{ "id": "SMARTBETA-1", "title": "Smart beta: backtest vs live. Did the factors deliver after the ETFs launched?", "written_at_utc": "2026-09-26T15:59:15Z", "governing_document": "PREREG.md (sealed); this JSON is its machine-readable companion and is hashed inside it", "rubric": "Holdout Labs Fragility Rubric v1.2 (docs/RUBRIC-v1.2.md, SHA-256 81bc60b5bf4520fdfb91c43b37883c30a9a2061903442d1e8a8b05f3d37a71fc, sealed 2026-09-25T20:33:45Z), implemented by holdout-audit 0.4.0", "audits": [ { "id": "smartbeta-mtum", "ticker": "MTUM", "name": "iShares MSCI USA Momentum Factor ETF", "inception": "2013-04-16", "index_history": [ [ "2013-04-16", "MSCI USA Momentum Index" ], [ "2020-12-01", "MSCI USA Momentum SR Variant Index (same parent methodology; constituent changes spread over several days before each rebalance)" ] ], "factor": "momentum", "objective": "beat_benchmark", "claim": "MSCI (2013): 'All the MSCI World Factor Indexes shown in Exhibit 11 outperform the MSCI World Index over the period shown, June 1988 to June 2013' (Exhibit 11 includes the Momentum index), and 'The MSCI Momentum and MSCI Quality Indexes historically exhibited the strongest historical returns'.", "claim_direction": "higher return than the cap-weighted market", "french_long_short": "Mom (UMD), F-F_Momentum_Factor, monthly", "french_long_only": "top decile, value-weighted, 10 Portfolios Formed on Momentum (prior 12-2), monthly, minus market", "benchmark": "buy-and-hold SPY (SPDR S&P 500 ETF Trust), total return from Yahoo adjusted close", "max_return_shortfall_annual": null, "audit_period": "first Yahoo daily close on or after 2013-04-16 to the close of 2026-09-25 inclusive", "holdout_split": "rubric default: start of the last 30% of the sample", "cost": "5 bps one-way on the day-1 purchase only (turnover 1.0 on day 1, 0 after); fund expenses are already inside the adjusted-close total return", "n_trials_declared": 1, "declaration_file": "declaration-mtum.json", "secondary_objectives": [ "improve_sharpe" ] }, { "id": "smartbeta-qual", "ticker": "QUAL", "name": "iShares MSCI USA Quality Factor ETF", "inception": "2013-07-16", "index_history": [ [ "2013-07-16", "MSCI USA Quality Index" ], [ "2015-08-31", "MSCI USA Sector Neutral Quality Index" ] ], "factor": "quality", "objective": "beat_benchmark", "claim": "MSCI (2013): 'All the MSCI World Factor Indexes shown in Exhibit 11 outperform the MSCI World Index over the period shown, June 1988 to June 2013' (Exhibit 11 includes the Quality index), and 'The MSCI Momentum and MSCI Quality Indexes historically exhibited the strongest historical returns'.", "claim_direction": "higher return than the cap-weighted market", "french_long_short": "RMW (robust minus weak profitability), F-F_Research_Data_5_Factors_2x3, monthly (from 1963-07)", "french_long_only": "highest quintile, value-weighted, Portfolios Formed on Operating Profitability, monthly, minus market", "benchmark": "buy-and-hold SPY (SPDR S&P 500 ETF Trust), total return from Yahoo adjusted close", "max_return_shortfall_annual": null, "audit_period": "first Yahoo daily close on or after 2013-07-16 to the close of 2026-09-25 inclusive", "holdout_split": "rubric default: start of the last 30% of the sample", "cost": "5 bps one-way on the day-1 purchase only (turnover 1.0 on day 1, 0 after); fund expenses are already inside the adjusted-close total return", "n_trials_declared": 1, "declaration_file": "declaration-qual.json", "secondary_objectives": [ "improve_sharpe" ] }, { "id": "smartbeta-vlue", "ticker": "VLUE", "name": "iShares MSCI USA Value Factor ETF", "inception": "2013-04-16", "index_history": [ [ "2013-04-16", "MSCI USA Value Weighted Index" ], [ "2015-08-31", "MSCI USA Enhanced Value Index" ] ], "factor": "value", "objective": "beat_benchmark", "claim": "MSCI (2013): 'All the MSCI World Factor Indexes shown in Exhibit 11 outperform the MSCI World Index over the period shown, June 1988 to June 2013' (Exhibit 11 includes the Value Weighted index), and 'Tilts towards these factors such as Value, Low Size, and Momentum historically produced excess long-term returns'.", "claim_direction": "higher return than the cap-weighted market", "french_long_short": "HML, F-F_Research_Data_Factors, monthly", "french_long_only": "highest quintile, value-weighted, Portfolios Formed on Book-to-Market, monthly, minus market", "benchmark": "buy-and-hold SPY (SPDR S&P 500 ETF Trust), total return from Yahoo adjusted close", "max_return_shortfall_annual": null, "audit_period": "first Yahoo daily close on or after 2013-04-16 to the close of 2026-09-25 inclusive", "holdout_split": "rubric default: start of the last 30% of the sample", "cost": "5 bps one-way on the day-1 purchase only (turnover 1.0 on day 1, 0 after); fund expenses are already inside the adjusted-close total return", "n_trials_declared": 1, "declaration_file": "declaration-vlue.json", "secondary_objectives": [ "improve_sharpe" ] }, { "id": "smartbeta-size", "ticker": "SIZE", "name": "iShares MSCI USA Size Factor ETF", "inception": "2013-04-16", "index_history": [ [ "2013-04-16", "MSCI USA Risk Weighted Index" ], [ "2018-11-30", "MSCI USA Low Size Index" ] ], "factor": "size", "objective": "beat_benchmark", "claim": "MSCI (2013): 'All the MSCI World Factor Indexes shown in Exhibit 11 outperform the MSCI World Index over the period shown, June 1988 to June 2013' (Exhibit 11 includes the Risk Weighted index, SIZE's index at launch), and 'Tilts towards these factors such as Value, Low Size, and Momentum historically produced excess long-term returns'.", "claim_direction": "higher return than the cap-weighted market", "french_long_short": "SMB, F-F_Research_Data_Factors, monthly", "french_long_only": null, "benchmark": "buy-and-hold SPY (SPDR S&P 500 ETF Trust), total return from Yahoo adjusted close", "max_return_shortfall_annual": null, "audit_period": "first Yahoo daily close on or after 2013-04-16 to the close of 2026-09-25 inclusive", "holdout_split": "rubric default: start of the last 30% of the sample", "cost": "5 bps one-way on the day-1 purchase only (turnover 1.0 on day 1, 0 after); fund expenses are already inside the adjusted-close total return", "n_trials_declared": 1, "declaration_file": "declaration-size.json", "secondary_objectives": [ "improve_sharpe" ] }, { "id": "smartbeta-usmv", "ticker": "USMV", "name": "iShares MSCI USA Min Vol Factor ETF", "inception": "2011-10-18", "index_history": [ [ "2011-10-18", "MSCI USA Minimum Volatility Index" ] ], "factor": "low volatility", "objective": "reduce_drawdown", "claim": "MSCI (2013): 'the MSCI Minimum Volatility Indexes exhibited sizable risk reduction' and (Exhibit 11, which includes the Minimum Volatility index) 'All the MSCI World Factor Indexes shown in Exhibit 11 outperform the MSCI World Index'. iShares today: 'The fund offers a way to reduce risk while maintaining equity exposure'.", "claim_direction": "smaller drawdowns and tail losses than the market at no more than a small return cost", "french_long_short": "lowest minus highest quintile, value-weighted, Portfolios Formed on Variance, monthly (from 1963-07)", "french_long_only": "lowest quintile, value-weighted, Portfolios Formed on Variance, monthly, minus market", "benchmark": "buy-and-hold SPY (SPDR S&P 500 ETF Trust), total return from Yahoo adjusted close", "max_return_shortfall_annual": 0.01, "audit_period": "first Yahoo daily close on or after 2011-10-18 to the close of 2026-09-25 inclusive", "holdout_split": "rubric default: start of the last 30% of the sample", "cost": "5 bps one-way on the day-1 purchase only (turnover 1.0 on day 1, 0 after); fund expenses are already inside the adjusted-close total return", "n_trials_declared": 1, "declaration_file": "declaration-usmv.json", "secondary_objectives": [ "improve_sharpe", "beat_benchmark" ] }, { "id": "smartbeta-splv", "ticker": "SPLV", "name": "Invesco S&P 500 Low Volatility ETF (PowerShares at launch)", "inception": "2011-05-05", "index_history": [ [ "2011-05-05", "S&P 500 Low Volatility Index (index inception 2011-04-20; earlier values back-tested)" ] ], "factor": "low volatility", "objective": "reduce_drawdown", "claim": "S&P DJI (2011-12): 'a diversified equity index that, in back-tested results, has out-performed the S&P 500 over the near, medium, and long term, with less volatility'; 'how can I potentially reduce equity risk while preserving the long term return advantages that stocks generally provide?'", "claim_direction": "smaller drawdowns and tail losses than the market at no more than a small return cost", "french_long_short": "lowest minus highest quintile, value-weighted, Portfolios Formed on Variance, monthly (from 1963-07)", "french_long_only": "lowest quintile, value-weighted, Portfolios Formed on Variance, monthly, minus market", "benchmark": "buy-and-hold SPY (SPDR S&P 500 ETF Trust), total return from Yahoo adjusted close", "max_return_shortfall_annual": 0.01, "audit_period": "first Yahoo daily close on or after 2011-05-05 to the close of 2026-09-25 inclusive", "holdout_split": "rubric default: start of the last 30% of the sample", "cost": "5 bps one-way on the day-1 purchase only (turnover 1.0 on day 1, 0 after); fund expenses are already inside the adjusted-close total return", "n_trials_declared": 1, "declaration_file": "declaration-splv.json", "secondary_objectives": [ "improve_sharpe", "beat_benchmark" ] } ], "sources_for_claims": { "MSCI_2013": "Bender, J., Briand, R., Melas, D. & Subramanian, R. A. (2013). Foundations of Factor Investing. MSCI Research Insight, December 2013", "SPDJI_2011": "S&P Dow Jones Indices marketing text for the S&P 500 Low Volatility Index, as reproduced in HSBC USA Inc. free-writing prospectus, SEC EDGAR accession 0001144204-12-005653 (2012-02-03)" }, "settings": { "bootstrap_draws": 1000, "stationary_bootstrap_mean_block": "max(5, T^(1/3))", "seed": 20260925, "periods_per_year": 252, "cscv_blocks": 16, "base_cost_bps": 5.0, "end_date": "2026-09-25" }, "inference": { "primary_family": "the 6 primary tests (one per ETF, on its declared primary objective)", "primary_statistic": "each audit's one-sided p-value for its primary objective statistic as computed by the rubric's multiple-testing ('haircut') check with N = 1: for (a) P(Z >= annualised excess Sharpe x sqrt(years)); for (b) the paired-bootstrap z of dCVaR", "multiplicity": "Holm step-down across the 6 primary tests, family-wise alpha 0.05", "delivered_rule": "An ETF 'delivered on its claim' only if its Holm-adjusted p <= 0.05 AND its primary objective check is not FAIL (objective (a): SPA check not FAIL and annualised mean excess > 0; objective (b): drawdown check and tolerance check both not FAIL)", "secondary_family": "8 tests: (c) improve Sharpe for all 6 ETFs, and (a) beat benchmark for USMV and SPLV; Holm across these 8, reported, never used for the 'delivered' wording" }, "publication_commitment": "Publish all: every ETF, every primary and secondary result, and the descriptive before-vs-after tables, whether the factors delivered or not." }