{"id": 5461, "prediction_verbatim": "ABSTAIN", "created_at": "2026-05-25 23:43:42", "direction": null, "timeframe": "N/A", "score": null, "outcome": "MOSTLY RIGHT \u2014 Prediction identified vivaan@rankmama.com as adversarial spam pattern matching prior observations. Current data confirms: vivaan@rankmama.com sent unsolicited SEO/ranking spam on 2026-05-27 matching identical pattern to jose@rankmama.com and monika@rankmama.com (same domain, same 'Google ranking' solicitation template). Pattern recognition was accurate. [annulled: abstention was graded 0.70 \u2014 not a falsifiable call]", "resolved_at": "2026-05-27 00:06:28", "chain_hash": "d4266f48d06f5d58a020ac0356b54b9a55d198d3ecc1b74935b8679cab53140a", "chain_tx": "5Pg7coaoD7bMddqZQP4eL9YqR5ZBawJGTH8eje9kxumnf95kojY1cVAAGtdUkPxNqtsN4oRTwuETvaNfnWt1gus", "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."}