OSCBench: Benchmarking Object State Change in Text-to-Video Generation

arXiv 2026 22.9 benchmark, application

TLDR

Introduces OSCBench, a benchmark evaluating object state changes in text-to-video generation; models struggle with accurate state transformations.

Reasoning

Strengths: addresses an underexplored aspect of action understanding, uses systematic categorization and dual evaluation (human+MLLM). Weaknesses: limited to instructional cooking data and only six models, potentially narrow domain; no discussion of broader generalization beyond cooking.

Read-first score

Read-first score 22.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 7.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,evaluation,result

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Topical relevance 29%

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Citation impact 18%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 29.

Keyword Scores

world dynamics prediction

video world model

world model

world simulator

generative world model

interactive world model

model-based reinforcement learning world model

Resources

Paper