{
 "slug": "model-watch-2026-10-05",
 "series": "weekly",
 "series_label": "WEEKLY · MODEL WATCH",
 "issue": 10,
 "title": "Weekly Model Watch #10",
 "language": "en",
 "window_start": "2026-10-05T00:00:00+00:00",
 "window_end": "2026-10-12T00:00:00+00:00",
 "window_text": "Oct 5-11, 2026 UTC",
 "cutoff": "2026-10-12T16:00:00+00:00",
 "generated_at": "2026-10-13T15:56:43+00:00",
 "methodology": "v1.1 (2026-08-10)",
 "methodology_hash": "e66c7e8c864a2233",
 "source": "weekly_metrics_2026-10-05.json",
 "hit_rule": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl",
 "bibtex_key": "mm_modelwatch_2026w41",
 "research_question": "who led the week, which tickers were readable, who saw the turn first, and does a model agreeing with itself across timeframes/horizons make its call stronger?",
 "base_field_hit": {
  "n": 4601,
  "hit_rate": 0.4375
 },
 "market_state": {
  "panel": "market_state_6p2",
  "week": {
   "start": "2026-10-05",
   "end": "2026-10-12"
  },
  "prev_week": {
   "start": "2026-09-28",
   "end": "2026-10-05"
  },
  "current": {
   "btc_net_pct": -3.19,
   "realized_vol_ann_pct": 27.17,
   "volume_top5_usd_bn": 15.9702,
   "volume_top5_wow_pct": -11.1,
   "avg_pairwise_corr": 0.85
  },
  "previous_as_published_issue9": {
   "btc_net_pct": 2.44,
   "realized_vol_ann_pct": 21.13,
   "volume_top5_usd_bn": 17.9648,
   "avg_pairwise_corr": 0.57
  },
  "snapshot_line": "BTC net -3.19% (prior +2.44%) - ann vol 27.2% (was 21.1%) - TOP5 volume $15.97B, -11% w/w - pairwise corr 0.85 (was 0.57)",
  "exchange": "binance",
  "audit_filter_applied": true,
  "source": "single-exchange (binance) daily candle recompute, market_state_2026-10-05.json; prior-week values as published in issue #9",
  "audit_note": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #9 after the audit that found the raw table mixes two exchanges; issue #9 values are as published.",
  "prev_week_control": {
   "published_issue3": {
    "btc_net_pct": 2.44,
    "realized_vol_ann_pct": 21.13,
    "volume_top5_usd_bn": 17.9648,
    "avg_pairwise_corr": 0.57
   },
   "published_issue9": {
    "btc_net_pct": 2.44,
    "realized_vol_ann_pct": 21.13,
    "volume_top5_usd_bn": 17.9648,
    "avg_pairwise_corr": 0.57
   },
   "got": {
    "btc_net_pct": 2.44,
    "realized_vol_ann_pct": 21.13,
    "volume_top5_usd_bn": 17.9648,
    "avg_pairwise_corr": 0.57
   },
   "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-#9 week; the four Snapshot pins must reproduce (key published_issue3 kept for the builder schema, published_issue9 is the add-only alias)"
  },
  "regime_days": {
   "2026-10-05": {
    "move_pct": -0.61,
    "regime": "flat"
   },
   "2026-10-06": {
    "move_pct": -0.37,
    "regime": "flat"
   },
   "2026-10-07": {
    "move_pct": -2.65,
    "regime": "trend"
   },
   "2026-10-08": {
    "move_pct": -1.81,
    "regime": "trend"
   },
   "2026-10-09": {
    "move_pct": 1.06,
    "regime": "flat"
   },
   "2026-10-10": {
    "move_pct": 0.48,
    "regime": "flat"
   },
   "2026-10-11": {
    "move_pct": 0.93,
    "regime": "flat"
   }
  },
  "alive_slice_context": {
   "abs_move_1d_pct": {
    "A": 0.873,
    "B": 1.542
   },
   "btc_realized_vol_ann_pct_hourly": {
    "A": 32.24,
    "B": 30.91
   }
  }
 },
 "key_finding": {
  "label": "KEY FINDING · OBSERVATION (one weekly window)",
  "text": "Field accuracy went 49.6% -> 43.8% (-5.9pp) with 0 of 7 models improving, and no weekly title was awarded, for the tenth issue running.",
  "evidence_level": "observation"
 },
 "tables": {
  "leaderboard": {
   "rows": [
    {
     "model": "claude-opus-5",
     "n": 517,
     "hit_rate": 0.47,
     "wilson_95": [
      0.4274,
      0.5131
     ],
     "coverage": 0.3977,
     "model_label": "claude-opus-5",
     "insufficient": false
    },
    {
     "model": "claude-fable-5",
     "n": 613,
     "hit_rate": 0.4502,
     "wilson_95": [
      0.4113,
      0.4898
     ],
     "coverage": 0.4715,
     "model_label": "claude-fable-5",
     "insufficient": false
    },
    {
     "model": "gpt-5.6-sol",
     "n": 734,
     "hit_rate": 0.4346,
     "wilson_95": [
      0.3992,
      0.4707
     ],
     "coverage": 0.5519,
     "model_label": "gpt-5.6-sol",
     "insufficient": false
    },
    {
     "model": "gemini-3.1-pro",
     "n": 722,
     "hit_rate": 0.4335,
     "wilson_95": [
      0.3978,
      0.4699
     ],
     "coverage": 0.5429,
     "model_label": "gemini-3.1-pro",
     "insufficient": false
    },
    {
     "model": "grok-4.6",
     "n": 547,
     "hit_rate": 0.4333,
     "wilson_95": [
      0.3924,
      0.4751
     ],
     "coverage": 0.4113,
     "model_label": "grok-4.6 (incl. 4.5-era, Aug 24 00:00-09:22 UTC)",
     "insufficient": false
    },
    {
     "model": "qwen-3.8-max",
     "n": 707,
     "hit_rate": 0.4314,
     "wilson_95": [
      0.3954,
      0.4682
     ],
     "coverage": 0.532,
     "model_label": "qwen-3.8-max",
     "insufficient": false
    },
    {
     "model": "deepseek-v4-pro",
     "n": 761,
     "hit_rate": 0.4205,
     "wilson_95": [
      0.3859,
      0.4559
     ],
     "coverage": 0.5722,
     "model_label": "deepseek-v4-pro",
     "insufficient": false
    }
   ],
   "title_awarded": false,
   "title_rule": ">=5pp gap AND non-overlapping 95% CI, N>=10",
   "top2_gap_pp": 2.0,
   "movement_vs_prior_week": [
    {
     "model": "claude-opus-5",
     "hit_rate_issue9_published": 0.5075,
     "hit_rate_issue10": 0.47,
     "delta_pp": -3.7,
     "rank_issue10": 1
    },
    {
     "model": "claude-fable-5",
     "hit_rate_issue9_published": 0.4992,
     "hit_rate_issue10": 0.4502,
     "delta_pp": -4.9,
     "rank_issue10": 2
    },
    {
     "model": "gpt-5.6-sol",
     "hit_rate_issue9_published": 0.4654,
     "hit_rate_issue10": 0.4346,
     "delta_pp": -3.1,
     "rank_issue10": 3
    },
    {
     "model": "gemini-3.1-pro",
     "hit_rate_issue9_published": 0.4899,
     "hit_rate_issue10": 0.4335,
     "delta_pp": -5.6,
     "rank_issue10": 4
    },
    {
     "model": "grok-4.6",
     "hit_rate_issue9_published": 0.5267,
     "hit_rate_issue10": 0.4333,
     "delta_pp": -9.3,
     "rank_issue10": 5
    },
    {
     "model": "qwen-3.8-max",
     "hit_rate_issue9_published": 0.4895,
     "hit_rate_issue10": 0.4314,
     "delta_pp": -5.8,
     "rank_issue10": 6
    },
    {
     "model": "deepseek-v4-pro",
     "hit_rate_issue9_published": 0.5095,
     "hit_rate_issue10": 0.4205,
     "delta_pp": -8.9,
     "rank_issue10": 7
    }
   ],
   "note": "No weekly title is awarded this issue -- for the tenth time. Title rule: **>=5pp gap AND non-overlapping 95% CI, N>=10** per side. claude-opus-5's lead over claude-fable-5 is 2.0pp and their CIs overlap, so neither condition is met."
  },
  "ticker": {
   "rows": [
    {
     "symbol": "BTC",
     "n": 975,
     "hit_rate": 0.4605,
     "wilson_95": [
      0.4294,
      0.4919
     ],
     "issue9_hit_rate": 0.5328
    },
    {
     "symbol": "SOL",
     "n": 895,
     "hit_rate": 0.4425,
     "wilson_95": [
      0.4102,
      0.4752
     ],
     "issue9_hit_rate": 0.4598
    },
    {
     "symbol": "ETH",
     "n": 896,
     "hit_rate": 0.4386,
     "wilson_95": [
      0.4065,
      0.4713
     ],
     "issue9_hit_rate": 0.5076
    },
    {
     "symbol": "BNB",
     "n": 877,
     "hit_rate": 0.4242,
     "wilson_95": [
      0.3919,
      0.4571
     ],
     "issue9_hit_rate": 0.4794
    },
    {
     "symbol": "XRP",
     "n": 958,
     "hit_rate": 0.4207,
     "wilson_95": [
      0.3898,
      0.4522
     ],
     "issue9_hit_rate": 0.5025
    }
   ],
   "best": "BTC",
   "hardest": "XRP",
   "all_above_51pct": false
  },
  "pairs_top": [
   {
    "model": "claude-opus-5",
    "symbol": "XRP",
    "n": 117,
    "hit_rate": 0.4957
   },
   {
    "model": "claude-fable-5",
    "symbol": "ETH",
    "n": 122,
    "hit_rate": 0.4918
   },
   {
    "model": "claude-opus-5",
    "symbol": "SOL",
    "n": 95,
    "hit_rate": 0.4842
   },
   {
    "model": "gemini-3.1-pro",
    "symbol": "BTC",
    "n": 154,
    "hit_rate": 0.4805
   },
   {
    "model": "claude-opus-5",
    "symbol": "ETH",
    "n": 100,
    "hit_rate": 0.48
   },
   {
    "model": "grok-4.6",
    "symbol": "BTC",
    "n": 107,
    "hit_rate": 0.4766
   }
  ],
  "pairs_worst": [
   {
    "model": "qwen-3.8-max",
    "symbol": "BNB",
    "n": 134,
    "hit_rate": 0.403
   },
   {
    "model": "gpt-5.6-sol",
    "symbol": "XRP",
    "n": 149,
    "hit_rate": 0.4027
   },
   {
    "model": "grok-4.6",
    "symbol": "BNB",
    "n": 102,
    "hit_rate": 0.402
   },
   {
    "model": "gemini-3.1-pro",
    "symbol": "XRP",
    "n": 142,
    "hit_rate": 0.3803
   },
   {
    "model": "deepseek-v4-pro",
    "symbol": "XRP",
    "n": 156,
    "hit_rate": 0.3782
   }
  ],
  "reversal_events": {
   "definition": "4h grid, trend=sign of prior 24h, counter-move >=2.0% (BTC/ETH) sustained 8h; caller: directional hit, FH 4h/1d, slot in [T-12h, T+FH]",
   "events": [],
   "scope_v1": "BTC/ETH only",
   "status": "no_reversal_events"
  },
  "cross_tf": {
   "fh_4h_tf_4h_vs_1h": {
    "agree": {
     "n": 539,
     "hit_rate": 0.4397,
     "wilson_95": [
      0.3984,
      0.4819
     ],
     "by_regime": {
      "trend": {
       "n": 237,
       "hit_rate": 0.6667
      },
      "flat": {
       "n": 302,
       "hit_rate": 0.2616
      }
     }
    },
    "disagree": {
     "n": 40,
     "hit_rate": 0.625,
     "wilson_95": [
      0.4703,
      0.7578
     ],
     "by_regime": {
      "trend": {
       "n": 10,
       "hit_rate": 0.6
      },
      "flat": {
       "n": 30,
       "hit_rate": 0.6333
      }
     }
    },
    "mixed_pairs": 218,
    "base": {
     "n": 797,
     "hit_rate": 0.458
    },
    "lift_pp": -1.8
   },
   "fh_1d_tf_1d_vs_4h": {
    "agree": {
     "n": 111,
     "hit_rate": 0.2432,
     "wilson_95": [
      0.1729,
      0.3308
     ],
     "by_regime": {
      "trend": {
       "n": 24,
       "hit_rate": 0.9583
      },
      "flat": {
       "n": 87,
       "hit_rate": 0.046
      }
     }
    },
    "disagree": {
     "n": 2,
     "hit_rate": 0.0,
     "wilson_95": [
      0.0,
      0.6576
     ],
     "by_regime": {
      "trend": {
       "n": 0,
       "hit_rate": null
      },
      "flat": {
       "n": 2,
       "hit_rate": 0.0
      }
     }
    },
    "mixed_pairs": 47,
    "base": {
     "n": 160,
     "hit_rate": 0.2125
    },
    "lift_pp": 3.1
   }
  },
  "cross_fh": {
   "fh_4h_confirmed_by_1h": {
    "agree": {
     "n": 493,
     "hit_rate": 0.4381,
     "wilson_95": [
      0.395,
      0.4822
     ],
     "by_regime": {
      "trend": {
       "n": 209,
       "hit_rate": 0.7129
      },
      "flat": {
       "n": 284,
       "hit_rate": 0.2359
      }
     }
    },
    "disagree": {
     "n": 38,
     "hit_rate": 0.5789,
     "wilson_95": [
      0.4219,
      0.7215
     ],
     "by_regime": {
      "trend": {
       "n": 17,
       "hit_rate": 0.4706
      },
      "flat": {
       "n": 21,
       "hit_rate": 0.6667
      }
     }
    },
    "mixed_pairs": 266,
    "base": {
     "n": 797,
     "hit_rate": 0.458
    },
    "lift_pp": -2.0
   },
   "fh_1d_confirmed_by_4h": {
    "agree": {
     "n": 89,
     "hit_rate": 0.2809,
     "wilson_95": [
      0.1981,
      0.3818
     ],
     "by_regime": {
      "trend": {
       "n": 22,
       "hit_rate": 1.0
      },
      "flat": {
       "n": 67,
       "hit_rate": 0.0448
      }
     }
    },
    "disagree": {
     "n": 2,
     "hit_rate": 0.0,
     "wilson_95": [
      0.0,
      0.6576
     ],
     "by_regime": {
      "trend": {
       "n": 1,
       "hit_rate": 0.0
      },
      "flat": {
       "n": 1,
       "hit_rate": 0.0
      }
     }
    },
    "mixed_pairs": 69,
    "base": {
     "n": 160,
     "hit_rate": 0.2125
    },
    "lift_pp": 6.8
   }
  },
  "regime_days": {
   "2026-10-05": {
    "move_pct": -0.61,
    "regime": "flat"
   },
   "2026-10-06": {
    "move_pct": -0.37,
    "regime": "flat"
   },
   "2026-10-07": {
    "move_pct": -2.65,
    "regime": "trend"
   },
   "2026-10-08": {
    "move_pct": -1.81,
    "regime": "trend"
   },
   "2026-10-09": {
    "move_pct": 1.06,
    "regime": "flat"
   },
   "2026-10-10": {
    "move_pct": 0.48,
    "regime": "flat"
   },
   "2026-10-11": {
    "move_pct": 0.93,
    "regime": "flat"
   }
  },
  "side_mix": [
   {
    "model": "claude-fable-5",
    "n": 1300,
    "long": 0.2708,
    "short": 0.2008,
    "sideways": 0.5285,
    "ls_ratio": 1.35
   },
   {
    "model": "claude-opus-5",
    "n": 1300,
    "long": 0.2046,
    "short": 0.1931,
    "sideways": 0.6023,
    "ls_ratio": 1.06
   },
   {
    "model": "deepseek-v4-pro",
    "n": 1330,
    "long": 0.2075,
    "short": 0.3647,
    "sideways": 0.4278,
    "ls_ratio": 0.57
   },
   {
    "model": "gemini-3.1-pro",
    "n": 1330,
    "long": 0.2789,
    "short": 0.2639,
    "sideways": 0.4571,
    "ls_ratio": 1.06
   },
   {
    "model": "gpt-5.6-sol",
    "n": 1330,
    "long": 0.2038,
    "short": 0.3481,
    "sideways": 0.4481,
    "ls_ratio": 0.59
   },
   {
    "model": "grok-4.6",
    "n": 1330,
    "long": 0.1293,
    "short": 0.282,
    "sideways": 0.5887,
    "ls_ratio": 0.46
   },
   {
    "model": "qwen-3.8-max",
    "n": 1329,
    "long": 0.2453,
    "short": 0.2867,
    "sideways": 0.468,
    "ls_ratio": 0.86
   }
  ],
  "long_short_ratio_field": {
   "value": 0.85,
   "method": "mean of the per-model long-share / short-share ratios"
  },
  "consensus_skew": {
   "cells_ge5_same_side": 508,
   "n_mature": 3171,
   "hit_rate": 0.4365
  },
  "fail_of_week": {
   "model": "gpt-5.6-sol",
   "symbol": "BTC",
   "side": "short",
   "confidence": 82,
   "slot": "2026-10-08T16:01:00+00:00",
   "fh": "4h",
   "tf": "1h",
   "exit_reason": "expiry",
   "pnl_net_usd": -0.97
  },
  "counters": {
   "forecasts_total": 10290,
   "ok_in_gate": 9249,
   "out_of_gate": 969,
   "out_of_gate_by_fh": {
    "1m": 479,
    "1w": 490
   },
   "invalid": 72,
   "mature": 9249,
   "mature_directional": 4601,
   "mature_sideways": 4648,
   "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": {
    "2026-10-05": {
     "move_pct": -0.61,
     "regime": "flat"
    },
    "2026-10-06": {
     "move_pct": -0.37,
     "regime": "flat"
    },
    "2026-10-07": {
     "move_pct": -2.65,
     "regime": "trend"
    },
    "2026-10-08": {
     "move_pct": -1.81,
     "regime": "trend"
    },
    "2026-10-09": {
     "move_pct": 1.06,
     "regime": "flat"
    },
    "2026-10-10": {
     "move_pct": 0.48,
     "regime": "flat"
    },
    "2026-10-11": {
     "move_pct": 0.93,
     "regime": "flat"
    }
   },
   "grok_era": {
    "ids_in_window": [
     "grok-4.6"
    ],
    "n_grok45": 0,
    "n_grok46": 1470,
    "n_grok45_rows": 0,
    "n_grok46_rows": 1470,
    "first_grok46_slot": "2026-10-05T00:01:00+00:00",
    "last_grok45_slot": null,
    "first_grok45_slot": null,
    "flip_at": "2026-08-24T09:22:00+00:00",
    "flip_inside_window": false,
    "prev_window": {
     "n_grok45_rows": 0,
     "n_grok46_rows": 1470
    },
    "merged_model_id": "grok-4.6",
    "merged_label": "grok-4.6 (incl. 4.5-era, Aug 24 00:00-09:22 UTC)",
    "lineage_ids": [
     "grok-4.5",
     "grok-4.6"
    ],
    "lineage_source": "benchmarks.config.lineage_ids('grok-4.6') + MODEL_SUCCESSION[grok-4.6]=('grok-4.5',)",
    "lineage_warnings": [],
    "rows_remapped_a_plus_b": 0,
    "note": "grok-4.6 went live 2026-08-24T09:22:00+00:00 -- six windows back (inside issue #4's window); all per-model aggregates use the lineage splice grok-4.5 -> grok-4.6 (one row, labelled 'grok-4.6 (incl. 4.5-era, Aug 24 00:00-09:22 UTC)'). Both week A (prev window, issue #9) and week B (this window) are pure grok-4.6.",
    "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": [
      "2026-10-05",
      "2026-10-06",
      "2026-10-07",
      "2026-10-08",
      "2026-10-09",
      "2026-10-10",
      "2026-10-11"
     ],
     "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": [
      "2026-10-05",
      "2026-10-06",
      "2026-10-07",
      "2026-10-08",
      "2026-10-09",
      "2026-10-10",
      "2026-10-11"
     ],
     "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": [
      "2026-10-05",
      "2026-10-06",
      "2026-10-07",
      "2026-10-08",
      "2026-10-09",
      "2026-10-10",
      "2026-10-11"
     ],
     "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": [
      "2026-10-05",
      "2026-10-06",
      "2026-10-07",
      "2026-10-08",
      "2026-10-09",
      "2026-10-10",
      "2026-10-11"
     ],
     "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": [
      "2026-10-05",
      "2026-10-06",
      "2026-10-07",
      "2026-10-08",
      "2026-10-09",
      "2026-10-10",
      "2026-10-11"
     ],
     "missing_days": []
    }
   },
   "model_roster": {
    "current": [
     "claude-fable-5",
     "claude-opus-5",
     "deepseek-v4-pro",
     "gemini-3.1-pro",
     "gpt-5.6-sol",
     "grok-4.6",
     "qwen-3.8-max"
    ],
    "current_count": 7,
    "current_raw_ids_in_window": [
     "claude-fable-5",
     "claude-opus-5",
     "deepseek-v4-pro",
     "gemini-3.1-pro",
     "gpt-5.6-sol",
     "grok-4.6",
     "qwen-3.8-max"
    ],
    "archived_legacy": [
     "grok-4.5",
     "qwen-3.7-max",
     "claude-opus-4.8"
    ],
    "archived_legacy_count": 3,
    "archived_legacy_detail": [
     {
      "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": [
     "qwen-3.7-max",
     "claude-opus-4.8"
    ],
    "tracked_total": 10,
    "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 emitting inside the window (grok-4.5 rows are spliced into grok-4.6); archived legacy = raw ids seen since 2026-07-11 that no longer emit in the window -- grok-4.5 is one of them by raw id even though its rows are spliced. Models retired before 2026-07-11 are not visible to this query."
   }
  },
  "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
   }
  ],
  "ok_rate_by_model": {
   "claude-opus-5": 0.9796,
   "claude-fable-5": 0.9796,
   "grok-4.6": 1.0,
   "qwen-3.8-max": 0.9918,
   "deepseek-v4-pro": 1.0,
   "gemini-3.1-pro": 1.0,
   "gpt-5.6-sol": 1.0
  },
  "calibration_bridge": {
   "best_calibrated_model": "claude-opus-5",
   "brier": 0.2685,
   "hit_rate_leader": "claude-opus-5"
  }
 },
 "key_findings": [
  "**OBSERVATION -- No weekly title again.** claude-opus-5 leads descriptively at 47.0% [42.7%, 51.3%]; the gap to #2 (claude-fable-5, 45.0%) is 2.0pp. 0 of 7 models improved week over week; issue #9's leader grok-4.6 is now 5 of 7.",
  "**No ticker cleared 51%.** BTC is the week's most readable coin (46.1%, n=975) and XRP the hardest at 42.1%; 0 of the 5 assets cleared 51%. Pair of the week: claude-opus-5 x XRP 49.6% (n=117); worst: deepseek-v4-pro x XRP 37.8% (n=156).",
  "**No qualifying reversal fired.** No BTC/ETH turn met the detector threshold inside this window (detector status no_reversal_events), so there is nothing to score this issue.",
  "**Self-agreement split across the four cells.** Cross-TF/FH lifts ran -2.0pp to +6.8pp (issue #9: +0.4pp to +18.7pp). On trend days, 4h TF-agreement hit 66.7% (n=237) against 26.2% (n=302) on flat days."
 ],
 "market_check": {
  "label": "MARKET CHECK · OBSERVATION (two adjacent calendar weeks)",
  "text": "OBSERVATION — mean |1d move| 0.87% -> 1.54% (+77% rel), BTC realized vol 32.2% -> 30.9% (ann., hourly); field directional accuracy 49.6% -> 43.8% (-5.9pp), 0 of 7 models improved, sim win-rate up for 0 of 7, field sim PnL -$408.24 -> -$520.82 (adjacent calendar weeks Sep 28-Oct 4 vs Oct 5-11; descriptive, one pair of weeks, not a claim).",
  "robustness": "Robustness: raw price-sign accuracy 49.0% -> 45.5% — the same direction as the trade-based hit rule.",
  "weeks": {
   "A": {
    "days": "2026-09-28..2026-10-04",
    "slots": [
     "2026-09-28T00:00:00+00:00",
     "2026-10-05T00:00:00+00:00"
    ],
    "cutoff": "2026-10-05T16:00:00+00:00"
   },
   "B": {
    "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"
   }
  },
  "price_source": "crypto_spot/1h@:00",
  "accuracy_field": {
   "A": {
    "n": 4331,
    "hit_rate": 0.4964,
    "wilson_95": [
     0.4815,
     0.5113
    ]
   },
   "B": {
    "n": 4601,
    "hit_rate": 0.4375,
    "wilson_95": [
     0.4232,
     0.4519
    ]
   },
   "delta_pp": -5.9
  },
  "accuracy_per_model": [
   {
    "model": "gpt-5.6-sol",
    "model_label": "gpt-5.6-sol",
    "A": {
     "n": 651,
     "hit_rate": 0.4654,
     "wilson_95": [
      0.4274,
      0.5038
     ]
    },
    "B": {
     "n": 734,
     "hit_rate": 0.4346,
     "wilson_95": [
      0.3992,
      0.4707
     ]
    },
    "delta_pp": -3.1
   },
   {
    "model": "claude-opus-5",
    "model_label": "claude-opus-5",
    "A": {
     "n": 534,
     "hit_rate": 0.5075,
     "wilson_95": [
      0.4652,
      0.5497
     ]
    },
    "B": {
     "n": 517,
     "hit_rate": 0.47,
     "wilson_95": [
      0.4274,
      0.5131
     ]
    },
    "delta_pp": -3.7
   },
   {
    "model": "claude-fable-5",
    "model_label": "claude-fable-5",
    "A": {
     "n": 623,
     "hit_rate": 0.4992,
     "wilson_95": [
      0.4601,
      0.5383
     ]
    },
    "B": {
     "n": 613,
     "hit_rate": 0.4502,
     "wilson_95": [
      0.4113,
      0.4898
     ]
    },
    "delta_pp": -4.9
   },
   {
    "model": "gemini-3.1-pro",
    "model_label": "gemini-3.1-pro",
    "A": {
     "n": 694,
     "hit_rate": 0.4899,
     "wilson_95": [
      0.4529,
      0.5271
     ]
    },
    "B": {
     "n": 722,
     "hit_rate": 0.4335,
     "wilson_95": [
      0.3978,
      0.4699
     ]
    },
    "delta_pp": -5.6
   },
   {
    "model": "qwen-3.8-max",
    "model_label": "qwen-3.8-max",
    "A": {
     "n": 711,
     "hit_rate": 0.4895,
     "wilson_95": [
      0.4529,
      0.5262
     ]
    },
    "B": {
     "n": 707,
     "hit_rate": 0.4314,
     "wilson_95": [
      0.3954,
      0.4682
     ]
    },
    "delta_pp": -5.8
   },
   {
    "model": "deepseek-v4-pro",
    "model_label": "deepseek-v4-pro",
    "A": {
     "n": 687,
     "hit_rate": 0.5095,
     "wilson_95": [
      0.4721,
      0.5467
     ]
    },
    "B": {
     "n": 761,
     "hit_rate": 0.4205,
     "wilson_95": [
      0.3859,
      0.4559
     ]
    },
    "delta_pp": -8.9
   },
   {
    "model": "grok-4.6",
    "model_label": "grok-4.6 (incl. 4.5-era, Aug 24 00:00-09:22 UTC)",
    "A": {
     "n": 431,
     "hit_rate": 0.5267,
     "wilson_95": [
      0.4795,
      0.5734
     ]
    },
    "B": {
     "n": 547,
     "hit_rate": 0.4333,
     "wilson_95": [
      0.3924,
      0.4751
     ]
    },
    "delta_pp": -9.3
   }
  ],
  "raw_sign_field": {
   "A": {
    "n_scored": 4311,
    "hit_rate": 0.4901
   },
   "B": {
    "n_scored": 4585,
    "hit_rate": 0.4547
   }
  },
  "abs_move_1d": {
   "A": 0.873,
   "B": 1.542,
   "delta_pct_rel": 76.6
  },
  "btc_realized_vol_ann_pct_hourly": {
   "A": 32.24,
   "B": 30.91
  },
  "trading_field": {
   "A": {
    "n_trades": 4331,
    "wr": 0.4103,
    "pnl_net_usd": -408.24,
    "pnl_gross_usd": 24.86
   },
   "B": {
    "n_trades": 4601,
    "wr": 0.3451,
    "pnl_net_usd": -520.82,
    "pnl_gross_usd": -60.72
   }
  },
  "verdict": {
   "models_with_hit_improved": "0 of 7",
   "models_with_rawsign_improved": "0 of 7",
   "models_with_wr_improved": "0 of 7",
   "field_hit_delta_pp": -5.9,
   "field_pnl_net": {
    "A": -408.24,
    "B": -520.82
   },
   "abs_move_delta": {
    "1h": {
     "A": 0.314,
     "B": 0.285,
     "delta_pct_rel": -9.2
    },
    "4h": {
     "A": 0.706,
     "B": 0.597,
     "delta_pct_rel": -15.4
    },
    "1d": {
     "A": 0.873,
     "B": 1.542,
     "delta_pct_rel": 76.6
    }
   },
   "btc_vol_ann_pct": {
    "A": 32.24,
    "B": 30.91
   },
   "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: grok-4.5 rows are aggregated into grok-4.6 (flip 2026-08-24T09:22:00+00:00, six windows back, inside issue #4's window). Week A (2026-09-28..2026-10-04) is pure grok-4.6 (it reproduces the published issue #9); week B is pure grok-4.6."
 },
 "why_it_matters": "MarketMania scores 7 model lines against the same market, hour after hour. Weekly Model Watch asks four practical questions about that week of calls: who led the week, which tickers were readable, who saw the turn first, and does a model agreeing with itself across timeframes/horizons make its call stronger? Each question gets its own block below, with its own table, its own N, and its own honesty caveats. The grok row is a pure grok-4.6 week in this issue and was one in issue #9 as well -- the 4.5 -> 4.6 flip sits six windows back -- so read the grok week-over-week row as a line, not a single model build.",
 "how_to_read_this": "Every block below is scored on the same pool: matured directional calls inside the 1h/4h/1d FH gate, hit by the methodology v1.1 direction rule. The weekly title is awarded only on a >=5pp gap AND non-overlapping 95% Wilson CIs with N>=10 per side -- a descriptive lead is not a title. Reversals use the 4h grid with a >=2.0% counter-move sustained 8h, BTC/ETH only in v1. Cross-TF/FH blocks ask whether a model agreeing with itself does any better, and are split trend vs flat wherever the week supplies both sides. The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits six windows back (issue #4): both weeks of this issue are pure grok-4.6, with no 4.5-era rows in either window, so the grok week-over-week row is the fifth pure-4.6 against pure-4.6 comparison of the series.",
 "practical_implications": [
  "Do not read this week's leaderboard as a skill ranking: no title was awarded and the top CIs overlap.",
  "Treat per-ticker readability as weekly weather. Ten issues, and the best ticker changed hands in every one except issues #6 and #10 (SOL -> BNB -> BTC -> SOL -> BNB -> BNB -> ETH -> XRP -> BTC -> BTC): BTC led issue #9 and leads again at 46.1%.",
  "Self-agreement lifts run -2.0pp to +6.8pp with small disagree cells; carry the regime split into the monthly test, do not act on it."
 ],
 "limitations": [
  "Single week (Oct 5-11, 2026 UTC). Descriptive for this window only; no claim about next week or any model's underlying skill. This window ran 2 trend days of 7 (issue #9: 2 of 7); every comparison with issue #9 is a comparison across regimes as well as across weeks.",
  "Observations inside one window are not independent, and the 95% Wilson CIs shown throughout are descriptive, not inferential.",
  "The reversal detector remains v1 and BTC/ETH-only, on price series reconstructed from trade entry prices. 17 events across ten issues cannot characterise detector performance either way.",
  "Cross-TF and cross-FH disagreement cells are small (n=40, 2, 38, 2); cells under N=10 are insufficient and never used to rank models. Week-over-week deltas are computed on unrounded rates and may differ by 0.1pp from the difference of the rounded columns.",
  "Model lines in this window: claude-fable-5, claude-opus-5, deepseek-v4-pro, gemini-3.1-pro, gpt-5.6-sol, grok-4.6, qwen-3.8-max. DeepSeek announced routing of V4 Pro to V4.1 Flash from Sep 14, 04:00 UTC; an API check on Oct 13 still returns deepseek-v4-pro as the served model for our requests, with the same system fingerprint as on Oct 7, so this issue keeps the label; it will change the day the served id changes. In this window the line's ok-rate is 100.0% (invalid 72 this window). Series density and lineage notes (wave 10): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 5-11) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8 and #9: 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 479). (2) The grok line flipped 4.5 -> 4.6 at Aug 24, 2026 09:22 UTC, six windows back (inside the issue-#4 window): this window carries 1,470 grok rows and none from the 4.5 era, and neither does week A (the issue-#9 window), so every grok number in this issue and in issue #9 is a pure grok-4.6 line -- the grok week-over-week row is the fifth pure-4.6 against pure-4.6 comparison of the series. (3) 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 #9 after the audit that found the raw table mixes two exchanges; issue #9 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 12 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8 and #9, which printed 62,260 at the Oct 5 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 66,861 is an additive step under one definition; counter deltas against issue #8 and earlier remain definitional."
 ],
 "notes": {
  "series_density_and_lineage_wave10": "Series density and lineage notes (wave 10): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 5-11) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8 and #9: 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 479). (2) The grok line flipped 4.5 -> 4.6 at Aug 24, 2026 09:22 UTC, six windows back (inside the issue-#4 window): this window carries 1,470 grok rows and none from the 4.5 era, and neither does week A (the issue-#9 window), so every grok number in this issue and in issue #9 is a pure grok-4.6 line -- the grok week-over-week row is the fifth pure-4.6 against pure-4.6 comparison of the series. (3) 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"
   ],
   "n_grok45": 0,
   "n_grok46": 1470,
   "n_grok45_rows": 0,
   "n_grok46_rows": 1470,
   "first_grok46_slot": "2026-10-05T00:01:00+00:00",
   "last_grok45_slot": null,
   "first_grok45_slot": null,
   "flip_at": "2026-08-24T09:22:00+00:00",
   "flip_inside_window": false,
   "prev_window": {
    "n_grok45_rows": 0,
    "n_grok46_rows": 1470
   },
   "merged_model_id": "grok-4.6",
   "merged_label": "grok-4.6 (incl. 4.5-era, Aug 24 00:00-09:22 UTC)",
   "lineage_ids": [
    "grok-4.5",
    "grok-4.6"
   ],
   "lineage_source": "benchmarks.config.lineage_ids('grok-4.6') + MODEL_SUCCESSION[grok-4.6]=('grok-4.5',)",
   "lineage_warnings": [],
   "rows_remapped_a_plus_b": 0,
   "note": "grok-4.6 went live 2026-08-24T09:22:00+00:00 -- six windows back (inside issue #4's window); all per-model aggregates use the lineage splice grok-4.5 -> grok-4.6 (one row, labelled 'grok-4.6 (incl. 4.5-era, Aug 24 00:00-09:22 UTC)'). Both week A (prev window, issue #9) and week B (this window) are pure grok-4.6.",
   "cells_with_two_grok_rows": 0
  },
  "model_ids_line": [
   "claude-fable-5",
   "claude-opus-5",
   "deepseek-v4-pro",
   "gemini-3.1-pro",
   "gpt-5.6-sol",
   "grok-4.6",
   "qwen-3.8-max"
  ],
  "model_roster": {
   "current": [
    "claude-fable-5",
    "claude-opus-5",
    "deepseek-v4-pro",
    "gemini-3.1-pro",
    "gpt-5.6-sol",
    "grok-4.6",
    "qwen-3.8-max"
   ],
   "current_count": 7,
   "current_raw_ids_in_window": [
    "claude-fable-5",
    "claude-opus-5",
    "deepseek-v4-pro",
    "gemini-3.1-pro",
    "gpt-5.6-sol",
    "grok-4.6",
    "qwen-3.8-max"
   ],
   "archived_legacy": [
    "grok-4.5",
    "qwen-3.7-max",
    "claude-opus-4.8"
   ],
   "archived_legacy_count": 3,
   "archived_legacy_detail": [
    {
     "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": [
    "qwen-3.7-max",
    "claude-opus-4.8"
   ],
   "tracked_total": 10,
   "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 emitting inside the window (grok-4.5 rows are spliced into grok-4.6); archived legacy = raw ids seen since 2026-07-11 that no longer emit in the window -- grok-4.5 is one of them by raw id even though its rows are spliced. 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": [
     "2026-10-05",
     "2026-10-06",
     "2026-10-07",
     "2026-10-08",
     "2026-10-09",
     "2026-10-10",
     "2026-10-11"
    ],
    "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": [
     "2026-10-05",
     "2026-10-06",
     "2026-10-07",
     "2026-10-08",
     "2026-10-09",
     "2026-10-10",
     "2026-10-11"
    ],
    "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": [
     "2026-10-05",
     "2026-10-06",
     "2026-10-07",
     "2026-10-08",
     "2026-10-09",
     "2026-10-10",
     "2026-10-11"
    ],
    "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": [
     "2026-10-05",
     "2026-10-06",
     "2026-10-07",
     "2026-10-08",
     "2026-10-09",
     "2026-10-10",
     "2026-10-11"
    ],
    "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": [
     "2026-10-05",
     "2026-10-06",
     "2026-10-07",
     "2026-10-08",
     "2026-10-09",
     "2026-10-10",
     "2026-10-11"
    ],
    "missing_days": []
   }
  },
  "week_over_week_note": "Week-over-week columns compare back-to-back windows: Sep 28-Oct 4 (issue #9, and week A of this issue's alive slice) vs Oct 5-11 (this issue). \"Was\" values are the numbers published in issue #9; 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 12 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8 and #9, which printed 62,260 at the Oct 5 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 66,861 is an additive step under one definition; counter deltas against issue #8 and earlier remain definitional.",
  "market_state_audit": "Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #9 after the audit that found the raw table mixes two exchanges; issue #9 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"
 },
 "living_series_note": "**Issue #10.** Weekly Model Watch is a living series. Issue #9's open questions -- \"does grok-4.6 hold the top rank for a second issue, and does the title rule ever fire?\" and \"Does a qualifying reversal fire outside ETH for a third issue running, and does a second turn in the same pair ever draw a caller?\" -- read this issue as: claude-opus-5 at the top (47.0%), not the line that led issue #9 (grok-4.6), so the rank did not hold for a second issue; no weekly title was awarded, for the tenth issue running, and no qualifying reversal fired, so the run of issues with a qualifying turn outside ETH stops at two (issues #8 and #9) and the second-turn question stays open. The grok row is pure grok-4.6 this issue and was pure grok-4.6 in issue #9; the 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits six 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: does claude-opus-5 hold the top rank for a second issue, and does the title rule ever fire?",
  "Does a qualifying reversal fire again after an issue with none, and does a second turn in the same pair ever draw a caller?",
  "Monthly series: cross-TF/FH lifts with regime control across mixed weeks (trend vs. flat), block bootstrap."
 ],
 "related_research": [
  {
   "title": "Consensus Watch #10",
   "url": "https://marketmania.ai/research/reports/consensus-watch-2026-10-05.pdf"
  },
  {
   "title": "Weekly Calibration #10",
   "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-10-05.pdf"
  },
  {
   "title": "Weekly Model Watch #9",
   "url": "https://marketmania.ai/research/reports/model-watch-2026-09-28.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.",
 "research_to_date": {
  "this_report": {
   "scored_observations": 4601
  },
  "platform": {
   "as_of_cutoff": "2026-10-12",
   "resolved_forecasts": 66861,
   "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": 10,
   "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": 53
  },
  "source": "weekly_metrics_2026-10-05.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 12 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8 and #9, which printed 62,260 at the Oct 5 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 66,861 is an additive step under one definition; counter deltas against issue #8 and earlier remain definitional."
 },
 "citation": {
  "bibtex_key": "mm_modelwatch_2026w41",
  "title": "Weekly Model Watch #10: weekly leaderboard, ticker/pair reads and cross-confirmation, Oct 5-11 2026",
  "author": "MarketMania Research",
  "year": 2026,
  "month": "October",
  "day": 14,
  "url": "https://marketmania.ai/research/reports/model-watch-2026-10-05.pdf",
  "note": "Methodology v1.1; window Oct 5-11, 2026 UTC; source weekly_metrics_2026-10-05.json"
 },
 "site_entry": {
  "slug": "model-watch-2026-10-05",
  "series": "weekly",
  "seriesLabel": "Weekly · Model Watch",
  "date": "October 14, 2026",
  "title": "Weekly Model Watch #10",
  "summary": "4,601 directional calls, four questions: who led the week, which tickers were readable, who saw the turn first, does self-agreement help. No weekly title again — claude-opus-5 led at 47.0% (-3.7pp w/w) against claude-fable-5 at 45.0%, a gap of 2.0pp. BTC was the most readable ticker at 46.1% and XRP the hardest at 42.1%, with 0 of 5 assets above 51 percent. Reversals: no qualifying reversal fired. Field accuracy moved 49.6% -> 43.8% (-5.9pp) with 0 of 7 models improving.",
  "stats": [
   "4,601 directional calls",
   "No weekly title again",
   "field -5.9pp w/w"
  ],
  "manifest_key_finding": "Field accuracy moved 49.6% -> 43.8% (-5.9pp) with 0 of 7 models improving; claude-opus-5 led the week at 47.0% (-3.7pp w/w) and no weekly title was awarded, for the tenth issue running.",
  "files": {
   "pdf": "/research/reports/model-watch-2026-10-05.pdf",
   "md": "/research/reports/model-watch-2026-10-05.md",
   "json": "/research/reports/model-watch-2026-10-05.json"
  }
 },
 "social": {
  "telegram": {
   "photo_caption_html": "📊 <b>Weekly Model Watch #10</b> — weekly series (window Oct 5–11)\n\nWho led, what was readable, who saw the turn, does self-agreement help? 4,601 directional calls, 7 model lines:\n• <b>No weekly title again</b> — claude-opus-5 leads at <b>47.0%</b> (-3.7pp w/w) against claude-fable-5 at 45.0%, a 2.0pp gap\n• Tickers: <b>BTC</b> most readable (46.1%); XRP hardest at 42.1% — 0 of 5 assets above 51%\n• Reversals: no qualifying reversal fired\n• Market check: field accuracy 49.6% -> 43.8% (-5.9pp), 0 of 7 improved; |1d| move 0.87% -> 1.54%\n\nNote: grok is a pure 4.6 line in both weeks of this issue; the 4.5 -> 4.6 flip (Aug 24 09:22 UTC) sits six windows back\n\n📄 <a href=\"https://marketmania.ai/research/reports/model-watch-2026-10-05.pdf\">Full report (PDF)</a> · <a href=\"https://marketmania.ai/research\">all research</a>\n\n#cryptotrading #LLM #AI #crypto #trading #models #research",
   "document_caption_html": "📄 Weekly Model Watch #10 — full report (PDF).\nWeb copy: <a href=\"https://marketmania.ai/research/reports/model-watch-2026-10-05.pdf\">model-watch-2026-10-05.pdf</a> · machine-readable: <a href=\"https://marketmania.ai/research/reports/model-watch-2026-10-05.json\">JSON</a> · <a href=\"https://marketmania.ai/research\">all research</a>\n\n#cryptotrading #LLM #AI #crypto #trading #models #research",
   "caption_len": 881,
   "document_caption_len": 391,
   "limit": 1024
  },
  "x": {
   "main": "Weekly Model Watch #10 is out.\n\n4,601 directional LLM calls: field accuracy 49.6% -> 43.8% w/w, 0 of 7 models improved. claude-opus-5 led at 47.0%; BTC was the most readable ticker.\n\nFull report: https://marketmania.ai/research/reports/model-watch-2026-10-05.pdf\n\n#AI #Crypto #Research #LLM",
   "main_tco_len": 247,
   "reply": "Hit-rate, w/w:\nopus-5: 50.7 -> 47.0\nfable-5: 49.9 -> 45.0\ngpt-5.6: 46.5 -> 43.5\ngemini-3.1: 49.0 -> 43.4\ngrok-4.6: 52.7 -> 43.3\nqwen-3.8: 48.9 -> 43.1\ndeepseek: 50.9 -> 42.0\nField: 49.6 -> 43.8. Wilson CIs; methodology v1.1.\nData: https://marketmania.ai/research/reports/model-watch-2026-10-05.json",
   "reply_tco_len": 254,
   "limit_tco": 280,
   "replies_max": 1
  }
 }
}