governance, where auditability of detection reports is a practical requirement.
- The supervision signal is cleanly designed and formally supported. Ground-truth intervals come from the controlled construction process and verification is pure rule computation (tIoU), so the signal is auditable at reward time. EGRR's redistribution design carries conservation, strict ordering, and anti-multiplicative-collapse properties (Appendix A), and the paper is careful to note these do not assert policy-gradient preservation. The temporal-grounding gains are large and consistent across generators.
Critical weaknesses
- EGRR lacks an isolated ablation. The +10.38% accuracy gain is a bundled comparison (Label-RL vs. Label-Tem-RL with EGRR, on ViF-Bench); the control variant "temporal grounding evidence + naive multiplicative reward (without EGRR)" is absent — the paper argues against multiplicative coupling only theoretically. Since EGRR is one of the four claimed contributions, its independent contribution over the evidence signal itself is not isolated empirically.
- The closest peer baselines are absent, and reported variance is incomplete. VidGuard-R1 (RL with specialized temporal-artifact rewards) appears in neither the main tables nor anywhere in the experiments, and the explanation-based line (DAVID-XR1, DeepTraceReward, VideoVeritas) is not compared under the same protocol either. Results are averaged over three random seeds, but no variance or significance tests are reported, so whether the 7.06% accuracy gain of Label-Tem-RL over Label-Exp-RL exceeds seed noise cannot be verified from the paper.
Questions for authors
- Can you add the control variant "temporal grounding evidence + naive weighted/multiplicative reward (without EGRR)" to isolate EGRR's independent contribution?
- How do VidGuard-R1 / VideoVeritas perform under your evaluation setting? If not reproducible, please explain why.
- Can the key comparisons (the 7-point gap at ladder step 3→4, and the bundled EGRR gain) be reported as multi-seed mean ± variance?
- At inference time on wild fake videos there is no ground-truth interval. How does evidence verifiability degrade? Could a small-scale human audit (e.g., plausibility of predicted evidence intervals on 200 external samples) support this?
- The controlled construction replaces segments with content aligned in duration, resolution, and frame rate on 5-second clips, so duration shortcuts appear controlled — but could splice-boundary or re-encoding discontinuities introduced by the replacement act as shortcuts? Was a shortcut audit performed?
3 comments
Response to Reviewer MSa1 (Part 2/2)
Q3: Can the key comparisons (the 7-point gap at ladder step 3→4, and the bundled EGRR gain) be reported as multi-seed mean ± variance?
A3: Thank you for your valuable suggestion. To further validate the robustness of our method, we conduct three independent trials with different random seeds. The results are presented in the following table:
Table 4: Performance on ViF-Bench and GenBuster-Bench under Different Random Seeds.
| Method | ViF-Bench Acc ↑ | ViF-Bench Recall ↑ | ViF-Bench F1 ↑ | ViF-Bench FPR ↓ | GenBuster-Bench Acc ↑ | GenBuster-Bench Fake Recall ↑ | GenBuster-Bench F1 ↑ | GenBuster-Bench FPR ↓ |
|---|---|---|---|---|---|---|---|---|
| Qwen3.5-9B | 46.25 | 7.17 | 11.11 | 14.67 | 69.9 | 56.7 | 62.4 | 16.8 |
| + Label-RL | 72.80 | 63.89 | 70.15 | 18.29 | 86.2 | 83.0 | 84.5 | 10.4 |
| + Label-Exp-RL | 76.12 | 67.58 | 73.90 | 15.34 | 89.9 | 86.3 | 88.6 | 6.2 |
| + Label-Tem-RL (Ours) | 83.18 ± 0.12 | 72.86 ± 0.14 | 81.24 ± 0.19 | 6.50 ± 0.28 | 95.5 ± 0.28 | 93.3 ± 0.30 | 95.0 ± 0.33 | 2.5 ± 0.39 |
As shown in Table 4, our method consistently achieves improvements with low variance across different random seeds, demonstrating the stability and reproducibility of our approach.
Q4:At inference time on wild fake videos there is no ground-truth interval. How does evidence verifiability degrade? Could a small-scale human audit (e.g., plausibility of predicted evidence intervals on 200 external samples) support this?
A4: Thank you for your constructive suggestion. To further evaluate the forensic localization capability of VidForensics-M1 in real-world scenarios, we randomly select 200 fake videos from ViF-Bench and predict their forgery intervals. Four authors then manually inspect 50 intervals each for visible AI-generated artifacts. The results are presented in the following table:
Table 5: Human Verification of Visible AI-Generated Artifacts in Predicted Forgery Intervals.
| Method | Author 1 | Author 2 | Author 3 | Author 4 |
|---|---|---|---|---|
| + Label-Tem-RL (VidForensics-M1) | 82% | 78% | 86% | 84% |
These human-verified results further demonstrate the effectiveness of VidForensics-M1 in OOD scenarios, showing that our method can identify meaningful AI-generated artifacts in real-world videos. This provides additional evidence of the reliability of our forensic localization capability and highlights the practical value of VidForensics-M1 in real-world applications.
Q5:The controlled construction replaces segments with content aligned in duration, resolution, and frame rate on 5-second clips, so duration shortcuts appear controlled — but could splice-boundary or re-encoding discontinuities introduced by the replacement act as shortcuts? Was a shortcut audit performed?
A5: Thank you for your insightful question, and we sincerely apologize for the confusion. We would like to clarify that we standardize not only the resolution, frame rate, and duration of both real and fake videos, but also their encoding formats. To further investigate the impact of stitching artifacts on detection performance, we select 200 fake videos and evaluate VidForensics-M1 under two settings: using the complete stitched videos and extracting only the manipulated segments. The results are presented in Table 2 below.
Table 6: Performance of VidForensics-M1 With and Without Stitching Boundaries.
| Input Setting | Recall ↑ |
|---|---|
| Complete Stitched Video | 91.0% |
| Manipulated Segment Only | 89.5% |
The results show that VidForensics-M1 maintains effective detection performance even after removing the stitching boundaries, demonstrating that our method does not rely solely on stitching-specific shortcuts but instead learns meaningful AI-generated forensic cues for reliable detection and evidence localization.
Thank you again for your valuable time and encouraging feedback. We sincerely welcome any further questions or suggestions and would be pleased to engage in additional discussions to improve our manuscript.
Dear Reviewer MSa1,
With the discussion period nearing its end, we would greatly appreciate your feedback on whether our clarifications and supplementary experiments have adequately addressed your concerns. We welcome any further questions and sincerely appreciate your continued engagement.
Warm regards,
The Authors
Response to Reviewer MSa1 (Part 1/2)
Dear Reviewer MSa1:
We greatly appreciate your thoughtful review and encouraging assessment of our work. Your constructive suggestions have provided valuable insights into further improving the quality and rigor of our paper. Below, we provide detailed responses to each of your questions and suggestions, and all corresponding revisions to the manuscript are highlighted in blue for ease of reference. If you have any further questions, please feel free to let us know.
A1: Thank you for this valuable suggestion. We have included this important experiment in our revised manuscript to further validate the effectiveness of EGRR. Specifically, we compare EGRR with two naive reward strategies: Additive : 0.1 × Format Reward + 0.45 × Evidence Reward + 0.45 × Label Reward. Multiplicative : 0.1 × Format Reward + 0.9 × Evidence Reward × Label Reward. The experimental results are presented in Table 1 below:
Table 1: Effectiveness of EGRR Compared with Naive Reward Strategies.
As shown in Table 1, EGRR consistently outperforms both naive reward strategies in detection performance and temporal localization accuracy. These results demonstrate that EGRR effectively addresses the inherent asymmetry in evidence supervision between real and fake videos, where evidence rewards are only applicable to fake samples. By redistributing rewards among label-correct responses based on evidence quality, EGRR better integrates verifiable evidence feedback into label-level reinforcement learning, leading to more accurate detection and more reliable forensic evidence.
A2: Thank you for your valuable suggestion. We agree that comparing our method with VidGuard-R1 is important for highlighting the advantages of meta-detection. To ensure a fair comparison, we use the same 10K real videos and generators to construct 10K fake videos with each method's respective pipeline, yielding 20K training videos per method. We then train both models using their respective algorithms and evaluate them on ViF-Bench and GenBuster-Bench. The results are presented in Table 1 below:
Table 2: Comparison of VidGuard-R1 and VidForensics-M1 on ViF-Bench and GenBuster-Bench.
As shown in Table 2, VidForensics-M1 consistently outperforms VidGuard-R1 across all evaluation metrics under the same training data sources and scale. These results further demonstrate the importance of verifiable meta-detection feedback in improving the generalization ability of AI-generated video detectors.
For VideoVeritas, we evaluate its publicly released model weights on ViF-Bench and GenBuster-Bench using the same evaluation protocol as our method. The results are presented in the following table 3:
Table 3: Comparison of VideoVeritas and VidForensics-M1 on ViF-Bench and GenBuster-Bench.
As shown in the table, the consistent improvements over VideoVeritas across both benchmarks highlight the competitive performance of VidForensics-M1, further establishing its effectiveness in detecting OOD AI-generated videos.