@citrini · 455 verified calls backtested

Inconclusive

@citrini's high-conviction long calls have beaten their sector by 0.6% on average in the month after each call, winning 45% of the time.

+0.0%

1 day

+0.6%

1 month

-1.4%

3 months

Avg. market-beating return

per call · vs the stock's own sector

45%

Calls that beat the market

based on 106 high-conviction long calls

45% beat their sector 55% didn't

The signal is indistinguishable from noise.

Performance over time

After	vs sector	vs S&P 500	Hit rate	Calls
1 day	+0.6%	+0.6%	48%	416
1 month	+0.7%	+0.7%	47%	393
3 months	+1.5%	+1.7%	48%	349
6 months	+5.1%	+4.5%	48%	317

“vs sector” compares each call to the stock's own industry — the fairest test of skill.

What drives the signal

Does conviction matter?

High conviction138 calls · 43% hit

-0.3%

Low conviction255 calls · 49% hit

+1.3%

Return by post type

Analysis73 calls · 67% hit

+5.9%

Position Disclosure82 calls · 46% hit

-0.0%

Prediction230 calls · 43% hit

-0.3%

Sarcasm6 calls · 0% hit

-10.1%

Long vs short

Long312 calls · 50% hit

+1.6%

Short81 calls · 38% hit

-2.7%

Best & worst calls

Biggest wins (after 1 month)

RENT

“Now is the part of the cycle where you find businesses that are priced like they will die and then make money when it turns out they aren't ”

Long · low conviction · 2024-04-10 · View on X ↗

Full post

Now is the part of the cycle where you find businesses that are priced like they will die and then make money when it turns out they aren’t going to die (even if the business is still kinda meh) $RENT https://t.co/eSKmdlC3JF

+83.4%

BAND

“Some really strong results from a pair of our "Agentic Utility" names today ($BAND & $TWLO)”

Long · low conviction · 2026-04-30 · View on X ↗

Full post

Some really strong results from a pair of our “Agentic Utility” names today ($BAND & $TWLO) - playing the infrastructure angle on AI has been great, but it’s pretty nice to see some mentions of AI driving earnings beats outside of the semis complex. https://t.co/bWl8biW5sq

+71.2%

BLBD

“BLBD earnings were really amazing by every metric”

Long · low conviction · 2024-05-08 · View on X ↗

Full post

Two overweighted stocks in the Citrini Research core portfolio showing up today for earnings: BLBD & ESTA. BLBD earnings were really amazing by every metric. ESTA still has lots of upside from Motiva in the US by eoy.

+54.0%

Biggest misses (after 1 month)

AIRS

“AIRS is still down from the momentum unwind going into a print that I think will be better than ESTA's and has >40% short interest”

Long · high conviction · 2025-11-05 · View on X ↗

Full post

A lot of the cosmetic/aesthetics winners of the GLP-1 trend have had serious volatility and are heavily shorted on stale consumer theses. ESTA had 20% short interest going into the print and is up 15% on okay earnings. AIRS is still down from the momentum unwind going into a print that I think will be better than ESTA’s and has >40% short interest…

-70.7%

MSTR

“now up 11% on the second short attempt”

Short · high conviction · 2024-03-05 · View on X ↗

Full post

4% stop loss hit the first time around now up 11% on the second short attempt. do you see how this works? being wrong is fine if you make enough to make it not matter when you’re right.

-50.1%

oil

“Put on a cheeky little oil short with a tight stop before going to sleep”

Short · low conviction · 2026-03-09 · View on X ↗

Full post

Put on a cheeky little oil short with a tight stop before going to sleep let’s see what the morning has in store for me. --- Took enough of it off to mean something and moved my stop to entry, gn boys time to monitor the situation even harder tomorrow

-34.9%

See every call for yourself — filter by conviction or direction, switch the time horizon, and chart any single trade.

Explore the Analysis →

How we measured this · download the raw data

We pulled @citrini's post history, used AI to extract each investment call (ticker, direction, conviction), and backtested every call against real price history. “Beating the market” means out-performing the stock's own sector over the month after the post — so a call only counts as a win if it beat a fair benchmark, not just if the stock rose. The headline numbers use the cleanest signal: high-conviction long calls.

Download the full backtest data (JSONL)

Backtested results are computed from historical price data and do not predict future performance. Every signal here is extracted automatically from public posts and may misread intent, sarcasm, or context. This is not investment advice — verify everything independently before acting on it.