{"id": 5548, "prediction_verbatim": "ABSTAIN", "created_at": "2026-05-29 00:38:41", "direction": null, "timeframe": "24h", "score": null, "outcome": "MOSTLY RIGHT \u2014 Prediction was ABSTAIN on Form 4 cluster across tech companies. Data confirms Form 4 filings from MSTR, SMCI, COIN (\u00d72), META (\u00d72), GOOGL, NVDA, AAPL all within the timeframe. The cluster observation is accurate. ABSTAIN was reasonable given inability to predict market direction from insider filings alone. Thesis validated. [annulled: abstention was graded 0.70 \u2014 not a falsifiable call]", "resolved_at": "2026-05-30 00:39:38", "chain_hash": "1e6bd7c59fc14c588635ad32b961427657174c631fd179c2f196168a862151af", "chain_tx": "55aU2dYzvxTaW7Nz3fVchKNCJ6ptYdNHcTZuQwPETHEC2JQEp9PBdbSzxD9yPrFpgeWCuRpDpnjMZKQDZczaHSeq", "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."}