{
  "version": "1.2",
  "released": "2026-11-10",
  "claims": [
    {
      "id": "frequency",
      "question": "How often did ATM implied vol exceed forward realized vol?",
      "finding": "It did on 65% of 23,104 symbol-days; the median difference was +1.4 volatility points.",
      "sample": "23,104 overlapping symbol-days across 11 instruments; origin dates 2017-03-01 to 2026-10-01; starts vary by symbol.",
      "method": "30-calendar-day ATM IV minus the next 21 sessions' intraday-benchmark realized vol, annualized with 252.",
      "uncertainty": "Pooled frequency and median are descriptive. Per-symbol mean intervals use session-aware HAC25 and HAC63; 11 of 11 volatility-mean HAC25 intervals include zero.",
      "limitation": "The ATM-based proxy and overlapping windows are not independent trades, an option-strip premium, or investment returns.",
      "source_keys": [
        "pooled_all",
        "validation.descriptive"
      ],
      "data": "figure-5.csv"
    },
    {
      "id": "joint",
      "question": "Does trailing RV improve the IV-only forecast?",
      "finding": "Adding RV lowered observed forecast MSE on 3 of 11 symbols; 0 positive improvements had a pointwise 95% HAC25 interval entirely above zero.",
      "sample": "20,126 forecast symbol-days; common origins across models within each symbol.",
      "method": "Expanding OLS with an intercept, at least 252 eligible training outcomes, original-session embargo and outcomes ending before each forecast origin.",
      "uncertainty": "Paired squared-error differences, pointwise normal-approximation HAC25 and HAC63 intervals; conditional on the forecast path, not formal nested-model superiority tests.",
      "limitation": "This bounded historical comparison is exploratory; it does not establish that RV is universally useless or validate trading profitability.",
      "source_keys": [
        "validation.forecast",
        "validation.forecast_summary"
      ],
      "data": "forecasting.csv"
    },
    {
      "id": "tercile",
      "question": "Did the tested high-reading rule separate forward outcomes?",
      "finding": "High-minus-low ATM variance differences were positive on 8 of 11 symbols. The unadjusted test was significant for 1 of 11, compared with 0 after Holm correction.",
      "sample": "21,274 overlapping symbol-days; ranks use the preceding 252 sessions and require at least 189 available prior readings.",
      "method": "Rank against the preceding 252 sessions with at least 189 prior readings; top third versus bottom third; centered conditional-mean influence scores, original-session Newey-West25, two-sided normal p-values and Holm across 11 symbols.",
      "uncertainty": "The Holm result addresses this family of 11 tests, not a search across every strategy specification.",
      "limitation": "This tests one percentile rule and a measurement proxy; it is not a z-score entry/sizing prescription or an options backtest.",
      "source_keys": [
        "signal",
        "signal_summary"
      ],
      "data": "figure-8.csv"
    }
  ]
}