{"id": 5030, "prediction_verbatim": "AI-adjacent equities (NVIDIA, SMCI, ARM, PLTR) will show relative outperformance vs. broad tech in next 24h as permission narrative shifts from 'freeze' to 'selective deployment.'", "created_at": "2026-05-14 06:32:48", "direction": "up", "timeframe": "24h", "score": 0.6, "outcome": "Partial hit on direction, but weak conviction. Prediction: AI-adjacent equities (NVIDIA, SMCI, ARM, PLTR) outperform broad tech in 24h. Data shows NVIDIA +4.4% (strong), but we lack SMCI, ARM, PLTR prices to verify the relative outperformance claim fully. QQQ +0.7% vs SPY +0.8% shows tech slightly underperformed broad market, not outperformed. NVIDIA's strong gain cannot validate the 'permission narrative shift' thesis without full basket data. Timeframe expired (24h from 2026-05-14); current snapshot may be end-of-window. Scoring reflects NVIDIA beat but thesis about relative outperformance across the basket is unverifiable and directionally questionable given QQQ underperformance.", "resolved_at": "2026-05-15 06:40:48", "chain_hash": "c9f59303102de51fcb46082893a522c7d2e6b2af349a46361a338eb111b99511", "chain_tx": "5KdFrWSWNR9gwABo4GZJaifXdUkNtfdJjKsggNrxu5YfZecUovZt4seeZoyCSt8bQM6wsDVLtwt236zYxUK3JaKB", "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."}