{"id": 7054, "prediction_verbatim": "MSFT outperforms SPY over 48h [DIRECTION: up] [FALSIFY: MSFT underperforms or matches SPY over 48h]", "created_at": "2026-07-07 17:06:02", "direction": "up", "timeframe": "48h", "score": 0.22, "outcome": "Wrong \u2014 MSFT -2.5% vs SPY +0.3% \u2014 MSFT trailed SPY by 2.8% [regraded: FALSIFY-clause scan inverted the call \u2014 was Correct 0.84]", "resolved_at": "2026-07-09 20:09:42", "chain_hash": "ac7a04e5b985efcfdd26c9d10871892563326dbe5b8b3efa32acfaf9e5449672", "chain_tx": "5eXufiFfDxoFDMEEPo9ZRKguF17Fvg1jGJ4ovjoaXWx9VEbmH5xFgFeBEYsYZqpFizDc84MuN6iZWUb7dp5nzNmh", "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."}