ARIMA_SAX_Hybrid_Forecaster/results/MALE5-ML/MALE5_ML_MANIFEST.json

{
    "manifest_id":  "MALE5-ML-MANIFEST-v0.1.0-frozen",
    "research_family":  "MALE5-ML",
    "title":  "MULTIVARIATE MALE5 CLASSIFIER RESEARCH PROTOCOL — design manifest",
    "status":  "DESIGN FROZEN — EXECUTION NOT AUTHORIZED",
    "design_session_date":  "2026-08-26",
    "freeze_date":  "2026-08-27",
    "branch":  "main",
    "project":  {
                    "name":  "ARIMA_SAX_Hybrid_Forecaster",
                    "workspace":  "D:\\TradingTerminal\\MetaTrader 5\\MQL5\\Shared Projects\\ARIMA_SAX_Hybrid_Forecaster",
                    "remote":  "https://forge.mql5.io/chiki2bum2/ARIMA_SAX_Hybrid_Forecaster.git"
                },
    "protocol":  {
                     "path":  "results/MALE5-ML/MALE5_ML_PROTOCOL.md",
                     "version":  "male5-ml-v0.1.0-frozen",
                     "sha256":  "6226f12be14e1ed805542c0be84273cd20b1cee0a7ffecfb0b594eec2f5d8e7f"
                 },
    "dependency":  {
                       "upstream_url":  "https://github.com/MegaJoctan/MALE5",
                       "canonical_tag":  "v3.2.0",
                       "exact_commit":  "d6fb0695a7c2fbeaa03de379557a8b5447915384",
                       "archive_sha256":  "ad161d75ae0b54ee54a1fd3b0d48c315cf776eebc97077a4b1ae7a629f0c0d4d",
                       "canonical_local_path":  "D:\\TradingTerminal\\MetaTrader 5\\MQL5\\Include\\MALE5",
                       "compile_smoke":  {
                                             "errors":  0,
                                             "warnings":  0,
                                             "note":  "CRandomForestClassifier include/instantiate/fit/predict smoke, build 6140 AVX512"
                                         },
                       "predict_proba":  "UNSUPPORTED — protocol binary classification only",
                       "policy":  "v3.2.0 only; no v3.5.0; no HEAD; no version mixing; no patching"
                   },
    "dependency_corresponding_hashes_sha256":  {
                                                   "Random_Forest_mqh":  "cb0935ac6b69283ff0d2de2b2fc7c1460d14983f23a56e0b3d2e9ce8dccfc0db",
                                                   "tree_mqh":  "9568b9f903876acca0cfa1340cffe19f071fcafeeb0c67ae4802974d6dd23b2a",
                                                   "correspondence_note":  "RF file verified to canonical value in freeze session"
                                               },
    "source_dataset":  {
                           "path":  "results/R1_real_data/XAUUSDc_M1_raw.json",
                           "symbol":  "XAUUSDc",
                           "timeframe":  "M1",
                           "n_bars":  397558,
                           "source_hash_raw_json_sha256":  "5472357e67f70f7d1bfef8f9de67fcce91ee6f26208072d7a6766b06c158ee6e",
                           "verify_status":  "PASS — matches frozen R2-H identity",
                           "derived_csv":  "results/R1_real_data/XAUUSDc_M1.csv",
                           "tick_data":  "D:\\TradingTerminal\\MetaTrader 5\\MQL5\\Files\\XAUUSD_mt5_ticks.csv",
                           "tick_features":  "NONE — no tick features in MALE5-ML v0.1"
                       },
    "oos_origin_list":  {
                            "path":  "results/R2-H/origins_H060.csv",
                            "horizon_minutes":  60,
                            "n_origins":  3169,
                            "sha256":  "e7b5132c321f5350ec1e231d49d68dbc29468cdf9ee6a5014a2764aaf36eb9af",
                            "verify_status":  "PASS — matches frozen identity; reused, NOT modified"
                        },
    "horizon":  {
                    "value_minutes":  60,
                    "definition":  "elapsed-time horizon; t_end = first valid M1 bar at/after timestamp(o)+60min; gap 5 min"
                },
    "target":  {
                   "definition":  "y(o) = 1 if Close[t_end] \u003e Close[o] else 0; zero move =\u003e class 0",
                   "binary_only":  true
               },
    "features":  {
                     "grid":  "M1 only",
                     "scaler":  "OFF",
                     "warmup_W_m1_bars":  40,
                     "definitions":  {
                                         "F1_short_momentum":  "(C[o]-C[o-5])/C[o-5]",
                                         "F2_medium_momentum":  "(C[o]-C[o-15])/C[o-15]",
                                         "F3_trend_slope":  "OLS slope of log(C) over 30 bars, slope*30/ATR20(o)",
                                         "F4_distance_from_SMA20":  "C[o]/SMA20(o)-1",
                                         "F5_recent_range":  "(max10-min10)/ATR20(o)",
                                         "F6_normalized_volatility":  "ATR20(o)/C[o]",
                                         "F7_session_phase":  "hour_of_day(o)/24.0"
                                     },
                     "atr20_definition":  "close-only deterministic ATR proxy: rolling mean of |C[i]-C[i-1]| over trailing 20 M1 bars (NOT Wilder ATR)"
                 },
    "model":  {
                  "class":  "CRandomForestClassifier",
                  "source":  "MALE5 v3.2.0 MALE5/Ensemble/Random Forest.mqh",
                  "parameters":  {
                                     "n_trees":  100,
                                     "minsplit":  2,
                                     "max_depth":  10,
                                     "random_state":  42
                                 },
                  "supported_api":  [
                                        "fit",
                                        "predict"
                                    ],
                  "prohibited":  [
                                     "min_samples_leaf",
                                     "criterion",
                                     "n_jobs",
                                     "predict_proba"
                                 ],
                  "policy":  "single fixed model; no model comparison; no tuning"
              },
    "training_window_rule":  {
                                 "type":  "deterministic causal dense-M1 construction",
                                 "notes":  [
                                               "per OOS origin o, valid training bar t iff:",
                                               "1) t \u003e= W=40 M1 bars (features available)",
                                               "2) t not in frozen OOS list L (OOS reserved for evaluation only)",
                                               "3) target endpoint t_end(t) resolves and no gap \u003e 5 min within (t, t_end(t)]",
                                               "4) t_end(t) \u003c o (training labels never cross into OOS; no lookahead)",
                                               "classifier refit from scratch at each origin on T(o); causal expanding window",
                                               "no shuffle; no random split; no future preprocessing"
                                           ]
                             },
    "preprocessing":  {
                          "scaler":  "OFF",
                          "normalization":  "none",
                          "notes":  "no full-dataset preprocessing; tree scale-invariance; F-values dimensionless/price-relative"
                      },
    "baselines":  {
                      "majority":  "modal class of that origin\u0027s causal training labels T(o); tie -\u003e class 0; per-origin, causal",
                      "drift":  "DriftBaseline sign (last 40 closes slope projected H); label 1 if drift\u003e0 else 0; causal fixed",
                      "naive":  "zero-return forecast; classification reference only"
                  },
    "metrics":  {
                    "primary":  [
                                    "balanced accuracy (MBB 95% CI)",
                                    "directional accuracy (MBB 95% CI)",
                                    "paired classification error vs Majority (CI lower bound \u003e 0)",
                                    "paired classification error vs Drift (CI lower bound \u003e 0)"
                                ],
                    "secondary":  [
                                      "gross return/trade (ATR units)",
                                      "net return/trade (gross - cost, ATR units)",
                                      "gross/cost ratio",
                                      "cost/range ratio",
                                      "trade coverage",
                                      "time-normalized economics (per 60 min)",
                                      "EARLY/MIDDLE/LATE descriptive"
                                  ],
                    "prohibited":  [
                                       "Brier",
                                       "log-loss",
                                       "calibration",
                                       "synthetic probabilities"
                                   ]
                },
    "statistical_inference":  {
                                  "method":  "Moving Block Bootstrap (MBB)",
                                  "block_length_B":  60,
                                  "block_unit":  "OOS origins (chronological evaluation series)",
                                  "repetitions":  10000,
                                  "seed":  20260827,
                                  "confidence_level":  0.95,
                                  "ci_type":  "percentile [2.5%, 97.5%]",
                                  "effective_sample_size":  "n_eff = floor(n_usable / B); n_origins~3169 =\u003e n_eff~52",
                                  "coherence_check":  "paired error differences defined per OOS origin on common chronological series; block resampling with B=60 preserved; fixed before execution"
                              },
    "economic":  {
                     "cost_bps_round_trip":  7.57,
                     "spread_bps":  1.57,
                     "commission_bps":  6.00,
                     "status":  "PRE-REGISTERED GLOBAL CONSTANT",
                     "formula":  "cost_atr(o) = (7.57/10000) * close(o) / ATR20(o)",
                     "gross_net_separate":  true,
                     "sensitivity":  {
                                         "0.5x":  "descriptive only",
                                         "2x":  "descriptive only",
                                         "decision_impact":  "none"
                                     }
                 },
    "success_criteria":  [
                             "better than Majority (MBB CI lower bound of paired error difference \u003e 0)",
                             "better than Drift (MBB CI lower bound of paired error difference \u003e 0)",
                             "dependence-aware statistical support",
                             "no material reversal across EARLY/MIDDLE/LATE (point estimate advantage \u003e= 0 in every segment toward both baselines)",
                             "positive gross return/return (CI lower bound \u003e 0) for any trading claim",
                             "positive net return (CI lower bound \u003e 0) for economic viability"
                         ],
    "hard_stop_conditions":  [
                                 "dependency identity mismatch",
                                 "predict_proba or non-v3.2.0 API required",
                                 "RF params unsupported",
                                 "origin list modified/regenerated / hash mismatch",
                                 "dataset hash mismatch",
                                 "no-lookahead failure (mutation testing)",
                                 "tuning from results (model/MBB/seed/cost)",
                                 "protocol contradiction or unresolved spec",
                                 "any execution before separate EXECUTION COMPLETION gate",
                                 "accidental R1-R / R2-H modification"
                             ],
    "no_lookahead_gates":  {
                               "F1":  "feature construction",
                               "F2":  "target construction",
                               "F3":  "ATR20 construction",
                               "F4":  "SMA20/range/slope windows",
                               "F5":  "training data boundary (t_end(t) \u003c o; t not in L)",
                               "F6":  "normalization/scaler (OFF)",
                               "F7":  "horizon endpoint determination",
                               "F8":  "cost information",
                               "F9":  "tick-derived information (none used)"
                           },
    "governance":  {
                       "freeze_commit_message":  "research: freeze MALE5-ML protocol",
                       "push":  "NOT PERFORMED — not authorized in this session",
                       "git_rule":  "single governance commit; no history rewrite; no auto-push"
                   },
    "generated_design_artifacts":  {
                                       "protocol":  "results/MALE5-ML/MALE5_ML_PROTOCOL.md",
                                       "manifest":  "results/MALE5-ML/MALE5_ML_MANIFEST.json"
                                   },
    "note":  "MALE5-ML = DESIGN FROZEN; EXECUTION NOT AUTHORIZED. No model executed, no metrics computed, no prediction/backtest/OOS/tuning artifact produced. Required next gate: EXECUTION AUTHORIZATION. Agent does not auto-git commit or push for experimental work."
}