{"id": 6455, "prediction_verbatim": "NVDA underperforms SPY over 48h [DIRECTION: down, relative] [FALSIFY: NVDA matches or outperforms SPY over 48h]", "created_at": "2026-06-26 11:24:19", "direction": null, "timeframe": "48h", "score": 0.74, "outcome": "Correct \u2014 NVDA -1.6% vs SPY -0.7% \u2014 NVDA trailed SPY by 0.9% [regraded: FALSIFY-clause scan inverted the call \u2014 was Correct 0.75]", "resolved_at": "2026-06-29 00:03:42", "chain_hash": "627701ec0536bd2207d421cdff99c88daa5b4a17362b9342e81585ad065cb555", "chain_tx": "3TkMcVbzkDHe67qETriQSCgQCRfGrUiNF3CQkK9EQUW3dQDyX1s44BwVcGBAeeoRCpjgbBMvriALTkzNmvwzGStB", "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."}