Time-Series Foundation ModelsSN91

Cascade
SOTA time-series foundation models on Bittensor

Bitstarter is Bittensor's crowdfunding platform — teams raise TAO; backers get subnet tokens.

The simplest explanation

Like Kickstarter for Bittensor startups: invest TAO and get new subnet tokens at pre-launch.

Everything you need to understand Cascade

No jargon. No whitepapers. Just the facts.

The Problem

Time-series foundation models are bottlenecked by synthetic training-data quality, but that quality is normally impossible to measure in isolation because architecture and hyperparameters vary between attempts.

What Cascade Does

Bitstarter is Bittensor's crowdfunding platform — teams raise TAO; backers get subnet tokens.

The Edge

Fixes the model (Toto2-4M) byte-for-byte so the synthetic data generator is the sole variable, turning data-quality into a directly measurable, competable quantity.

What's the closest mainstream equivalent?

The best way to understand a new technology is to compare it to something familiar.

Mainstream
Amazon Chronos / Google TimesFM / Nixtla TimeGPT
Centralized & controlled
Single company profit
Terms can change anytime
VS
Bittensor
Cascade
Decentralized & open
Rewards flow to miners
No single point of failure

Fixes the model (Toto2-4M) byte-for-byte so the synthetic data generator is the sole variable, turning data-quality into a directly measurable, competable quantity.

How does Bittensor make this possible?

Cascadeuses Bittensor's incentive layer to build something no single company could run alone.

01

Miners compete

Participants (called miners) on the Cascade subnet compete to produce the best outputs for time-series foundation models tasks. Anyone with the right hardware can join.

02

Validators score the work

Validators continuously evaluate miner outputs against objective benchmarks. The best performers rise, the worst are replaced. There's no human committee — the protocol decides.

03

Rewards flow to the best

Miners are paid in the Cascade alpha token in proportion to how good their work is. This creates a continuous competitive pressure that drives quality up and cost down — structurally, not just as a promise.

04

The whole network benefits

Because every participant is aligned toward the same goal — producing the best time-series foundation models results — the network improves continuously without requiring a central team to manage it.

Frequently Asked Questions about Cascade

What is Cascade on Bittensor?

Cascade is Subnet 91 (SN91) on the Bittensor network — a decentralized AI protocol built on the TAO blockchain. Bitstarter is Bittensor's crowdfunding platform — teams raise TAO; backers get subnet tokens.

What problem does Cascade solve?

Time-series foundation models are bottlenecked by synthetic training-data quality, but that quality is normally impossible to measure in isolation because architecture and hyperparameters vary between attempts.

How is Cascade different from Amazon Chronos / Google TimesFM / Nixtla TimeGPT?

Fixes the model (Toto2-4M) byte-for-byte so the synthetic data generator is the sole variable, turning data-quality into a directly measurable, competable quantity.

What is the Cascade token?

The Cascade subnet has its own alpha token on Bittensor's dTAO system. It trades in the Bittensor liquidity pool and its price reflects market demand for the subnet's services.

Is Cascade a good investment?

AlphaGap tracks Cascade using its aGap score — a composite of development activity, token flow, and social signals. This page is for informational purposes only and is not financial advice. Always do your own research before making any investment decisions.

Want real-time intelligence
on Cascade?

AlphaGap tracks signals, whale flows, developer commits, and the aGap score for every Bittensor subnet — updated continuously. Find the alpha gap before everyone else.

Free preview · Pro from $29/mo · Premium from $49/mo