ORACLE: Time-Dependent Recursive Summary Graphs for Foresight on News Data Using LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kharlashkin, Lev, Morooka, Eiaki, Tereshchenko, Yehor, Hämäläinen, Mika
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918252325634048
author Kharlashkin, Lev
Morooka, Eiaki
Tereshchenko, Yehor
Hämäläinen, Mika
author_facet Kharlashkin, Lev
Morooka, Eiaki
Tereshchenko, Yehor
Hämäläinen, Mika
contents ORACLE turns daily news into week-over-week, decision-ready insights for one of the Finnish University of Applied Sciences. The platform crawls and versions news, applies University-specific relevance filtering, embeds content, classifies items into PESTEL dimensions and builds a concise Time-Dependent Recursive Summary Graph (TRSG): two clustering layers summarized by an LLM and recomputed weekly. A lightweight change detector highlights what is new, removed or changed, then groups differences into themes for PESTEL-aware analysis. We detail the pipeline, discuss concrete design choices that make the system stable in production and present a curriculum-intelligence use case with an evaluation plan.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15397
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ORACLE: Time-Dependent Recursive Summary Graphs for Foresight on News Data Using LLMs
Kharlashkin, Lev
Morooka, Eiaki
Tereshchenko, Yehor
Hämäläinen, Mika
Computation and Language
ORACLE turns daily news into week-over-week, decision-ready insights for one of the Finnish University of Applied Sciences. The platform crawls and versions news, applies University-specific relevance filtering, embeds content, classifies items into PESTEL dimensions and builds a concise Time-Dependent Recursive Summary Graph (TRSG): two clustering layers summarized by an LLM and recomputed weekly. A lightweight change detector highlights what is new, removed or changed, then groups differences into themes for PESTEL-aware analysis. We detail the pipeline, discuss concrete design choices that make the system stable in production and present a curriculum-intelligence use case with an evaluation plan.
title ORACLE: Time-Dependent Recursive Summary Graphs for Foresight on News Data Using LLMs
topic Computation and Language
url https://arxiv.org/abs/2512.15397