Can we recognize a recovery starting?

The verdict

Three exchange-data bottoming signs did worse than none in this test.

What we tried

After a large decline, we checked three exchange-data signs intended to describe a recovery beginning. More signs should have helped if the idea worked.

What happened

Coins with all three signs beat the typical coin 42% of the time in 2020–2024 and 33% in 2025–2026. Coins with none did so 47% and 44% of the time. The three-sign group did worse in every tested year except 2020.

What this means

This implementation used exchange-data proxies. It does not refute Sparsity’s on-chain approach or its DEX memecoin setting. A failed proxy is a failed proxy, not a verdict on every possible bottoming signal.

Evidence record

Published figures are from the original experiment summaries and the approved research handoff, dated October 7, 2026. They describe the implementation tested, not every version of the underlying idea.

Keep exploring