MODEL CARD · XGB · REGIME

Regime-routed XGBoost family

One XGBoost classifier per admitted regime and instrument, chosen by the regime model; the global classifier is the fallback.

FROZEN
SOURCE-INSPECTED
DOWN / NEUTRAL / UP

Evidence labels used here: reported stated by the run owner; independently tested re-checked by a tool, with method, date and scope; source-inspected read from code or committed files.

Intended use

Estimate Down, Neutral and Up probabilities for a stored historical bar and explain them in the terminal. Its output is shown as model output, not a signal.

Not for

Live trading, recommendations or position sizing.

Target

The forward target is the close return to the sixth subsequent M5 row. Up is assigned when r_t>0.001; Down when r_t<−0.001; Neutral includes both boundaries and the intervening region. Elapsed horizon must be 25–35 minutes.

Source: experiments/cp2_report_draft2_v1/manuscript_v1/CH03/CH03_DRAFT2.md §3.2.2 · source-inspected

Inputs

The recorded final classifier schema has 170 ordered inputs, including volume-profile features (point-of-control distance, value-area position). Target, future_return, horizon_elapsed and identity fields are excluded from classifier input.

Source: experiments/cp2_report_draft2_v1/manuscript_v1/CH03/CH03_DRAFT2.md §3.2.3 · source-inspected

Settings

Same explicit settings as the global model: multi:softprob, 200 trees, depth 4, learning_rate=0.05, subsample=0.8, colsample_bytree=0.8, seed 42, tree_method hist. A regime is admitted with ≥1,000 training rows and ≥2 distinct labels; otherwise the global fallback is used.

Source: experiments/cp2_report_draft2_v1/manuscript_v1/CH03/CH03_DRAFT2.md §3.2.4 Table 3.3 · source-inspected

Evaluation design

Development uses four expanding folds with initial training 60%, validation 10% and step 10%; the latest 15% rounded row count is the fixed holdout; a later historical fresh period is evaluated separately.

Source: experiments/cp2_report_draft2_v1/manuscript_v1/CH03/CH03_DRAFT2.md §3.2.6 · source-inspected

Known failure modes

MR02: the inspected original adjacent split functions did not establish an explicit target-maturity purge. No affected-row count is calculated and no performance correction is claimed.

Routing depends on retrospective HMM state assignments (MR-01).

Source: experiments/cp2_report_draft2_v1/manuscript_v1/CH03/CH03_DRAFT2.md §3.2.2, §3.2.5; MR02 record · source-inspected

Version

Frozen original CP2 bundles. Model files are not published on this site.

Validation

Headline model figures: development, fixed holdout and historical fresh

values as written in the Chapter 4 claims ledger
populations reported separately, never pooled

Direction-model figures exactly as the Chapter 4 results-claims ledger of the CP2 report draft records them: the regime-adaptive model under its original whole-sequence regime labels, and the unchanged global model relisted from its saved metrics, for each instrument on the development folds (equal mean of the four folds, as the file gives it), the fixed holdout and the historical fresh period. Populations are named as the ledger names them; the ledger rows give no calendar dates. Exploratory research results, not a trading recommendation and not investment advice.

Headline model figures: development, fixed holdout and historical fresh: values with source and evidence label
Value	Result	Evidence	Source
QQQM development (equal mean of the four folds) whole-sequence Macro-F1 (C04-R179)	0.3896784170912872	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R179/value_as_written`
QQQM development (equal mean of the four folds) whole-sequence accuracy (C04-R181)	0.468969167659124	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R181/value_as_written`
QQQM fixed holdout whole-sequence Macro-F1 (C04-R99)	0.391185042763235	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R99/value_as_written`
QQQM fixed holdout whole-sequence accuracy (C04-R101)	0.47222013946164804	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R101/value_as_written`
QQQM fixed holdout global Macro-F1 (relisted) (C04-R105)	0.3559988734227451	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R105/value_as_written`
QQQM historical fresh whole-sequence Macro-F1 (C04-R109)	0.3943384106077888	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R109/value_as_written`
QQQM historical fresh whole-sequence accuracy (C04-R111)	0.44534412955465585	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R111/value_as_written`
QQQM historical fresh global Macro-F1 (relisted) (C04-R115)	0.3624472129438476	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R115/value_as_written`
XAUUSD development (equal mean of the four folds) whole-sequence Macro-F1 (C04-R185)	0.3439477396205161	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R185/value_as_written`
XAUUSD development (equal mean of the four folds) whole-sequence accuracy (C04-R187)	0.7081746552856205	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R187/value_as_written`
XAUUSD fixed holdout whole-sequence Macro-F1 (C04-R159)	0.40280872264291845	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R159/value_as_written`
XAUUSD fixed holdout whole-sequence accuracy (C04-R161)	0.4931092987260388	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R161/value_as_written`
XAUUSD fixed holdout global Macro-F1 (relisted) (C04-R165)	0.3634154387733373	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R165/value_as_written`
XAUUSD historical fresh whole-sequence Macro-F1 (C04-R169)	0.37821750685585914	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R169/value_as_written`
XAUUSD historical fresh whole-sequence accuracy (C04-R171)	0.4774417451660882	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R171/value_as_written`
XAUUSD historical fresh global Macro-F1 (relisted) (C04-R175)	0.3465026681071915	reported	`experiments/cp2_report_draft2_v1/manuscript_v1/CH04/CH04_RESULTS_CLAIMS.csv` @ fa88153ed383 · `C04-R175/value_as_written`

MR-01: causal versus whole-sequence regime labels

REPLICATION GATE PASS IN EVERY POPULATION

sensitivity analysis of a stated limitation; exploratory; not a new model, not confirmatory
primary variant: causal_online_viterbi_cold

The original regime labels were decoded over whole sequences, which can use bars after the row being labelled. MR-01 re-decoded them causally (online, no later bars) and compared the two. For each instrument and population the table gives the replication-gate status and the share of rows on which the causal labels equal the whole-sequence labels, as written in the metrics file. Populations are not pooled and instruments are not averaged.

Dot plot of MR-01 label agreement for 12 populations (QQQM and XAUUSD development folds 1 to 4, fixed holdout, historical fresh); every value is between 0.98 and 1. — Each dot is one population's share of rows on which causal (online) regime labels equal the whole-sequence labels, as written in the MR-01 metrics file. The lowest plotted value is 0.9861179970252851 (XAUUSD · historical fresh) and the highest is 0.9985443959243085 (QQQM · development fold 4). The axis starts at 0.98, not 0. Evidence label: reported (owner-run; metrics file as posted; not recomputed).

MR-01: causal versus whole-sequence regime labels: values with source and evidence label
Value	Result	Evidence	Source
Label recorded with the result	sensitivity analysis of a stated limitation; exploratory; not a new model, not confirmatory	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/label`
Primary causal variant	causal_online_viterbi_cold	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/primary_variant`
Run date	2026-11-02	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/run_date`
QQQM development fold 1: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1development_fold_1/status`
QQQM development fold 1: label agreement, causal vs whole-sequence	0.9958978430594151	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1development_fold_1/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
QQQM development fold 2: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1development_fold_2/status`
QQQM development fold 2: label agreement, causal vs whole-sequence	0.9943099113404791	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1development_fold_2/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
QQQM development fold 3: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1development_fold_3/status`
QQQM development fold 3: label agreement, causal vs whole-sequence	0.9915310308323408	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1development_fold_3/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
QQQM development fold 4: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1development_fold_4/status`
QQQM development fold 4: label agreement, causal vs whole-sequence	0.9985443959243085	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1development_fold_4/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
QQQM fixed holdout: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1fixed_holdout/status`
QQQM fixed holdout: label agreement, causal vs whole-sequence	0.9939266701657045	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1fixed_holdout/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
QQQM historical fresh: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1historical_fresh/status`
QQQM historical fresh: label agreement, causal vs whole-sequence	0.9919028340080972	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/QQQM~1historical_fresh/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
XAUUSD development fold 1: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1development_fold_1/status`
XAUUSD development fold 1: label agreement, causal vs whole-sequence	0.9983453709783322	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1development_fold_1/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
XAUUSD development fold 2: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1development_fold_2/status`
XAUUSD development fold 2: label agreement, causal vs whole-sequence	0.9965331582403152	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1development_fold_2/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
XAUUSD development fold 3: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1development_fold_3/status`
XAUUSD development fold 3: label agreement, causal vs whole-sequence	0.9977675640183847	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1development_fold_3/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
XAUUSD development fold 4: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1development_fold_4/status`
XAUUSD development fold 4: label agreement, causal vs whole-sequence	0.9962967826657912	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1development_fold_4/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
XAUUSD fixed holdout: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1fixed_holdout/status`
XAUUSD fixed holdout: label agreement, causal vs whole-sequence	0.9903559947612811	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1fixed_holdout/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`
XAUUSD historical fresh: replication gate	PASS	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1historical_fresh/status`
XAUUSD historical fresh: label agreement, causal vs whole-sequence	0.9861179970252851	reported (owner-run; metrics file as posted; not recomputed)	`experiments/cp2_mr01_causal_v1/results/mr01_metrics.json` @ fa88153ed383 · `/populations/XAUUSD~1historical_fresh/variants/causal_online_viterbi_cold/label_agreement_with_whole_sequence`

MR-01 frozen protocol experiments/cp2_mr01_causal_v1/PROTOCOL_FROZEN_v1.md, sha256 e06465f6c87ed7e40b66b381b9b767053c738c72d02a631bea8185b0d469fbca (computed from the committed file at build time) · source-inspected

Per-population results are on the Research page.

Frozen-protocol hash

UNAVAILABLE No committed file records a frozen-protocol hash for the original CP2 model bundle. The bundle hash is checked in the private terminal's model registry; model files are not published.

All model cards