# Stable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice Evaluation

arXiv: https://arxiv.org/abs/2610.08649 · HTML: https://mlsanity.com/paper/2610.08649/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [MiMo-VL Technical Report](https://mlsanity.com/paper/2506.03569/) (2025)
- [Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models](https://mlsanity.com/paper/2510.10104/) (2025)
- [Frame Sampling Strategies Matter: A Benchmark for small vision language models](https://mlsanity.com/paper/2509.14769/) (2025)
- [Hearing the Order: Investigating Position Bias in Large Audio-Language Models](https://mlsanity.com/paper/2510.00628/) (2025)
- [TempCore: Are Video QA Benchmarks Temporally Grounded?](https://mlsanity.com/paper/2509.01167/) (2025)
- [When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding](https://mlsanity.com/paper/2606.08239/) (2026)
- [Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs](https://mlsanity.com/paper/2608.07014/) (2026)
- [PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs](https://mlsanity.com/paper/2511.10979/) (2025)
- [Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models](https://mlsanity.com/paper/2606.26079/) (2026)
- [Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models](https://mlsanity.com/paper/2608.03160/) (2026)
- [Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs](https://mlsanity.com/paper/2609.03820/) (2026)

## Abstract (arXiv)

Video-language models are ranked by multiple-choice accuracy on frames from a uniform grid. The grid has two parameters, a rate and a phase, and benchmarks report only the rate. The phase moves answers: two deployed samplers differing only by a half-step phase offset answer 23.6% of questions differently while scoring within a point, and across four releases from two families shifting only the phase changes roughly one answer in five after controlling option order. PHASEFUSION decodes three offset grids and averages the option posteriors. The grids are the polyphase components of the dense grid. Fusion matches a 32-frame single pass in accuracy within a prespecified margin (logit-scored) and cuts the answers a half-step shift of all three grids changes from 18.2% to 10.1%. Option order, which changes only the presentation, is flagged instead by a one-pass answer margin. Report the phase convention with the budget, or marginalize it.