Five research rounds on free, point-in-time data — hunting for edge in Bitcoin sentiment. Some found it, some refuted our own hypotheses. Every number on these pages is computed by the script that generated the page.
| Round | Question | Method | Verdict |
|---|---|---|---|
| R1 | Which pillars matter? (weights by brute sweep) | 1,771 combos · walk-forward | Attention belongs in the mix at ~25% — but flips sign by regime. On-chain is the long-horizon validator. |
| R2 | Can attention time tops? | cycle event study 2017–25 | Flagged 3/10 extremes; attention is systematically contrarian at capitulation. Thermometer, not bell. |
| R3 | Does it reproduce? | 3 folds · feature drop-out | Composite IC positive in every fold (0.23/0.14/0.07). Regime model lags SMA200 by ~26d — honest ceiling. |
| R4 | Does structure beat holding? | A–E level engine · 6/6 suite | +8,209% vs +6,570% B&H — same return, half the drawdown. |
| R5 | Where else could edge live? | carry bands · jev NOUL/CHOICE/SCORE | Carry = cash-plus (Sharpe 3, tiny abs). Synthesis: park the level system's idle cash in strict-band carry. |