{
 "slug": "weekly-calibration-2026-10-12",
 "series": "weekly",
 "series_label": "WEEKLY · CALIBRATION",
 "issue": 11,
 "title": "Weekly Calibration #11",
 "language": "en",
 "window_start": "2026-10-12T00:00:00+00:00",
 "window_end": "2026-10-19T00:00:00+00:00",
 "window_text": "Oct 12-18, 2026 UTC",
 "cutoff": "2026-10-19T16:00:00+00:00",
 "generated_at": "2026-10-21T07:03:33+00:00",
 "methodology": "v1.1 (2026-08-10)",
 "methodology_hash": "e66c7e8c864a2233",
 "source": "weekly_metrics_2026-10-12.json",
 "hit_rule": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl",
 "bibtex_key": "mm_calibration_2026w42",
 "market_state": {
  "panel": "market_state_6p2",
  "week": {
   "start": "2026-10-12",
   "end": "2026-10-19"
  },
  "prev_week": {
   "start": "2026-10-05",
   "end": "2026-10-12"
  },
  "current": {
   "btc_net_pct": -1.98,
   "realized_vol_ann_pct": 27.36,
   "volume_top5_usd_bn": 15.8439,
   "volume_top5_wow_pct": -0.8,
   "avg_pairwise_corr": 0.94
  },
  "previous_as_published_issue10": {
   "btc_net_pct": -3.19,
   "realized_vol_ann_pct": 27.17,
   "volume_top5_usd_bn": 15.9702,
   "avg_pairwise_corr": 0.85
  },
  "snapshot_line": "BTC net -1.98% (prior -3.19%) - ann vol 27.4% (was 27.2%) - TOP5 volume $15.84B, -1% w/w - pairwise corr 0.94 (was 0.85)",
  "exchange": "binance",
  "audit_filter_applied": true,
  "source": "single-exchange (binance) daily candle recompute, market_state_2026-10-12.json; prior-week values as published in issue #10",
  "audit_note": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #10 after the audit that found the raw table mixes two exchanges; issue #10 values are as published.",
  "prev_week_control": {
   "published_issue3": {
    "btc_net_pct": -3.19,
    "realized_vol_ann_pct": 27.17,
    "volume_top5_usd_bn": 15.9702,
    "avg_pairwise_corr": 0.85
   },
   "published_issue10": {
    "btc_net_pct": -3.19,
    "realized_vol_ann_pct": 27.17,
    "volume_top5_usd_bn": 15.9702,
    "avg_pairwise_corr": 0.85
   },
   "got": {
    "btc_net_pct": -3.19,
    "realized_vol_ann_pct": 27.17,
    "volume_top5_usd_bn": 15.9702,
    "avg_pairwise_corr": 0.85
   },
   "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-#10 week; the four Snapshot pins must reproduce (key published_issue3 kept for the builder schema, published_issue10 is the add-only alias)"
  },
  "regime_days": {
   "2026-10-12": {
    "move_pct": -2.17,
    "regime": "trend"
   },
   "2026-10-13": {
    "move_pct": 1.56,
    "regime": "trend"
   },
   "2026-10-14": {
    "move_pct": -1.68,
    "regime": "trend"
   },
   "2026-10-15": {
    "move_pct": 0.52,
    "regime": "flat"
   },
   "2026-10-16": {
    "move_pct": -0.77,
    "regime": "flat"
   },
   "2026-10-17": {
    "move_pct": -0.26,
    "regime": "flat"
   },
   "2026-10-18": {
    "move_pct": 0.83,
    "regime": "flat"
   }
  },
  "alive_slice_context": {
   "abs_move_1d_pct": {
    "A": 1.542,
    "B": 2.054
   },
   "btc_realized_vol_ann_pct_hourly": {
    "A": 30.91,
    "B": 34.86
   }
  }
 },
 "tables": {
  "calibration_main": [
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "legacy": false,
    "is_field": false,
    "n": 767,
    "coverage": 0.59,
    "hit_rate": 0.4824,
    "mean_conf": 59.9,
    "gap_pp": 11.6,
    "brier": 0.2657,
    "wilson_95": {
     "lo": 0.4472,
     "hi": 0.5178
    }
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "legacy": false,
    "is_field": false,
    "n": 766,
    "coverage": 0.5759,
    "hit_rate": 0.4634,
    "mean_conf": 59.1,
    "gap_pp": 12.7,
    "brier": 0.2664,
    "wilson_95": {
     "lo": 0.4284,
     "hi": 0.4989
    }
   },
   {
    "model": "grok-4.7",
    "model_label": "grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "legacy": false,
    "is_field": false,
    "n": 695,
    "coverage": 0.5305,
    "hit_rate": 0.4705,
    "mean_conf": 60.0,
    "gap_pp": 12.9,
    "brier": 0.2682,
    "wilson_95": {
     "lo": 0.4337,
     "hi": 0.5077
    }
   },
   {
    "model": "claude-opus-5-5",
    "model_label": "claude-opus-5.5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "legacy": false,
    "is_field": false,
    "n": 572,
    "coverage": 0.4366,
    "hit_rate": 0.4633,
    "mean_conf": 59.7,
    "gap_pp": 13.4,
    "brier": 0.2688,
    "wilson_95": {
     "lo": 0.4228,
     "hi": 0.5043
    }
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "legacy": false,
    "is_field": false,
    "n": 704,
    "coverage": 0.5293,
    "hit_rate": 0.456,
    "mean_conf": 60.0,
    "gap_pp": 14.4,
    "brier": 0.2714,
    "wilson_95": {
     "lo": 0.4195,
     "hi": 0.4929
    }
   },
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "legacy": false,
    "is_field": false,
    "n": 765,
    "coverage": 0.5849,
    "hit_rate": 0.4575,
    "mean_conf": 65.8,
    "gap_pp": 20.0,
    "brier": 0.2898,
    "wilson_95": {
     "lo": 0.4225,
     "hi": 0.4929
    }
   },
   {
    "model": "gpt-6.1-sol",
    "model_label": "gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "legacy": false,
    "is_field": false,
    "n": 815,
    "coverage": 0.6221,
    "hit_rate": 0.465,
    "mean_conf": 68.0,
    "gap_pp": 21.5,
    "brier": 0.2971,
    "wilson_95": {
     "lo": 0.431,
     "hi": 0.4994
    }
   },
   {
    "model": "Field (all models)",
    "legacy": false,
    "is_field": true,
    "n": 5084,
    "coverage": null,
    "hit_rate": 0.4656,
    "mean_conf": 61.9,
    "gap_pp": 15.4,
    "brier": 0.2759,
    "wilson_95": {
     "lo": null,
     "hi": null
    }
   }
  ],
  "buckets": [
   {
    "model": "deepseek-v4-pro",
    "bucket": "50-60",
    "n": 324,
    "hit_rate": 0.5031,
    "mean_conf": 56.9,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "60-70",
    "n": 435,
    "hit_rate": 0.4667,
    "mean_conf": 61.9,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "70-80",
    "n": 7,
    "hit_rate": 0.4286,
    "mean_conf": 70.3,
    "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": "qwen-3.8-max",
    "bucket": "50-60",
    "n": 415,
    "hit_rate": 0.4651,
    "mean_conf": 56.9,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "60-70",
    "n": 338,
    "hit_rate": 0.4586,
    "mean_conf": 61.9,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "70-80",
    "n": 5,
    "hit_rate": 0.6,
    "mean_conf": 70.6,
    "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": "grok-4.7",
    "bucket": "50-60",
    "n": 275,
    "hit_rate": 0.5164,
    "mean_conf": 57.2,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "grok-4.7",
    "bucket": "60-70",
    "n": 420,
    "hit_rate": 0.4405,
    "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": "claude-opus-5-5",
    "bucket": "50-60",
    "n": 219,
    "hit_rate": 0.484,
    "mean_conf": 56.5,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-opus-5-5",
    "bucket": "60-70",
    "n": 353,
    "hit_rate": 0.4504,
    "mean_conf": 61.7,
    "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": "claude-fable-5",
    "bucket": "50-60",
    "n": 247,
    "hit_rate": 0.4858,
    "mean_conf": 56.4,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-fable-5",
    "bucket": "60-70",
    "n": 457,
    "hit_rate": 0.4398,
    "mean_conf": 61.9,
    "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": "gemini-3.1-pro",
    "bucket": "50-60",
    "n": 2,
    "hit_rate": 0.0,
    "mean_conf": 55,
    "insufficient": true,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "60-70",
    "n": 528,
    "hit_rate": 0.4545,
    "mean_conf": 63.1,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "70-80",
    "n": 233,
    "hit_rate": 0.4721,
    "mean_conf": 71.8,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "80-100",
    "n": 2,
    "hit_rate": 0.0,
    "mean_conf": 80,
    "insufficient": true,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "50-60",
    "n": 36,
    "hit_rate": 0.4722,
    "mean_conf": 58.4,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "60-70",
    "n": 489,
    "hit_rate": 0.4642,
    "mean_conf": 64.8,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "70-80",
    "n": 282,
    "hit_rate": 0.4645,
    "mean_conf": 74.3,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "80-100",
    "n": 8,
    "hit_rate": 0.5,
    "mean_conf": 81.4,
    "insufficient": true,
    "no_data": false
   }
  ],
  "sub50": [
   {
    "model": "deepseek-v4-pro",
    "n": 1,
    "hit_rate": 1.0
   },
   {
    "model": "qwen-3.8-max",
    "n": 8,
    "hit_rate": 0.5
   },
   {
    "model": "grok-4.7",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "claude-opus-5-5",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "claude-fable-5",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "gemini-3.1-pro",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "gpt-6.1-sol",
    "n": 0,
    "hit_rate": null
   }
  ],
  "by_fh": [
   {
    "model": "deepseek-v4-pro",
    "fh": "1h",
    "n": 445,
    "hit_rate": 0.4966,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "4h",
    "n": 274,
    "hit_rate": 0.4526,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "1d",
    "n": 48,
    "hit_rate": 0.5208,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "1h",
    "n": 473,
    "hit_rate": 0.4672,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "4h",
    "n": 247,
    "hit_rate": 0.4413,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "1d",
    "n": 46,
    "hit_rate": 0.5435,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "1h",
    "n": 408,
    "hit_rate": 0.4681,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "4h",
    "n": 238,
    "hit_rate": 0.4496,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "1d",
    "n": 49,
    "hit_rate": 0.5918,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "1h",
    "n": 336,
    "hit_rate": 0.5089,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "4h",
    "n": 196,
    "hit_rate": 0.3673,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "1d",
    "n": 40,
    "hit_rate": 0.55,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "1h",
    "n": 447,
    "hit_rate": 0.4743,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "4h",
    "n": 212,
    "hit_rate": 0.4198,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "1d",
    "n": 45,
    "hit_rate": 0.4444,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "1h",
    "n": 481,
    "hit_rate": 0.4906,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "4h",
    "n": 234,
    "hit_rate": 0.3846,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "1d",
    "n": 50,
    "hit_rate": 0.48,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "1h",
    "n": 471,
    "hit_rate": 0.4586,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "4h",
    "n": 281,
    "hit_rate": 0.452,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "1d",
    "n": 63,
    "hit_rate": 0.5714,
    "flag": null
   }
  ],
  "trading": [
   {
    "model": "grok-4.7",
    "n_trades": 695,
    "wr": 0.3971,
    "pnl_net_usd": -24.12,
    "pnl_gross_usd": 45.38,
    "max_dd_usd": -62.19
   },
   {
    "model": "deepseek-v4-pro",
    "n_trades": 767,
    "wr": 0.4172,
    "pnl_net_usd": -42.95,
    "pnl_gross_usd": 33.75,
    "max_dd_usd": -76.15
   },
   {
    "model": "qwen-3.8-max",
    "n_trades": 766,
    "wr": 0.3864,
    "pnl_net_usd": -45.59,
    "pnl_gross_usd": 31.01,
    "max_dd_usd": -77.3
   },
   {
    "model": "gpt-6.1-sol",
    "n_trades": 815,
    "wr": 0.3951,
    "pnl_net_usd": -50.53,
    "pnl_gross_usd": 30.97,
    "max_dd_usd": -72.48
   },
   {
    "model": "claude-opus-5-5",
    "n_trades": 572,
    "wr": 0.3934,
    "pnl_net_usd": -50.97,
    "pnl_gross_usd": 6.23,
    "max_dd_usd": -71.66
   },
   {
    "model": "claude-fable-5",
    "n_trades": 704,
    "wr": 0.3835,
    "pnl_net_usd": -65.96,
    "pnl_gross_usd": 4.44,
    "max_dd_usd": -84.75
   },
   {
    "model": "gemini-3.1-pro",
    "n_trades": 765,
    "wr": 0.3699,
    "pnl_net_usd": -71.98,
    "pnl_gross_usd": 4.52,
    "max_dd_usd": -89.35
   }
  ],
  "gap_week_over_week": [
   {
    "model": "deepseek-v4-pro",
    "gap_pp_issue10": 18.1,
    "gap_pp_issue11": 11.6,
    "delta_pp": -6.5
   },
   {
    "model": "qwen-3.8-max",
    "gap_pp_issue10": 15.4,
    "gap_pp_issue11": 12.7,
    "delta_pp": -2.7
   },
   {
    "model": "grok-4.7",
    "gap_pp_issue10": 16.3,
    "gap_pp_issue11": 12.9,
    "delta_pp": -3.4
   },
   {
    "model": "claude-opus-5-5",
    "gap_pp_issue10": 13.8,
    "gap_pp_issue11": 13.4,
    "delta_pp": -0.4
   },
   {
    "model": "claude-fable-5",
    "gap_pp_issue10": 14.9,
    "gap_pp_issue11": 14.4,
    "delta_pp": -0.5
   },
   {
    "model": "gemini-3.1-pro",
    "gap_pp_issue10": 21.8,
    "gap_pp_issue11": 20.0,
    "delta_pp": -1.8
   },
   {
    "model": "gpt-6.1-sol",
    "gap_pp_issue10": 24.7,
    "gap_pp_issue11": 21.5,
    "delta_pp": -3.2
   },
   {
    "model": "Field",
    "gap_pp_issue10": 18.2,
    "gap_pp_issue11": 15.4,
    "delta_pp": -2.8
   }
  ],
  "ok_rate_by_model": {
   "deepseek-v4-pro": 1.0,
   "qwen-3.8-max": 1.0,
   "grok-4.7": 0.9864,
   "claude-opus-5-5": 0.985,
   "claude-fable-5": 0.9966,
   "gemini-3.1-pro": 0.985,
   "gpt-6.1-sol": 0.9864
  },
  "counters": {
   "forecasts_total": 10260,
   "ok_in_gate": 9198,
   "out_of_gate": 973,
   "out_of_gate_by_fh": {
    "1m": 483,
    "1w": 490
   },
   "invalid": 89,
   "mature": 9198,
   "mature_directional": 5084,
   "mature_sideways": 4114,
   "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": {
    "2026-10-12": {
     "move_pct": -2.17,
     "regime": "trend"
    },
    "2026-10-13": {
     "move_pct": 1.56,
     "regime": "trend"
    },
    "2026-10-14": {
     "move_pct": -1.68,
     "regime": "trend"
    },
    "2026-10-15": {
     "move_pct": 0.52,
     "regime": "flat"
    },
    "2026-10-16": {
     "move_pct": -0.77,
     "regime": "flat"
    },
    "2026-10-17": {
     "move_pct": -0.26,
     "regime": "flat"
    },
    "2026-10-18": {
     "move_pct": 0.83,
     "regime": "flat"
    }
   },
   "grok_era": {
    "ids_in_window": [
     "grok-4.6",
     "grok-4.7"
    ],
    "n_grok45": 0,
    "n_grok46": 1155,
    "n_grok45_rows": 0,
    "n_grok46_rows": 1155,
    "n_grok47_rows": 315,
    "first_grok46_slot": "2026-10-12T00:01:00+00:00",
    "last_grok45_slot": null,
    "first_grok45_slot": null,
    "first_grok47_slot": "2026-10-17T09:01:00+00:00",
    "last_grok46_slot": "2026-10-17T08:01:00+00:00",
    "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": true,
    "prev_window": {
     "n_grok45_rows": 0,
     "n_grok46_rows": 1470
    },
    "merged_model_id": "grok-4.7",
    "merged_label": "grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "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": 2625,
    "note": "grok-4.7 went live 2026-10-17T09:01:00+00:00 (B0) -- INSIDE this window (day 6 of 7); all per-model aggregates use the lineage splice grok-4.6/grok-4.5 -> grok-4.7 (one row, labelled 'grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)'). Week A (prev window, issue #10) is pure grok-4.6 and reproduces issue #10 under the head id; week B mixes the 4.6-era with grok-4.7. The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits seven 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": [
      "2026-10-12",
      "2026-10-13",
      "2026-10-14",
      "2026-10-15",
      "2026-10-16",
      "2026-10-17",
      "2026-10-18"
     ],
     "missing_days": []
    },
    "1h": {
     "days_with_slots": 7,
     "expected_days": 7,
     "full_daily_coverage": true,
     "in_fh_gate": true,
     "n_slots": 168,
     "n_rows": 5860,
     "days": [
      "2026-10-12",
      "2026-10-13",
      "2026-10-14",
      "2026-10-15",
      "2026-10-16",
      "2026-10-17",
      "2026-10-18"
     ],
     "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": [
      "2026-10-12",
      "2026-10-13",
      "2026-10-14",
      "2026-10-15",
      "2026-10-16",
      "2026-10-17",
      "2026-10-18"
     ],
     "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": [
      "2026-10-12",
      "2026-10-13",
      "2026-10-14",
      "2026-10-15",
      "2026-10-16",
      "2026-10-17",
      "2026-10-18"
     ],
     "missing_days": []
    },
    "4h": {
     "days_with_slots": 7,
     "expected_days": 7,
     "full_daily_coverage": true,
     "in_fh_gate": true,
     "n_slots": 42,
     "n_rows": 2930,
     "days": [
      "2026-10-12",
      "2026-10-13",
      "2026-10-14",
      "2026-10-15",
      "2026-10-16",
      "2026-10-17",
      "2026-10-18"
     ],
     "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",
     "claude-opus-5-5",
     "deepseek-v4-pro",
     "gemini-3.1-pro",
     "gpt-5.6-sol",
     "gpt-6.1-sol",
     "grok-4.6",
     "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": [
     "claude-opus-5",
     "gpt-5.6-sol",
     "grok-4.6"
    ],
    "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 inside this 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 inside this window (repeated in retired_inside_window) next to the long-archived ones. 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": "2026-10-12T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": null,
     "flip_inside_window": false,
     "label": "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": 1155,
     "n_head_rows_b": 315,
     "n_prev_rows_a": 1470,
     "n_head_rows_a": 0,
     "first_head_slot": "2026-10-17T09:01:00+00:00",
     "last_prev_slot": "2026-10-17T08:01:00+00:00",
     "flip_at": "2026-10-17T09:01:00+00:00",
     "flip_inside_window": true,
     "label": "claude-opus-5-5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC)",
     "cells_with_two_rows": 0
    },
    "gpt-6.1-sol": {
     "prev_ids": [
      "gpt-5.6-sol"
     ],
     "n_prev_rows_b": 1155,
     "n_head_rows_b": 315,
     "n_prev_rows_a": 1470,
     "n_head_rows_a": 0,
     "first_head_slot": "2026-10-17T09:01:00+00:00",
     "last_prev_slot": "2026-10-17T08:01:00+00:00",
     "flip_at": "2026-10-17T09:01:00+00:00",
     "flip_inside_window": true,
     "label": "gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
     "cells_with_two_rows": 0
    },
    "deepseek-v4-pro": {
     "prev_ids": [],
     "n_prev_rows_b": 0,
     "n_head_rows_b": 1440,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1470,
     "first_head_slot": "2026-10-12T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": null,
     "flip_inside_window": false,
     "label": "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": "2026-10-12T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": null,
     "flip_inside_window": false,
     "label": "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": "2026-10-12T00:01:00+00:00",
     "last_prev_slot": null,
     "flip_at": null,
     "flip_inside_window": false,
     "label": "qwen-3.8-max",
     "cells_with_two_rows": 0
    },
    "grok-4.7": {
     "prev_ids": [
      "grok-4.6",
      "grok-4.5"
     ],
     "n_prev_rows_b": 1155,
     "n_head_rows_b": 315,
     "n_prev_rows_a": 1470,
     "n_head_rows_a": 0,
     "first_head_slot": "2026-10-17T09:01:00+00:00",
     "last_prev_slot": "2026-10-17T08:01:00+00:00",
     "flip_at": "2026-10-17T09:01:00+00:00",
     "flip_inside_window": true,
     "label": "grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
     "cells_with_two_rows": 0
    }
   },
   "invalid_by_slot_b0": {
    "2026-10-17T07:01:00+00:00": {
     "claude-opus-5": 5,
     "gpt-5.6-sol": 5,
     "grok-4.6": 5
    },
    "2026-10-17T08:01:00+00:00": {
     "claude-opus-5": 15,
     "gpt-5.6-sol": 15,
     "grok-4.6": 15
    }
   }
  }
 },
 "key_finding": {
  "label": "KEY FINDING · OBSERVATION (one weekly window)",
  "text": "The field's overconfidence gap moved +18.2pp -> +15.4pp week over week, 7 of 7 model lines narrowed, and field Brier went 0.2822 -> 0.2759.",
  "evidence_level": "observation"
 },
 "key_findings": [
  "**OBSERVATION -- The gap read +15.4pp this week.** Directional calls hit 46.6% against 61.9 stated mean confidence (issue #10: +18.2pp on 43.8% vs 61.9). Field Brier is 0.2759 (was 0.2822) 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 deepseek-v4-pro's -6.5pp (+18.1pp -> +11.6pp) to claude-opus-5.5 (spliced)'s -0.4pp (+13.8pp -> +13.4pp); 7 of 7 model lines narrowed week over week. deepseek-v4-pro is both the lowest-Brier line (Brier 0.2657) and the hit-rate leader (48.2%).",
  "**The high-confidence buckets, N>=10 only.** gemini-3.1-pro 70-80 47.2% (n=233), gpt-6.1-sol (spliced) 70-80 46.5% (n=282). 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 -$24.12 (grok-4.7 (spliced), best) to -$71.98 (gemini-3.1-pro, worst), field -$352.09 against issue #10's -$520.82."
 ],
 "market_check": {
  "label": "MARKET CHECK · OBSERVATION (two adjacent calendar weeks)",
  "text": "OBSERVATION — mean |1d move| 1.54% -> 2.05% (+33% rel), BTC realized vol 30.9% -> 34.9% (ann., hourly); field directional accuracy 43.8% -> 46.6% (+2.8pp), 6 of 7 models improved, sim win-rate up for 7 of 7, field sim PnL -$520.82 -> -$352.09 (adjacent calendar weeks Oct 5-11 vs Oct 12-18; descriptive, one pair of weeks, not a claim).",
  "robustness": "Robustness: raw price-sign accuracy 45.5% -> 44.1% — the opposite direction to the trade-based hit rule.",
  "weeks": {
   "A": {
    "days": "2026-10-05..2026-10-11",
    "slots": [
     "2026-10-05T00:00:00+00:00",
     "2026-10-12T00:00:00+00:00"
    ],
    "cutoff": "2026-10-12T16:00:00+00:00"
   },
   "B": {
    "days": "2026-10-12..2026-10-18",
    "slots": [
     "2026-10-12T00:00:00+00:00",
     "2026-10-19T00:00:00+00:00"
    ],
    "cutoff": "2026-10-19T16:00:00+00:00"
   }
  },
  "price_source": "crypto_spot/1h@:00",
  "accuracy_field": {
   "A": {
    "n": 4601,
    "hit_rate": 0.4375,
    "wilson_95": [
     0.4232,
     0.4519
    ]
   },
   "B": {
    "n": 5084,
    "hit_rate": 0.4656,
    "wilson_95": [
     0.4519,
     0.4793
    ]
   },
   "delta_pp": 2.8
  },
  "accuracy_per_model": [
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "A": {
     "n": 761,
     "hit_rate": 0.4205,
     "wilson_95": [
      0.3859,
      0.4559
     ]
    },
    "B": {
     "n": 767,
     "hit_rate": 0.4824,
     "wilson_95": [
      0.4472,
      0.5178
     ]
    },
    "delta_pp": 6.2
   },
   {
    "model": "grok-4.7",
    "model_label": "grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "A": {
     "n": 547,
     "hit_rate": 0.4333,
     "wilson_95": [
      0.3924,
      0.4751
     ]
    },
    "B": {
     "n": 695,
     "hit_rate": 0.4705,
     "wilson_95": [
      0.4337,
      0.5077
     ]
    },
    "delta_pp": 3.7
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "A": {
     "n": 707,
     "hit_rate": 0.4314,
     "wilson_95": [
      0.3954,
      0.4682
     ]
    },
    "B": {
     "n": 766,
     "hit_rate": 0.4634,
     "wilson_95": [
      0.4284,
      0.4989
     ]
    },
    "delta_pp": 3.2
   },
   {
    "model": "gpt-6.1-sol",
    "model_label": "gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "A": {
     "n": 734,
     "hit_rate": 0.4346,
     "wilson_95": [
      0.3992,
      0.4707
     ]
    },
    "B": {
     "n": 815,
     "hit_rate": 0.465,
     "wilson_95": [
      0.431,
      0.4994
     ]
    },
    "delta_pp": 3.0
   },
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "A": {
     "n": 722,
     "hit_rate": 0.4335,
     "wilson_95": [
      0.3978,
      0.4699
     ]
    },
    "B": {
     "n": 765,
     "hit_rate": 0.4575,
     "wilson_95": [
      0.4225,
      0.4929
     ]
    },
    "delta_pp": 2.4
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "A": {
     "n": 613,
     "hit_rate": 0.4502,
     "wilson_95": [
      0.4113,
      0.4898
     ]
    },
    "B": {
     "n": 704,
     "hit_rate": 0.456,
     "wilson_95": [
      0.4195,
      0.4929
     ]
    },
    "delta_pp": 0.6
   },
   {
    "model": "claude-opus-5-5",
    "model_label": "claude-opus-5.5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "A": {
     "n": 517,
     "hit_rate": 0.47,
     "wilson_95": [
      0.4274,
      0.5131
     ]
    },
    "B": {
     "n": 572,
     "hit_rate": 0.4633,
     "wilson_95": [
      0.4228,
      0.5043
     ]
    },
    "delta_pp": -0.7
   }
  ],
  "raw_sign_field": {
   "A": {
    "n_scored": 4585,
    "hit_rate": 0.4547
   },
   "B": {
    "n_scored": 5074,
    "hit_rate": 0.4411
   }
  },
  "abs_move_1d": {
   "A": 1.542,
   "B": 2.054,
   "delta_pct_rel": 33.2
  },
  "btc_realized_vol_ann_pct_hourly": {
   "A": 30.91,
   "B": 34.86
  },
  "trading_field": {
   "A": {
    "n_trades": 4601,
    "wr": 0.3451,
    "pnl_net_usd": -520.82,
    "pnl_gross_usd": -60.72
   },
   "B": {
    "n_trades": 5084,
    "wr": 0.3918,
    "pnl_net_usd": -352.09,
    "pnl_gross_usd": 156.31
   }
  },
  "verdict": {
   "models_with_hit_improved": "6 of 7",
   "models_with_rawsign_improved": "1 of 7",
   "models_with_wr_improved": "7 of 7",
   "field_hit_delta_pp": 2.8,
   "field_pnl_net": {
    "A": -520.82,
    "B": -352.09
   },
   "abs_move_delta": {
    "1h": {
     "A": 0.285,
     "B": 0.355,
     "delta_pct_rel": 24.6
    },
    "4h": {
     "A": 0.597,
     "B": 0.793,
     "delta_pct_rel": 32.8
    },
    "1d": {
     "A": 1.542,
     "B": 2.054,
     "delta_pct_rel": 33.2
    }
   },
   "btc_vol_ann_pct": {
    "A": 30.91,
    "B": 34.86
   },
   "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, inside week B, day 6 of 7) splices 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 (2026-10-05..2026-10-11) is entirely pre-B0: its old-id rows are aggregated under the heads (it reproduces the published issue #10); week B mixes the old-id era with the new ids. The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits seven 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 #11 the series has eleven 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. Three model lines flipped at Oct 17, 2026 09:01 UTC, INSIDE this window: gpt-5.6-sol -> gpt-6.1-sol, claude-opus-5 -> claude-opus-5.5 and grok-4.6 -> grok-4.7. Every row of those three lines in this issue is a lineage splice (old-era rows Oct 12 00:00-Oct 17 09:01, new-era rows after), week A (the issue-#10 window) is entirely old-era, so each of the three week-over-week rows joins a spliced line to a single-build line. Engine ids are kept; the vendors' names are Claude Opus 5.5, GPT-6.1 Sol and Grok 4.7. claude-opus-5.5 (spliced) = claude-opus-5.5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC); gpt-6.1-sol (spliced) = gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC); grok-4.7 (spliced) = grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC).",
 "practical_implications": [
  "Stated confidence is still a ranking hint at best, not a probability: the field's gap is +15.4pp this week against +18.2pp in issue #10.",
  "Gap and regime move together. The field hit 46.6% against 43.8% in issue #10 and stated mean confidence read 61.9 against 61.9, so the gap came out at +15.4pp: a field that hits 46.6% instead of 43.8% 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 same lines printed the opposite sign inside nine weeks."
 ],
 "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 5,084 scored calls sit inside one market regime. This window ran 3 trend days of 7 (issue #10: 2 of 7); every comparison with issue #10 is a comparison across regimes as well as across weeks. Eleven 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 11): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 12-18) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9 and #10: 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 483). (2) Model lineage is a splice. Three lines flipped at Oct 17, 2026 09:01 UTC, INSIDE this window (day 6 of 7): \"claude-opus-5.5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC)\" (1,155 rows from the claude-opus-5 era, 315 from claude-opus-5.5); \"gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC)\" (1,155 rows from the gpt-5.6-sol era, 315 from gpt-6.1-sol); \"grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)\" (1,155 rows from the grok-4.6 era, 315 from grok-4.7). Week A (the issue-#10 window) carries no new-build rows, so each of the three week-over-week rows joins a spliced line to a single-build line, and a remapped comparison is not the same model build. (3) The two hourly slots before the flip (Oct 17, 07:01 and 08:01 UTC) hold 60 invalid rows (claude-opus-5 20, gpt-5.6-sol 20, grok-4.6 20), counted in the invalid counter as they are; in those two hours the other 4 lines (claude-fable-5, deepseek-v4-pro, gemini-3.1-pro, qwen-3.8-max) carry ok rows. (4) deepseek-v4-pro carries 1,440 rows in this window against 1,470 for every other line (Oct 15: 180 rows instead of 210). (5) The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits seven 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 #10 after the audit that found the raw table mixes two exchanges; issue #10 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 (Oct 19 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9 and #10, which printed 66,861 at the Oct 12 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 71,945 is an additive step under one definition; counter deltas against issue #9 and earlier remain definitional."
 ],
 "notes": {
  "series_density_and_lineage_wave11": "Series density and lineage notes (wave 11): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 12-18) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9 and #10: 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 483). (2) Model lineage is a splice. Three lines flipped at Oct 17, 2026 09:01 UTC, INSIDE this window (day 6 of 7): \"claude-opus-5.5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC)\" (1,155 rows from the claude-opus-5 era, 315 from claude-opus-5.5); \"gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC)\" (1,155 rows from the gpt-5.6-sol era, 315 from gpt-6.1-sol); \"grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)\" (1,155 rows from the grok-4.6 era, 315 from grok-4.7). Week A (the issue-#10 window) carries no new-build rows, so each of the three week-over-week rows joins a spliced line to a single-build line, and a remapped comparison is not the same model build. (3) The two hourly slots before the flip (Oct 17, 07:01 and 08:01 UTC) hold 60 invalid rows (claude-opus-5 20, gpt-5.6-sol 20, grok-4.6 20), counted in the invalid counter as they are; in those two hours the other 4 lines (claude-fable-5, deepseek-v4-pro, gemini-3.1-pro, qwen-3.8-max) carry ok rows. (4) deepseek-v4-pro carries 1,440 rows in this window against 1,470 for every other line (Oct 15: 180 rows instead of 210). (5) The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits seven 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-4.6",
    "grok-4.7"
   ],
   "n_grok45": 0,
   "n_grok46": 1155,
   "n_grok45_rows": 0,
   "n_grok46_rows": 1155,
   "n_grok47_rows": 315,
   "first_grok46_slot": "2026-10-12T00:01:00+00:00",
   "last_grok45_slot": null,
   "first_grok45_slot": null,
   "first_grok47_slot": "2026-10-17T09:01:00+00:00",
   "last_grok46_slot": "2026-10-17T08:01:00+00:00",
   "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": true,
   "prev_window": {
    "n_grok45_rows": 0,
    "n_grok46_rows": 1470
   },
   "merged_model_id": "grok-4.7",
   "merged_label": "grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
   "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": 2625,
   "note": "grok-4.7 went live 2026-10-17T09:01:00+00:00 (B0) -- INSIDE this window (day 6 of 7); all per-model aggregates use the lineage splice grok-4.6/grok-4.5 -> grok-4.7 (one row, labelled 'grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)'). Week A (prev window, issue #10) is pure grok-4.6 and reproduces issue #10 under the head id; week B mixes the 4.6-era with grok-4.7. The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits seven 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",
    "claude-opus-5-5",
    "deepseek-v4-pro",
    "gemini-3.1-pro",
    "gpt-5.6-sol",
    "gpt-6.1-sol",
    "grok-4.6",
    "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": [
    "claude-opus-5",
    "gpt-5.6-sol",
    "grok-4.6"
   ],
   "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 inside this 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 inside this window (repeated in retired_inside_window) next to the long-archived ones. 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": [
     "2026-10-12",
     "2026-10-13",
     "2026-10-14",
     "2026-10-15",
     "2026-10-16",
     "2026-10-17",
     "2026-10-18"
    ],
    "missing_days": []
   },
   "1h": {
    "days_with_slots": 7,
    "expected_days": 7,
    "full_daily_coverage": true,
    "in_fh_gate": true,
    "n_slots": 168,
    "n_rows": 5860,
    "days": [
     "2026-10-12",
     "2026-10-13",
     "2026-10-14",
     "2026-10-15",
     "2026-10-16",
     "2026-10-17",
     "2026-10-18"
    ],
    "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": [
     "2026-10-12",
     "2026-10-13",
     "2026-10-14",
     "2026-10-15",
     "2026-10-16",
     "2026-10-17",
     "2026-10-18"
    ],
    "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": [
     "2026-10-12",
     "2026-10-13",
     "2026-10-14",
     "2026-10-15",
     "2026-10-16",
     "2026-10-17",
     "2026-10-18"
    ],
    "missing_days": []
   },
   "4h": {
    "days_with_slots": 7,
    "expected_days": 7,
    "full_daily_coverage": true,
    "in_fh_gate": true,
    "n_slots": 42,
    "n_rows": 2930,
    "days": [
     "2026-10-12",
     "2026-10-13",
     "2026-10-14",
     "2026-10-15",
     "2026-10-16",
     "2026-10-17",
     "2026-10-18"
    ],
    "missing_days": []
   }
  },
  "week_over_week_note": "Week-over-week columns compare back-to-back windows: Oct 5-11 (issue #10, and week A of this issue's alive slice) vs Oct 12-18 (this issue). \"Was\" values are the numbers published in issue #10; 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 (Oct 19 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9 and #10, which printed 66,861 at the Oct 12 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 71,945 is an additive step under one definition; counter deltas against issue #9 and earlier remain definitional.",
  "market_state_audit": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #10 after the audit that found the raw table mixes two exchanges; issue #10 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": "2026-10-12T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": null,
    "flip_inside_window": false,
    "label": "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": 1155,
    "n_head_rows_b": 315,
    "n_prev_rows_a": 1470,
    "n_head_rows_a": 0,
    "first_head_slot": "2026-10-17T09:01:00+00:00",
    "last_prev_slot": "2026-10-17T08:01:00+00:00",
    "flip_at": "2026-10-17T09:01:00+00:00",
    "flip_inside_window": true,
    "label": "claude-opus-5-5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "cells_with_two_rows": 0
   },
   "gpt-6.1-sol": {
    "prev_ids": [
     "gpt-5.6-sol"
    ],
    "n_prev_rows_b": 1155,
    "n_head_rows_b": 315,
    "n_prev_rows_a": 1470,
    "n_head_rows_a": 0,
    "first_head_slot": "2026-10-17T09:01:00+00:00",
    "last_prev_slot": "2026-10-17T08:01:00+00:00",
    "flip_at": "2026-10-17T09:01:00+00:00",
    "flip_inside_window": true,
    "label": "gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "cells_with_two_rows": 0
   },
   "deepseek-v4-pro": {
    "prev_ids": [],
    "n_prev_rows_b": 0,
    "n_head_rows_b": 1440,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1470,
    "first_head_slot": "2026-10-12T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": null,
    "flip_inside_window": false,
    "label": "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": "2026-10-12T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": null,
    "flip_inside_window": false,
    "label": "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": "2026-10-12T00:01:00+00:00",
    "last_prev_slot": null,
    "flip_at": null,
    "flip_inside_window": false,
    "label": "qwen-3.8-max",
    "cells_with_two_rows": 0
   },
   "grok-4.7": {
    "prev_ids": [
     "grok-4.6",
     "grok-4.5"
    ],
    "n_prev_rows_b": 1155,
    "n_head_rows_b": 315,
    "n_prev_rows_a": 1470,
    "n_head_rows_a": 0,
    "first_head_slot": "2026-10-17T09:01:00+00:00",
    "last_prev_slot": "2026-10-17T08:01:00+00:00",
    "flip_at": "2026-10-17T09:01:00+00:00",
    "flip_inside_window": true,
    "label": "grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
    "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"
   }
  }
 },
 "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 #11.** Weekly Calibration is a living series. Issue #10's open questions -- \"the gap moved +5.3pp while the field base moved -5.9pp -- the fifth issue running in which the two move nearly one-for-one in opposite directions; does that hold for a sixth?\" and \"The best-Brier line changed hands again, to claude-opus-5 -- does it hold for a second issue, or change hands again?\" -- read this issue as: field gap +18.2pp -> +15.4pp (7 of 7 lines narrowed) on a field base that moved +2.8pp, a sixth issue running in opposite directions, and the best-Brier line changed hands again: deepseek-v4-pro at 0.2657 (issue #10: claude-opus-5 at 0.2685). Also on the record: gpt-6.1-sol's 70-80 bucket read 46.5% (n=282) against its own 60-70 at 46.4% (n=489). Three rows are lineage splices this issue (claude-opus-5.5 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC); gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC); grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)) because the flip (Oct 17, 2026 09:01 UTC) fell inside the window; in issue #10 they were pure claude-opus-5, gpt-5.6-sol and grok-4.6. The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits seven 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 -2.8pp while the field base moved +2.8pp -- the sixth issue running in which the two move nearly one-for-one in opposite directions; does that hold for a seventh?",
  "The best-Brier line changed hands again, to deepseek-v4-pro -- does it hold for a second issue, or change hands again?",
  "Monthly series: is the overconfidence gap stable across market regimes (trend vs flat) at monthly n?"
 ],
 "related_research": [
  {
   "title": "Consensus Watch #11",
   "url": "https://marketmania.ai/research/reports/consensus-watch-2026-10-12.pdf"
  },
  {
   "title": "Weekly Model Watch #11",
   "url": "https://marketmania.ai/research/reports/model-watch-2026-10-12.pdf"
  },
  {
   "title": "Weekly Calibration #10",
   "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-10-05.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_2026w42",
  "title": "Weekly Calibration #11: confidence vs. direction-hit, Oct 12-18 2026",
  "author": "MarketMania Research",
  "year": 2026,
  "month": "October",
  "day": 21,
  "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-10-12.pdf",
  "note": "Methodology v1.1; window Oct 12-18, 2026 UTC; source weekly_metrics_2026-10-12.json"
 },
 "research_to_date": {
  "this_report": {
   "scored_observations": 5084
  },
  "platform": {
   "as_of_cutoff": "2026-10-19",
   "resolved_forecasts": 71945,
   "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": 56
  },
  "source": "weekly_metrics_2026-10-12.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 (Oct 19 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9 and #10, which printed 66,861 at the Oct 12 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 71,945 is an additive step under one definition; counter deltas against issue #9 and earlier remain definitional."
 },
 "site_entry": {
  "slug": "weekly-calibration-2026-10-12",
  "series": "weekly",
  "seriesLabel": "Weekly · Calibration",
  "date": "October 21, 2026",
  "title": "Weekly Calibration #11",
  "summary": "5,084 directional calls asked whether stated confidence tracks reality. The field hit 46.6% against 61.9 stated mean confidence, an overconfidence gap of +15.4pp against +18.2pp in issue #10, and 7 of 7 model lines narrowed week over week. Field Brier moved 0.2822 -> 0.2759; deepseek-v4-pro is the lowest-Brier line at 0.2657 and deepseek-v4-pro leads on hit-rate at 48.2%. Trading, kept in its own section, finished with 0 of 7 lines net-positive as field accuracy moved 43.8% -> 46.6% (+2.8pp).",
  "stats": [
   "5,084 directional calls",
   "gap +15.4pp (was +18.2pp)",
   "0 of 7 net-positive"
  ],
  "manifest_key_finding": "The overconfidence gap read +15.4pp against +18.2pp in issue #10, with 7 of 7 model lines narrowing and field Brier moving 0.2822 -> 0.2759; trading, kept separate, finished 0 of 7 lines net-positive.",
  "files": {
   "pdf": "/research/reports/weekly-calibration-2026-10-12.pdf",
   "md": "/research/reports/weekly-calibration-2026-10-12.md",
   "json": "/research/reports/weekly-calibration-2026-10-12.json"
  }
 },
 "social": {
  "telegram": {
   "photo_caption_html": "🎯 <b>Weekly Calibration #11</b> — weekly series (window Oct 12–18)\n\nResearch question: when a model says 70, does it hit 70% of the time?\n\n5,084 directional calls across 7 model lines:\n• Field hit <b>46.6%</b> vs <b>61.9</b> stated — an overconfidence gap of <b>+15.4pp</b> (issue #10: +18.2pp)\n• Gap week over week: <b>7 of 7 lines narrowed</b>; field Brier 0.2822 -> 0.2759\n• Lowest-Brier line: <b>deepseek-v4-pro</b> (Brier 0.2657); hit-rate leader deepseek-v4-pro at 48.2%\n• Market check: field accuracy 43.8% -> 46.6% (+2.8pp); trading kept separate — <b>0 of 7 net-positive</b>\n\nNote: the opus, gpt and grok rows are lineage splices this issue — claude-opus-5.5, gpt-6.1-sol and grok-4.7 took over on Oct 17 09:01 UTC, inside the window\n\n📄 <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-12.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 #11 — full report (PDF).\nWeb copy: <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-12.pdf\">weekly-calibration-2026-10-12.pdf</a> · machine-readable: <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-12.json\">JSON</a> · <a href=\"https://marketmania.ai/research\">all research</a>\n\n#cryptotrading #LLM #AI #crypto #trading #calibration #research",
   "caption_len": 977,
   "document_caption_len": 417,
   "limit": 1024
  },
  "x": {
   "main": "Weekly Calibration #11 is out.\n\n5,084 LLM calls: 46.6% hit vs 61.9 stated confidence — an overconfidence gap of +15.4pp against +18.2pp a week earlier, with 7 of 7 lines narrowing.\n\nFull report: https://marketmania.ai/research/reports/weekly-calibration-2026-10-12.pdf\n\n#AI #Crypto #Research #Calibration",
   "main_tco_len": 254,
   "reply": "Overconfidence gap, w/w (pp):\ndeepseek: 18.1 -> 11.6\nqwen-3.8: 15.4 -> 12.7\ngrok-4.7: 16.3 -> 12.9\nopus-5.5: 13.8 -> 13.4\nfable-5: 14.9 -> 14.4\ngemini-3.1: 21.8 -> 20.0\ngpt-6.1: 24.7 -> 21.5\nField: +18.2pp -> +15.4pp. Methodology v1.1.\nData: https://marketmania.ai/research/reports/weekly-calibration-2026-10-12.json",
   "reply_tco_len": 265,
   "limit_tco": 280,
   "replies_max": 1
  }
 }
}
