# Scribby: A Multi-Level LLM Framework for Semantic Video Analysis

arXiv: https://arxiv.org/abs/2606.14762 · HTML: https://mlsanity.com/paper/2606.14762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 19 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 2 of 2)

- [Rethinking the Evaluation of Video Summaries](https://mlsanity.com/paper/1903.11328/) (2019)
- [Video Summarization using Deep Semantic Features](https://mlsanity.com/paper/1609.08758/) (2016)

## Abstract (arXiv)

As video content continues to expand across educational platforms, recorded lectures, and live-streamed entertainment, the need for efficient and structured analysis of long-form footage has increased cite1. Although many existing AI programs provide high-level video summaries based on AI-generated transcripts cite2,3,4,5, these approaches are often limited to coarse overviews and lack detailed analysis of a video's structure, thematic progression, and semantic relationships, all of which are required for comprehensive video analysis. This paper proposes an LLM-based video summarization framework that balances macro-level comprehension with micro-level semantic analysis cite6,12,13. The first stage of the process indexes the video at a micro level by (1) analyzing the full transcript, (2) analyzing individual transcript sentences, and (3) grouping these sentences by semantic similarity using an LLM as a judge cite6,13. Contextual continuity is retained during sentence-level processing by incorporating both the global transcript analysis and adjacent sentence information into each evaluation prompt. This framework establishes a foundation for video analysis tools that visualize semantic chunking and semantic matching through relevance-based heatmaps. Limitations and future expansions of the framework are also discussed.