finish experiment 46 (exp/46-q15-the-5-seed-rankicensemblelgbmodel-sh)

code/MANIFEST.txt

@@ -1,5 +1,5 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : 59839ff48760b632a2d1bb40877766b1da105891
+# parent repo HEAD : bba17bd401cd9cca714c329f7eb3ab71c36a490b
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):

queue/README.md

@@ -0,0 +1,69 @@
+# TradeAC Experiment Queue — Series 2 (Q12+)
+
+**Purpose.** The next pre-registered batch of experiments, continuing Series 1
+(Q01–Q11, exp 33–43, all executed and folded into `book/CLAIMS.md` /
+`book/EVIDENCE.md`). Each entry targets a still-unproven `HYPOTHESIS` from the
+book or an open question flagged in `CLAIMS.md`/`book/README.md`, and follows the
+Series-1 discipline: one variable changed vs the exp-26 reference, acceptance
+fixed BEFORE the run, sequential execution, trace-first, verify-then-close.
+
+**Reference / control (MUST reproduce first).** exp 26 (`21afc6af…`, mlflow exp
+25) is the campaign baseline; exp 39 (Q07, weekly rebalance) is the best
+construction. Reference config is byte-reproduced in `workflows/exp26/` on the
+`exp/26-…` branch and in this dir's `workflows/*.yaml`.
+
+| Config element | exp-26 reference value |
+|---|---|
+| Universe | 50-ETF panel (`UNIVERSE` below) |
+| Features | compact stochastic 25-field set (no ou/hmm/moments/garch) |
+| Label | `Ref($close,-6)/Ref($close,-1)-1` (5d) |
+| Model | `RankICEnsembleLGBModel`, seeds `42,7,2026,99,123`, lr 0.02, leaves 31, 3000 rounds, ES 200 |
+| Segments | train 2016-01-04..2025-09-01 / valid 2025-09-03..2026-01-03 / test 2026-01-04..2026-08-10 |
+| Strategy | TopkDropout, topk 10, n_drop 1, risk_degree 0.95 |
+| Costs | open 0.0005 / close 0.0015 / min $5, deal $close, SPY benchmark, $1M |
+
+**Reference metrics to beat (EVIDENCE#015):** net_ann +2.13%, net_IR 0.21, gross
++7.02%, maxDD −7.69%, RankIC 0.0663, RankICIR 0.2545, L/S Sharpe 4.54. Weekly
+(Q07, EVIDENCE#028): net +12.51%, IR 1.24, maxDD −4.13%, ~1.1pp cost drag.
+
+## The queue (ordered by value × feasibility)
+
+| ID | Title / hypothesis | Change vs reference (ONE var) | Acceptance | Config | Ready? |
+|----|--------------------|-------------------------------|------------|--------|--------|
+| Q12 | **22d label + weekly recompute** — the untested combo: Q05's label edge (IC 0.097, RankIC 0.117) with Q07's cost relief | label → 22d AND strategy → weekly (two coupled, explicitly pre-registered) | net_IR > 0.5, net_ann > +5%, cost drag ≤ 2pp | `workflows/q12_label22d_weekly.yaml` | ✅ |
+| Q13 | **Weekly rebalance reproduction on a 2nd window** — Q07 was a single OOS window; reproduce on test 2025-01-02..2025-12-31 before promoting to a live round | segments only (shifted) | net_IR > 0.21, net_ann > +2.13% on the new window | `workflows/q13_weekly_second_window.yaml` | ✅ |
+| Q14 | **Out-of-universe validation** — compact stochastic set generalizes off the 50-ETF panel to a single-stock universe | universe → 30 liquid single names | RankIC > 0.03, ICIR > 0.15, net IR > 0 on stocks | `workflows/q14_out_of_universe.yaml` | ⚠️ needs stock-lake backfill (see design) |
+| Q15 | **5-seed vs single-model clean A/B** — seed-count claim (exp 12 idea, re-validated exp 22–24, never a clean A/B) | seeds → 1 (`2026`) | single-model RankIC/IR < 5-seed ref; net_IR ≥ 0.21 acceptable if ≥ single | `workflows/q15_single_seed.yaml` | ✅ |
+| Q16 | **HMM family added as features** — settles "dropping model-specific (ou,hmm) improves signal" (exp 25 tested OU; hmm-as-feature untested) | features += `sp_hmm_p_regime1,sp_hmm_state` | no improvement: RankIC ≤ 0.0663, net_IR ≤ 0.21 | `workflows/q16_hmm_features.yaml` | ✅ |
+| Q17 | **Realized-moments family added** — settles "moment/volatility families regress" (exp 11 idea, never clean A/B) | features += `sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22` | no improvement: RankIC ≤ 0.0663, net_IR ≤ 0.21 | `workflows/q17_moments_features.yaml` | ✅ |
+| Q18 | **OptimalStopControl clean re-test** — exp 13/14 claim (TopkDropout > stop-control) never re-tested post-reset | strategy → `OptimalStopControl` (exp-13 params) | TopkDropout net_IR ≥ stop-control net_IR; document cost drag | `workflows/q18_optstop.yaml` | ✅ (module verified in venv) |
+| Q19 | **Martingale / variance-ratio study close-out** — exp 19 never closed; VR<1 at 5–20d on clean lake | ad-hoc script (no qrun) | VR stats + drift decomposition on 50-ETF panel | `designs/q19_martingale_vr.md` | ✅ script |
+| Q20 | **Effective independent names (≈4)** — eigenvalue analysis on clean-lake covariance | ad-hoc script | eigenvalue spectrum + effective-rank count | `designs/q20_effective_names.md` | ✅ script |
+
+### Deferred (methodology / infra, P3)
+- Purged / walk-forward CV (was queue's old Q12) — methodology, not an alpha lever.
+- PSI-based drift-aware retraining cadence — needs a drift-gate module + a retrain decision rule.
+- No-trade buffer band / notional-vs-qty sizing — siblings of Q12/Q13; queue only if weekly reproduces.
+- Macro/drift overlays (SPY>200d regime gate, momentum tilt) — needs new data pipeline.
+
+## Execution protocol (per queued run)
+
+1. **Validate the lake first** (`validate_lake_dataset` + `rd_status`) — clean-lake lesson: silent NaN-drops and hollow coverage invalidate a run. Q14 additionally requires backfilling the single-stock universe (bars + sp/ta features, full range, explicit `start`/`end`).
+2. **Trace before running** (`rd_trace_start` with the hypothesis as `rational`, fresh `experiment_name`, `evolved_from=auto`).
+3. **Run** `rd_run_workflow config_path=<abs path to the queue YAML> experiment_name=<fresh name>` — `wait=false`, poll `rd_exp_get_run` until `FINISHED`.
+4. **Verify against acceptance** via `rd_exp_result` (headline + backtest risk).
+5. **Finish the trace** (`rd_trace_finish` with `metrics` + `evaluation`), snapshot any changed contrib modules.
+6. **Report to the book** — PROVE/REFUTE → update `book/CLAIMS.md` + `book/EVIDENCE.md`.
+
+Sequential execution only (concurrent runs hang — chat-ideas.md ops lesson). Any
+custom strategy/module changed here must be copied into the venv site-packages
+snapshot before `rd_run_workflow` can import it (see `/app/AGENTS.md`). As of
+2026-08-20 `WeeklyRebalanceDropoutStrategy` and `OptimalStopControl` are verified
+in sync with the venv snapshot; the lake already persists the `sp_hmm_*` and
+`sp_moments` families on the 50-ETF panel.
+
+## Provenance
+
+Mined 2026-08-20 from `book/CLAIMS.md`, `book/EVIDENCE.md`, `book/README.md`,
+`book/references/chat-ideas.md`, and Series-1 `queue/` (Q01–Q11, executed exp
+33–43). Reference numbers are post-clean-lake (exp 21+).

queue/designs/q19_martingale_vr.md

@@ -0,0 +1,26 @@
+# QUEUE-19 — Martingale / variance-ratio study close-out (no qrun)
+
+**Status:** QUEUED · **Priority:** P2 · **Effort:** ad-hoc script under `book/data/`
+
+## Hypothesis (settle)
+Assets are submartingales long-horizon / mean-reverting short-horizon
+(`VR < 1` at 5–20d). CLAIMS.md marks this HYPOTHESIS (chat-derived martingale
+study; exp 19 was opened but never closed). It is a market-structure claim, not a
+trading claim — settle it with a clean-lake script, then close exp 19 or open a
+scripted EVIDENCE entry.
+
+## Method (persist everything under `book/data/evidence/q19-vr/`)
+1. Load the 50-ETF panel 1d bars from the lake for 2015-01-01..2026-08-19.
+2. Compute the Lo–MacKinlay variance ratio at horizons 5 / 10 / 20d per symbol,
+   with heteroskedasticity-robust z-stats.
+3. Report: per-horizon VR distribution, fraction of symbols with VR < 1 and the
+   z-significance, pooled drift vs daily variance (submartingale check).
+4. Cross-check the pooled `sp_trend_slope_5` regression beta claim (β ≈ −0.53,
+   t ≈ −24) on the clean lake.
+5. Write `VR_stats.csv` + a one-page summary into the evidence dir.
+
+## Acceptance
+- VR < 1 at 5–20d for a material fraction of the panel with |z| > 2 → supports
+  the mean-reversion HYPOTHESIS; else mark REFUTED or REFERENCED.
+- The result updates CLAIMS.md's "Assets are submartingales…" row and closes the
+  exp-19 open thread.

queue/designs/q20_effective_names.md

@@ -0,0 +1,22 @@
+# QUEUE-20 — Effective independent names in the 50-ETF book (no qrun)
+
+**Status:** QUEUED · **Priority:** P2 · **Effort:** ad-hoc script under `book/data/`
+
+## Hypothesis (settle)
+The 50-ETF book has only ~4 effective independent names (CLAIMS.md HYPOTHESIS,
+chat-derived eigenvalue analysis, pre-reset). This is a concentration/diversification
+claim with direct sizing relevance; verify it on the clean lake.
+
+## Method (persist everything under `book/data/evidence/q20-effective-names/`)
+1. Load the 50-ETF panel 1d returns from the lake for the test window 2026-01-04..2026-08-10.
+2. Standardize returns; compute the correlation matrix and its eigendecomposition.
+3. Count eigenvalues above the Marchenko–Pastur bound (N=50, T≈150) and report the
+   cumulative-variance share of the top k components.
+4. Effective-rank measures: participation ratio `(Σλ)² / Σλ²` and cumulative 80%
+   variance count.
+5. Write `eigenanalysis.csv` + a one-page summary.
+
+## Acceptance
+- If effective rank ≈ 4 (top-4 explain ~80%+ variance), the concentration claim is
+  PROVEN and feeds chapter 08 sizing guidance (why topk 10→20 adds no breadth).
+- If effective rank is much larger, mark the claim REFUTED.

queue/workflows/q12_label22d_weekly.yaml

@@ -1,22 +1,12 @@
-# QUEUE-ly
+# QUEUE-12 — Long-horizon label (22d) + weekly recompute construction.
-# Weekly rebalance (Q07): TopkDropout recomputed once per ISO week, hold otherwise (turnover relief).
+# Untested combination from book/CLAIMS.md open questions: Q05 (exp 37) proved the
-# Acceptance: total_cost/turnover strictly below reference AND net_IR > 0.21 AND net_ann > +2.13%.
+# 22d label has the strongest signal (IC 0.097, RankIC 0.117) but daily turnover
-
+# killed the book (net -4.60%); Q07 (exp 39) proved weekly recompute is the cost
-
+# lever (net +12.51%). Hypothesis: pairing them monetizes the label edge.
-
+# Change vs exp-26 reference: label 5d -> 22d AND strategy -> WeeklyRebalanceDropoutStrategy.
-
+# Acceptance: net_IR > 0.5, net_ann > +5%, cost drag <= 2pp.
-
+# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q12_label22d_weekly.yaml \
-
+#        experiment_name=tac-rd-q12-label22d-weekly
-
-
-
-
-
-
-
-
-
-
 {%- 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" %}
@@ -26,30 +16,19 @@ qlib_init:
     region: us
     expression_cache: null
     dataset_cache: null
-
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            lake_root: "{{ LAKE }}"
-            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            lake_root: "{{ LAKE }}"
-            market: US
-
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs:
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q12-label22d-weekly" }
-            uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-q07-weekly"
 
 task:
     model:
@@ -70,7 +49,6 @@ task:
             reg_alpha: 0.1
             reg_lambda: 1.0
             seeds: "42,7,2026,99,123"
-            parallel: 5
 
     dataset:
         class: DatasetH
@@ -88,33 +66,22 @@ task:
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    label: "Ref($close,-23)/Ref($close,-1)-1"
                     feature_fields: "{{ FEATURES }}"
                     infer_processors:
-                        - class: DropAllNaN
+                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                          kwargs: {}
+                        - { class: ProcessInf, kwargs: {} }
-                        - class: ProcessInf
+                        - { class: CSRankNorm, kwargs: {} }
-                          kwargs: {}
+                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - class: CSRankNorm
+                        - { class: Fillna, kwargs: {} }
-                          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
+        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-          module_path: qlib.workflow.record_temp
+        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
-          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:
@@ -122,12 +89,7 @@ task:
                   strategy:
                       class: WeeklyRebalanceDropoutStrategy
                       module_path: tac_qlib.contrib.strategy.weekly_rebalance
-                      kwargs:
+                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
-                          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

queue/workflows/q13_weekly_second_window.yaml

@@ -0,0 +1,106 @@
+# QUEUE-13 — Weekly rebalance reproduction on a second OOS window.
+# Q07 (exp 39) proved weekly recompute on test 2026-01-04..2026-08-10 (net +12.51%,
+# IR 1.24) but that is a single OOS window. Before promoting the weekly construction
+# to a live round, reproduce it on a disjoint window: test 2025-01-02..2025-12-31
+# with train/valid shifted to end 2024.
+# Change vs exp-26 reference: segments shifted only (train ends 2024-08, test = 2025);
+# strategy is the SAME weekly recompute as exp 39. Label stays 5d.
+# Acceptance: net_IR > 0.21 AND net_ann > +2.13% on the 2025 window.
+# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q13_weekly_second_window.yaml \
+#        experiment_name=tac-rd-q13-weekly-second-window
+{%- 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" %}
+
+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-q13-weekly-second-window" }
+
+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: 2025-12-31
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2024-08-30
+                    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: "2024-08-30" } }
+                        - { class: ProcessInf, kwargs: {} }
+                        - { class: CSRankNorm, kwargs: {} }
+                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2024-08-30" } }
+                        - { class: Fillna, kwargs: {} }
+            segments:
+                train: [2016-01-04, 2024-08-30]
+                valid: [2024-09-03, 2024-12-31]
+                test: [2025-01-02, 2025-12-31]
+
+    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: WeeklyRebalanceDropoutStrategy
+                      module_path: tac_qlib.contrib.strategy.weekly_rebalance
+                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
+                  backtest:
+                      start_time: 2025-01-02
+                      end_time: 2025-12-31
+                      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

queue/workflows/q14_out_of_universe.yaml

@@ -0,0 +1,107 @@
+# QUEUE-14 — Out-of-universe validation: compact stochastic set on single-stock names.
+# The 50-ETF panel results (compact feature set, RankIC 0.0663) are panel-specific;
+# book/CLAIMS.md marks "generalizes to other universes" HYPOTHESIS - TODO(evidence-needed).
+# Change vs exp-26 reference: universe -> 30 liquid US single-stock names.
+# PREREQUISITE: backfill lake bars + sp/ta features for these symbols (full range,
+# explicit start/end) — the stock panel currently has only ~180d of data (2025-12-01+).
+# Backfill: get_lake_bars symbols=... start=2000-01-03 then
+#   get_lake_sp symbol=<s> start=2000-01-03 end=<today> fit_end=<train-end> persist=true
+# Acceptance: RankIC > 0.03, ICIR > 0.15, net IR > 0 on the stock universe.
+# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q14_out_of_universe.yaml \
+#        experiment_name=tac-rd-q14-out-of-universe
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "AAPL,MSFT,NVDA,AMZN,GOOGL,META,TSLA,AVGO,AMD,JPM,UNH,PG,JNJ,MA,V,WMT,DIS,HD,KO,PEP,BAC,XOM,MCD,ABBV,COST,CRM,NFLX,ORCL,IBM,T" %}
+{%- 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" %}
+
+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-q14-out-of-universe" }
+
+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

queue/workflows/q15_single_seed.yaml

@@ -0,0 +1,104 @@
+# QUEUE-15 — 5-seed vs single-model clean A/B on the compact stochastic set.
+# CLAIMS.md HYPOTHESIS: "5-seed RankIC ensemble raises performance vs single model
+# on ablated set" — pre-clean-lake exp 12 idea, re-validated directionally by exp
+# 22–24, never a clean A/B post-reset. Seed count is load-bearing (exp 28: 2<5).
+# Change vs exp-26 reference: seeds "42,7,2026,99,123" -> single seed "2026".
+# Acceptance: single-model RankIC < 0.0663, net_IR < 0.21 (ensemble beats single).
+# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q15_single_seed.yaml \
+#        experiment_name=tac-rd-q15-single-seed
+{%- 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" %}
+
+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-q15-single-seed" }
+
+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: "2026"
+
+    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

queue/workflows/q16_hmm_features.yaml

@@ -0,0 +1,105 @@
+# QUEUE-16 — HMM family added as model features to the compact set.
+# CLAIMS.md HYPOTHESIS: "Dropping model-specific feature families (ou, hmm)
+# improves the rank signal" — exp 25 cleanly tested OU (adding it hurts: IC 0.0511->0.0343);
+# hmm-as-features has NOT been clean A/B'd post-reset (exp 42 tested hmm as an entry
+# GATE overlay, refuted). This run adds the hmm family columns to the compact set.
+# Change vs exp-26 reference: features += sp_hmm_p_regime1, sp_hmm_state.
+# Acceptance (prune-hypothesis): no improvement — RankIC <= 0.0663, net_IR <= 0.21.
+# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q16_hmm_features.yaml \
+#        experiment_name=tac-rd-q16-hmm-features
+{%- 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_hmm_p_regime1,sp_hmm_state" %}
+
+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-q16-hmm-features" }
+
+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

queue/workflows/q17_moments_features.yaml

@@ -1,52 +1,34 @@
-# -----------------------------------------------------------------------------
+# QUEUE-17 — Realized-moments family added to the compact set.
-# QUEUE-03 — topk 20 vs 10 diversification on the compact reference.
+# CLAIMS.md HYPOTHESIS: "Adding moment/volatility families regresses the signal"
-#
+# (idea: pre-clean-lake exp 11). M1 momentum bundle (exp 29) and M3 GARCH (exp 31)
-# Hypothesis (book ch.05/chat-ideas): the effective independent names in the
+# were refuted post-reset; the realized-moments family (sp_rskew/sp_rkurt/sp_dsv)
-# 50-ETF book is small (~4, chat-derived eigenvalue analysis); raising topk
+# has NOT been clean A/B'd. This run adds the moments columns to the compact set.
-# diversifies the book and should cut drawdown / raise net IR without hurting
+# Change vs exp-26 reference: features += sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22.
-# the (weak) rank signal — cost relief by spreading the book wider.
+# Acceptance (prune-hypothesis): no improvement — RankIC <= 0.0663, net_IR <= 0.21.
-#
+# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q17_moments_features.yaml \
-# Change vs exp-26 reference: ONE variable — strategy topk 10 -> 20 (n_drop 1).
+#        experiment_name=tac-rd-q17-moments-features
-# Everything else identical.
-#
-# Acceptance: net_IR > 0.21 AND net_max_drawdown < 7.69% AND net_ann_return >=
-#   +2.13%; watch total_cost — more names held must not raise turnover/cost.
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q03_topk20.yaml \
-#        experiment_name=tac-rd-q03-topk20
-# -----------------------------------------------------------------------------
 {%- 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 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_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
     region: us
     expression_cache: null
     dataset_cache: null
-
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            lake_root: "{{ LAKE }}"
-            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            lake_root: "{{ LAKE }}"
-            market: US
-
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs:
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q17-moments-features" }
-            uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-q03-topk20"
 
 task:
     model:
@@ -67,7 +49,6 @@ task:
             reg_alpha: 0.1
             reg_lambda: 1.0
             seeds: "42,7,2026,99,123"
-            parallel: 5
 
     dataset:
         class: DatasetH
@@ -88,30 +69,19 @@ task:
                     label: "Ref($close,-6)/Ref($close,-1)-1"
                     feature_fields: "{{ FEATURES }}"
                     infer_processors:
-                        - class: DropAllNaN
+                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                          kwargs: {}
+                        - { class: ProcessInf, kwargs: {} }
-                        - class: ProcessInf
+                        - { class: CSRankNorm, kwargs: {} }
-                          kwargs: {}
+                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - class: CSRankNorm
+                        - { class: Fillna, kwargs: {} }
-                          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
+        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-          module_path: qlib.workflow.record_temp
+        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
-          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:
@@ -119,12 +89,7 @@ task:
                   strategy:
                       class: TopkDropoutStrategy
                       module_path: qlib.contrib.strategy
-                      kwargs:
+                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
-                          signal: "<PRED>"
-                          topk: 20
-                          n_drop: 1
-                          only_tradable: true
-                          risk_degree: 0.95
                   backtest:
                       start_time: 2026-01-04
                       end_time: 2026-08-10

queue/workflows/q18_optstop.yaml

@@ -0,0 +1,106 @@
+# QUEUE-18 — OptimalStopControl clean re-test vs TopkDropout (exp 13/14 claim).
+# CLAIMS.md HYPOTHESIS: "TopkDropout beats stochastic-control OptimalStopControl on
+# the ensemble signal" — exp 13/14 were pre-clean-lake; never re-tested post-reset.
+# Same compact signal as the exp-26 reference; ONLY the strategy changes to
+# OptimalStopControl with exp-13 params (entry 0.85 / exit 0.7 / hold 10 / sl -0.08).
+# PREREQUISITE: tac_qlib/contrib/strategy/optimal_stop.py must be synced to the venv
+# site-packages snapshot before running (see /app/AGENTS.md).
+# Acceptance: TopkDropout net_IR >= stop-control net_IR; document cost drag of both.
+# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q18_optstop.yaml \
+#        experiment_name=tac-rd-q18-optstop
+{%- 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" %}
+
+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-q18-optstop" }
+
+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: OptimalStopControl
+                      module_path: tac_qlib.contrib.strategy.optimal_stop
+                      kwargs: { signal: "<PRED>", topk: 10, entry_pct: 0.85, exit_pct: 0.7, max_hold_days: 10, min_hold_days: 2, sl: -0.08 }
+                  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