Feature Iteration Run #843: zz_sylvain

# AUTOLOOP: zz_sylvain (3 iterations)

> **Phase**: Y4.7 Option B (DSL → Python code → FeatureSet candidate)
> **Target indicator**: zz_sylvain
> **Base feature_set_id**: 1194
> **Claim**: (default) Propose a new k_* feature that improves risk-adjusted returns
> **Objective mode**: scalarize
> **Metrics**: ['profit_factor', 'sharpe_ratio', 'win_rate', 'max_drawdown', 'test_accuracy']
> **Total duration**: 72.08s
> **Total accepted**: 1
> **Total rejected**: 2

## Iterations 詳情

### Iteration 1
- DSL: `k_high.pct_change(12) * (1 - dist_to_high) * (1 + i_rsi(k_close, 14) / 100)` (feature=k_loop_iter_1_5c7d8c)
- DSL valid: True
- FeatureSet candidate id: 1194
- baseline PF: 1.947 → modified PF: 2.386
- t_stat: 0.000, p_value: 0.027, cohens_d: 0.391
- scalar_score: 1.3748
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.386, diff=0.439
  - sharpe_ratio: baseline=19.162, modified=25.291, diff=6.128
  - win_rate: baseline=0.600, modified=0.607, diff=0.007
  - max_drawdown: baseline=0.056, modified=0.027, diff=-0.029
  - test_accuracy: baseline=0.992, modified=0.991, diff=-0.001

### Iteration 2
- DSL: `k_high.pct_change(12) * (1 - dist_to_high) * i_macd(k_close, 12, 26, 9) / (1 + atr_norm)` (feature=k_iter2_k_high_pct_change_dist_to_high_i_macd)
- DSL valid: True
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: generate unexpected error: value too long for type character varying(100)


### Iteration 3
- DSL: `k_high.pct_change(12) * (1 - price_position) * (1 + i_rsi(k_close, 14) / 100) / (1 + atr_norm)` (feature=k_iter3_k_high_pct_change_price_position_i_rsi)
- DSL valid: True
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: generate unexpected error: value too long for type character varying(100)