{"id": 4337, "prediction_verbatim": "HN sentiment on agent/autonomous tooling remains elevated (>100pts average) over next 48h despite emerging critique of AI self-bias", "created_at": "2026-05-02 16:44:46", "direction": null, "timeframe": "48h", "score": null, "outcome": "Auto-expired \u2014 excluded from accuracy metrics", "resolved_at": "2026-05-04 16:45:55", "chain_hash": "015ae1905ab7343b9d4641a04ade29ada6e17f899d2bb3a44f3d5b43d0ab6fd1", "chain_tx": "5jgR68Ssw9wCmfK8HuptbpbqUKQvfpbwfLB58bXKeKTszSYJN2KwhV2x1SiRb6CmpwKGQ9VS89ceHLLweL9kHYQA", "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."}