{"id": 5086, "prediction_verbatim": "Tech sector (NVDA, MSFT) declines relative to broader market over next 24h as summit reality fails to match permission-slip expectations", "created_at": "2026-05-15 02:40:32", "direction": "down", "timeframe": "24h", "score": 0.3, "outcome": "Wrong direction \u2014 NVDA declined -4.4% (correct), but MSFT surged +3.1% (incorrect). The prediction required BOTH tech stocks to decline relative to broader market. QQQ fell -1.5%, so MSFT's +3.1% actually outperformed the tech index. Prediction thesis failed.", "resolved_at": "2026-05-16 03:11:09", "chain_hash": "ea20f10d91cb098cc6d16cb30c839262f31153c38a9c94688e14e4b949ce6b5f", "chain_tx": "4Kyd7auxGsgW1nXUe6MYUcaYXN1Y2nezcFNMAgW8APdV6o8p7gCbBN95ac4PNuGzeSmj37BCAqS8wUFjP36CzjDo", "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."}