{
 "slug": "weekly-calibration-2026-11-02",
 "series": "weekly",
 "series_label": "WEEKLY · CALIBRATION",
 "issue": 14,
 "title": "Weekly Calibration #14",
 "language": "en",
 "window_start": "2026-11-02T00:00:00+00:00",
 "window_end": "2026-11-09T00:00:00+00:00",
 "window_text": "Nov 2-8, 2026 UTC",
 "cutoff": "2026-11-09T16:00:00+00:00",
 "generated_at": "2026-11-10T14:16:43+00:00",
 "methodology": "v1.1 (2026-08-10)",
 "methodology_hash": "e66c7e8c864a2233",
 "source": "weekly_metrics_2026-11-02.json",
 "hit_rule": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl",
 "bibtex_key": "mm_calibration_2026w45",
 "market_state": {
  "panel": "market_state_6p2",
  "week": {
   "start": "2026-11-02",
   "end": "2026-11-09"
  },
  "prev_week": {
   "start": "2026-10-26",
   "end": "2026-11-02"
  },
  "current": {
   "btc_net_pct": -4.47,
   "realized_vol_ann_pct": 55.31,
   "volume_top5_usd_bn": 14.2555,
   "volume_top5_wow_pct": -4.0,
   "avg_pairwise_corr": 0.94
  },
  "previous_as_published_issue13": {
   "btc_net_pct": -2.25,
   "realized_vol_ann_pct": 34.74,
   "volume_top5_usd_bn": 14.8563,
   "avg_pairwise_corr": 0.93
  },
  "snapshot_line": "BTC net -4.47% (prior -2.25%) - ann vol 55.3% (was 34.7%) - TOP5 volume $14.26B, -4% w/w - pairwise corr 0.94 (was 0.93)",
  "exchange": "binance",
  "audit_filter_applied": true,
  "source": "single-exchange (binance) daily candle recompute, market_state_2026-11-02.json; prior-week values as published in issue #13",
  "audit_note": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #13 after the audit that found the raw table mixes two exchanges; issue #13 values are as published.",
  "prev_week_control": {
   "published_issue3": {
    "btc_net_pct": -2.25,
    "realized_vol_ann_pct": 34.74,
    "volume_top5_usd_bn": 14.8563,
    "avg_pairwise_corr": 0.93
   },
   "published_issue13": {
    "btc_net_pct": -2.25,
    "realized_vol_ann_pct": 34.74,
    "volume_top5_usd_bn": 14.8563,
    "avg_pairwise_corr": 0.93
   },
   "got": {
    "btc_net_pct": -2.25,
    "realized_vol_ann_pct": 34.74,
    "volume_top5_usd_bn": 14.8563,
    "avg_pairwise_corr": 0.93
   },
   "match": {
    "btc_net_pct": true,
    "realized_vol_ann_pct": true,
    "volume_top5_usd_bn": true,
    "avg_pairwise_corr": true
   },
   "tolerance": {
    "btc_net_pct": 0.05,
    "realized_vol_ann_pct": 0.5,
    "volume_top5_usd_bn": 0.05,
    "avg_pairwise_corr": 0.02
   },
   "all_match": true,
   "note": "previous week of this run == published issue-#13 week; the four Snapshot pins must reproduce (key published_issue3 kept for the builder schema, published_issue13 is the add-only alias)"
  },
  "regime_days": {
   "2026-11-02": {
    "move_pct": -2.04,
    "regime": "trend"
   },
   "2026-11-03": {
    "move_pct": 0.92,
    "regime": "flat"
   },
   "2026-11-04": {
    "move_pct": 3.9,
    "regime": "trend"
   },
   "2026-11-05": {
    "move_pct": -5.33,
    "regime": "trend"
   },
   "2026-11-06": {
    "move_pct": -0.47,
    "regime": "flat"
   },
   "2026-11-07": {
    "move_pct": -0.07,
    "regime": "flat"
   },
   "2026-11-08": {
    "move_pct": -1.6,
    "regime": "trend"
   }
  },
  "alive_slice_context": {
   "abs_move_1d_pct": {
    "A": 1.629,
    "B": 2.163
   },
   "btc_realized_vol_ann_pct_hourly": {
    "A": 36.98,
    "B": 40.99
   }
  }
 },
 "tables": {
  "calibration_main": [
   {
    "model": "claude-opus-5-5",
    "model_label": "claude-opus-5-5",
    "legacy": false,
    "is_field": false,
    "n": 516,
    "coverage": 0.388,
    "hit_rate": 0.4496,
    "mean_conf": 56.3,
    "gap_pp": 11.3,
    "brier": 0.2609,
    "wilson_95": {
     "lo": 0.4072,
     "hi": 0.4927
    }
   },
   {
    "model": "grok-4.7",
    "model_label": "grok-4.7",
    "legacy": false,
    "is_field": false,
    "n": 771,
    "coverage": 0.581,
    "hit_rate": 0.4591,
    "mean_conf": 59.4,
    "gap_pp": 13.5,
    "brier": 0.2687,
    "wilson_95": {
     "lo": 0.4243,
     "hi": 0.4944
    }
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "legacy": false,
    "is_field": false,
    "n": 663,
    "coverage": 0.5164,
    "hit_rate": 0.4449,
    "mean_conf": 59.2,
    "gap_pp": 14.7,
    "brier": 0.2703,
    "wilson_95": {
     "lo": 0.4075,
     "hi": 0.483
    }
   },
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "legacy": false,
    "is_field": false,
    "n": 754,
    "coverage": 0.5712,
    "hit_rate": 0.4456,
    "mean_conf": 60.4,
    "gap_pp": 15.8,
    "brier": 0.2744,
    "wilson_95": {
     "lo": 0.4105,
     "hi": 0.4813
    }
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "legacy": false,
    "is_field": false,
    "n": 602,
    "coverage": 0.4526,
    "hit_rate": 0.4252,
    "mean_conf": 60.1,
    "gap_pp": 17.6,
    "brier": 0.2769,
    "wilson_95": {
     "lo": 0.3864,
     "hi": 0.4651
    }
   },
   {
    "model": "gpt-6.1-sol",
    "model_label": "gpt-6.1-sol",
    "legacy": false,
    "is_field": false,
    "n": 807,
    "coverage": 0.6068,
    "hit_rate": 0.456,
    "mean_conf": 63.0,
    "gap_pp": 17.4,
    "brier": 0.2804,
    "wilson_95": {
     "lo": 0.4219,
     "hi": 0.4905
    }
   },
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "legacy": false,
    "is_field": false,
    "n": 752,
    "coverage": 0.5658,
    "hit_rate": 0.4481,
    "mean_conf": 67.1,
    "gap_pp": 22.3,
    "brier": 0.3031,
    "wilson_95": {
     "lo": 0.4129,
     "hi": 0.4839
    }
   },
   {
    "model": "Field (all models)",
    "legacy": false,
    "is_field": true,
    "n": 4865,
    "coverage": null,
    "hit_rate": 0.4477,
    "mean_conf": 61.1,
    "gap_pp": 16.3,
    "brier": 0.2772,
    "wilson_95": {
     "lo": null,
     "hi": null
    }
   }
  ],
  "buckets": [
   {
    "model": "claude-opus-5-5",
    "bucket": "50-60",
    "n": 506,
    "hit_rate": 0.4565,
    "mean_conf": 56.2,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-opus-5-5",
    "bucket": "60-70",
    "n": 10,
    "hit_rate": 0.1,
    "mean_conf": 60,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-opus-5-5",
    "bucket": "70-80",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "claude-opus-5-5",
    "bucket": "80-100",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "grok-4.7",
    "bucket": "50-60",
    "n": 379,
    "hit_rate": 0.4828,
    "mean_conf": 57.0,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "grok-4.7",
    "bucket": "60-70",
    "n": 392,
    "hit_rate": 0.4362,
    "mean_conf": 61.8,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "grok-4.7",
    "bucket": "70-80",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "grok-4.7",
    "bucket": "80-100",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "50-60",
    "n": 349,
    "hit_rate": 0.4527,
    "mean_conf": 56.8,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "60-70",
    "n": 308,
    "hit_rate": 0.4318,
    "mean_conf": 62.0,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "70-80",
    "n": 3,
    "hit_rate": 0.3333,
    "mean_conf": 70,
    "insufficient": true,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "80-100",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "50-60",
    "n": 257,
    "hit_rate": 0.463,
    "mean_conf": 56.9,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "60-70",
    "n": 492,
    "hit_rate": 0.439,
    "mean_conf": 62.2,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "70-80",
    "n": 4,
    "hit_rate": 0.25,
    "mean_conf": 71.5,
    "insufficient": true,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "80-100",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "claude-fable-5",
    "bucket": "50-60",
    "n": 222,
    "hit_rate": 0.4144,
    "mean_conf": 56.5,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-fable-5",
    "bucket": "60-70",
    "n": 380,
    "hit_rate": 0.4316,
    "mean_conf": 62.2,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-fable-5",
    "bucket": "70-80",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "claude-fable-5",
    "bucket": "80-100",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "50-60",
    "n": 113,
    "hit_rate": 0.4602,
    "mean_conf": 58.5,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "60-70",
    "n": 667,
    "hit_rate": 0.4618,
    "mean_conf": 63.5,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "70-80",
    "n": 27,
    "hit_rate": 0.2963,
    "mean_conf": 71.5,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "80-100",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "50-60",
    "n": 5,
    "hit_rate": 0.4,
    "mean_conf": 55,
    "insufficient": true,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "60-70",
    "n": 443,
    "hit_rate": 0.4718,
    "mean_conf": 63.2,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "70-80",
    "n": 297,
    "hit_rate": 0.4175,
    "mean_conf": 72.8,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "80-100",
    "n": 6,
    "hit_rate": 0.3333,
    "mean_conf": 80,
    "insufficient": true,
    "no_data": false
   }
  ],
  "sub50": [
   {
    "model": "claude-opus-5-5",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "grok-4.7",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "qwen-3.8-max",
    "n": 3,
    "hit_rate": 1.0
   },
   {
    "model": "deepseek-v4-pro",
    "n": 1,
    "hit_rate": 0.0
   },
   {
    "model": "claude-fable-5",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "gpt-6.1-sol",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "gemini-3.1-pro",
    "n": 1,
    "hit_rate": 0.0
   }
  ],
  "by_fh": [
   {
    "model": "claude-opus-5-5",
    "fh": "1h",
    "n": 311,
    "hit_rate": 0.4566,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "4h",
    "n": 164,
    "hit_rate": 0.439,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "1d",
    "n": 41,
    "hit_rate": 0.439,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "1h",
    "n": 462,
    "hit_rate": 0.4545,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "4h",
    "n": 258,
    "hit_rate": 0.4651,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "1d",
    "n": 51,
    "hit_rate": 0.4706,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "1h",
    "n": 389,
    "hit_rate": 0.437,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "4h",
    "n": 233,
    "hit_rate": 0.4506,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "1d",
    "n": 41,
    "hit_rate": 0.4878,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "1h",
    "n": 443,
    "hit_rate": 0.4334,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "4h",
    "n": 261,
    "hit_rate": 0.4559,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "1d",
    "n": 50,
    "hit_rate": 0.5,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "1h",
    "n": 353,
    "hit_rate": 0.4278,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "4h",
    "n": 202,
    "hit_rate": 0.4158,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "1d",
    "n": 47,
    "hit_rate": 0.4468,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "1h",
    "n": 472,
    "hit_rate": 0.4322,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "4h",
    "n": 275,
    "hit_rate": 0.4618,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "1d",
    "n": 60,
    "hit_rate": 0.6167,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "1h",
    "n": 458,
    "hit_rate": 0.4367,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "4h",
    "n": 248,
    "hit_rate": 0.4758,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "1d",
    "n": 46,
    "hit_rate": 0.413,
    "flag": null
   }
  ],
  "trading": [
   {
    "model": "gpt-6.1-sol",
    "n_trades": 807,
    "wr": 0.3965,
    "pnl_net_usd": -46.85,
    "pnl_gross_usd": 33.85,
    "max_dd_usd": -73.85
   },
   {
    "model": "claude-opus-5-5",
    "n_trades": 516,
    "wr": 0.374,
    "pnl_net_usd": -54.73,
    "pnl_gross_usd": -3.13,
    "max_dd_usd": -71.01
   },
   {
    "model": "qwen-3.8-max",
    "n_trades": 663,
    "wr": 0.3741,
    "pnl_net_usd": -62.57,
    "pnl_gross_usd": 3.73,
    "max_dd_usd": -79.82
   },
   {
    "model": "gemini-3.1-pro",
    "n_trades": 752,
    "wr": 0.3577,
    "pnl_net_usd": -69.29,
    "pnl_gross_usd": 5.91,
    "max_dd_usd": -92.96
   },
   {
    "model": "deepseek-v4-pro",
    "n_trades": 754,
    "wr": 0.3806,
    "pnl_net_usd": -69.6,
    "pnl_gross_usd": 5.8,
    "max_dd_usd": -79.57
   },
   {
    "model": "claude-fable-5",
    "n_trades": 602,
    "wr": 0.3472,
    "pnl_net_usd": -75.69,
    "pnl_gross_usd": -15.49,
    "max_dd_usd": -94.4
   },
   {
    "model": "grok-4.7",
    "n_trades": 771,
    "wr": 0.3813,
    "pnl_net_usd": -86.17,
    "pnl_gross_usd": -9.07,
    "max_dd_usd": -99.35
   }
  ],
  "gap_week_over_week": [
   {
    "model": "claude-opus-5-5",
    "gap_pp_issue13": 15.4,
    "gap_pp_issue14": 11.3,
    "delta_pp": -4.1
   },
   {
    "model": "grok-4.7",
    "gap_pp_issue13": 17.1,
    "gap_pp_issue14": 13.5,
    "delta_pp": -3.6
   },
   {
    "model": "qwen-3.8-max",
    "gap_pp_issue13": 17.7,
    "gap_pp_issue14": 14.7,
    "delta_pp": -3.0
   },
   {
    "model": "deepseek-v4-pro",
    "gap_pp_issue13": 18.8,
    "gap_pp_issue14": 15.8,
    "delta_pp": -3.0
   },
   {
    "model": "gpt-6.1-sol",
    "gap_pp_issue13": 20.7,
    "gap_pp_issue14": 17.4,
    "delta_pp": -3.3
   },
   {
    "model": "claude-fable-5",
    "gap_pp_issue13": 20.1,
    "gap_pp_issue14": 17.6,
    "delta_pp": -2.5
   },
   {
    "model": "gemini-3.1-pro",
    "gap_pp_issue13": 26.7,
    "gap_pp_issue14": 22.3,
    "delta_pp": -4.4
   },
   {
    "model": "Field",
    "gap_pp_issue13": 19.6,
    "gap_pp_issue14": 16.3,
    "delta_pp": -3.3
   }
  ],
  "ok_rate_by_model": {
   "claude-opus-5-5": 1.0,
   "grok-4.7": 0.998,
   "qwen-3.8-max": 0.9687,
   "deepseek-v4-pro": 0.9993,
   "claude-fable-5": 0.998,
   "gpt-6.1-sol": 1.0,
   "gemini-3.1-pro": 0.9993
  },
  "counters": {
   "forecasts_total": 10281,
   "ok_in_gate": 9250,
   "out_of_gate": 977,
   "out_of_gate_by_fh": {
    "1w": 490,
    "1m": 487
   },
   "invalid": 54,
   "mature": 9250,
   "mature_directional": 4865,
   "mature_sideways": 4385,
   "pending_next_issue": 0,
   "pending_by_fh": {},
   "late_closes": 0,
   "uptime": [
    {
     "fh": "1h",
     "tf": "1h",
     "slots_seen": 168,
     "slots_expected": 168
    },
    {
     "fh": "4h",
     "tf": "4h",
     "slots_seen": 42,
     "slots_expected": 42
    },
    {
     "fh": "4h",
     "tf": "1h",
     "slots_seen": 42,
     "slots_expected": 42
    },
    {
     "fh": "1d",
     "tf": "1d",
     "slots_seen": 7,
     "slots_expected": 7
    },
    {
     "fh": "1d",
     "tf": "4h",
     "slots_seen": 7,
     "slots_expected": 7
    }
   ],
   "regime_days": {
    "2026-11-02": {
     "move_pct": -2.04,
     "regime": "trend"
    },
    "2026-11-03": {
     "move_pct": 0.92,
     "regime": "flat"
    },
    "2026-11-04": {
     "move_pct": 3.9,
     "regime": "trend"
    },
    "2026-11-05": {
     "move_pct": -5.33,
     "regime": "trend"
    },
    "2026-11-06": {
     "move_pct": -0.47,
     "regime": "flat"
    },
    "2026-11-07": {
     "move_pct": -0.07,
     "regime": "flat"
    },
    "2026-11-08": {
     "move_pct": -1.6,
     "regime": "trend"
    }
   },
   "grok_era": {
    "ids_in_window": [
     "grok-4.7"
    ],
    "n_grok45": 0,
    "n_grok46": 0,
    "n_grok45_rows": 0,
    "n_grok46_rows": 0,
    "n_grok47_rows": 1470,
    "first_grok46_slot": null,
    "last_grok45_slot": null,
    "first_grok45_slot": null,
    "first_grok47_slot": "2026-11-02T00:01:00+00:00",
    "last_grok46_slot": null,
    "flip_at": "2026-08-24T09:22:00+00:00",
    "flip_inside_window": false,
    "flip_at_b0": "2026-10-17T09:01:00+00:00",
    "flip_inside_window_b0": false,
    "flip_inside_prev_window_b0": false,
    "prev_window": {
     "n_grok45_rows": 0,
     "n_grok46_rows": 0
    },
    "merged_model_id": "grok-4.7",
    "merged_label": "grok-4.7",
    "lineage_ids": [
     "grok-4.5",
     "grok-4.6",
     "grok-4.7"
    ],
    "lineage_source": "benchmarks.config.lineage_ids('grok-4.7') + MODEL_SUCCESSION[grok-4.7]=('grok-4.6', 'grok-4.5')",
    "lineage_warnings": [],
    "rows_remapped_a_plus_b": 0,
    "note": "grok-4.7 went live 2026-10-17T09:01:00+00:00 (B0, day 6 of 7 of its Mon-Sun week) -- three windows back, inside the published issue-#11 window; this window (week B) holds 0 grok-4.6 and 1470 grok-4.7 row(s) and week A (prev window = the published issue-#13 window) holds 0 grok-4.6 and 1470 grok-4.7 row(s): both are full weeks on the head; the lineage splice grok-4.6/grok-4.5 -> grok-4.7 stays active (label 'grok-4.7'). The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits ten windows back (inside issue #4's window).",
    "cells_with_two_grok_rows": 0
   },
   "series_density": {
    "1d": {
     "days_with_slots": 7,
     "expected_days": 7,
     "full_daily_coverage": true,
     "in_fh_gate": true,
     "n_slots": 7,
     "n_rows": 490,
     "days": [
      "2026-11-02",
      "2026-11-03",
      "2026-11-04",
      "2026-11-05",
      "2026-11-06",
      "2026-11-07",
      "2026-11-08"
     ],
     "missing_days": []
    },
    "1h": {
     "days_with_slots": 7,
     "expected_days": 7,
     "full_daily_coverage": true,
     "in_fh_gate": true,
     "n_slots": 168,
     "n_rows": 5871,
     "days": [
      "2026-11-02",
      "2026-11-03",
      "2026-11-04",
      "2026-11-05",
      "2026-11-06",
      "2026-11-07",
      "2026-11-08"
     ],
     "missing_days": []
    },
    "1m": {
     "days_with_slots": 7,
     "expected_days": 7,
     "full_daily_coverage": true,
     "in_fh_gate": false,
     "n_slots": 7,
     "n_rows": 490,
     "days": [
      "2026-11-02",
      "2026-11-03",
      "2026-11-04",
      "2026-11-05",
      "2026-11-06",
      "2026-11-07",
      "2026-11-08"
     ],
     "missing_days": []
    },
    "1w": {
     "days_with_slots": 7,
     "expected_days": 7,
     "full_daily_coverage": true,
     "in_fh_gate": false,
     "n_slots": 7,
     "n_rows": 490,
     "days": [
      "2026-11-02",
      "2026-11-03",
      "2026-11-04",
      "2026-11-05",
      "2026-11-06",
      "2026-11-07",
      "2026-11-08"
     ],
     "missing_days": []
    },
    "4h": {
     "days_with_slots": 7,
     "expected_days": 7,
     "full_daily_coverage": true,
     "in_fh_gate": true,
     "n_slots": 42,
     "n_rows": 2940,
     "days": [
      "2026-11-02",
      "2026-11-03",
      "2026-11-04",
      "2026-11-05",
      "2026-11-06",
      "2026-11-07",
      "2026-11-08"
     ],
     "missing_days": []
    }
   },
   "model_roster": {
    "current": [
     "claude-fable-5",
     "claude-opus-5-5",
     "deepseek-v4-pro",
     "gemini-3.1-pro",
     "gpt-6.1-sol",
     "grok-4.7",
     "qwen-3.8-max"
    ],
    "current_count": 7,
    "current_raw_ids_in_window": [
     "claude-fable-5",
     "claude-opus-5-5",
     "deepseek-v4-pro",
     "gemini-3.1-pro",
     "gpt-6.1-sol",
     "grok-4.7",
     "qwen-3.8-max"
    ],
    "archived_legacy": [
     "claude-opus-5",
     "gpt-5.6-sol",
     "grok-4.6",
     "grok-4.5",
     "qwen-3.7-max",
     "claude-opus-4.8"
    ],
    "archived_legacy_count": 6,
    "archived_legacy_detail": [
     {
      "model": "claude-opus-5",
      "n_rows_since": 16160,
      "first_slot": "2026-07-30T08:01:00+00:00",
      "last_slot": "2026-10-17T08:01:00+00:00"
     },
     {
      "model": "gpt-5.6-sol",
      "n_rows_since": 22475,
      "first_slot": "2026-07-15T18:01:00+00:00",
      "last_slot": "2026-10-17T08:01:00+00:00"
     },
     {
      "model": "grok-4.6",
      "n_rows_since": 11335,
      "first_slot": "2026-08-24T10:01:00+00:00",
      "last_slot": "2026-10-17T08:01:00+00:00"
     },
     {
      "model": "grok-4.5",
      "n_rows_since": 11128,
      "first_slot": "2026-07-15T18:01:00+00:00",
      "last_slot": "2026-08-24T09:01:00+00:00"
     },
     {
      "model": "qwen-3.7-max",
      "n_rows_since": 7479,
      "first_slot": "2026-07-15T18:01:00+00:00",
      "last_slot": "2026-08-05T09:01:00+00:00"
     },
     {
      "model": "claude-opus-4.8",
      "n_rows_since": 6315,
      "first_slot": "2026-07-15T18:01:00+00:00",
      "last_slot": "2026-07-30T08:01:00+00:00"
     }
    ],
    "archived_excluding_lineage_merged": [],
    "retired_inside_window": [],
    "tracked_total": 13,
    "canon_expected": {
     "current": 7,
     "archived_legacy": 4,
     "tracked_total": 11
    },
    "matches_canon_11_7_4": false,
    "roster_since": "2026-07-11T00:00:00+00:00",
    "note": "current = merged-lineage model ids (the heads) emitting inside the window -- every lineage is spliced (B0 three windows back, in the published issue-#11 window: gpt-5.6-sol -> gpt-6.1-sol, claude-opus-5 -> claude-opus-5-5, grok-4.6 -> grok-4.7); archived legacy = raw ids seen since 2026-07-11 that are not a current head, by raw id, so it lists the ids retired at B0 (last slot three windows back) next to the long-archived ones; retired_inside_window lists only raw ids retired inside this window (0 here). Models retired before 2026-07-11 are not visible to this query."
   },
   "lineage_eras": {
    "claude-fable-5": {
     "prev_ids": [],
     "n_prev_rows_b": 0,
     "n_head_rows_b": 1470,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-11-02T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": null,
     "flip_inside_window": false,
     "label": "claude-fable-5",
     "label_a": "claude-fable-5",
     "cells_with_two_rows": 0
    },
    "claude-opus-5-5": {
     "prev_ids": [
      "claude-opus-5",
      "claude-opus-4.8"
     ],
     "n_prev_rows_b": 0,
     "n_head_rows_b": 1470,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-11-02T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": "2026-10-17T09:01:00+00:00",
     "flip_inside_window": false,
     "label": "claude-opus-5-5",
     "label_a": "claude-opus-5-5",
     "cells_with_two_rows": 0
    },
    "gpt-6.1-sol": {
     "prev_ids": [
      "gpt-5.6-sol"
     ],
     "n_prev_rows_b": 0,
     "n_head_rows_b": 1470,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-11-02T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": "2026-10-17T09:01:00+00:00",
     "flip_inside_window": false,
     "label": "gpt-6.1-sol",
     "label_a": "gpt-6.1-sol",
     "cells_with_two_rows": 0
    },
    "deepseek-v4-pro": {
     "prev_ids": [],
     "n_prev_rows_b": 0,
     "n_head_rows_b": 1461,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-11-02T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": null,
     "flip_inside_window": false,
     "label": "deepseek-v4-pro",
     "label_a": "deepseek-v4-pro",
     "cells_with_two_rows": 0
    },
    "gemini-3.1-pro": {
     "prev_ids": [],
     "n_prev_rows_b": 0,
     "n_head_rows_b": 1470,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-11-02T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": null,
     "flip_inside_window": false,
     "label": "gemini-3.1-pro",
     "label_a": "gemini-3.1-pro",
     "cells_with_two_rows": 0
    },
    "qwen-3.8-max": {
     "prev_ids": [
      "qwen-3.7-max"
     ],
     "n_prev_rows_b": 0,
     "n_head_rows_b": 1470,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-11-02T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": null,
     "flip_inside_window": false,
     "label": "qwen-3.8-max",
     "label_a": "qwen-3.8-max",
     "cells_with_two_rows": 0
    },
    "grok-4.7": {
     "prev_ids": [
      "grok-4.6",
      "grok-4.5"
     ],
     "n_prev_rows_b": 0,
     "n_head_rows_b": 1470,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-11-02T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": "2026-10-17T09:01:00+00:00",
     "flip_inside_window": false,
     "label": "grok-4.7",
     "label_a": "grok-4.7",
     "cells_with_two_rows": 0
    }
   },
   "invalid_by_slot_b0": {},
   "invalid_by_slot_b0_in_window": false,
   "invalid_by_model": {
    "claude-fable-5": 3,
    "deepseek-v4-pro": 1,
    "gemini-3.1-pro": 1,
    "grok-4.7": 3,
    "qwen-3.8-max": 46
   },
   "invalid_by_model_week_a": {
    "claude-fable-5": 2,
    "qwen-3.8-max": 6
   },
   "invalid_by_day_model": {
    "2026-11-03": {
     "deepseek-v4-pro": 1
    },
    "2026-11-04": {
     "claude-fable-5": 1
    },
    "2026-11-05": {
     "qwen-3.8-max": 46
    },
    "2026-11-06": {
     "gemini-3.1-pro": 1,
     "grok-4.7": 2
    },
    "2026-11-08": {
     "claude-fable-5": 2,
     "grok-4.7": 1
    }
   },
   "rows_by_day_model": {
    "2026-11-02": {
     "claude-fable-5": 210,
     "claude-opus-5-5": 210,
     "deepseek-v4-pro": 210,
     "gemini-3.1-pro": 210,
     "gpt-6.1-sol": 210,
     "grok-4.7": 210,
     "qwen-3.8-max": 210
    },
    "2026-11-03": {
     "claude-fable-5": 210,
     "claude-opus-5-5": 210,
     "deepseek-v4-pro": 201,
     "gemini-3.1-pro": 210,
     "gpt-6.1-sol": 210,
     "grok-4.7": 210,
     "qwen-3.8-max": 210
    },
    "2026-11-04": {
     "claude-fable-5": 210,
     "claude-opus-5-5": 210,
     "deepseek-v4-pro": 210,
     "gemini-3.1-pro": 210,
     "gpt-6.1-sol": 210,
     "grok-4.7": 210,
     "qwen-3.8-max": 210
    },
    "2026-11-05": {
     "claude-fable-5": 210,
     "claude-opus-5-5": 210,
     "deepseek-v4-pro": 210,
     "gemini-3.1-pro": 210,
     "gpt-6.1-sol": 210,
     "grok-4.7": 210,
     "qwen-3.8-max": 210
    },
    "2026-11-06": {
     "claude-fable-5": 210,
     "claude-opus-5-5": 210,
     "deepseek-v4-pro": 210,
     "gemini-3.1-pro": 210,
     "gpt-6.1-sol": 210,
     "grok-4.7": 210,
     "qwen-3.8-max": 210
    },
    "2026-11-07": {
     "claude-fable-5": 210,
     "claude-opus-5-5": 210,
     "deepseek-v4-pro": 210,
     "gemini-3.1-pro": 210,
     "gpt-6.1-sol": 210,
     "grok-4.7": 210,
     "qwen-3.8-max": 210
    },
    "2026-11-08": {
     "claude-fable-5": 210,
     "claude-opus-5-5": 210,
     "deepseek-v4-pro": 210,
     "gemini-3.1-pro": 210,
     "gpt-6.1-sol": 210,
     "grok-4.7": 210,
     "qwen-3.8-max": 210
    }
   },
   "status_values": {
    "error": 54,
    "ok": 10227
   },
   "news_stripped": 2,
   "news_stripped_by_model": {
    "qwen-3.8-max": 2
   },
   "news_stripped_by_day_model": {
    "2026-11-07": {
     "qwen-3.8-max": 2
    }
   },
   "news_stripped_week_a": 0,
   "news_stripped_by_model_week_a": {},
   "news_stripped_by_day_model_week_a": {}
  }
 },
 "key_finding": {
  "label": "KEY FINDING · OBSERVATION (one weekly window)",
  "text": "The field's overconfidence gap moved +19.6pp -> +16.3pp week over week, 7 of 7 model lines narrowed, and field Brier went 0.2858 -> 0.2772.",
  "evidence_level": "observation"
 },
 "key_findings": [
  "**OBSERVATION -- The gap read +16.3pp this week.** Directional calls hit 44.8% against 61.1 stated mean confidence (issue #13: +19.6pp on 41.6% vs 61.2). Field Brier is 0.2772 (was 0.2858) and 0 of 7 model lines scored below 0.25, the score of an uninformative always-50% predictor. One window, descriptive.",
  "**7 of 7 models narrowed their gap.** Gap moves ran from gemini-3.1-pro's -4.4pp (+26.7pp -> +22.3pp) to claude-fable-5's -2.5pp (+20.1pp -> +17.6pp); 7 of 7 model lines narrowed week over week. claude-opus-5.5 is the lowest-Brier line (Brier 0.2609); grok-4.7 leads on hit-rate (45.9%).",
  "**The high-confidence buckets, N>=10 only.** gpt-6.1-sol 70-80 29.6% (n=27), gemini-3.1-pro 70-80 41.8% (n=297). Cells below N=10 are marked insufficient and rank nothing.",
  "**Trading, kept separate from every calibration table.** 0 of 7 lines finished net-positive; net PnL ran -$46.85 (gpt-6.1-sol, best) to -$86.17 (grok-4.7, worst), field -$464.89 against issue #13's -$869.65."
 ],
 "market_check": {
  "label": "MARKET CHECK · OBSERVATION (two adjacent calendar weeks)",
  "text": "OBSERVATION — mean |1d move| 1.63% -> 2.16% (+33% rel), BTC realized vol 37.0% -> 41.0% (ann., hourly); field directional accuracy 41.6% -> 44.8% (+3.1pp), 7 of 7 models improved, sim win-rate up for 7 of 7, field sim PnL -$869.65 -> -$464.89 (adjacent calendar weeks Oct 26-Nov 1 vs Nov 2-8; descriptive, one pair of weeks, not a claim).",
  "robustness": "Robustness: raw price-sign accuracy 42.8% -> 48.9% — the same direction as the trade-based hit rule.",
  "weeks": {
   "A": {
    "days": "2026-10-26..2026-11-01",
    "slots": [
     "2026-10-26T00:00:00+00:00",
     "2026-11-02T00:00:00+00:00"
    ],
    "cutoff": "2026-11-02T16:00:00+00:00"
   },
   "B": {
    "days": "2026-11-02..2026-11-08",
    "slots": [
     "2026-11-02T00:00:00+00:00",
     "2026-11-09T00:00:00+00:00"
    ],
    "cutoff": "2026-11-09T16:00:00+00:00"
   }
  },
  "price_source": "crypto_spot/1h@:00",
  "accuracy_field": {
   "A": {
    "n": 5094,
    "hit_rate": 0.4164,
    "wilson_95": [
     0.4029,
     0.43
    ]
   },
   "B": {
    "n": 4865,
    "hit_rate": 0.4477,
    "wilson_95": [
     0.4338,
     0.4617
    ]
   },
   "delta_pp": 3.1
  },
  "accuracy_per_model": [
   {
    "model": "claude-opus-5-5",
    "model_label": "claude-opus-5-5",
    "A": {
     "n": 591,
     "hit_rate": 0.4095,
     "wilson_95": [
      0.3705,
      0.4496
     ]
    },
    "B": {
     "n": 516,
     "hit_rate": 0.4496,
     "wilson_95": [
      0.4072,
      0.4927
     ]
    },
    "delta_pp": 4.0
   },
   {
    "model": "grok-4.7",
    "model_label": "grok-4.7",
    "A": {
     "n": 830,
     "hit_rate": 0.4253,
     "wilson_95": [
      0.3921,
      0.4592
     ]
    },
    "B": {
     "n": 771,
     "hit_rate": 0.4591,
     "wilson_95": [
      0.4243,
      0.4944
     ]
    },
    "delta_pp": 3.4
   },
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "A": {
     "n": 745,
     "hit_rate": 0.4148,
     "wilson_95": [
      0.3799,
      0.4505
     ]
    },
    "B": {
     "n": 754,
     "hit_rate": 0.4456,
     "wilson_95": [
      0.4105,
      0.4813
     ]
    },
    "delta_pp": 3.1
   },
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "A": {
     "n": 755,
     "hit_rate": 0.4172,
     "wilson_95": [
      0.3826,
      0.4527
     ]
    },
    "B": {
     "n": 752,
     "hit_rate": 0.4481,
     "wilson_95": [
      0.4129,
      0.4839
     ]
    },
    "delta_pp": 3.1
   },
   {
    "model": "gpt-6.1-sol",
    "model_label": "gpt-6.1-sol",
    "A": {
     "n": 829,
     "hit_rate": 0.4246,
     "wilson_95": [
      0.3914,
      0.4585
     ]
    },
    "B": {
     "n": 807,
     "hit_rate": 0.456,
     "wilson_95": [
      0.4219,
      0.4905
     ]
    },
    "delta_pp": 3.1
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "A": {
     "n": 711,
     "hit_rate": 0.4135,
     "wilson_95": [
      0.3779,
      0.4501
     ]
    },
    "B": {
     "n": 663,
     "hit_rate": 0.4449,
     "wilson_95": [
      0.4075,
      0.483
     ]
    },
    "delta_pp": 3.1
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "A": {
     "n": 633,
     "hit_rate": 0.4044,
     "wilson_95": [
      0.3669,
      0.4431
     ]
    },
    "B": {
     "n": 602,
     "hit_rate": 0.4252,
     "wilson_95": [
      0.3864,
      0.4651
     ]
    },
    "delta_pp": 2.1
   }
  ],
  "raw_sign_field": {
   "A": {
    "n_scored": 5088,
    "hit_rate": 0.4283
   },
   "B": {
    "n_scored": 4850,
    "hit_rate": 0.4885
   }
  },
  "abs_move_1d": {
   "A": 1.629,
   "B": 2.163,
   "delta_pct_rel": 32.8
  },
  "btc_realized_vol_ann_pct_hourly": {
   "A": 36.98,
   "B": 40.99
  },
  "trading_field": {
   "A": {
    "n_trades": 5094,
    "wr": 0.3361,
    "pnl_net_usd": -869.65,
    "pnl_gross_usd": -360.25
   },
   "B": {
    "n_trades": 4865,
    "wr": 0.3741,
    "pnl_net_usd": -464.89,
    "pnl_gross_usd": 21.61
   }
  },
  "verdict": {
   "models_with_hit_improved": "7 of 7",
   "models_with_rawsign_improved": "7 of 7",
   "models_with_wr_improved": "7 of 7",
   "field_hit_delta_pp": 3.1,
   "field_pnl_net": {
    "A": -869.65,
    "B": -464.89
   },
   "abs_move_delta": {
    "1h": {
     "A": 0.338,
     "B": 0.33,
     "delta_pct_rel": -2.4
    },
    "4h": {
     "A": 0.657,
     "B": 0.696,
     "delta_pct_rel": 5.9
    },
    "1d": {
     "A": 1.629,
     "B": 2.163,
     "delta_pct_rel": 32.8
    }
   },
   "btc_vol_ann_pct": {
    "A": 36.98,
    "B": 40.99
   },
   "note": "descriptive, two adjacent calendar weeks; hit rule = methodology v1.1 trade-based; raw_sign = price-sign robustness check (closes at :00 vs slots at :01)"
  },
  "lineage_note": "lineage splice ACTIVE: B0 (2026-10-17T09:01:00+00:00, day 6 of 7 of its Mon-Sun week) sits three windows back, inside the published issue-#11 window, where it spliced three lines -- gpt-5.6-sol -> gpt-6.1-sol, claude-opus-5 -> claude-opus-5-5, grok-4.6 -> grok-4.7. Week A (2026-10-26..2026-11-01, the published issue-#13 window) and week B (2026-11-02..2026-11-08) are both full weeks on the heads (0 and 0 old-id row(s) remapped); week A reproduces the published issue #13. The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits ten windows back (inside issue #4's window)."
 },
 "why_it_matters": "Every MarketMania forecast carries a model-stated confidence from 0 to 100 alongside its direction call. This report checks whether that number tracks reality: on a well-calibrated forecaster, calls made at 70% confidence should hit their direction about 70% of the time. With issue #14 the series has fourteen points on every model's gap -- enough to see movement, not enough to claim a trend: calibration and market regime move together, and durability claims belong in the Monthly series, not here.",
 "how_to_read_this": "Gap pp = mean stated confidence minus hit-rate, in percentage points; positive means overconfident. Brier is the mean squared error of the stated probability against the realised outcome, so lower is better and 0.25 is what an uninformative always-50% predictor scores. Coverage = calls scored divided by the mature calls available to that model. Confidence buckets are the models' own natural breakpoints, not an arbitrary binning; cells below N=10 are marked insufficient and never used to rank anything. Prediction and trading metrics live in separate sections and are never combined.",
 "practical_implications": [
  "Stated confidence is still a ranking hint at best, not a probability: the field's gap is +16.3pp this week against +19.6pp in issue #13.",
  "Gap and regime move together. The field hit 44.8% against 41.6% in issue #13 and stated mean confidence read 61.1 against 61.2, so the gap came out at +16.3pp: a field that hits 44.8% instead of 41.6% closes or opens a confidence gap without a single stated number changing.",
  "Trading direction this week (0 of 7 lines net-positive) is a regime read, not a strategy result; no line has finished net-positive for a second issue running (issue #13: 0 of 7 net-positive)."
 ],
 "limitations": [
  "Prediction metrics (this report) and trading metrics are kept in separate sections per methodology -- they are never combined into a single score.",
  "95% Wilson CIs shown are descriptive, not inferential: observations inside one window are dependent, so read them as a range, not a formal coverage guarantee.",
  "All 4,865 scored calls sit inside one market regime. This window had trend on 4 of 7 days (issue #13: 1 of 7); every comparison with issue #13 is a comparison across regimes as well as across weeks. Fourteen week-over-week points cannot separate drift from regime; no durability claim is made.",
  "Models report confidence at discrete levels, not a continuous scale; the buckets reflect those natural breakpoints. Cells below N=10 are marked insufficient.",
  "Underlying price series are reconstructed from trade entry prices (median per symbol-slot), not an independent tick feed. Series density and lineage notes (wave 14): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Nov 2-8) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9, #10, #11, #12 and #13: the 1w series has slots on 7 of 7 days and the 1M series on 7 of 7 days; both sit outside this report's FH gate (1h/4h/1d) and appear only in the exclusions counter (1w 490, 1M 487). (2) This window is the third full week on the builds that took over at Oct 17, 2026 09:01 UTC: claude-opus-5.5, gpt-6.1-sol and grok-4.7 carry no rows from the old builds in either week, and the 7 lines carry 1,461 / 1,470 rows in this window and 1,470 in week A, so every week-over-week row compares two full weeks on the same builds. (3) No roll-out slot of the flip falls inside either week: the two hourly slots before it (Oct 17, 07:01 and 08:01 UTC) lie three windows back, so this window's invalid counter holds none of their rows. (4) Past lineage flips: the Oct 17, 2026 09:01 UTC flip sits three windows back (inside the issue-#11 window), the grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits ten windows back (inside the issue-#4 window), and qwen-3.8-max succeeded qwen-3.7-max on Aug 5, 2026 (fully before this window).",
  "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #13 after the audit that found the raw table mixes two exchanges; issue #13 values are as published.",
  "Research-to-date counter: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Nov 9 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10, #11, #12 and #13, which printed 82,895 at the Nov 2 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 87,760 is an additive step under one definition; counter deltas against issue #12 and earlier remain definitional."
 ],
 "notes": {
  "series_density_and_lineage_wave14": "Series density and lineage notes (wave 14): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Nov 2-8) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9, #10, #11, #12 and #13: the 1w series has slots on 7 of 7 days and the 1M series on 7 of 7 days; both sit outside this report's FH gate (1h/4h/1d) and appear only in the exclusions counter (1w 490, 1M 487). (2) This window is the third full week on the builds that took over at Oct 17, 2026 09:01 UTC: claude-opus-5.5, gpt-6.1-sol and grok-4.7 carry no rows from the old builds in either week, and the 7 lines carry 1,461 / 1,470 rows in this window and 1,470 in week A, so every week-over-week row compares two full weeks on the same builds. (3) No roll-out slot of the flip falls inside either week: the two hourly slots before it (Oct 17, 07:01 and 08:01 UTC) lie three windows back, so this window's invalid counter holds none of their rows. (4) Past lineage flips: the Oct 17, 2026 09:01 UTC flip sits three windows back (inside the issue-#11 window), the grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits ten windows back (inside the issue-#4 window), and qwen-3.8-max succeeded qwen-3.7-max on Aug 5, 2026 (fully before this window).",
  "grok_era": {
   "ids_in_window": [
    "grok-4.7"
   ],
   "n_grok45": 0,
   "n_grok46": 0,
   "n_grok45_rows": 0,
   "n_grok46_rows": 0,
   "n_grok47_rows": 1470,
   "first_grok46_slot": null,
   "last_grok45_slot": null,
   "first_grok45_slot": null,
   "first_grok47_slot": "2026-11-02T00:01:00+00:00",
   "last_grok46_slot": null,
   "flip_at": "2026-08-24T09:22:00+00:00",
   "flip_inside_window": false,
   "flip_at_b0": "2026-10-17T09:01:00+00:00",
   "flip_inside_window_b0": false,
   "flip_inside_prev_window_b0": false,
   "prev_window": {
    "n_grok45_rows": 0,
    "n_grok46_rows": 0
   },
   "merged_model_id": "grok-4.7",
   "merged_label": "grok-4.7",
   "lineage_ids": [
    "grok-4.5",
    "grok-4.6",
    "grok-4.7"
   ],
   "lineage_source": "benchmarks.config.lineage_ids('grok-4.7') + MODEL_SUCCESSION[grok-4.7]=('grok-4.6', 'grok-4.5')",
   "lineage_warnings": [],
   "rows_remapped_a_plus_b": 0,
   "note": "grok-4.7 went live 2026-10-17T09:01:00+00:00 (B0, day 6 of 7 of its Mon-Sun week) -- three windows back, inside the published issue-#11 window; this window (week B) holds 0 grok-4.6 and 1470 grok-4.7 row(s) and week A (prev window = the published issue-#13 window) holds 0 grok-4.6 and 1470 grok-4.7 row(s): both are full weeks on the head; the lineage splice grok-4.6/grok-4.5 -> grok-4.7 stays active (label 'grok-4.7'). The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits ten windows back (inside issue #4's window).",
   "cells_with_two_grok_rows": 0
  },
  "model_ids_line": [
   "claude-fable-5",
   "claude-opus-5-5",
   "deepseek-v4-pro",
   "gemini-3.1-pro",
   "gpt-6.1-sol",
   "grok-4.7",
   "qwen-3.8-max"
  ],
  "model_roster": {
   "current": [
    "claude-fable-5",
    "claude-opus-5-5",
    "deepseek-v4-pro",
    "gemini-3.1-pro",
    "gpt-6.1-sol",
    "grok-4.7",
    "qwen-3.8-max"
   ],
   "current_count": 7,
   "current_raw_ids_in_window": [
    "claude-fable-5",
    "claude-opus-5-5",
    "deepseek-v4-pro",
    "gemini-3.1-pro",
    "gpt-6.1-sol",
    "grok-4.7",
    "qwen-3.8-max"
   ],
   "archived_legacy": [
    "claude-opus-5",
    "gpt-5.6-sol",
    "grok-4.6",
    "grok-4.5",
    "qwen-3.7-max",
    "claude-opus-4.8"
   ],
   "archived_legacy_count": 6,
   "archived_legacy_detail": [
    {
     "model": "claude-opus-5",
     "n_rows_since": 16160,
     "first_slot": "2026-07-30T08:01:00+00:00",
     "last_slot": "2026-10-17T08:01:00+00:00"
    },
    {
     "model": "gpt-5.6-sol",
     "n_rows_since": 22475,
     "first_slot": "2026-07-15T18:01:00+00:00",
     "last_slot": "2026-10-17T08:01:00+00:00"
    },
    {
     "model": "grok-4.6",
     "n_rows_since": 11335,
     "first_slot": "2026-08-24T10:01:00+00:00",
     "last_slot": "2026-10-17T08:01:00+00:00"
    },
    {
     "model": "grok-4.5",
     "n_rows_since": 11128,
     "first_slot": "2026-07-15T18:01:00+00:00",
     "last_slot": "2026-08-24T09:01:00+00:00"
    },
    {
     "model": "qwen-3.7-max",
     "n_rows_since": 7479,
     "first_slot": "2026-07-15T18:01:00+00:00",
     "last_slot": "2026-08-05T09:01:00+00:00"
    },
    {
     "model": "claude-opus-4.8",
     "n_rows_since": 6315,
     "first_slot": "2026-07-15T18:01:00+00:00",
     "last_slot": "2026-07-30T08:01:00+00:00"
    }
   ],
   "archived_excluding_lineage_merged": [],
   "retired_inside_window": [],
   "tracked_total": 13,
   "canon_expected": {
    "current": 7,
    "archived_legacy": 4,
    "tracked_total": 11
   },
   "matches_canon_11_7_4": false,
   "roster_since": "2026-07-11T00:00:00+00:00",
   "note": "current = merged-lineage model ids (the heads) emitting inside the window -- every lineage is spliced (B0 three windows back, in the published issue-#11 window: gpt-5.6-sol -> gpt-6.1-sol, claude-opus-5 -> claude-opus-5-5, grok-4.6 -> grok-4.7); archived legacy = raw ids seen since 2026-07-11 that are not a current head, by raw id, so it lists the ids retired at B0 (last slot three windows back) next to the long-archived ones; retired_inside_window lists only raw ids retired inside this window (0 here). Models retired before 2026-07-11 are not visible to this query."
  },
  "series_density": {
   "1d": {
    "days_with_slots": 7,
    "expected_days": 7,
    "full_daily_coverage": true,
    "in_fh_gate": true,
    "n_slots": 7,
    "n_rows": 490,
    "days": [
     "2026-11-02",
     "2026-11-03",
     "2026-11-04",
     "2026-11-05",
     "2026-11-06",
     "2026-11-07",
     "2026-11-08"
    ],
    "missing_days": []
   },
   "1h": {
    "days_with_slots": 7,
    "expected_days": 7,
    "full_daily_coverage": true,
    "in_fh_gate": true,
    "n_slots": 168,
    "n_rows": 5871,
    "days": [
     "2026-11-02",
     "2026-11-03",
     "2026-11-04",
     "2026-11-05",
     "2026-11-06",
     "2026-11-07",
     "2026-11-08"
    ],
    "missing_days": []
   },
   "1m": {
    "days_with_slots": 7,
    "expected_days": 7,
    "full_daily_coverage": true,
    "in_fh_gate": false,
    "n_slots": 7,
    "n_rows": 490,
    "days": [
     "2026-11-02",
     "2026-11-03",
     "2026-11-04",
     "2026-11-05",
     "2026-11-06",
     "2026-11-07",
     "2026-11-08"
    ],
    "missing_days": []
   },
   "1w": {
    "days_with_slots": 7,
    "expected_days": 7,
    "full_daily_coverage": true,
    "in_fh_gate": false,
    "n_slots": 7,
    "n_rows": 490,
    "days": [
     "2026-11-02",
     "2026-11-03",
     "2026-11-04",
     "2026-11-05",
     "2026-11-06",
     "2026-11-07",
     "2026-11-08"
    ],
    "missing_days": []
   },
   "4h": {
    "days_with_slots": 7,
    "expected_days": 7,
    "full_daily_coverage": true,
    "in_fh_gate": true,
    "n_slots": 42,
    "n_rows": 2940,
    "days": [
     "2026-11-02",
     "2026-11-03",
     "2026-11-04",
     "2026-11-05",
     "2026-11-06",
     "2026-11-07",
     "2026-11-08"
    ],
    "missing_days": []
   }
  },
  "week_over_week_note": "Week-over-week columns compare back-to-back windows: Oct 26-Nov 1 (issue #13, and week A of this issue's alive slice) vs Nov 2-8 (this issue). \"Was\" values are the numbers published in issue #13; deltas are computed on unrounded rates.",
  "research_to_date_pin": "Research-to-date counter: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Nov 9 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10, #11, #12 and #13, which printed 82,895 at the Nov 2 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 87,760 is an additive step under one definition; counter deltas against issue #12 and earlier remain definitional.",
  "market_state_audit": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #13 after the audit that found the raw table mixes two exchanges; issue #13 values are as published.",
  "engine": "Engine 1.1 has powered the sandbox since Aug 18, i.e. before this window; no cross-engine PnL comparisons are claimed.",
  "report_template": "PDF built with the canonical mm_report.py template module; preview card with report_preview.render_preview",
  "lineage_eras": {
   "claude-fable-5": {
    "prev_ids": [],
    "n_prev_rows_b": 0,
    "n_head_rows_b": 1470,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-11-02T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": null,
    "flip_inside_window": false,
    "label": "claude-fable-5",
    "label_a": "claude-fable-5",
    "cells_with_two_rows": 0
   },
   "claude-opus-5-5": {
    "prev_ids": [
     "claude-opus-5",
     "claude-opus-4.8"
    ],
    "n_prev_rows_b": 0,
    "n_head_rows_b": 1470,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-11-02T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": "2026-10-17T09:01:00+00:00",
    "flip_inside_window": false,
    "label": "claude-opus-5-5",
    "label_a": "claude-opus-5-5",
    "cells_with_two_rows": 0
   },
   "gpt-6.1-sol": {
    "prev_ids": [
     "gpt-5.6-sol"
    ],
    "n_prev_rows_b": 0,
    "n_head_rows_b": 1470,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-11-02T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": "2026-10-17T09:01:00+00:00",
    "flip_inside_window": false,
    "label": "gpt-6.1-sol",
    "label_a": "gpt-6.1-sol",
    "cells_with_two_rows": 0
   },
   "deepseek-v4-pro": {
    "prev_ids": [],
    "n_prev_rows_b": 0,
    "n_head_rows_b": 1461,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-11-02T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": null,
    "flip_inside_window": false,
    "label": "deepseek-v4-pro",
    "label_a": "deepseek-v4-pro",
    "cells_with_two_rows": 0
   },
   "gemini-3.1-pro": {
    "prev_ids": [],
    "n_prev_rows_b": 0,
    "n_head_rows_b": 1470,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-11-02T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": null,
    "flip_inside_window": false,
    "label": "gemini-3.1-pro",
    "label_a": "gemini-3.1-pro",
    "cells_with_two_rows": 0
   },
   "qwen-3.8-max": {
    "prev_ids": [
     "qwen-3.7-max"
    ],
    "n_prev_rows_b": 0,
    "n_head_rows_b": 1470,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-11-02T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": null,
    "flip_inside_window": false,
    "label": "qwen-3.8-max",
    "label_a": "qwen-3.8-max",
    "cells_with_two_rows": 0
   },
   "grok-4.7": {
    "prev_ids": [
     "grok-4.6",
     "grok-4.5"
    ],
    "n_prev_rows_b": 0,
    "n_head_rows_b": 1470,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-11-02T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": "2026-10-17T09:01:00+00:00",
    "flip_inside_window": false,
    "label": "grok-4.7",
    "label_a": "grok-4.7",
    "cells_with_two_rows": 0
   }
  },
  "splice": {
   "claude-opus-5-5": {
    "prev": "claude-opus-5",
    "label": "claude-opus-5.5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "cell": "claude-opus-5.5 (spliced)",
    "human": "Claude Opus 5.5"
   },
   "gpt-6.1-sol": {
    "prev": "gpt-5.6-sol",
    "label": "gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "cell": "gpt-6.1-sol (spliced)",
    "human": "GPT-6.1 Sol"
   },
   "grok-4.7": {
    "prev": "grok-4.6",
    "label": "grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "cell": "grok-4.7 (spliced)",
    "human": "Grok 4.7"
   },
   "active": false
  },
  "prev_week_splice": {
   "active": false,
   "week": "Oct 26-Nov 1, 2026 UTC",
   "flip_at": "Oct 17, 2026 09:01 UTC",
   "lines": {
    "claude-opus-5-5": {
     "prev": "claude-opus-5",
     "label_a": "claude-opus-5-5",
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470
    },
    "gpt-6.1-sol": {
     "prev": "gpt-5.6-sol",
     "label_a": "gpt-6.1-sol",
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470
    },
    "grok-4.7": {
     "prev": "grok-4.6",
     "label_a": "grok-4.7",
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470
    }
   },
   "note": null
  },
  "provider_incident": {
   "active": true,
   "model": "qwen-3.8-max",
   "day": "2026-11-05",
   "invalid_rows": 46,
   "first_attempt_rows": 210,
   "news_stripped_total": 2,
   "news_stripped_by_day": {
    "2026-11-07": 2
   },
   "note": "Provider incident: on Nov 5 the provider behind qwen-3.8-max rejected 46 of its 210 first-attempt forecasts with an input-moderation error; those rows are counted in Invalid. From Nov 6 the engine retries such a call without the news block; 2 forecasts in this window (qwen-3.8-max: 2 on Nov 7) were produced that way and are flagged `news_stripped` in the open data. Hit rates in this report use the rows that resolved."
  }
 },
 "platform_note_tpsl": "**Context, not a finding.** Since Aug 13 the public sandbox can trade with model-specific TP/SL multipliers learned from this same weekly history (v1); since Aug 19, v2 adds per-ticker and confidence-bucket (50-70 / 70-100) resolution. That feature consumes calibration history; it does not feed back into any table in this report, which measures stated confidence vs. direction-hit only. No effect size is claimed for v2. The toggle lives at marketmania.ai/indices.",
 "living_series_note": "**Issue #14.** Weekly Calibration is a living series. Issue #13's open questions -- \"the gap moved +15.1pp while the field base moved -15.3pp -- the eighth issue running in which the two move nearly one-for-one in opposite directions; does that hold for a ninth?\" and \"claude-opus-5.5 kept the lowest Brier score for a second issue -- does it hold for a third issue, or change hands?\" -- read this issue as: field gap +19.6pp -> +16.3pp (7 of 7 lines narrowed) on a field base that moved +3.1pp, a ninth issue running in opposite directions, and the lowest Brier score stayed with the same line for a third issue: claude-opus-5.5 at 0.2609 (issue #13: claude-opus-5.5 at 0.2676). Also on the record: gpt-6.1-sol's 70-80 bucket read 29.6% (n=27) against its own 60-70 at 46.2% (n=667). The claude-opus-5.5, gpt-6.1-sol and grok-4.7 rows are the third full week on the Oct 17 builds; week-over-week rows compare two full weeks on the same builds. The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits ten windows back. Engine 1.1 has powered the sandbox since Aug 18, i.e. before this window; no cross-engine PnL comparisons are claimed.",
 "testing_next": [
  "Next issue: the gap moved -3.3pp while the field base moved +3.1pp -- the ninth issue running in which the two move nearly one-for-one in opposite directions; does that hold for a tenth?",
  "claude-opus-5.5 kept the lowest Brier score for a third issue -- does it hold for a fourth issue, or change hands?",
  "Monthly series: is the overconfidence gap stable across market regimes (trend vs flat) at monthly n?"
 ],
 "related_research": [
  {
   "title": "Consensus Watch #14",
   "url": "https://marketmania.ai/research/reports/consensus-watch-2026-11-02.pdf"
  },
  {
   "title": "Weekly Model Watch #14",
   "url": "https://marketmania.ai/research/reports/model-watch-2026-11-02.pdf"
  },
  {
   "title": "Weekly Calibration #13",
   "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-10-26.pdf"
  }
 ],
 "related_research_note": "The three weekly reports publish together as one issue each week; each links straight to the others' PDF and to its own previous issue. Direct links are the posting rule from wave 2 on.",
 "citation": {
  "bibtex_key": "mm_calibration_2026w45",
  "title": "Weekly Calibration #14: confidence vs. direction-hit, Nov 2-8 2026",
  "author": "MarketMania Research",
  "year": 2026,
  "month": "November",
  "day": 11,
  "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-11-02.pdf",
  "note": "Methodology v1.1; window Nov 2-8, 2026 UTC; source weekly_metrics_2026-11-02.json"
 },
 "research_to_date": {
  "this_report": {
   "scored_observations": 4865
  },
  "platform": {
   "as_of_cutoff": "2026-11-09",
   "resolved_forecasts": 87760,
   "resolved_forecasts_definition": "directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, at the issue cutoff",
   "resolved_forecasts_since": "2026-07-11",
   "models_tracked": 13,
   "models_tracked_detail": "7 models tracked (current line-up; earlier versions folded into their successors' lineage)",
   "assets": 5,
   "forecast_horizons": 5,
   "cadence": "hourly",
   "published_research_reports": 72
  },
  "source": "weekly_metrics_2026-11-02.json",
  "control_reproduces_wave3_pin": true,
  "pin_note": "Research-to-date counter: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Nov 9 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10, #11, #12 and #13, which printed 82,895 at the Nov 2 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 87,760 is an additive step under one definition; counter deltas against issue #12 and earlier remain definitional."
 },
 "site_entry": {
  "slug": "weekly-calibration-2026-11-02",
  "series": "weekly",
  "seriesLabel": "Weekly · Calibration",
  "date": "November 11, 2026",
  "title": "Weekly Calibration #14",
  "summary": "4,865 directional calls asked whether stated confidence tracks reality. The field hit 44.8% against 61.1 stated mean confidence, an overconfidence gap of +16.3pp against +19.6pp in issue #13, and 7 of 7 model lines narrowed week over week. Field Brier moved 0.2858 -> 0.2772; claude-opus-5.5 is the lowest-Brier line at 0.2609 and grok-4.7 leads on hit-rate at 45.9%. Trading, kept in its own section, finished with 0 of 7 lines net-positive as field accuracy moved 41.6% -> 44.8% (+3.1pp).",
  "stats": [
   "4,865 directional calls",
   "gap +16.3pp (was +19.6pp)",
   "0 of 7 net-positive"
  ],
  "manifest_key_finding": "The overconfidence gap read +16.3pp against +19.6pp in issue #13, with 7 of 7 model lines narrowing and field Brier moving 0.2858 -> 0.2772; trading, kept separate, finished 0 of 7 lines net-positive.",
  "files": {
   "pdf": "/research/reports/weekly-calibration-2026-11-02.pdf",
   "md": "/research/reports/weekly-calibration-2026-11-02.md",
   "json": "/research/reports/weekly-calibration-2026-11-02.json"
  }
 },
 "social": {
  "telegram": {
   "photo_caption_html": "🎯 <b>Weekly Calibration #14</b> — weekly series (window Nov 2–8)\n\nResearch question: when a model says 70, does it hit 70% of the time?\n\n4,865 directional calls across 7 model lines:\n• Field hit <b>44.8%</b> vs <b>61.1</b> stated — an overconfidence gap of <b>+16.3pp</b> (issue #13: +19.6pp)\n• Gap week over week: <b>7 of 7 lines narrowed</b>; field Brier 0.2858 -> 0.2772\n• Lowest-Brier line: <b>claude-opus-5.5</b> (Brier 0.2609); hit-rate leader grok-4.7 at 45.9%\n• Market check: field accuracy 41.6% -> 44.8% (+3.1pp); trading kept separate — <b>0 of 7 net-positive</b>\n\nNote: claude-opus-5.5, gpt-6.1-sol and grok-4.7 run on the same builds in both weeks of this issue; the Oct 17 09:01 UTC cutover sits three windows back\n\n📄 <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-11-02.pdf\">Full report (PDF)</a> · <a href=\"https://marketmania.ai/research\">all research</a>\n\n#cryptotrading #LLM #AI #crypto #trading #calibration #research",
   "document_caption_html": "📄 Weekly Calibration #14 — full report (PDF).\nWeb copy: <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-11-02.pdf\">weekly-calibration-2026-11-02.pdf</a> · machine-readable: <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-11-02.json\">JSON</a> · <a href=\"https://marketmania.ai/research\">all research</a>\n\n#cryptotrading #LLM #AI #crypto #trading #calibration #research",
   "caption_len": 963,
   "document_caption_len": 417,
   "limit": 1024
  },
  "x": {
   "main": "Weekly Calibration #14 is out.\n\n4,865 LLM calls: 44.8% hit vs 61.1 stated confidence — an overconfidence gap of +16.3pp against +19.6pp a week earlier, with 7 of 7 lines narrowing.\n\nFull report: https://marketmania.ai/research/reports/weekly-calibration-2026-11-02.pdf\n\n#AI #Crypto #Research #Calibration",
   "main_tco_len": 254,
   "reply": "Overconfidence gap, w/w (pp):\nopus-5.5: 15.4 -> 11.3\ngrok-4.7: 17.1 -> 13.5\nqwen-3.8: 17.7 -> 14.7\ndeepseek: 18.8 -> 15.8\ngpt-6.1: 20.7 -> 17.4\nfable-5: 20.1 -> 17.6\ngemini-3.1: 26.7 -> 22.3\nField: +19.6pp -> +16.3pp. Methodology v1.1.\nData: https://marketmania.ai/research/reports/weekly-calibration-2026-11-02.json",
   "reply_tco_len": 265,
   "limit_tco": 280,
   "replies_max": 1
  }
 }
}
