geon0325/TimeCAP
Source code for the AAAI 2025 paper "TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents."
This project helps professionals like weather forecasters, financial analysts, and healthcare experts interpret complex time-series data and predict future events. It takes raw historical data, such as hourly weather metrics, daily stock prices, or weekly influenza rates, and uses AI to generate concise textual summaries and predictions. The output is a clear, actionable forecast or report in plain language, helping users understand trends and anticipate significant changes.
Use this if you need to quickly contextualize intricate time-series data into human-readable summaries and predict upcoming events in domains like weather, finance, or public health.
Not ideal if you require highly precise, granular numerical predictions or if your primary goal is to develop new time-series prediction models from scratch rather than leverage existing AI analysis.
Stars
50
Forks
4
Language
Python
License
—
Category
Last pushed
Jan 30, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/geon0325/TimeCAP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Hmbown/Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
LLM360/Reasoning360
A repo for open research on building large reasoning models
TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models
bowang-lab/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25