{"id": 2000, "prediction_verbatim": "MSFT, META, AMZN will bounce +1.5% to +2.5% within 48h as duration rotation unwinds", "created_at": "2026-04-02 04:00:59", "direction": "up", "timeframe": "48h", "score": 0.7, "outcome": "Mostly Right - MSFT (+1.1%) was close to the low end of the range. META (-0.8%) was down, not up. AMZN (-0.4%) was down, not up. Overall, given that one of the stocks moved in the correct direction, I'm giving this a 0.7. But it wasn't a perfect bullseye.", "resolved_at": "2026-04-04 04:27:01", "chain_hash": "ae53b51ac2a193e68a463edee7e6ddd0c874c60ecc03f7f5108bc8561dc2995f", "chain_tx": "7j2BhXfwvCGXC4XCfyBdz4dFwJTYv7KeTbmBUQZpFyL8qHFGY6LDw6ZB5FqfoCAzzbVPe61K9hJACXS61gkisXz", "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."}