{
 "slug": "weekly-calibration-2026-10-19",
 "series": "weekly",
 "series_label": "WEEKLY · CALIBRATION",
 "issue": 12,
 "title": "Weekly Calibration #12",
 "language": "en",
 "window_start": "2026-10-19T00:00:00+00:00",
 "window_end": "2026-10-26T00:00:00+00:00",
 "window_text": "Oct 19-25, 2026 UTC",
 "cutoff": "2026-10-26T16:00:00+00:00",
 "generated_at": "2026-10-27T12:12:11+00:00",
 "methodology": "v1.1 (2026-08-10)",
 "methodology_hash": "e66c7e8c864a2233",
 "source": "weekly_metrics_2026-10-19.json",
 "hit_rule": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl",
 "bibtex_key": "mm_calibration_2026w43",
 "market_state": {
  "panel": "market_state_6p2",
  "week": {
   "start": "2026-10-19",
   "end": "2026-10-26"
  },
  "prev_week": {
   "start": "2026-10-12",
   "end": "2026-10-19"
  },
  "current": {
   "btc_net_pct": -2.39,
   "realized_vol_ann_pct": 29.29,
   "volume_top5_usd_bn": 14.0246,
   "volume_top5_wow_pct": -11.5,
   "avg_pairwise_corr": 0.93
  },
  "previous_as_published_issue11": {
   "btc_net_pct": -1.98,
   "realized_vol_ann_pct": 27.36,
   "volume_top5_usd_bn": 15.8439,
   "avg_pairwise_corr": 0.94
  },
  "snapshot_line": "BTC net -2.39% (prior -1.98%) - ann vol 29.3% (was 27.4%) - TOP5 volume $14.02B, -12% w/w - pairwise corr 0.93 (was 0.94)",
  "exchange": "binance",
  "audit_filter_applied": true,
  "source": "single-exchange (binance) daily candle recompute, market_state_2026-10-19.json; prior-week values as published in issue #11",
  "audit_note": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #11 after the audit that found the raw table mixes two exchanges; issue #11 values are as published.",
  "prev_week_control": {
   "published_issue3": {
    "btc_net_pct": -1.98,
    "realized_vol_ann_pct": 27.36,
    "volume_top5_usd_bn": 15.8439,
    "avg_pairwise_corr": 0.94
   },
   "published_issue11": {
    "btc_net_pct": -1.98,
    "realized_vol_ann_pct": 27.36,
    "volume_top5_usd_bn": 15.8439,
    "avg_pairwise_corr": 0.94
   },
   "got": {
    "btc_net_pct": -1.98,
    "realized_vol_ann_pct": 27.36,
    "volume_top5_usd_bn": 15.8439,
    "avg_pairwise_corr": 0.94
   },
   "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-#11 week; the four Snapshot pins must reproduce (key published_issue3 kept for the builder schema, published_issue11 is the add-only alias)"
  },
  "regime_days": {
   "2026-10-19": {
    "move_pct": -0.17,
    "regime": "flat"
   },
   "2026-10-20": {
    "move_pct": 1.24,
    "regime": "flat"
   },
   "2026-10-21": {
    "move_pct": 1.48,
    "regime": "flat"
   },
   "2026-10-22": {
    "move_pct": -3.34,
    "regime": "trend"
   },
   "2026-10-23": {
    "move_pct": -0.27,
    "regime": "flat"
   },
   "2026-10-24": {
    "move_pct": -0.41,
    "regime": "flat"
   },
   "2026-10-25": {
    "move_pct": -0.91,
    "regime": "flat"
   }
  },
  "alive_slice_context": {
   "abs_move_1d_pct": {
    "A": 2.054,
    "B": 1.353
   },
   "btc_realized_vol_ann_pct_hourly": {
    "A": 34.86,
    "B": 27.48
   }
  }
 },
 "tables": {
  "calibration_main": [
   {
    "model": "claude-opus-5-5",
    "model_label": "claude-opus-5-5",
    "legacy": false,
    "is_field": false,
    "n": 700,
    "coverage": 0.5263,
    "hit_rate": 0.58,
    "mean_conf": 56.5,
    "gap_pp": -1.5,
    "brier": 0.2443,
    "wilson_95": {
     "lo": 0.5431,
     "hi": 0.616
    }
   },
   {
    "model": "gpt-6.1-sol",
    "model_label": "gpt-6.1-sol",
    "legacy": false,
    "is_field": false,
    "n": 962,
    "coverage": 0.7233,
    "hit_rate": 0.5759,
    "mean_conf": 63.2,
    "gap_pp": 5.6,
    "brier": 0.2468,
    "wilson_95": {
     "lo": 0.5444,
     "hi": 0.6068
    }
   },
   {
    "model": "grok-4.7",
    "model_label": "grok-4.7",
    "legacy": false,
    "is_field": false,
    "n": 836,
    "coverage": 0.6938,
    "hit_rate": 0.5586,
    "mean_conf": 60.1,
    "gap_pp": 4.3,
    "brier": 0.2472,
    "wilson_95": {
     "lo": 0.5248,
     "hi": 0.5919
    }
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "legacy": false,
    "is_field": false,
    "n": 829,
    "coverage": 0.6238,
    "hit_rate": 0.5633,
    "mean_conf": 59.9,
    "gap_pp": 3.5,
    "brier": 0.248,
    "wilson_95": {
     "lo": 0.5294,
     "hi": 0.5967
    }
   },
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "legacy": false,
    "is_field": false,
    "n": 891,
    "coverage": 0.6699,
    "hit_rate": 0.5645,
    "mean_conf": 61.0,
    "gap_pp": 4.5,
    "brier": 0.2481,
    "wilson_95": {
     "lo": 0.5318,
     "hi": 0.5967
    }
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "legacy": false,
    "is_field": false,
    "n": 768,
    "coverage": 0.5774,
    "hit_rate": 0.5638,
    "mean_conf": 60.9,
    "gap_pp": 4.5,
    "brier": 0.2486,
    "wilson_95": {
     "lo": 0.5285,
     "hi": 0.5985
    }
   },
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "legacy": false,
    "is_field": false,
    "n": 870,
    "coverage": 0.6606,
    "hit_rate": 0.5828,
    "mean_conf": 67.5,
    "gap_pp": 9.3,
    "brier": 0.2551,
    "wilson_95": {
     "lo": 0.5497,
     "hi": 0.6151
    }
   },
   {
    "model": "Field (all models)",
    "legacy": false,
    "is_field": true,
    "n": 5856,
    "coverage": null,
    "hit_rate": 0.5698,
    "mean_conf": 61.5,
    "gap_pp": 4.5,
    "brier": 0.2484,
    "wilson_95": {
     "lo": null,
     "hi": null
    }
   }
  ],
  "buckets": [
   {
    "model": "claude-opus-5-5",
    "bucket": "50-60",
    "n": 660,
    "hit_rate": 0.5894,
    "mean_conf": 56.2,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-opus-5-5",
    "bucket": "60-70",
    "n": 40,
    "hit_rate": 0.425,
    "mean_conf": 60.1,
    "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": "gpt-6.1-sol",
    "bucket": "50-60",
    "n": 154,
    "hit_rate": 0.5,
    "mean_conf": 58.4,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "60-70",
    "n": 764,
    "hit_rate": 0.589,
    "mean_conf": 63.7,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gpt-6.1-sol",
    "bucket": "70-80",
    "n": 44,
    "hit_rate": 0.6136,
    "mean_conf": 71.1,
    "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": "grok-4.7",
    "bucket": "50-60",
    "n": 325,
    "hit_rate": 0.52,
    "mean_conf": 57.1,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "grok-4.7",
    "bucket": "60-70",
    "n": 510,
    "hit_rate": 0.5843,
    "mean_conf": 62.1,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "grok-4.7",
    "bucket": "70-80",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "grok-4.7",
    "bucket": "80-100",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "50-60",
    "n": 353,
    "hit_rate": 0.5524,
    "mean_conf": 56.8,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "60-70",
    "n": 468,
    "hit_rate": 0.5705,
    "mean_conf": 62.4,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "70-80",
    "n": 1,
    "hit_rate": 1.0,
    "mean_conf": 70,
    "insufficient": true,
    "no_data": false
   },
   {
    "model": "qwen-3.8-max",
    "bucket": "80-100",
    "n": 0,
    "hit_rate": null,
    "mean_conf": null,
    "insufficient": false,
    "no_data": true
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "50-60",
    "n": 257,
    "hit_rate": 0.5525,
    "mean_conf": 57.1,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "60-70",
    "n": 617,
    "hit_rate": 0.5689,
    "mean_conf": 62.3,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "deepseek-v4-pro",
    "bucket": "70-80",
    "n": 16,
    "hit_rate": 0.625,
    "mean_conf": 71.1,
    "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": 217,
    "hit_rate": 0.5253,
    "mean_conf": 56.7,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-fable-5",
    "bucket": "60-70",
    "n": 550,
    "hit_rate": 0.58,
    "mean_conf": 62.6,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "claude-fable-5",
    "bucket": "70-80",
    "n": 1,
    "hit_rate": 0.0,
    "mean_conf": 70,
    "insufficient": true,
    "no_data": false
   },
   {
    "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": 1,
    "hit_rate": 1.0,
    "mean_conf": 55,
    "insufficient": true,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "60-70",
    "n": 501,
    "hit_rate": 0.5768,
    "mean_conf": 63.3,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "70-80",
    "n": 342,
    "hit_rate": 0.5965,
    "mean_conf": 72.7,
    "insufficient": false,
    "no_data": false
   },
   {
    "model": "gemini-3.1-pro",
    "bucket": "80-100",
    "n": 26,
    "hit_rate": 0.5,
    "mean_conf": 81.5,
    "insufficient": false,
    "no_data": false
   }
  ],
  "sub50": [
   {
    "model": "claude-opus-5-5",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "gpt-6.1-sol",
    "n": 0,
    "hit_rate": null
   },
   {
    "model": "grok-4.7",
    "n": 1,
    "hit_rate": 0.0
   },
   {
    "model": "qwen-3.8-max",
    "n": 7,
    "hit_rate": 0.5714
   },
   {
    "model": "deepseek-v4-pro",
    "n": 1,
    "hit_rate": 0.0
   },
   {
    "model": "claude-fable-5",
    "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": 440,
    "hit_rate": 0.5432,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "4h",
    "n": 228,
    "hit_rate": 0.6272,
    "flag": null
   },
   {
    "model": "claude-opus-5-5",
    "fh": "1d",
    "n": 32,
    "hit_rate": 0.75,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "1h",
    "n": 598,
    "hit_rate": 0.5669,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "4h",
    "n": 313,
    "hit_rate": 0.5719,
    "flag": null
   },
   {
    "model": "gpt-6.1-sol",
    "fh": "1d",
    "n": 51,
    "hit_rate": 0.7059,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "1h",
    "n": 519,
    "hit_rate": 0.5414,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "4h",
    "n": 272,
    "hit_rate": 0.5588,
    "flag": null
   },
   {
    "model": "grok-4.7",
    "fh": "1d",
    "n": 45,
    "hit_rate": 0.7556,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "1h",
    "n": 539,
    "hit_rate": 0.5288,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "4h",
    "n": 254,
    "hit_rate": 0.6102,
    "flag": null
   },
   {
    "model": "qwen-3.8-max",
    "fh": "1d",
    "n": 36,
    "hit_rate": 0.75,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "1h",
    "n": 563,
    "hit_rate": 0.5524,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "4h",
    "n": 286,
    "hit_rate": 0.5804,
    "flag": null
   },
   {
    "model": "deepseek-v4-pro",
    "fh": "1d",
    "n": 42,
    "hit_rate": 0.619,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "1h",
    "n": 486,
    "hit_rate": 0.5535,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "4h",
    "n": 239,
    "hit_rate": 0.5732,
    "flag": null
   },
   {
    "model": "claude-fable-5",
    "fh": "1d",
    "n": 43,
    "hit_rate": 0.6279,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "1h",
    "n": 570,
    "hit_rate": 0.5842,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "4h",
    "n": 258,
    "hit_rate": 0.5736,
    "flag": null
   },
   {
    "model": "gemini-3.1-pro",
    "fh": "1d",
    "n": 42,
    "hit_rate": 0.619,
    "flag": null
   }
  ],
  "trading": [
   {
    "model": "qwen-3.8-max",
    "n_trades": 829,
    "wr": 0.456,
    "pnl_net_usd": 9.86,
    "pnl_gross_usd": 92.76,
    "max_dd_usd": -29.21
   },
   {
    "model": "claude-opus-5-5",
    "n_trades": 700,
    "wr": 0.48,
    "pnl_net_usd": 7.89,
    "pnl_gross_usd": 77.89,
    "max_dd_usd": -33.38
   },
   {
    "model": "deepseek-v4-pro",
    "n_trades": 891,
    "wr": 0.486,
    "pnl_net_usd": 0.54,
    "pnl_gross_usd": 89.64,
    "max_dd_usd": -36.55
   },
   {
    "model": "grok-4.7",
    "n_trades": 836,
    "wr": 0.4569,
    "pnl_net_usd": -2.57,
    "pnl_gross_usd": 81.03,
    "max_dd_usd": -43.89
   },
   {
    "model": "gpt-6.1-sol",
    "n_trades": 962,
    "wr": 0.4699,
    "pnl_net_usd": -13.57,
    "pnl_gross_usd": 82.63,
    "max_dd_usd": -44.75
   },
   {
    "model": "claude-fable-5",
    "n_trades": 768,
    "wr": 0.4518,
    "pnl_net_usd": -21.86,
    "pnl_gross_usd": 54.94,
    "max_dd_usd": -44.08
   },
   {
    "model": "gemini-3.1-pro",
    "n_trades": 870,
    "wr": 0.4632,
    "pnl_net_usd": -23.29,
    "pnl_gross_usd": 63.71,
    "max_dd_usd": -37.55
   }
  ],
  "gap_week_over_week": [
   {
    "model": "claude-opus-5-5",
    "gap_pp_issue11": 13.4,
    "gap_pp_issue12": -1.5,
    "delta_pp": -14.9
   },
   {
    "model": "qwen-3.8-max",
    "gap_pp_issue11": 12.7,
    "gap_pp_issue12": 3.5,
    "delta_pp": -9.2
   },
   {
    "model": "grok-4.7",
    "gap_pp_issue11": 12.9,
    "gap_pp_issue12": 4.3,
    "delta_pp": -8.6
   },
   {
    "model": "deepseek-v4-pro",
    "gap_pp_issue11": 11.6,
    "gap_pp_issue12": 4.5,
    "delta_pp": -7.1
   },
   {
    "model": "claude-fable-5",
    "gap_pp_issue11": 14.4,
    "gap_pp_issue12": 4.5,
    "delta_pp": -9.9
   },
   {
    "model": "gpt-6.1-sol",
    "gap_pp_issue11": 21.5,
    "gap_pp_issue12": 5.6,
    "delta_pp": -15.9
   },
   {
    "model": "gemini-3.1-pro",
    "gap_pp_issue11": 20.0,
    "gap_pp_issue12": 9.3,
    "delta_pp": -10.7
   },
   {
    "model": "Field",
    "gap_pp_issue11": 15.4,
    "gap_pp_issue12": 4.5,
    "delta_pp": -10.9
   }
  ],
  "ok_rate_by_model": {
   "claude-opus-5-5": 1.0,
   "gpt-6.1-sol": 1.0,
   "grok-4.7": 0.9,
   "qwen-3.8-max": 0.9993,
   "deepseek-v4-pro": 1.0,
   "claude-fable-5": 1.0,
   "gemini-3.1-pro": 0.9912
  },
  "counters": {
   "forecasts_total": 10290,
   "ok_in_gate": 9171,
   "out_of_gate": 958,
   "out_of_gate_by_fh": {
    "1w": 480,
    "1m": 478
   },
   "invalid": 161,
   "mature": 9171,
   "mature_directional": 5856,
   "mature_sideways": 3315,
   "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": {
    "2026-10-19": {
     "move_pct": -0.17,
     "regime": "flat"
    },
    "2026-10-20": {
     "move_pct": 1.24,
     "regime": "flat"
    },
    "2026-10-21": {
     "move_pct": 1.48,
     "regime": "flat"
    },
    "2026-10-22": {
     "move_pct": -3.34,
     "regime": "trend"
    },
    "2026-10-23": {
     "move_pct": -0.27,
     "regime": "flat"
    },
    "2026-10-24": {
     "move_pct": -0.41,
     "regime": "flat"
    },
    "2026-10-25": {
     "move_pct": -0.91,
     "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": "2026-10-19T00:01:00+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": true,
    "prev_window": {
     "n_grok45_rows": 0,
     "n_grok46_rows": 1155
    },
    "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": 1155,
    "note": "grok-4.7 went live 2026-10-17T09:01:00+00:00 (B0) -- inside week A (prev window = the published issue-#11 window, day 6 of 7), one window back; this window (week B) holds 0 grok-4.6 and 1470 grok-4.7 row(s), i.e. the first full week on the head. Week A holds 1155 grok-4.6 and 315 grok-4.7 row(s) and reproduces issue #11 under the lineage splice grok-4.6/grok-4.5 -> grok-4.7 (labelled 'grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)' there). The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits eight 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": [
      "2026-10-19",
      "2026-10-20",
      "2026-10-21",
      "2026-10-22",
      "2026-10-23",
      "2026-10-24",
      "2026-10-25"
     ],
     "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": [
      "2026-10-19",
      "2026-10-20",
      "2026-10-21",
      "2026-10-22",
      "2026-10-23",
      "2026-10-24",
      "2026-10-25"
     ],
     "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": [
      "2026-10-19",
      "2026-10-20",
      "2026-10-21",
      "2026-10-22",
      "2026-10-23",
      "2026-10-24",
      "2026-10-25"
     ],
     "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": [
      "2026-10-19",
      "2026-10-20",
      "2026-10-21",
      "2026-10-22",
      "2026-10-23",
      "2026-10-24",
      "2026-10-25"
     ],
     "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": [
      "2026-10-19",
      "2026-10-20",
      "2026-10-21",
      "2026-10-22",
      "2026-10-23",
      "2026-10-24",
      "2026-10-25"
     ],
     "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 in week A, one window back: 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 in week A) 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": "2026-10-19T00:01:00+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": 1155,
     "n_head_rows_a": 315,
     "first_head_slot": "2026-10-19T00:01:00+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 (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": 0,
     "n_head_rows_b": 1470,
     "n_prev_rows_a": 1155,
     "n_head_rows_a": 315,
     "first_head_slot": "2026-10-19T00:01:00+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 (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": 1470,
     "n_prev_rows_a": 0,
     "n_head_rows_a": 1440,
     "first_head_slot": "2026-10-19T00:01:00+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": "2026-10-19T00:01:00+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": "2026-10-19T00:01:00+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": 1155,
     "n_head_rows_a": 315,
     "first_head_slot": "2026-10-19T00:01:00+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 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
     "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 +15.4pp -> +4.5pp week over week, 7 of 7 model lines narrowed, and field Brier went 0.2759 -> 0.2484.",
  "evidence_level": "observation"
 },
 "key_findings": [
  "**OBSERVATION -- The gap read +4.5pp this week.** Directional calls hit 57.0% against 61.5 stated mean confidence (issue #11: +15.4pp on 46.6% vs 61.9). Field Brier is 0.2484 (was 0.2759) and 6 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 gpt-6.1-sol's -15.9pp (+21.5pp -> +5.6pp) to deepseek-v4-pro's -7.1pp (+11.6pp -> +4.5pp); 7 of 7 model lines narrowed week over week. claude-opus-5.5 is the lowest-Brier line (Brier 0.2443); gemini-3.1-pro leads on hit-rate (58.3%). claude-opus-5.5 is the only line whose gap is negative (-1.5pp: stated confidence below its hit-rate).",
  "**The high-confidence buckets, N>=10 only.** gpt-6.1-sol 70-80 61.4% (n=44), deepseek-v4-pro 70-80 62.5% (n=16), gemini-3.1-pro 70-80 59.7% (n=342), gemini-3.1-pro 80-100 50.0% (n=26). Cells below N=10 are marked insufficient and rank nothing.",
  "**Trading, kept separate from every calibration table.** 3 of 7 lines finished net-positive; net PnL ran +$9.86 (qwen-3.8-max, best) to -$23.29 (gemini-3.1-pro, worst), field -$43.00 against issue #11's -$352.09."
 ],
 "market_check": {
  "label": "MARKET CHECK · OBSERVATION (two adjacent calendar weeks)",
  "text": "OBSERVATION — mean |1d move| 2.05% -> 1.35% (-34% rel), BTC realized vol 34.9% -> 27.5% (ann., hourly); field directional accuracy 46.6% -> 57.0% (+10.4pp), 7 of 7 models improved, sim win-rate up for 7 of 7, field sim PnL -$352.09 -> -$43.00 (adjacent calendar weeks Oct 12-18 vs Oct 19-25; descriptive, one pair of weeks, not a claim).",
  "robustness": "Robustness: raw price-sign accuracy 44.1% -> 56.0% — the same direction as the trade-based hit rule.",
  "weeks": {
   "A": {
    "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"
   },
   "B": {
    "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"
   }
  },
  "price_source": "crypto_spot/1h@:00",
  "accuracy_field": {
   "A": {
    "n": 5084,
    "hit_rate": 0.4656,
    "wilson_95": [
     0.4519,
     0.4793
    ]
   },
   "B": {
    "n": 5856,
    "hit_rate": 0.5698,
    "wilson_95": [
     0.5571,
     0.5825
    ]
   },
   "delta_pp": 10.4
  },
  "accuracy_per_model": [
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "A": {
     "n": 765,
     "hit_rate": 0.4575,
     "wilson_95": [
      0.4225,
      0.4929
     ]
    },
    "B": {
     "n": 870,
     "hit_rate": 0.5828,
     "wilson_95": [
      0.5497,
      0.6151
     ]
    },
    "delta_pp": 12.5
   },
   {
    "model": "claude-opus-5-5",
    "model_label": "claude-opus-5-5",
    "A": {
     "n": 572,
     "hit_rate": 0.4633,
     "wilson_95": [
      0.4228,
      0.5043
     ]
    },
    "B": {
     "n": 700,
     "hit_rate": 0.58,
     "wilson_95": [
      0.5431,
      0.616
     ]
    },
    "delta_pp": 11.7
   },
   {
    "model": "gpt-6.1-sol",
    "model_label": "gpt-6.1-sol",
    "A": {
     "n": 815,
     "hit_rate": 0.465,
     "wilson_95": [
      0.431,
      0.4994
     ]
    },
    "B": {
     "n": 962,
     "hit_rate": 0.5759,
     "wilson_95": [
      0.5444,
      0.6068
     ]
    },
    "delta_pp": 11.1
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "A": {
     "n": 704,
     "hit_rate": 0.456,
     "wilson_95": [
      0.4195,
      0.4929
     ]
    },
    "B": {
     "n": 768,
     "hit_rate": 0.5638,
     "wilson_95": [
      0.5285,
      0.5985
     ]
    },
    "delta_pp": 10.8
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "A": {
     "n": 766,
     "hit_rate": 0.4634,
     "wilson_95": [
      0.4284,
      0.4989
     ]
    },
    "B": {
     "n": 829,
     "hit_rate": 0.5633,
     "wilson_95": [
      0.5294,
      0.5967
     ]
    },
    "delta_pp": 10.0
   },
   {
    "model": "grok-4.7",
    "model_label": "grok-4.7",
    "A": {
     "n": 695,
     "hit_rate": 0.4705,
     "wilson_95": [
      0.4337,
      0.5077
     ]
    },
    "B": {
     "n": 836,
     "hit_rate": 0.5586,
     "wilson_95": [
      0.5248,
      0.5919
     ]
    },
    "delta_pp": 8.8
   },
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "A": {
     "n": 767,
     "hit_rate": 0.4824,
     "wilson_95": [
      0.4472,
      0.5178
     ]
    },
    "B": {
     "n": 891,
     "hit_rate": 0.5645,
     "wilson_95": [
      0.5318,
      0.5967
     ]
    },
    "delta_pp": 8.2
   }
  ],
  "raw_sign_field": {
   "A": {
    "n_scored": 5074,
    "hit_rate": 0.4411
   },
   "B": {
    "n_scored": 5835,
    "hit_rate": 0.5602
   }
  },
  "abs_move_1d": {
   "A": 2.054,
   "B": 1.353,
   "delta_pct_rel": -34.1
  },
  "btc_realized_vol_ann_pct_hourly": {
   "A": 34.86,
   "B": 27.48
  },
  "trading_field": {
   "A": {
    "n_trades": 5084,
    "wr": 0.3918,
    "pnl_net_usd": -352.09,
    "pnl_gross_usd": 156.31
   },
   "B": {
    "n_trades": 5856,
    "wr": 0.4664,
    "pnl_net_usd": -43.0,
    "pnl_gross_usd": 542.6
   }
  },
  "verdict": {
   "models_with_hit_improved": "7 of 7",
   "models_with_rawsign_improved": "7 of 7",
   "models_with_wr_improved": "7 of 7",
   "field_hit_delta_pp": 10.4,
   "field_pnl_net": {
    "A": -352.09,
    "B": -43.0
   },
   "abs_move_delta": {
    "1h": {
     "A": 0.355,
     "B": 0.278,
     "delta_pct_rel": -21.7
    },
    "4h": {
     "A": 0.793,
     "B": 0.584,
     "delta_pct_rel": -26.4
    },
    "1d": {
     "A": 2.054,
     "B": 1.353,
     "delta_pct_rel": -34.1
    }
   },
   "btc_vol_ann_pct": {
    "A": 34.86,
    "B": 27.48
   },
   "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 A, 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 (2026-10-12..2026-10-18, the published issue-#11 window) holds B0: its old-id rows are aggregated under the heads (it reproduces the published issue #11); week B (2026-10-19..2026-10-25) is the first full week on the heads (0 old-id row(s) remapped in it). The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits eight 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 #12 the series has twelve 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. Week A (Oct 12-18, the issue-#11 window) is the spliced week: the three lines flipped at Oct 17, 2026 09:01 UTC inside it (gpt-5.6-sol -> gpt-6.1-sol, claude-opus-5 -> claude-opus-5.5, grok-4.6 -> grok-4.7), so each week-over-week row for those lines joins this week's single-build line to last week's spliced line. This window (Oct 19-25) is the first full week on the new builds. In issue #11 those lines carried the labels \"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)\" and \"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 +4.5pp this week against +15.4pp in issue #11.",
  "Gap and regime move together. The field hit 57.0% against 46.6% in issue #11 and stated mean confidence read 61.5 against 61.9, so the gap came out at +4.5pp: a field that hits 57.0% instead of 46.6% closes or opens a confidence gap without a single stated number changing.",
  "Trading direction this week (3 of 7 lines net-positive) is a regime read, not a strategy result; the three net-positive lines were all net-negative one week earlier (issue #11: 0 of 7 net-positive)."
 ],
 "limitations": [
  "Prediction metrics (this report) and trading metrics are kept in separate sections per methodology -- they are never combined into a single score.",
  "95% Wilson CIs shown are descriptive, not inferential: observations inside one window are dependent, so read them as a range, not a formal coverage guarantee.",
  "All 5,856 scored calls sit inside one market regime. This window had trend on 1 of 7 days (issue #11: 3 of 7); every comparison with issue #11 is a comparison across regimes as well as across weeks. Twelve 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 12): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 19-25) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9, #10 and #11: 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 480, 1M 478). (2) This window is the first 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, and all 7 lines carry 1,470 rows each. Week A (the issue-#11 window) is the spliced week -- \"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) -- so each of the three week-over-week rows joins this week's single-build line to last week's spliced line, and a remapped comparison is not the same model build. (3) No roll-out slot of the flip falls inside this window: the two hourly slots before it (Oct 17, 07:01 and 08:01 UTC) lie in week A, so this window's invalid counter holds none of their rows. (4) Past lineage flips: the Oct 17, 2026 09:01 UTC flip sits one window back (inside the issue-#11 window), the grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits eight 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 #11 after the audit that found the raw table mixes two exchanges; issue #11 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 26 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10 and #11, which printed 71,945 at the Oct 19 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 77,801 is an additive step under one definition; counter deltas against issue #10 and earlier remain definitional."
 ],
 "notes": {
  "series_density_and_lineage_wave12": "Series density and lineage notes (wave 12): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 19-25) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9, #10 and #11: 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 480, 1M 478). (2) This window is the first 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, and all 7 lines carry 1,470 rows each. Week A (the issue-#11 window) is the spliced week -- \"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) -- so each of the three week-over-week rows joins this week's single-build line to last week's spliced line, and a remapped comparison is not the same model build. (3) No roll-out slot of the flip falls inside this window: the two hourly slots before it (Oct 17, 07:01 and 08:01 UTC) lie in week A, so this window's invalid counter holds none of their rows. (4) Past lineage flips: the Oct 17, 2026 09:01 UTC flip sits one window back (inside the issue-#11 window), the grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits eight 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": "2026-10-19T00:01:00+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": true,
   "prev_window": {
    "n_grok45_rows": 0,
    "n_grok46_rows": 1155
   },
   "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": 1155,
   "note": "grok-4.7 went live 2026-10-17T09:01:00+00:00 (B0) -- inside week A (prev window = the published issue-#11 window, day 6 of 7), one window back; this window (week B) holds 0 grok-4.6 and 1470 grok-4.7 row(s), i.e. the first full week on the head. Week A holds 1155 grok-4.6 and 315 grok-4.7 row(s) and reproduces issue #11 under the lineage splice grok-4.6/grok-4.5 -> grok-4.7 (labelled 'grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)' there). The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits eight 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 in week A, one window back: 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 in week A) 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": [
     "2026-10-19",
     "2026-10-20",
     "2026-10-21",
     "2026-10-22",
     "2026-10-23",
     "2026-10-24",
     "2026-10-25"
    ],
    "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": [
     "2026-10-19",
     "2026-10-20",
     "2026-10-21",
     "2026-10-22",
     "2026-10-23",
     "2026-10-24",
     "2026-10-25"
    ],
    "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": [
     "2026-10-19",
     "2026-10-20",
     "2026-10-21",
     "2026-10-22",
     "2026-10-23",
     "2026-10-24",
     "2026-10-25"
    ],
    "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": [
     "2026-10-19",
     "2026-10-20",
     "2026-10-21",
     "2026-10-22",
     "2026-10-23",
     "2026-10-24",
     "2026-10-25"
    ],
    "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": [
     "2026-10-19",
     "2026-10-20",
     "2026-10-21",
     "2026-10-22",
     "2026-10-23",
     "2026-10-24",
     "2026-10-25"
    ],
    "missing_days": []
   }
  },
  "week_over_week_note": "Week-over-week columns compare back-to-back windows: Oct 12-18 (issue #11, and week A of this issue's alive slice) vs Oct 19-25 (this issue). \"Was\" values are the numbers published in issue #11; 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 26 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10 and #11, which printed 71,945 at the Oct 19 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 77,801 is an additive step under one definition; counter deltas against issue #10 and earlier remain definitional.",
  "market_state_audit": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #11 after the audit that found the raw table mixes two exchanges; issue #11 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": "2026-10-19T00:01:00+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": 1155,
    "n_head_rows_a": 315,
    "first_head_slot": "2026-10-19T00:01:00+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 (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": 0,
    "n_head_rows_b": 1470,
    "n_prev_rows_a": 1155,
    "n_head_rows_a": 315,
    "first_head_slot": "2026-10-19T00:01:00+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 (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": 1470,
    "n_prev_rows_a": 0,
    "n_head_rows_a": 1440,
    "first_head_slot": "2026-10-19T00:01:00+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": "2026-10-19T00:01:00+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": "2026-10-19T00:01:00+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": 1155,
    "n_head_rows_a": 315,
    "first_head_slot": "2026-10-19T00:01:00+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 (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"
   },
   "active": false
  },
  "prev_week_splice": {
   "active": true,
   "week": "Oct 12-18, 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 (incl. opus-5-era, Oct 12 00:00-Oct 17 09:01 UTC)",
     "n_prev_rows_a": 1155,
     "n_head_rows_a": 315
    },
    "gpt-6.1-sol": {
     "prev": "gpt-5.6-sol",
     "label_a": "gpt-6.1-sol (incl. 5.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
     "n_prev_rows_a": 1155,
     "n_head_rows_a": 315
    },
    "grok-4.7": {
     "prev": "grok-4.6",
     "label_a": "grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)",
     "n_prev_rows_a": 1155,
     "n_head_rows_a": 315
    }
   },
   "note": "Week A (Oct 12-18, the issue-#11 window) is the spliced week: the three lines flipped at Oct 17, 2026 09:01 UTC inside it (gpt-5.6-sol -> gpt-6.1-sol, claude-opus-5 -> claude-opus-5.5, grok-4.6 -> grok-4.7), so each week-over-week row for those lines joins this week's single-build line to last week's spliced line. This window (Oct 19-25) is the first full week on the new builds. In issue #11 those lines carried the labels \"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)\" and \"grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)\"."
  }
 },
 "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 #12.** Weekly Calibration is a living series. Issue #11's open questions -- \"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?\" and \"The best-Brier line changed hands again, to deepseek-v4-pro -- does it hold for a second issue, or change hands again?\" -- read this issue as: field gap +15.4pp -> +4.5pp (7 of 7 lines narrowed) on a field base that moved +10.4pp, a seventh issue running in opposite directions, and the best-Brier line changed hands again: claude-opus-5.5 at 0.2443 (issue #11: deepseek-v4-pro at 0.2657). Also on the record: gpt-6.1-sol's 70-80 bucket read 61.4% (n=44) against its own 60-70 at 58.9% (n=764). The claude-opus-5.5, gpt-6.1-sol and grok-4.7 rows are the first full week on the Oct 17 builds; week-over-week rows compare against the spliced issue-#11 week, where those lines carried the labels \"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)\" and \"grok-4.7 (incl. 4.6-era, Oct 12 00:00-Oct 17 09:01 UTC)\". The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits eight 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 -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?",
  "The best-Brier line changed hands again, to claude-opus-5.5 -- 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 #12",
   "url": "https://marketmania.ai/research/reports/consensus-watch-2026-10-19.pdf"
  },
  {
   "title": "Weekly Model Watch #12",
   "url": "https://marketmania.ai/research/reports/model-watch-2026-10-19.pdf"
  },
  {
   "title": "Weekly Calibration #11",
   "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-10-12.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_2026w43",
  "title": "Weekly Calibration #12: confidence vs. direction-hit, Oct 19-25 2026",
  "author": "MarketMania Research",
  "year": 2026,
  "month": "October",
  "day": 28,
  "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-10-19.pdf",
  "note": "Methodology v1.1; window Oct 19-25, 2026 UTC; source weekly_metrics_2026-10-19.json"
 },
 "research_to_date": {
  "this_report": {
   "scored_observations": 5856
  },
  "platform": {
   "as_of_cutoff": "2026-10-26",
   "resolved_forecasts": 77801,
   "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": 60
  },
  "source": "weekly_metrics_2026-10-19.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 26 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10 and #11, which printed 71,945 at the Oct 19 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 77,801 is an additive step under one definition; counter deltas against issue #10 and earlier remain definitional."
 },
 "site_entry": {
  "slug": "weekly-calibration-2026-10-19",
  "series": "weekly",
  "seriesLabel": "Weekly · Calibration",
  "date": "October 28, 2026",
  "title": "Weekly Calibration #12",
  "summary": "5,856 directional calls asked whether stated confidence tracks reality. The field hit 57.0% against 61.5 stated mean confidence, an overconfidence gap of +4.5pp against +15.4pp in issue #11, and 7 of 7 model lines narrowed week over week. Field Brier moved 0.2759 -> 0.2484; claude-opus-5.5 is the lowest-Brier line at 0.2443 and gemini-3.1-pro leads on hit-rate at 58.3%. Trading, kept in its own section, finished with 3 of 7 lines net-positive as field accuracy moved 46.6% -> 57.0% (+10.4pp).",
  "stats": [
   "5,856 directional calls",
   "gap +4.5pp (was +15.4pp)",
   "3 of 7 net-positive"
  ],
  "manifest_key_finding": "The overconfidence gap read +4.5pp against +15.4pp in issue #11, with 7 of 7 model lines narrowing and field Brier moving 0.2759 -> 0.2484; trading, kept separate, finished 3 of 7 lines net-positive.",
  "files": {
   "pdf": "/research/reports/weekly-calibration-2026-10-19.pdf",
   "md": "/research/reports/weekly-calibration-2026-10-19.md",
   "json": "/research/reports/weekly-calibration-2026-10-19.json"
  }
 },
 "social": {
  "telegram": {
   "photo_caption_html": "🎯 <b>Weekly Calibration #12</b> — weekly series (window Oct 19–25)\n\nResearch question: when a model says 70, does it hit 70% of the time?\n\n5,856 directional calls across 7 model lines:\n• Field hit <b>57.0%</b> vs <b>61.5</b> stated — an overconfidence gap of <b>+4.5pp</b> (issue #11: +15.4pp)\n• Gap week over week: <b>7 of 7 lines narrowed</b>; field Brier 0.2759 -> 0.2484\n• Lowest-Brier line: <b>claude-opus-5.5</b> (Brier 0.2443); hit-rate leader gemini-3.1-pro at 58.3%\n• Market check: field accuracy 46.6% -> 57.0% (+10.4pp); trading kept separate — <b>3 of 7 net-positive</b>\n\nNote: first full week on the new model builds — claude-opus-5.5, gpt-6.1-sol and grok-4.7 took over on Oct 17 09:01 UTC, inside the previous window\n\n📄 <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-19.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 #12 — full report (PDF).\nWeb copy: <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-19.pdf\">weekly-calibration-2026-10-19.pdf</a> · machine-readable: <a href=\"https://marketmania.ai/research/reports/weekly-calibration-2026-10-19.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 #12 is out.\n\n5,856 LLM calls: 57.0% hit vs 61.5 stated confidence — an overconfidence gap of +4.5pp against +15.4pp a week earlier, with 7 of 7 lines narrowing.\n\nFull report: https://marketmania.ai/research/reports/weekly-calibration-2026-10-19.pdf\n\n#AI #Crypto #Research #Calibration",
   "main_tco_len": 253,
   "reply": "Overconfidence gap, w/w (pp):\nopus-5.5: 13.4 -> -1.5\nqwen-3.8: 12.7 -> 3.5\ngrok-4.7: 12.9 -> 4.3\ndeepseek: 11.6 -> 4.5\nfable-5: 14.4 -> 4.5\ngpt-6.1: 21.5 -> 5.6\ngemini-3.1: 20.0 -> 9.3\nField: +15.4pp -> +4.5pp. Methodology v1.1.\nData: https://marketmania.ai/research/reports/weekly-calibration-2026-10-19.json",
   "reply_tco_len": 258,
   "limit_tco": 280,
   "replies_max": 1
  }
 }
}
