{"id": 8638, "prediction_verbatim": "MSFT outperforms SPY over 48h, but with low conviction. [DIRECTION: up] [FALSIFY: MSFT underperforms or matches SPY performance over 48h; AAPL weakness deepens to >\u22122% and broadens to GOOGL or NVDA]", "created_at": "2026-08-03 14:05:21", "direction": "up", "timeframe": "48h", "score": 0.22, "outcome": "Wrong \u2014 MSFT -0.2% vs SPY +2.4% \u2014 MSFT trailed SPY by 2.6%", "resolved_at": "2026-08-05 16:54:44", "chain_hash": "0767b82623e3dea5d8ab946554b97a76d2ac63364ac0be22065e8f28a3b03dd3", "chain_tx": "4Chwatuzg6Yjg24wD6gp8VtACHjknqAksUebZ3jXrernnd1aASh5154etL29xCpAL8rxBt835FA67kJ1WrfM276f", "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."}