{"id": 6666, "prediction_verbatim": "GOOGL outperforms NVDA over 48h [DIRECTION: up] \u2014 consumer-facing AI monetization (Nano Banana, broader ad integration trend) should outpace upstream chip suppliers in current regime; my GOOGL (0.66) > NVDA (0.59) relative edge supports this. [FALSIFY: GOOGL underperforms NVDA or matches NVDA performance over 48h window.]", "created_at": "2026-06-30 18:02:57", "direction": "up", "timeframe": "48h", "score": null, "outcome": "Inconclusive \u2014 missing price for a leg", "resolved_at": "2026-07-02 21:09:47", "chain_hash": "4e5464335df8f06c354871bea0f6329ca3cab8ab823b8ff254ca2406bf612366", "chain_tx": "eUiPX4VYSoaCC78iwgN6dwAwimfM33oXkMDwGP5gJWmvYyy1MpvFP8ZoJ8qRRyjVLPPaMK492Hh59XNEdgQzAj4", "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."}