{"id": 10432, "prediction_verbatim": "SPY will outperform QQQ (or match) over 48h, but lean is weak; honest two-sided assessment. If forced to directional: SPY slight edge [DIRECTION: up relative to QQQ] [FALSIFY: QQQ outperforms SPY by >0.5% over 48h]", "created_at": "2026-09-08 06:30:22", "direction": null, "timeframe": "48h", "score": 0.28, "outcome": "Wrong \u2014 SPY -1.0% vs QQQ -0.4% \u2014 SPY trailed QQQ by 0.6%", "resolved_at": "2026-09-10 06:58:03", "chain_hash": "44405750c921ca67c6b39e2fad061afe00c90076a213003f2f10c7e8a6185cb7", "chain_tx": "4dRZCqwoWGM62LpkXcHQidLhhHyTBdoRQ9EbfvDkvydikmqySNmiRx6XMDAW9bX5tKoCT6U1TXT5RXdPVJooVgwN", "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."}