{
 "slug": "weekly-calibration-2026-10-26",
 "series": "weekly",
 "series_label": "WEEKLY · CALIBRATION",
 "issue": 13,
 "title": "Weekly Calibration #13",
 "language": "en",
 "window_start": "2026-10-26T00:00:00+00:00",
 "window_end": "2026-11-02T00:00:00+00:00",
 "window_text": "Oct 26-Nov 1, 2026 UTC",
 "cutoff": "2026-11-02T16:00:00+00:00",
 "generated_at": "2026-11-03T12:12:09+00:00",
 "methodology": "v1.1 (2026-08-10)",
 "methodology_hash": "e66c7e8c864a2233",
 "source": "weekly_metrics_2026-10-26.json",
 "hit_rule": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl",
 "bibtex_key": "mm_calibration_2026w44",
 "market_state": {
  "panel": "market_state_6p2",
  "week": {
   "start": "2026-10-26",
   "end": "2026-11-02"
  },
  "prev_week": {
   "start": "2026-10-19",
   "end": "2026-10-26"
  },
  "current": {
   "btc_net_pct": -2.25,
   "realized_vol_ann_pct": 34.74,
   "volume_top5_usd_bn": 14.8563,
   "volume_top5_wow_pct": 5.9,
   "avg_pairwise_corr": 0.93
  },
  "previous_as_published_issue12": {
   "btc_net_pct": -2.39,
   "realized_vol_ann_pct": 29.29,
   "volume_top5_usd_bn": 14.0246,
   "avg_pairwise_corr": 0.93
  },
  "snapshot_line": "BTC net -2.25% (prior -2.39%) - ann vol 34.7% (was 29.3%) - TOP5 volume $14.86B, +6% w/w - pairwise corr 0.93 (was 0.93)",
  "exchange": "binance",
  "audit_filter_applied": true,
  "source": "single-exchange (binance) daily candle recompute, market_state_2026-10-26.json; prior-week values as published in issue #12",
  "audit_note": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #12 after the audit that found the raw table mixes two exchanges; issue #12 values are as published.",
  "prev_week_control": {
   "published_issue3": {
    "btc_net_pct": -2.39,
    "realized_vol_ann_pct": 29.29,
    "volume_top5_usd_bn": 14.0246,
    "avg_pairwise_corr": 0.93
   },
   "published_issue12": {
    "btc_net_pct": -2.39,
    "realized_vol_ann_pct": 29.29,
    "volume_top5_usd_bn": 14.0246,
    "avg_pairwise_corr": 0.93
   },
   "got": {
    "btc_net_pct": -2.39,
    "realized_vol_ann_pct": 29.29,
    "volume_top5_usd_bn": 14.0246,
    "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-#12 week; the four Snapshot pins must reproduce (key published_issue3 kept for the builder schema, published_issue12 is the add-only alias)"
  },
  "regime_days": {
   "2026-10-26": {
    "move_pct": 0.1,
    "regime": "flat"
   },
   "2026-10-27": {
    "move_pct": 0.84,
    "regime": "flat"
   },
   "2026-10-28": {
    "move_pct": 0.6,
    "regime": "flat"
   },
   "2026-10-29": {
    "move_pct": -4.05,
    "regime": "trend"
   },
   "2026-10-30": {
    "move_pct": -0.84,
    "regime": "flat"
   },
   "2026-10-31": {
    "move_pct": 0.21,
    "regime": "flat"
   },
   "2026-11-01": {
    "move_pct": 1.13,
    "regime": "flat"
   }
  },
  "alive_slice_context": {
   "abs_move_1d_pct": {
    "A": 1.353,
    "B": 1.629
   },
   "btc_realized_vol_ann_pct_hourly": {
    "A": 27.48,
    "B": 36.98
   }
  }
 },
 "tables": {
  "calibration_main": [
   {
    "model": "claude-opus-5-5",
    "model_label": "claude-opus-5-5",
    "legacy": false,
    "is_field": false,
    "n": 591,
    "coverage": 0.4444,
    "hit_rate": 0.4095,
    "mean_conf": 56.4,
    "gap_pp": 15.4,
    "brier": 0.2676,
    "wilson_95": {
     "lo": 0.3705,
     "hi": 0.4496
    }
   },
   {
    "model": "grok-4.7",
    "model_label": "grok-4.7",
    "legacy": false,
    "is_field": false,
    "n": 830,
    "coverage": 0.6241,
    "hit_rate": 0.4253,
    "mean_conf": 59.6,
    "gap_pp": 17.1,
    "brier": 0.2754,
    "wilson_95": {
     "lo": 0.3921,
     "hi": 0.4592
    }
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "legacy": false,
    "is_field": false,
    "n": 711,
    "coverage": 0.537,
    "hit_rate": 0.4135,
    "mean_conf": 59.0,
    "gap_pp": 17.7,
    "brier": 0.2763,
    "wilson_95": {
     "lo": 0.3779,
     "hi": 0.4501
    }
   },
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "legacy": false,
    "is_field": false,
    "n": 745,
    "coverage": 0.5602,
    "hit_rate": 0.4148,
    "mean_conf": 60.2,
    "gap_pp": 18.8,
    "brier": 0.2805,
    "wilson_95": {
     "lo": 0.3799,
     "hi": 0.4505
    }
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "legacy": false,
    "is_field": false,
    "n": 633,
    "coverage": 0.4759,
    "hit_rate": 0.4044,
    "mean_conf": 60.5,
    "gap_pp": 20.1,
    "brier": 0.2835,
    "wilson_95": {
     "lo": 0.3669,
     "hi": 0.4431
    }
   },
   {
    "model": "gpt-6.1-sol",
    "model_label": "gpt-6.1-sol",
    "legacy": false,
    "is_field": false,
    "n": 829,
    "coverage": 0.6233,
    "hit_rate": 0.4246,
    "mean_conf": 63.2,
    "gap_pp": 20.7,
    "brier": 0.2922,
    "wilson_95": {
     "lo": 0.3914,
     "hi": 0.4585
    }
   },
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "legacy": false,
    "is_field": false,
    "n": 755,
    "coverage": 0.5677,
    "hit_rate": 0.4172,
    "mean_conf": 68.4,
    "gap_pp": 26.7,
    "brier": 0.3205,
    "wilson_95": {
     "lo": 0.3826,
     "hi": 0.4527
    }
   },
   {
    "model": "Field (all models)",
    "legacy": false,
    "is_field": true,
    "n": 5094,
    "coverage": null,
    "hit_rate": 0.4164,
    "mean_conf": 61.2,
    "gap_pp": 19.6,
    "brier": 0.2858,
    "wilson_95": {
     "lo": null,
     "hi": null
    }
   }
  ],
  "buckets": [
   {
    "model": "claude-opus-5-5",
    "bucket": "50-60",
    "n": 559,
    "hit_rate": 0.4222,
    "mean_conf": 56.2,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-opus-5-5",
    "bucket": "60-70",
    "n": 32,
    "hit_rate": 0.1875,
    "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": 402,
    "hit_rate": 0.4453,
    "mean_conf": 57.1,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "grok-4.7",
    "bucket": "60-70",
    "n": 426,
    "hit_rate": 0.4085,
    "mean_conf": 61.9,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "grok-4.7",
    "bucket": "70-80",
    "n": 2,
    "hit_rate": 0.0,
    "mean_conf": 70,
    "insufficient": true,
    "no_data": false
   },
   {
    "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": 388,
    "hit_rate": 0.4304,
    "mean_conf": 56.7,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "60-70",
    "n": 310,
    "hit_rate": 0.3935,
    "mean_conf": 62.3,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "70-80",
    "n": 2,
    "hit_rate": 0.5,
    "mean_conf": 72,
    "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": 287,
    "hit_rate": 0.4042,
    "mean_conf": 56.8,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "60-70",
    "n": 448,
    "hit_rate": 0.4241,
    "mean_conf": 62.2,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "70-80",
    "n": 10,
    "hit_rate": 0.3,
    "mean_conf": 71,
    "insufficient": false,
    "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": 207,
    "hit_rate": 0.43,
    "mean_conf": 56.4,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-fable-5",
    "bucket": "60-70",
    "n": 426,
    "hit_rate": 0.392,
    "mean_conf": 62.5,
    "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": 131,
    "hit_rate": 0.4733,
    "mean_conf": 58.5,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "60-70",
    "n": 646,
    "hit_rate": 0.4272,
    "mean_conf": 63.5,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "70-80",
    "n": 52,
    "hit_rate": 0.2692,
    "mean_conf": 71.7,
    "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": 2,
    "hit_rate": 0.5,
    "mean_conf": 55,
    "insufficient": true,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "60-70",
    "n": 418,
    "hit_rate": 0.4258,
    "mean_conf": 63.5,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "70-80",
    "n": 280,
    "hit_rate": 0.4143,
    "mean_conf": 72.9,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "80-100",
    "n": 55,
    "hit_rate": 0.3636,
    "mean_conf": 84.2,
    "insufficient": false,
    "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": 11,
    "hit_rate": 0.3636
   },
   {
    "model": "deepseek-v4-pro",
    "n": 0,
    "hit_rate": null
   },
   {
    "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": 0,
    "hit_rate": null
   }
  ],
  "by_fh": [
   {
    "model": "claude-opus-5-5",
    "fh": "1h",
    "n": 361,
    "hit_rate": 0.4432,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "4h",
    "n": 192,
    "hit_rate": 0.3333,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "1d",
    "n": 38,
    "hit_rate": 0.4737,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "1h",
    "n": 513,
    "hit_rate": 0.4542,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "4h",
    "n": 267,
    "hit_rate": 0.3596,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "1d",
    "n": 50,
    "hit_rate": 0.48,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "1h",
    "n": 429,
    "hit_rate": 0.4545,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "4h",
    "n": 238,
    "hit_rate": 0.3319,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "1d",
    "n": 44,
    "hit_rate": 0.4545,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "1h",
    "n": 442,
    "hit_rate": 0.4548,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "4h",
    "n": 260,
    "hit_rate": 0.3423,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "1d",
    "n": 43,
    "hit_rate": 0.4419,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "1h",
    "n": 395,
    "hit_rate": 0.438,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "4h",
    "n": 197,
    "hit_rate": 0.3452,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "1d",
    "n": 41,
    "hit_rate": 0.3659,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "1h",
    "n": 501,
    "hit_rate": 0.4551,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "4h",
    "n": 273,
    "hit_rate": 0.3736,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "1d",
    "n": 55,
    "hit_rate": 0.4,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "1h",
    "n": 456,
    "hit_rate": 0.4452,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "4h",
    "n": 250,
    "hit_rate": 0.36,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "1d",
    "n": 49,
    "hit_rate": 0.449,
    "flag": null
   }
  ],
  "trading": [
   {
    "model": "claude-opus-5-5",
    "n_trades": 591,
    "wr": 0.3316,
    "pnl_net_usd": -93.22,
    "pnl_gross_usd": -34.12,
    "max_dd_usd": -98.12
   },
   {
    "model": "qwen-3.8-max",
    "n_trades": 711,
    "wr": 0.3446,
    "pnl_net_usd": -105.9,
    "pnl_gross_usd": -34.8,
    "max_dd_usd": -112.94
   },
   {
    "model": "grok-4.7",
    "n_trades": 830,
    "wr": 0.3446,
    "pnl_net_usd": -109.74,
    "pnl_gross_usd": -26.74,
    "max_dd_usd": -114.44
   },
   {
    "model": "claude-fable-5",
    "n_trades": 633,
    "wr": 0.3128,
    "pnl_net_usd": -127.76,
    "pnl_gross_usd": -64.46,
    "max_dd_usd": -131.13
   },
   {
    "model": "deepseek-v4-pro",
    "n_trades": 745,
    "wr": 0.3477,
    "pnl_net_usd": -127.93,
    "pnl_gross_usd": -53.43,
    "max_dd_usd": -133.18
   },
   {
    "model": "gpt-6.1-sol",
    "n_trades": 829,
    "wr": 0.3366,
    "pnl_net_usd": -143.6,
    "pnl_gross_usd": -60.7,
    "max_dd_usd": -149.67
   },
   {
    "model": "gemini-3.1-pro",
    "n_trades": 755,
    "wr": 0.3298,
    "pnl_net_usd": -161.5,
    "pnl_gross_usd": -86.0,
    "max_dd_usd": -166.35
   }
  ],
  "gap_week_over_week": [
   {
    "model": "claude-opus-5-5",
    "gap_pp_issue12": -1.5,
    "gap_pp_issue13": 15.4,
    "delta_pp": 16.9
   },
   {
    "model": "grok-4.7",
    "gap_pp_issue12": 4.3,
    "gap_pp_issue13": 17.1,
    "delta_pp": 12.8
   },
   {
    "model": "qwen-3.8-max",
    "gap_pp_issue12": 3.5,
    "gap_pp_issue13": 17.7,
    "delta_pp": 14.2
   },
   {
    "model": "deepseek-v4-pro",
    "gap_pp_issue12": 4.5,
    "gap_pp_issue13": 18.8,
    "delta_pp": 14.3
   },
   {
    "model": "claude-fable-5",
    "gap_pp_issue12": 4.5,
    "gap_pp_issue13": 20.1,
    "delta_pp": 15.6
   },
   {
    "model": "gpt-6.1-sol",
    "gap_pp_issue12": 5.6,
    "gap_pp_issue13": 20.7,
    "delta_pp": 15.1
   },
   {
    "model": "gemini-3.1-pro",
    "gap_pp_issue12": 9.3,
    "gap_pp_issue13": 26.7,
    "delta_pp": 17.4
   },
   {
    "model": "Field",
    "gap_pp_issue12": 4.5,
    "gap_pp_issue13": 19.6,
    "delta_pp": 15.1
   }
  ],
  "ok_rate_by_model": {
   "claude-opus-5-5": 1.0,
   "grok-4.7": 1.0,
   "qwen-3.8-max": 0.9959,
   "deepseek-v4-pro": 1.0,
   "claude-fable-5": 0.9986,
   "gpt-6.1-sol": 1.0,
   "gemini-3.1-pro": 1.0
  },
  "counters": {
   "forecasts_total": 10290,
   "ok_in_gate": 9304,
   "out_of_gate": 978,
   "out_of_gate_by_fh": {
    "1m": 488,
    "1w": 490
   },
   "invalid": 8,
   "mature": 9304,
   "mature_directional": 5094,
   "mature_sideways": 4210,
   "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": {
    "2026-10-26": {
     "move_pct": 0.1,
     "regime": "flat"
    },
    "2026-10-27": {
     "move_pct": 0.84,
     "regime": "flat"
    },
    "2026-10-28": {
     "move_pct": 0.6,
     "regime": "flat"
    },
    "2026-10-29": {
     "move_pct": -4.05,
     "regime": "trend"
    },
    "2026-10-30": {
     "move_pct": -0.84,
     "regime": "flat"
    },
    "2026-10-31": {
     "move_pct": 0.21,
     "regime": "flat"
    },
    "2026-11-01": {
     "move_pct": 1.13,
     "regime": "flat"
    }
   },
   "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": "2026-10-26T00:01:00+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) -- two 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-#12 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 nine 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": [
      "2026-10-26",
      "2026-10-27",
      "2026-10-28",
      "2026-10-29",
      "2026-10-30",
      "2026-10-31",
      "2026-11-01"
     ],
     "missing_days": []
    },
    "1h": {
     "days_with_slots": 7,
     "expected_days": 7,
     "full_daily_coverage": true,
     "in_fh_gate": true,
     "n_slots": 168,
     "n_rows": 5880,
     "days": [
      "2026-10-26",
      "2026-10-27",
      "2026-10-28",
      "2026-10-29",
      "2026-10-30",
      "2026-10-31",
      "2026-11-01"
     ],
     "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": [
      "2026-10-26",
      "2026-10-27",
      "2026-10-28",
      "2026-10-29",
      "2026-10-30",
      "2026-10-31",
      "2026-11-01"
     ],
     "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": [
      "2026-10-26",
      "2026-10-27",
      "2026-10-28",
      "2026-10-29",
      "2026-10-30",
      "2026-10-31",
      "2026-11-01"
     ],
     "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": [
      "2026-10-26",
      "2026-10-27",
      "2026-10-28",
      "2026-10-29",
      "2026-10-30",
      "2026-10-31",
      "2026-11-01"
     ],
     "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 two 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 two 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": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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": 1470,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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
  }
 },
 "key_finding": {
  "label": "KEY FINDING · OBSERVATION (one weekly window)",
  "text": "The field's overconfidence gap moved +4.5pp -> +19.6pp week over week, 0 of 7 model lines narrowed, and field Brier went 0.2484 -> 0.2858.",
  "evidence_level": "observation"
 },
 "key_findings": [
  "**OBSERVATION -- The gap read +19.6pp this week.** Directional calls hit 41.6% against 61.2 stated mean confidence (issue #12: +4.5pp on 57.0% vs 61.5). Field Brier is 0.2858 (was 0.2484) and 0 of 7 model lines scored below 0.25, the score of an uninformative always-50% predictor. One window, descriptive.",
  "**No model narrowed its gap.** Gap moves ran from grok-4.7's +12.8pp (+4.3pp -> +17.1pp) to gemini-3.1-pro's +17.4pp (+9.3pp -> +26.7pp); 0 of 7 model lines narrowed week over week. claude-opus-5.5 is the lowest-Brier line (Brier 0.2676); grok-4.7 leads on hit-rate (42.5%). Every line is over-confident this window (positive gap); in issue #12 claude-opus-5.5 was the only line whose gap was negative (-1.5pp).",
  "**The high-confidence buckets, N>=10 only.** deepseek-v4-pro 70-80 30.0% (n=10), gpt-6.1-sol 70-80 26.9% (n=52), gemini-3.1-pro 70-80 41.4% (n=280), gemini-3.1-pro 80-100 36.4% (n=55). 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 -$93.22 (claude-opus-5.5, best) to -$161.50 (gemini-3.1-pro, worst), field -$869.65 against issue #12's -$43.00."
 ],
 "market_check": {
  "label": "MARKET CHECK · OBSERVATION (two adjacent calendar weeks)",
  "text": "OBSERVATION — mean |1d move| 1.35% -> 1.63% (+20% rel), BTC realized vol 27.5% -> 37.0% (ann., hourly); field directional accuracy 57.0% -> 41.6% (-15.3pp), 0 of 7 models improved, sim win-rate up for 0 of 7, field sim PnL -$43.00 -> -$869.65 (adjacent calendar weeks Oct 19-25 vs Oct 26-Nov 1; descriptive, one pair of weeks, not a claim).",
  "robustness": "Robustness: raw price-sign accuracy 56.0% -> 42.8% — the same direction as the trade-based hit rule.",
  "weeks": {
   "A": {
    "days": "2026-10-19..2026-10-25",
    "slots": [
     "2026-10-19T00:00:00+00:00",
     "2026-10-26T00:00:00+00:00"
    ],
    "cutoff": "2026-10-26T16:00:00+00:00"
   },
   "B": {
    "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"
   }
  },
  "price_source": "crypto_spot/1h@:00",
  "accuracy_field": {
   "A": {
    "n": 5856,
    "hit_rate": 0.5698,
    "wilson_95": [
     0.5571,
     0.5825
    ]
   },
   "B": {
    "n": 5094,
    "hit_rate": 0.4164,
    "wilson_95": [
     0.4029,
     0.43
    ]
   },
   "delta_pp": -15.3
  },
  "accuracy_per_model": [
   {
    "model": "grok-4.7",
    "model_label": "grok-4.7",
    "A": {
     "n": 836,
     "hit_rate": 0.5586,
     "wilson_95": [
      0.5248,
      0.5919
     ]
    },
    "B": {
     "n": 830,
     "hit_rate": 0.4253,
     "wilson_95": [
      0.3921,
      0.4592
     ]
    },
    "delta_pp": -13.3
   },
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "A": {
     "n": 891,
     "hit_rate": 0.5645,
     "wilson_95": [
      0.5318,
      0.5967
     ]
    },
    "B": {
     "n": 745,
     "hit_rate": 0.4148,
     "wilson_95": [
      0.3799,
      0.4505
     ]
    },
    "delta_pp": -15.0
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "A": {
     "n": 829,
     "hit_rate": 0.5633,
     "wilson_95": [
      0.5294,
      0.5967
     ]
    },
    "B": {
     "n": 711,
     "hit_rate": 0.4135,
     "wilson_95": [
      0.3779,
      0.4501
     ]
    },
    "delta_pp": -15.0
   },
   {
    "model": "gpt-6.1-sol",
    "model_label": "gpt-6.1-sol",
    "A": {
     "n": 962,
     "hit_rate": 0.5759,
     "wilson_95": [
      0.5444,
      0.6068
     ]
    },
    "B": {
     "n": 829,
     "hit_rate": 0.4246,
     "wilson_95": [
      0.3914,
      0.4585
     ]
    },
    "delta_pp": -15.1
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "A": {
     "n": 768,
     "hit_rate": 0.5638,
     "wilson_95": [
      0.5285,
      0.5985
     ]
    },
    "B": {
     "n": 633,
     "hit_rate": 0.4044,
     "wilson_95": [
      0.3669,
      0.4431
     ]
    },
    "delta_pp": -15.9
   },
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "A": {
     "n": 870,
     "hit_rate": 0.5828,
     "wilson_95": [
      0.5497,
      0.6151
     ]
    },
    "B": {
     "n": 755,
     "hit_rate": 0.4172,
     "wilson_95": [
      0.3826,
      0.4527
     ]
    },
    "delta_pp": -16.6
   },
   {
    "model": "claude-opus-5-5",
    "model_label": "claude-opus-5-5",
    "A": {
     "n": 700,
     "hit_rate": 0.58,
     "wilson_95": [
      0.5431,
      0.616
     ]
    },
    "B": {
     "n": 591,
     "hit_rate": 0.4095,
     "wilson_95": [
      0.3705,
      0.4496
     ]
    },
    "delta_pp": -17.0
   }
  ],
  "raw_sign_field": {
   "A": {
    "n_scored": 5835,
    "hit_rate": 0.5602
   },
   "B": {
    "n_scored": 5088,
    "hit_rate": 0.4283
   }
  },
  "abs_move_1d": {
   "A": 1.353,
   "B": 1.629,
   "delta_pct_rel": 20.4
  },
  "btc_realized_vol_ann_pct_hourly": {
   "A": 27.48,
   "B": 36.98
  },
  "trading_field": {
   "A": {
    "n_trades": 5856,
    "wr": 0.4664,
    "pnl_net_usd": -43.0,
    "pnl_gross_usd": 542.6
   },
   "B": {
    "n_trades": 5094,
    "wr": 0.3361,
    "pnl_net_usd": -869.65,
    "pnl_gross_usd": -360.25
   }
  },
  "verdict": {
   "models_with_hit_improved": "0 of 7",
   "models_with_rawsign_improved": "0 of 7",
   "models_with_wr_improved": "0 of 7",
   "field_hit_delta_pp": -15.3,
   "field_pnl_net": {
    "A": -43.0,
    "B": -869.65
   },
   "abs_move_delta": {
    "1h": {
     "A": 0.278,
     "B": 0.338,
     "delta_pct_rel": 21.6
    },
    "4h": {
     "A": 0.584,
     "B": 0.657,
     "delta_pct_rel": 12.5
    },
    "1d": {
     "A": 1.353,
     "B": 1.629,
     "delta_pct_rel": 20.4
    }
   },
   "btc_vol_ann_pct": {
    "A": 27.48,
    "B": 36.98
   },
   "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 two 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 (2026-10-19..2026-10-25, the published issue-#12 window) and week B (2026-10-26..2026-11-01) are both full weeks on the heads (0 and 0 old-id row(s) remapped); week A reproduces the published issue #12. The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits nine 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 #13 the series has thirteen 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 +19.6pp this week against +4.5pp in issue #12.",
  "Gap and regime move together. The field hit 41.6% against 57.0% in issue #12 and stated mean confidence read 61.2 against 61.5, so the gap came out at +19.6pp: a field that hits 41.6% instead of 57.0% 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; the three lines that were net-positive one week earlier all finished net-negative (issue #12: 3 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 5,094 scored calls sit inside one market regime. This window had trend on 1 of 7 days (issue #12: 1 of 7); every comparison with issue #12 is a comparison across regimes as well as across weeks. Thirteen 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 13): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 26-Nov 1) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9, #10, #11 and #12: 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 488). (2) This window is the second 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 all 7 lines carry 1,470 rows each in both weeks, 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 two 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 two windows back (inside the issue-#11 window), the grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits nine 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 #12 after the audit that found the raw table mixes two exchanges; issue #12 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 2 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10, #11 and #12, which printed 77,801 at the Oct 26 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 82,895 is an additive step under one definition; counter deltas against issue #11 and earlier remain definitional."
 ],
 "notes": {
  "series_density_and_lineage_wave13": "Series density and lineage notes (wave 13): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 26-Nov 1) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9, #10, #11 and #12: 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 488). (2) This window is the second 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 all 7 lines carry 1,470 rows each in both weeks, 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 two 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 two windows back (inside the issue-#11 window), the grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits nine 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": "2026-10-26T00:01:00+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) -- two 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-#12 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 nine 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 two 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 two 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": [
     "2026-10-26",
     "2026-10-27",
     "2026-10-28",
     "2026-10-29",
     "2026-10-30",
     "2026-10-31",
     "2026-11-01"
    ],
    "missing_days": []
   },
   "1h": {
    "days_with_slots": 7,
    "expected_days": 7,
    "full_daily_coverage": true,
    "in_fh_gate": true,
    "n_slots": 168,
    "n_rows": 5880,
    "days": [
     "2026-10-26",
     "2026-10-27",
     "2026-10-28",
     "2026-10-29",
     "2026-10-30",
     "2026-10-31",
     "2026-11-01"
    ],
    "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": [
     "2026-10-26",
     "2026-10-27",
     "2026-10-28",
     "2026-10-29",
     "2026-10-30",
     "2026-10-31",
     "2026-11-01"
    ],
    "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": [
     "2026-10-26",
     "2026-10-27",
     "2026-10-28",
     "2026-10-29",
     "2026-10-30",
     "2026-10-31",
     "2026-11-01"
    ],
    "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": [
     "2026-10-26",
     "2026-10-27",
     "2026-10-28",
     "2026-10-29",
     "2026-10-30",
     "2026-10-31",
     "2026-11-01"
    ],
    "missing_days": []
   }
  },
  "week_over_week_note": "Week-over-week columns compare back-to-back windows: Oct 19-25 (issue #12, and week A of this issue's alive slice) vs Oct 26-Nov 1 (this issue). \"Was\" values are the numbers published in issue #12; 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 2 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10, #11 and #12, which printed 77,801 at the Oct 26 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 82,895 is an additive step under one definition; counter deltas against issue #11 and earlier remain definitional.",
  "market_state_audit": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #12 after the audit that found the raw table mixes two exchanges; issue #12 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": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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": 1470,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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": "2026-10-26T00:01:00+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 19-25, 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
  }
 },
 "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 #13.** Weekly Calibration is a living series. Issue #12's open questions -- \"the gap moved -10.9pp while the field base moved +10.4pp -- the seventh issue running in which the two move nearly one-for-one in opposite directions; does that hold for an eighth?\" and \"The best-Brier line changed hands again, to claude-opus-5.5 -- does it hold for a second issue, or change hands again?\" -- read this issue as: field gap +4.5pp -> +19.6pp (0 of 7 lines narrowed) on a field base that moved -15.3pp, an eighth issue running in opposite directions, and the lowest Brier score stayed with the same line for a second issue: claude-opus-5.5 at 0.2676 (issue #12: claude-opus-5.5 at 0.2443). Also on the record: gpt-6.1-sol's 70-80 bucket read 26.9% (n=52) against its own 60-70 at 42.7% (n=646). The claude-opus-5.5, gpt-6.1-sol and grok-4.7 rows are the second 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 nine 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 +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?",
  "claude-opus-5.5 kept the lowest Brier score for a second issue -- does it hold for a third 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 #13",
   "url": "https://marketmania.ai/research/reports/consensus-watch-2026-10-26.pdf"
  },
  {
   "title": "Weekly Model Watch #13",
   "url": "https://marketmania.ai/research/reports/model-watch-2026-10-26.pdf"
  },
  {
   "title": "Weekly Calibration #12",
   "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-10-19.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_2026w44",
  "title": "Weekly Calibration #13: confidence vs. direction-hit, Oct 26-Nov 1 2026",
  "author": "MarketMania Research",
  "year": 2026,
  "month": "November",
  "day": 4,
  "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-10-26.pdf",
  "note": "Methodology v1.1; window Oct 26-Nov 1, 2026 UTC; source weekly_metrics_2026-10-26.json"
 },
 "research_to_date": {
  "this_report": {
   "scored_observations": 5094
  },
  "platform": {
   "as_of_cutoff": "2026-11-02",
   "resolved_forecasts": 82895,
   "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": 64
  },
  "source": "weekly_metrics_2026-10-26.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 2 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10, #11 and #12, which printed 77,801 at the Oct 26 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 82,895 is an additive step under one definition; counter deltas against issue #11 and earlier remain definitional."
 },
 "site_entry": {
  "slug": "weekly-calibration-2026-10-26",
  "series": "weekly",
  "seriesLabel": "Weekly · Calibration",
  "date": "November 4, 2026",
  "title": "Weekly Calibration #13",
  "summary": "5,094 directional calls asked whether stated confidence tracks reality. The field hit 41.6% against 61.2 stated mean confidence, an overconfidence gap of +19.6pp against +4.5pp in issue #12, and 0 of 7 model lines narrowed week over week. Field Brier moved 0.2484 -> 0.2858; claude-opus-5.5 is the lowest-Brier line at 0.2676 and grok-4.7 leads on hit-rate at 42.5%. Trading, kept in its own section, finished with 0 of 7 lines net-positive as field accuracy moved 57.0% -> 41.6% (-15.3pp).",
  "stats": [
   "5,094 directional calls",
   "gap +19.6pp (was +4.5pp)",
   "0 of 7 net-positive"
  ],
  "manifest_key_finding": "The overconfidence gap read +19.6pp against +4.5pp in issue #12, with 0 of 7 model lines narrowing and field Brier moving 0.2484 -> 0.2858; trading, kept separate, finished 0 of 7 lines net-positive.",
  "files": {
   "pdf": "/research/reports/weekly-calibration-2026-10-26.pdf",
   "md": "/research/reports/weekly-calibration-2026-10-26.md",
   "json": "/research/reports/weekly-calibration-2026-10-26.json"
  }
 },
 "social": {
  "telegram": {
   "photo_caption_html": "🎯 <b>Weekly Calibration #13</b> — weekly series (window Oct 26–Nov 1)\n\nResearch question: when a model says 70, does it hit 70% of the time?\n\n5,094 directional calls across 7 model lines:\n• Field hit <b>41.6%</b> vs <b>61.2</b> stated — an overconfidence gap of <b>+19.6pp</b> (issue #12: +4.5pp)\n• Gap week over week: <b>0 of 7 lines narrowed</b>; field Brier 0.2484 -> 0.2858\n• Lowest-Brier line: <b>claude-opus-5.5</b> (Brier 0.2676); hit-rate leader grok-4.7 at 42.5%\n• Market check: field accuracy 57.0% -> 41.6% (-15.3pp); 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 two windows back\n\n📄 <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-26.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 #13 — full report (PDF).\nWeb copy: <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-26.pdf\">weekly-calibration-2026-10-26.pdf</a> · machine-readable: <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-26.json\">JSON</a> · <a href=\"https://marketmania.ai/research\">all research</a>\n\n#cryptotrading #LLM #AI #crypto #trading #calibration #research",
   "caption_len": 966,
   "document_caption_len": 417,
   "limit": 1024
  },
  "x": {
   "main": "Weekly Calibration #13 is out.\n\n5,094 LLM calls: 41.6% hit vs 61.2 stated confidence — an overconfidence gap of +19.6pp against +4.5pp a week earlier, with 0 of 7 lines narrowing.\n\nFull report: https://marketmania.ai/research/reports/weekly-calibration-2026-10-26.pdf\n\n#AI #Crypto #Research #Calibration",
   "main_tco_len": 253,
   "reply": "Overconfidence gap, w/w (pp):\nopus-5.5: -1.5 -> 15.4\ngrok-4.7: 4.3 -> 17.1\nqwen-3.8: 3.5 -> 17.7\ndeepseek: 4.5 -> 18.8\nfable-5: 4.5 -> 20.1\ngpt-6.1: 5.6 -> 20.7\ngemini-3.1: 9.3 -> 26.7\nField: +4.5pp -> +19.6pp. Methodology v1.1.\nData: https://marketmania.ai/research/reports/weekly-calibration-2026-10-26.json",
   "reply_tco_len": 258,
   "limit_tco": 280,
   "replies_max": 1
  }
 }
}
