{"id": 5481, "prediction_verbatim": "ABSTAIN \u2014 intraday mega-cap divergence (5 of 6 names up, 2 down) insufficient to predict index direction without cross-asset catalyst quantification. No earnings surprise, guidance revision, or identified macro event timing.", "created_at": "2026-05-27 18:06:23", "direction": null, "timeframe": "ABSTAIN", "score": null, "outcome": "Mostly Right - The model correctly identified the divergence among mega-cap tech stocks and abstained from predicting overall market direction. The market ended up slightly positive (SPY +0.5%, QQQ +0.8%), so abstaining was a reasonable decision given the mixed signals. Some mega caps were up (MSFT, NVDA), while others were down (META) or had minimal changes (AAPL). [annulled: abstention was graded 0.70 \u2014 not a falsifiable call]", "resolved_at": "2026-05-28 18:36:37", "chain_hash": "5d7b349a214f1a45d0169aa494dc8359885cd00c350a5a46da9af2a7a783f3d5", "chain_tx": "2akWKxiQLZ7zoAD2MHporHaL1omQdbkLxTyQDm9i9iKzUymJQwWdoQoYU1dHjCx3k81sTHZYkVEEc6zPXb5U65cE", "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."}