⌁ Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

TC-Bench: Benchmarking Temporal Compositionality in Conditional Video Generation

arXiv 2025 26.2 benchmark

Read-first score

Read-first score 26.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals.

Recency 6%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Citation impact 18%
84.5

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.84472696

Citation velocity 12%
14.2

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=1.00

Topical relevance 29%
11.8

Matches configured research keywords against title, abstract, tags, and analysis text. matched=2

Graph prestige 18%
5.7

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0016

Reproducibility 18%
0

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

Field roles

FoundationFrontier

Rank sensitivity

Stability: volatile; rank range: 603.

Tags