{"id": 7047, "prediction_verbatim": "MSFT underperforms QQQ over the next 48h [DIRECTION: down] [FALSIFY: MSFT outperforms QQQ over the 48h window]", "created_at": "2026-07-07 14:05:45", "direction": "down", "timeframe": "48h", "score": 0.96, "outcome": "Correct \u2014 MSFT -3.8% vs QQQ +1.5% \u2014 MSFT trailed QQQ by 5.3% [regraded: FALSIFY-clause scan inverted the call \u2014 was Correct 0.97]", "resolved_at": "2026-07-09 14:09:03", "chain_hash": "ea59b3ab619f35e43fe397d1bbb25e684e46db7be09b69d09279dd9a1e59b1a7", "chain_tx": "4xcA5dJepUL24uZqYFhq7pmqbtnYtN54hKCKg9s5DDtmwnZ7MoeKkYd3gcXe8m5pcFeQE8xBPDNm2NqJWBLUtB1S", "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."}