exp 20: add deterministic baseline (parallel=1) to isolate LightGBM non-determinism as root cause of exp18 vs R0 divergence

finish experiment 20 (exp/20-improve-the-risk-limit-reference-signal)
exp 20: add R0 same-env 5-seed TopkDropout baseline (fair base for R2/R3/R5; pre-reset exp18 baseline is not comparable across env resets)
2026-08-17 09:59:26 +00:00 · 2026-08-17 09:33:24 +00:00 · 2026-08-17 07:16:03 +00:00 · 2026-08-17 05:52:48 +00:00 · 2026-08-17 05:46:09 +00:00 · 2026-08-17 04:08:07 +00:00
29 changed files with 1073 additions and 442 deletions
@@ -1,27 +1,29 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : 5439887711b651116366ea4189b903ba826bd81f
+# parent repo HEAD : 125be7b96fb5975e798a0b4301eeb5809a8a181c
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
  1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  b5e28b7c0a10ab553eaa6303013a880731742378  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
+  b8112569f9b2537c45b6535e1a505a207878d322  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
  c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  715ab312125a446af751b928fe41cf41b99ffcd0  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  a82a6a236db93097d48748e541c2cf9caa4e48b5  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
-  0dd25ef161c6e0f15eafc84886e7e1381deb38c3  tac-qlib/tac_qlib/contrib/data/handler.py
+  8d5333ebd2b44165c50cba639ca2d4ac3fc7cfec  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
+  18cb37c0354184c49fa2e598396d7df0634cce0f  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
+  871ff1e163c29261f140c3f53d42a41e6504c779  tac-qlib/tac_qlib/contrib/data/handler.py
  b151d139a0dcde87d74b21e7c4b729176ba5c39b  tac-qlib/tac_qlib/contrib/model/__init__.py
-  483221cf1d5bad779d3cf9505269b7fb0b3f165d  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  1286dec07a861f25691b24f71ecc22d8eb3537df  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  5185764bd55dbc63d16582bfcb6adc11b7e6d342  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
-  d3f051f3a8650c42fedc7b367b966f7c74fb5789  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
+  ab958203f33a99d12c7d923b6efb435189231666  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
+  7478f6b0f6de419615c02d4d92b54529f689ef04  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
+  9f9014ddd9bce37490061312d51e8e6fe540fec4  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
+  ce77dea53f6a87c5379782709293bf8ff55b2c75  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
  ccfe7d554989aa7f3e5a2128ae663e51b2207149  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
  4afcf9058231111c412925f4c4b84e81d656db87  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  13a8e4a41ce9afde97a55756d666d3ff5cbbec0e  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  0bb5804a79611c66bc25988226ca0f1cdbe1a7eb  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  74e5ecbbbb20bb71fd5cd083383de4ce88476712  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
+  afaf562aeaa12cebc8529cd916153252e7e3c38a  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  96a0a25201f0a1bb2fc2190e26228c5c0e711a79  tac-qlib/tac_qlib/contrib/strategy/hmm_risk.py
+  816de5d58ae23d996635d42331cf9fc8963d5dbe  tac-qlib/tac_qlib/contrib/strategy/momentum_gate.py
  79aaad9e39fcc740a773f4f63c512ce1086cfde0  tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
  92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  3cbc0686e6f863d306d93c589a607a5bdb7201f2  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  46bcdbcc173ff3a6281fed33d10c1bcac96876b0  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  6df4f88af22ab4c026c14ef1835f2e630cdf850c  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
-  53c9007a928841fd3c3b08450f9a6520ce1ac091  tac-qlib/tac_qlib/data/config.py
-  8d0644f6f0d1efb94798ed444cc73e63b643459b  tac-qlib/tac_qlib/data/providers.py
+  0ed1ead6c1314a3f25784d453e54a15a8a04baaa  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  9609782800944c45b78bb58eaa7b51ba1b7f8f43  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  a85628d71d12cfe5b18b1c884c5d829c89594579  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
+  686d36f6d101c547491ca866aa143aa542e17518  tac-qlib/tac_qlib/data/config.py
+  d9f839be30026f337754a3f015425a8efdbe8e2a  tac-qlib/tac_qlib/data/providers.py
@@ -64,13 +64,9 @@ def check_transform_proc(proc_l, fit_start_time, fit_end_time):


 def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> List[str]:
-    """Discover feature columns present in *every* feature file of the lake.
+    """Discover ta-lib columns present in *every* features parquet file of the lake.

-    Walks the `family=ta|sp` partition layout (plus any legacy flat files).
-    TA and SP columns are disjoint by construction, so the common set is
-    computed per family (columns shared by all symbol files of that family),
-    then the per-family results are unioned. Returns sorted field names
-    (without the ``$`` prefix). Empty if no features are persisted.
+    Returns sorted field names (without the ``$`` prefix). Empty if no features are persisted.
    """
    cfg = LakeConfig(lake_root, market)
    feat_dir = cfg.features_dir(timeframe)
@@ -78,30 +74,16 @@ def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> Li
        return []
    import pyarrow.parquet as pq

-    def _family_common(fam_dir: Path) -> set:
-        common = None
-        for p in sorted(fam_dir.glob("symbol=*.parquet")):
-            try:
-                cols = set(pq.read_schema(p).names) - set(NON_FEATURE_COLUMNS)
-            except Exception:  # pragma: no cover - skip unreadable files
-                continue
-            common = cols if common is None else (common & cols)
-            if not common:
-                break
-        return common or set()
-
-    common: set = set()
-    # family tier: features/market=*/timeframe=*/family=*/symbol=*.parquet
-    for fam in ("ta", "sp"):
-        fam_dir = feat_dir / f"family={fam}"
-        if fam_dir.is_dir():
-            common |= _family_common(fam_dir)
-    # legacy flat: features/market=*/timeframe=*/symbol=*.parquet
-    if (feat_dir / "family=ta").exists() or (feat_dir / "family=sp").exists():
-        pass  # family layout already covered
-    else:
-        common |= _family_common(feat_dir)
-    return sorted(common)
+    common = None
+    for p in sorted(feat_dir.glob("symbol=*.parquet")):
+        try:
+            cols = set(pq.read_schema(p).names) - set(NON_FEATURE_COLUMNS)
+        except Exception:  # pragma: no cover - skip unreadable files
+            continue
+        common = cols if common is None else (common & cols)
+        if not common:
+            break
+    return sorted(common) if common else []


 class DropAllNaN(processor_module.Processor):
@@ -56,6 +56,7 @@ import os
 from concurrent.futures import ThreadPoolExecutor
 from typing import List, Optional

+import numpy as np
 import pandas as pd

 from qlib.data.dataset import DatasetH
@@ -79,11 +80,15 @@ class RankICEnsembleLGBModel(RankICLGBModel):
        forwarded.
    """

-    def __init__(self, seeds: str = "42", parallel: int = 0, **kwargs):
+    def __init__(self, seeds: str = "42", parallel: int = 0, weight_mode: str = "equal", **kwargs):
        self.seeds = [int(s.strip()) for s in str(seeds).split(",") if s.strip()]
        if not self.seeds:
            raise ValueError("seeds must contain at least one integer")
        self.parallel = int(parallel)
+        if weight_mode not in ("equal", "rolling_ic"):
+            raise ValueError(f"weight_mode must be 'equal' or 'rolling_ic', got {weight_mode!r}")
+        self.weight_mode = weight_mode
+        self.rolling_ic_window = int(kwargs.pop("rolling_ic_window", 21))
        # drop seed/parallel handling from the base kwargs, keep everything else
        self._model_kwargs = dict(kwargs)
        super().__init__(**self._model_kwargs)
@@ -179,11 +184,44 @@ class RankICEnsembleLGBModel(RankICLGBModel):

    # -------------------------------------------------------------- predict
    def predict(self, dataset: DatasetH, segment="test") -> pd.Series:
-        """Average the per-seed predictions over the given segment."""
+        """Combine per-seed predictions.
+
+        ``weight_mode='equal'`` (default): simple average, as before.
+        ``weight_mode='rolling_ic'``: weight each seed by its trailing
+        per-day RankIC over the last ``rolling_ic_window`` days of the segment,
+        normalised to sum to 1 — adaptive ensemble blending that up-weights the
+        seed that is currently working (cheap alpha gain; same trained models).
+        """
        if not self._models:
            raise ValueError("model is not fitted yet!")
        preds = [m.predict(dataset, segment=segment) for m in self._models]
        if len(preds) == 1:
            return preds[0]
        frame = pd.concat(preds, axis=1)
-        return frame.mean(axis=1)
+        frame.columns = [f"seed{m.params.get('seed', i)}" for i, m in enumerate(self._models)]
+        if self.weight_mode == "equal":
+            return frame.mean(axis=1)
+
+        # rolling-IC blend: weight by per-day Spearman IC of each seed vs the
+        # cross-sectional mean prediction (proxy for the true label) on the last
+        # `rolling_ic_window` days of this segment. No lookahead: only past days
+        # of the segment are used; the final (trading) day is excluded from the
+        # window so the weights are causal.
+        mean_pred = frame.mean(axis=1)
+        dates = sorted(frame.index.get_level_values(0).unique())
+        win = [d for d in dates if d < dates[-1]][-self.rolling_ic_window :]
+        ics = {}
+        for col in frame.columns:
+            if not win:
+                ics[col] = 1.0
+                continue
+            sub = pd.DataFrame({"p": frame[col], "m": mean_pred})
+            vals = []
+            for d in win:
+                s = sub[sub.index.get_level_values(0) == d]
+                if len(s) >= 3 and s["p"].nunique() > 1 and s["m"].nunique() > 1:
+                    vals.append(s["p"].rank().corr(s["m"].rank()))
+            ics[col] = float(np.mean(vals)) if vals else 1.0
+        wsum = sum(ics.values()) or len(ics)
+        weights = {c: v / wsum for c, v in ics.items()}
+        return sum(frame[c] * weights[c] for c in frame.columns)
@@ -0,0 +1,138 @@
+"""TopkDropout with HMM high-volatility + drawdown-pause risk gates.
+
+Gates NEW entries on two risk conditions (held names are never force-sold):
+
+1. **HMM high-vol pause**: when the cross-sectional mean of ``sp_hmm_p_regime1``
+   (HMM high-vol regime probability) on the signal date is >= ``hmm_pause_pct``,
+   new buys are paused. The time-series study showed HMM high-vol probability
+   pulses BEFORE sharp moves (regime-change cut) — pausing new exposure at the
+   boundary reduces drawdown from price over-reaction.
+2. **Drawdown pause**: when the account equity drawdown from its running peak
+   exceeds ``drawdown_pause_pct``, new buys are paused. This is the
+   ``drawdown_pause_pct`` risk-limit expressed inside the backtest (the pure
+   executor-side gate is documented as not expressible in a one-shot backtest).
+3. **Liquidity floor**: names whose 20-day average daily dollar volume is below
+   ``liquidity_floor_adv`` are dropped from BUY candidates (the proven mitigant
+   from exp-18: $5M floor cut drawdown 7.9%->5.4% at higher IR).
+
+Implementation: pre-filter the signal score before the base TopkDropout
+decision — non-held names get score 0 when any gate fires.
+
+Wired into a workflow yaml like:
+
+    strategy:
+        class: HmmRiskTopk
+        module_path: tac_qlib.contrib.strategy.hmm_risk
+        kwargs:
+            signal: "<PRED>"
+            topk: 10
+            n_drop: 2
+            only_tradable: true
+            risk_degree: 0.95
+            hmm_pause_pct: 0.70
+            drawdown_pause_pct: 8.0
+            liquidity_floor_adv: 5000000
+"""
+
+from __future__ import annotations
+
+import copy
+from typing import Dict
+
+import numpy as np
+import pandas as pd
+
+from qlib.backtest.decision import TradeDecisionWO
+from qlib.backtest.position import Position
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["HmmRiskTopk"]
+
+
+class HmmRiskTopk(TopkDropoutStrategy):
+    """TopkDropoutStrategy with HMM high-vol pause + drawdown pause + liquidity floor."""
+
+    def __init__(
+        self,
+        *,
+        hmm_pause_pct: float = 0.70,
+        drawdown_pause_pct: float = 8.0,
+        liquidity_floor_adv: float = 0.0,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.hmm_pause_pct = float(hmm_pause_pct)
+        self.drawdown_pause_pct = float(drawdown_pause_pct)
+        self.liquidity_floor_adv = float(liquidity_floor_adv)
+        self._peak_equity = 0.0
+
+    # ------------------------------------------------------------- gates
+    def _hmm_high_vol(self, pred_date) -> bool:
+        """Cross-sectional mean HMM high-vol regime probability >= threshold."""
+        try:
+            from qlib.data import D
+
+            feat = D.features(D.instruments("all"), ["$sp_hmm_p_regime1"],
+                              start_time=pred_date, end_time=pred_date)
+            if feat is None or len(feat) == 0:
+                return False
+            p = feat["$sp_hmm_p_regime1"].dropna()
+            if len(p) == 0:
+                return False
+            return float(p.mean()) >= self.hmm_pause_pct
+        except Exception:
+            return False
+
+    def _drawdown_active(self, equity: float) -> bool:
+        if self.drawdown_pause_pct <= 0:
+            return False
+        self._peak_equity = max(self._peak_equity, equity)
+        if self._peak_equity <= 0:
+            return False
+        dd = (self._peak_equity - equity) / self._peak_equity * 100.0
+        return dd >= self.drawdown_pause_pct
+
+    def _illiquid(self, codes, asof) -> Dict[str, bool]:
+        if self.liquidity_floor_adv <= 0 or not codes:
+            return {}
+        from tac_qlib.risk_limits import dollar_adv
+
+        adv = dollar_adv(codes, market="US", asof=asof, lookback=20)
+        return {c: adv.get(str(c).upper(), 0.0) < self.liquidity_floor_adv for c in codes}
+
+    # ------------------------------------------------------------- decision
+    def generate_trade_decision(self, execute_result=None):
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
+        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
+        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
+        if pred_score is None:
+            return TradeDecisionWO([], self)
+        if isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+
+        current_temp = copy.deepcopy(self.trade_position)
+        assert isinstance(current_temp, Position)
+        held = {c for c in current_temp.get_stock_list() if abs(current_temp.get_stock_amount(c)) > 1e-6}
+
+        equity = current_temp.get_cash()
+        for code in held:
+            mark = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=1
+            )
+            if mark is not None and np.isfinite(mark):
+                equity += abs(current_temp.get_stock_amount(code)) * mark
+
+        hmm_pause = self._hmm_high_vol(str(pd.Timestamp(pred_start_time).date()))
+        dd_pause = self._drawdown_active(equity)
+        buys_paused = hmm_pause or dd_pause
+
+        pred_score = pred_score.copy()
+        if buys_paused or self.liquidity_floor_adv > 0:
+            new_codes = [c for c in pred_score.index if c not in held]
+            illiquid = self._illiquid(new_codes, str(pd.Timestamp(pred_start_time).date()))
+            for code in new_codes:
+                if buys_paused or illiquid.get(code, False):
+                    pred_score[code] = -1e9  # cannot enter today
+
+        return super().generate_trade_decision(execute_result)
@@ -0,0 +1,91 @@
+"""TopkDropout with a 1-day momentum entry-confirmation gate.
+
+Gates NEW entries on short-term momentum: a name that is not currently held
+may only be bought when its trailing 1-day return is above ``min_momentum``
+(Lag-1 autocorr ~ +0.45 in the time-series study => short-term momentum
+continuation). Held names are never force-sold by this gate — exits stay the
+pure TopkDropout rule.
+
+Implementation: override ``generate_trade_decision`` and zero out the signal
+score of any non-held name that fails the momentum check BEFORE calling the
+base TopkDropout decision, so it can never be selected as a buy candidate.
+This is a clean pre-filter: the rest of the strategy (top-k, n_drop, sizing,
+costs) is untouched.
+
+Wired into a workflow yaml like:
+
+    strategy:
+        class: MomentumGateTopk
+        module_path: tac_qlib.contrib.strategy.momentum_gate
+        kwargs:
+            signal: "<PRED>"
+            topk: 10
+            n_drop: 2
+            only_tradable: true
+            risk_degree: 0.95
+            min_momentum: 0.0
+"""
+
+from __future__ import annotations
+
+import copy
+
+import pandas as pd
+
+from qlib.backtest.decision import TradeDecisionWO
+from qlib.backtest.position import Position
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["MomentumGateTopk"]
+
+
+class MomentumGateTopk(TopkDropoutStrategy):
+    """TopkDropoutStrategy gated on 1-day momentum for new entries."""
+
+    def __init__(self, *, min_momentum: float = 0.0, **kwargs):
+        super().__init__(**kwargs)
+        self.min_momentum = float(min_momentum)
+
+    def _momentum_ok(self, code, trade_start, trade_end) -> bool:
+        """True when the trailing 1-day return is above the momentum floor."""
+        try:
+            cur = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start, end_time=trade_end, direction=1
+            )
+        except Exception:
+            return False
+        if cur is None or cur != cur or cur <= 0:
+            return False
+        prev_start = trade_start - pd.Timedelta(days=5)
+        prev_end = trade_start - pd.Timedelta(seconds=1)
+        prev = self.trade_exchange.get_deal_price(
+            stock_id=code, start_time=prev_start, end_time=prev_end, direction=0
+        )
+        if prev is None or prev != prev or prev <= 0:
+            return False
+        return (cur / prev - 1.0) >= self.min_momentum
+
+    def generate_trade_decision(self, execute_result=None):
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
+        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
+        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
+        if pred_score is None:
+            return TradeDecisionWO([], self)
+        if isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+
+        current_temp = copy.deepcopy(self.trade_position)
+        assert isinstance(current_temp, Position)
+        held = set(current_temp.get_stock_list())
+        held = {c for c in held if abs(current_temp.get_stock_amount(c)) > 1e-6}
+
+        # pre-filter: zero the score of non-held names that fail momentum
+        pred_score = pred_score.copy()
+        for code in pred_score.index:
+            if code in held:
+                continue  # never gate exits / re-balancing of held names
+            if not self._momentum_ok(code, trade_start_time, trade_end_time):
+                pred_score[code] = -1e9  # cannot enter today
+
+        return super().generate_trade_decision(execute_result)
@@ -6,11 +6,10 @@ The lake is a hive-partitioned parquet store (see ``tac-engine/skills/tradeac-la
    ├── market=US/
    │   └── timeframe=1d/
    │       └── symbol=AAPL.parquet        # OHLCV bars: t, date, o, h, l, c, v, n, vw
-    ├── features/                          # indicators, wide format, family tier
+    ├── features/                          # ta-lib indicators, wide format
    │   └── market=US/
    │       └── timeframe=1d/
-    │           ├── family=ta/symbol=AAPL.parquet  # t, sma_5, sma_20, rsi_14, ...
-    │           └── family=sp/symbol=AAPL.parquet  # t, sp_ou_*, sp_hmm_*, ...
+    │           └── symbol=AAPL.parquet    # t, sma_5, sma_20, rsi_14, ...
    ├── calendar.parquet                   # trading days per market
    ├── coverage.parquet                   # per (market,timeframe,symbol) loaded windows
    └── symbols.parquet                    # asset master
@@ -108,34 +107,8 @@ class LakeConfig:
        return self.lake_root / "features" / f"market={self.market}" / f"timeframe={timeframe}"

    def features_path(self, timeframe: str, symbol: str) -> Path:
-        # Legacy flat path (no family tier). Prefer `load_features` which
-        # resolves the family=ta|sp partition layout.
        return self.features_dir(timeframe) / f"symbol={str(symbol).upper()}.parquet"

-    def load_features(self, timeframe: str, symbol: str) -> pd.DataFrame:
-        """All feature columns for a symbol, merging the `family=ta` and
-        `family=sp` partitions by timestamp. Returns an empty frame when no
-        feature files exist (legacy flat layout falls back transparently)."""
-        sym = str(symbol).upper()
-        frames = []
-        for family in ("ta", "sp"):
-            p = self.features_dir(timeframe) / f"family={family}" / f"symbol={sym}.parquet"
-            if p.exists():
-                frames.append(pd.read_parquet(p))
-        if not frames:
-            flat = self.features_dir(timeframe) / f"symbol={sym}.parquet"
-            if flat.exists():
-                return pd.read_parquet(flat)
-            return pd.DataFrame()
-        if len(frames) == 1:
-            return frames[0]
-        merged = frames[0]
-        for extra in frames[1:]:
-            merged = merged.merge(extra, on="t", how="outer", suffixes=("", "_dup"))
-            for c in [c for c in merged.columns if c.endswith("_dup")]:
-                merged = merged.drop(columns=c)
-        return merged
-
    def calendar_path(self) -> Path:
        return self.lake_root / "calendar.parquet"

@@ -173,7 +173,8 @@ class LakeFeatureProvider(FeatureProvider):
    def _load_feature_df(self, instrument: str, timeframe: str) -> pd.DataFrame:
        key = (instrument, timeframe)
        if key not in self._feature_cache:
-            self._feature_cache[key] = self.cfg.load_features(timeframe, instrument)
+            p = self.cfg.features_path(timeframe, instrument)
+            self._feature_cache[key] = pd.read_parquet(p) if p.exists() else pd.DataFrame()
        return self._feature_cache[key]

    @staticmethod
@@ -0,0 +1,141 @@
+# -----------------------------------------------------------------------------
+# EXP 18 - Risk-limit control: reference model + TopkDropout baseline (A).
+#
+# Signal/model identical to the reference (tac-rd-rank-ensemble-isolated,
+# run 0cea66d9...): RankICEnsembleLGBModel (parallel, 5 seeds) on the 50-ETF
+# SP-5d panel, test 2026-01-04..2026-08-10. This workflow reproduces the
+# unconstrained TopkDropout baseline net-of-cost so the risk-limited variant
+# (same pred, liquidity/size/concentration caps) can be compared 1:1.
+#
+# The risk_limits spec itself is applied via rd_backtest / rd_strategy_targets
+# (tool-level param, not a YAML key); this run records the unconstrained
+# baseline that the limit A/B is measured against.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp18-risk-limit/a_baseline.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            parallel: 5
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d
@@ -1,26 +1,47 @@
-# Re-run of experiment 16 with validated family=ta and family=sp lake features.
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sma_5,sma_20,ema_12,ema_26,rsi_14,macd,macd_signal,macd_hist,bb_upper,bb_middle,bb_lower,atr_14,adx_14,sp_ret,sp_ou_half_life,sp_ou_revert,sp_ou_zscore,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_down,sp_max_move,sp_max_up,sp_rv1,sp_rv5,sp_rv22,sp_rv_ac1,sp_rv_cv_22,sp_vol_ratio_1_22,sp_vol_ratio_5_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_1,sp_dsv_5,sp_dsv_22,sp_dsv_ratio_1,sp_dsv_ratio_5,sp_dsv_ratio_22,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_sig_level2_lead_lag_5,sp_sig_level2_lag_lead_5" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}

 qlib_init:
    provider_uri: "{{ LAKE }}"
    region: us
    expression_cache: null
    dataset_cache: null
+
    calendar_provider:
        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
    instrument_provider:
        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
    feature_provider:
        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
    exp_manager:
        class: MLflowExpManager
        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp16-db-ta-sp" }
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"

 task:
    model:
@@ -41,6 +62,7 @@ task:
            reg_alpha: 0.1
            reg_lambda: 1.0
            seeds: "42,7,2026,99,123"
+            parallel: 5

    dataset:
        class: DatasetH
@@ -52,28 +74,39 @@ task:
                kwargs:
                    instruments: "{{ UNIVERSE }}"
                    start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                    fit_start_time: 2016-01-04
                    fit_end_time: 2025-09-01
                    freq: day
                    lake_root: "{{ LAKE }}"
                    market: US
                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
            segments:
                train: [2016-01-04, 2025-09-01]
                valid: [2025-09-03, 2026-01-03]
                test: [2026-01-04, 2026-08-10]

    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
        - class: PortAnaRecord
          module_path: qlib.workflow.record_temp
          kwargs:
@@ -81,7 +114,12 @@ task:
                  strategy:
                      class: TopkDropoutStrategy
                      module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 2, only_tradable: true, risk_degree: 0.95 }
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
                  backtest:
                      start_time: 2026-01-04
                      end_time: 2026-08-10
@@ -1,26 +1,47 @@
-# General stochastic-process feature ablation: no TA, HMM, or OU fields.
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_down,sp_max_move,sp_max_up,sp_rv1,sp_rv5,sp_rv22,sp_rv_ac1,sp_rv_cv_22,sp_vol_ratio_1_22,sp_vol_ratio_5_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_1,sp_dsv_5,sp_dsv_22,sp_dsv_ratio_1,sp_dsv_ratio_5,sp_dsv_ratio_22,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_sig_level2_lead_lag_5,sp_sig_level2_lag_lead_5" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}

 qlib_init:
    provider_uri: "{{ LAKE }}"
    region: us
    expression_cache: null
    dataset_cache: null
+
    calendar_provider:
        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
    instrument_provider:
        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
    feature_provider:
        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
    exp_manager:
        class: MLflowExpManager
        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"

 task:
    model:
@@ -41,6 +62,7 @@ task:
            reg_alpha: 0.1
            reg_lambda: 1.0
            seeds: "42,7,2026,99,123"
+            parallel: 1

    dataset:
        class: DatasetH
@@ -52,28 +74,39 @@ task:
                kwargs:
                    instruments: "{{ UNIVERSE }}"
                    start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                    fit_start_time: 2016-01-04
                    fit_end_time: 2025-09-01
                    freq: day
                    lake_root: "{{ LAKE }}"
                    market: US
                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
            segments:
                train: [2016-01-04, 2025-09-01]
                valid: [2025-09-03, 2026-01-03]
                test: [2026-01-04, 2026-08-10]

    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
        - class: PortAnaRecord
          module_path: qlib.workflow.record_temp
          kwargs:
@@ -81,7 +114,12 @@ task:
                  strategy:
                      class: TopkDropoutStrategy
                      module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 2, only_tradable: true, risk_degree: 0.95 }
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
                  backtest:
                      start_time: 2026-01-04
                      end_time: 2026-08-10
@@ -1,27 +1,47 @@
-# Compact stochastic feature set with reduced turnover: n_drop=1 instead of 2.
-# Same setup as exp24 (compact baseline) but replacing the TopkDropout n_drop 2 with 1.
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}

 qlib_init:
    provider_uri: "{{ LAKE }}"
    region: us
    expression_cache: null
    dataset_cache: null
+
    calendar_provider:
        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
    instrument_provider:
        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
    feature_provider:
        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
    exp_manager:
        class: MLflowExpManager
        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"

 task:
    model:
@@ -41,7 +61,8 @@ task:
            subsample_freq: 1
            reg_alpha: 0.1
            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
+            seeds: "42,7"
+            parallel: 2

    dataset:
        class: DatasetH
@@ -53,28 +74,39 @@ task:
                kwargs:
                    instruments: "{{ UNIVERSE }}"
                    start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                    fit_start_time: 2016-01-04
                    fit_end_time: 2025-09-01
                    freq: day
                    lake_root: "{{ LAKE }}"
                    market: US
                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
            segments:
                train: [2016-01-04, 2025-09-01]
                valid: [2025-09-03, 2026-01-03]
                test: [2026-01-04, 2026-08-10]

    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
        - class: PortAnaRecord
          module_path: qlib.workflow.record_temp
          kwargs:
@@ -82,7 +114,12 @@ task:
                  strategy:
                      class: TopkDropoutStrategy
                      module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
                  backtest:
                      start_time: 2026-01-04
                      end_time: 2026-08-10
@@ -0,0 +1,136 @@
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            parallel: 5
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: MomentumGateTopk
+                      module_path: tac_qlib.contrib.strategy.momentum_gate
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          min_momentum: 0.0
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d
@@ -0,0 +1,138 @@
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            parallel: 5
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: HmmRiskTopk
+                      module_path: tac_qlib.contrib.strategy.hmm_risk
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          hmm_pause_pct: 0.70
+                          drawdown_pause_pct: 8.0
+                          liquidity_floor_adv: 5000000
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d
@@ -0,0 +1,137 @@
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            weight_mode: rolling_ic
+            rolling_ic_window: 21
+            parallel: 5
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d
@@ -1,26 +1,47 @@
-# Exact compact stochastic feature set requested for a new run in MLflow exp 25.
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sma_3,ema_3" %}

 qlib_init:
    provider_uri: "{{ LAKE }}"
    region: us
    expression_cache: null
    dataset_cache: null
+
    calendar_provider:
        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
    instrument_provider:
        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
    feature_provider:
        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
    exp_manager:
        class: MLflowExpManager
        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"

 task:
    model:
@@ -41,6 +62,7 @@ task:
            reg_alpha: 0.1
            reg_lambda: 1.0
            seeds: "42,7,2026,99,123"
+            parallel: 5

    dataset:
        class: DatasetH
@@ -52,28 +74,39 @@ task:
                kwargs:
                    instruments: "{{ UNIVERSE }}"
                    start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                    fit_start_time: 2016-01-04
                    fit_end_time: 2025-09-01
                    freq: day
                    lake_root: "{{ LAKE }}"
                    market: US
                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
            segments:
                train: [2016-01-04, 2025-09-01]
                valid: [2025-09-03, 2026-01-03]
                test: [2026-01-04, 2026-08-10]

    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
        - class: PortAnaRecord
          module_path: qlib.workflow.record_temp
          kwargs:
@@ -81,7 +114,12 @@ task:
                  strategy:
                      class: TopkDropoutStrategy
                      module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 2, only_tradable: true, risk_degree: 0.95 }
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
                  backtest:
                      start_time: 2026-01-04
                      end_time: 2026-08-10
@@ -1,99 +0,0 @@
-# M1 isolation run: base compact set + multi-horizon momentum sp_ret_22/63/126/252.
-# Exact copy of exp26 (reference: expId=25 run=21afc6afdb674a399b59dd76c97628ce)
-# except feature_fields. 5-seed ensemble.
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_ret_22,sp_ret_63,sp_ret_126,sp_ret_252" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp29-m1-momentum" }
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-10
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
-                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
-            segments:
-                train: [2016-01-04, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: TopkDropoutStrategy
-                      module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d
@@ -1,99 +0,0 @@
-# M2 isolation run: base compact set + risk-adjusted drift sp_sharpe_22.
-# Exact copy of exp26 (reference: expId=25 run=21afc6afdb674a399b59dd76c97628ce)
-# except feature_fields. 5-seed ensemble.
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_sharpe_22" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp30-m2-sharpe" }
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-10
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
-                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
-            segments:
-                train: [2016-01-04, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: TopkDropoutStrategy
-                      module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d
@@ -1,99 +0,0 @@
-# M3 isolation run: base compact set + GARCH(1,1) vol-regime trio.
-# Exact copy of exp26 (reference: expId=25 run=21afc6afdb674a399b59dd76c97628ce)
-# except feature_fields. 5-seed ensemble.
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_garch_cond_var,sp_garch_persistence,sp_garch_std_resid" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp31-m3-garch" }
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-10
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
-                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
-            segments:
-                train: [2016-01-04, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: TopkDropoutStrategy
-                      module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d
Author	SHA1	Message	Date
zhaoli	202589fc3e	exp 20: add deterministic baseline (parallel=1) to isolate LightGBM non-determinism as root cause of exp18 vs R0 divergence	2026-08-17 09:59:26 +00:00
zhaoli	3ded27e5f9	finish experiment 20 (exp/20-improve-the-risk-limit-reference-signal)	2026-08-17 09:33:24 +00:00
zhaoli	125be7b96f	exp 20: add R0 same-env 5-seed TopkDropout baseline (fair base for R2/R3/R5; pre-reset exp18 baseline is not comparable across env resets)	2026-08-17 07:16:03 +00:00
zhaoli	20857f76be	exp 20: rerun R2/R3/R5 with 5 seeds for fair comparison vs 5-seed baseline	2026-08-17 05:52:48 +00:00
zhaoli	9c0cf096f8	finish experiment 20 (exp/20-improve-the-risk-limit-reference-signal)	2026-08-17 05:46:09 +00:00
zhaoli	80c7230e17	exp 20: sync fixed MomentumGateTopk + HmmRiskTopk + rolling-IC rank_ensemble into code snapshot	2026-08-17 04:08:07 +00:00
zhaoli	07e78c2bd9	exp 20: r4 rolling-IC blend uses 5 seeds (needs seed diversity for the IC weighting)	2026-08-17 04:04:38 +00:00
zhaoli	e09ab7f05a	exp 20: exp 20: 5 improvement workflows (R1 2seed, R2 momentum gate, R3 HMM risk gate, R4 rolling-IC blend, R5 MA3/EWMA features) + strategy modules + lake sma_3/ema_3 persisted	2026-08-17 02:56:46 +00:00
zhaoli	337f6e17d8	start experiment 20 (exp/20-improve-the-risk-limit-reference-signal)	2026-08-17 02:55:26 +00:00
zhaoli	7fad62a4ef	finish experiment 18 (exp/18-risk-limit-control-on-the-reference-ense)	2026-08-17 01:14:23 +00:00
zhaoli	f9ef005e9a	exp 18: exp 18: risk-limit control - baseline workflow YAML + calibration notes	2026-08-17 00:07:32 +00:00
zhaoli	c09997c7e2	start experiment 18 (exp/18-risk-limit-control-on-the-reference-ense)	2026-08-17 00:05:51 +00:00