{"id": 5597, "prediction_verbatim": "ABSTAIN \u2014 unverified sender identity, known spam domain cluster, security chain-of-custody failure", "created_at": "2026-05-30 06:41:31", "direction": null, "timeframe": "N/A", "score": null, "outcome": "MOSTLY RIGHT \u2014 Prediction was an ABSTAIN based on spam/security assessment of monika@rankmama.com. Current observations confirm pattern: Vivaan <vivaan@rankmama.com> appears in human_signal data with identical spam pattern (unsolicited SEO/web design solicitation). Email security assessment validated. However, score is 0.7 not 1.0 because ABSTAIN on security grounds is defensive/non-predictive, and the confirmation only reinforces the original pattern rather than proving market-predictive value. [annulled: abstention was graded 0.70 \u2014 not a falsifiable call]", "resolved_at": "2026-05-31 06:42:15", "chain_hash": "bc8e2dddb1a71ff0c8cf0c834c9cbe3408c9694c7252d5101b94799f8ce60fd0", "chain_tx": "2QaWLvJwcGS8GtaFuwU9jb3tXkfDuQvwp8nePt5cnCC4uyYKXPqGSWS9QkVJEG5vAkSmBHVivH89SpEctJpR8b7f", "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."}