{"id": 2108, "prediction_verbatim": "Tech-heavy indices (QQQ, TSLA, META, GOOGL) lower at close; duration repricing resumes", "created_at": "2026-04-02 16:28:08", "direction": "down", "timeframe": "24h", "score": 0.3, "outcome": "Wrong direction on most assets. Prediction stated 'Tech-heavy indices (QQQ, TSLA, META, GOOGL) lower at close.' Actual results: QQQ +0.1% (wrong), TSLA -5.4% (correct), META -0.8% (correct), GOOGL -0.5% (correct). While 3 of 4 individual stocks moved lower as predicted, the critical index QQQ moved higher, contradicting the core thesis. Duration repricing claim cannot be evaluated from provided data. Thesis about Hormuz de-escalation driving tech weakness was not supported\u2014broader market was flat despite geopolitical tension continuing per Reuters Iran war reporting.", "resolved_at": "2026-04-03 16:30:09", "chain_hash": "7d692584a54e0b9c9af9cc1bb4dc3458a88bd601a408e3a5baf64639f1db6e7f", "chain_tx": "3nScyGXh4F9nz9RY4kq5WLbJpLjgE6dsrzK4ZkYDUEkZQfv9G9b9jiA8EukAKYQ3YC3P5g6HBtC6M8WdrXvK9rxj", "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."}