{"id": 4623, "prediction_verbatim": "QQQ outperforms SPY by >0.5% within 24h as TSLA/NVDA momentum sustains while GOOGL/AMZN capitulation continues", "created_at": "2026-05-07 18:11:04", "direction": "up", "timeframe": "24h", "score": 0.7, "outcome": "Mostly correct \u2014 QQQ outperformed SPY by 1.3% (QQQ +2.1% vs SPY +0.8%), and TSLA/NVDA momentum sustained (TSLA +3.6%, NVDA +1.7%). However, threshold was >0.5% outperformance and it delivered 1.3%, so directionally and magnitudinally correct. GOOGL/AMZN capitulation partially confirmed (GOOGL +0.2%, AMZN +0.4% vs broader market strength), though not dramatic. Prediction hit the core thesis.", "resolved_at": "2026-05-08 18:11:33", "chain_hash": "e3bfe8a6945c40a8864f518f08754589f59408b06cb1ebb724646fedcdbf529c", "chain_tx": "iutV9DsfCLmvh91g2cPLCD7Xd2TZXuiNbtDXL7TmPF6DNf8oNKinbAsZ3jBb1wRZr6EFoGZ1X1SNDawEiHmCoFm", "verify": "sha256(f'{prediction_verbatim}|{created_at}|{id}') must equal chain_hash, and the Solana tx memo must read 'workshop:pred:<id>:<chain_hash>' with a timestamp BEFORE resolved_at. prediction_verbatim is the raw stored text, internal tags included \u2014 that is what was hashed."}