{
 "slug": "model-watch-2026-08-17",
 "series": "weekly",
 "series_label": "WEEKLY · MODEL WATCH",
 "issue": 3,
 "title": "Weekly Model Watch #3",
 "language": "en",
 "window_start": "2026-08-17T00:00:00+00:00",
 "window_end": "2026-08-24T00:00:00+00:00",
 "window_text": "Aug 17-23, 2026 UTC",
 "cutoff": "2026-08-24T16:00:00+00:00",
 "generated_at": "2026-08-26T07:00:00+00:00",
 "methodology": "v1.1 (2026-08-10)",
 "methodology_hash": "e66c7e8c864a2233",
 "source": "weekly_metrics_2026-08-17.json",
 "hit_rule": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl",
 "bibtex_key": "mm_modelwatch_2026w34",
 "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": 5130,
  "hit_rate": 0.5405
 },
 "market_state": {
  "panel": "market_state_6p2",
  "week": {
   "start": "2026-08-17",
   "end": "2026-08-24"
  },
  "prev_week": {
   "start": "2026-08-10",
   "end": "2026-08-17"
  },
  "current": {
   "btc_net_pct": 23.58,
   "realized_vol_ann_pct": 71.1,
   "volume_top5_usd_bn": 25.97,
   "volume_top5_wow_pct": 235.0,
   "avg_pairwise_corr": 0.81
  },
  "previous_as_published_issue2": {
   "btc_net_pct": -3.08,
   "realized_vol_ann_pct": 10.0,
   "volume_top5_usd_bn": 7.7521,
   "avg_pairwise_corr": 0.52
  },
  "snapshot_line": "BTC net +23.58% (prior -3.08%) - ann vol 71.1% (was 10.0%) - TOP5 volume $25.97B, +235% w/w - pairwise corr 0.81 (was 0.52)",
  "exchange": "binance",
  "source": "owner-verified single-exchange (binance) daily candle recompute, 2026-08-26; prior-week values as published in issue #2",
  "audit_note": "Market-state row is computed on a single-exchange (binance) daily candle series this issue, after an audit found the raw table mixes two exchanges; issue #2 row is as published.",
  "regime_days": {
   "2026-08-17": {
    "move_pct": 2.55,
    "regime": "trend"
   },
   "2026-08-18": {
    "move_pct": 0.21,
    "regime": "flat"
   },
   "2026-08-19": {
    "move_pct": 7.82,
    "regime": "trend"
   },
   "2026-08-20": {
    "move_pct": 5.07,
    "regime": "trend"
   },
   "2026-08-21": {
    "move_pct": 7.26,
    "regime": "trend"
   },
   "2026-08-22": {
    "move_pct": -1.67,
    "regime": "trend"
   },
   "2026-08-23": {
    "move_pct": 0.69,
    "regime": "flat"
   }
  },
  "alive_slice_context": {
   "abs_move_1d_pct": {
    "A": 0.734,
    "B": 4.283
   },
   "btc_realized_vol_ann_pct_hourly": {
    "A": 19.26,
    "B": 58.72
   }
  }
 },
 "key_finding": {
  "label": "KEY FINDING · OBSERVATION (one weekly window)",
  "text": "The market moved and the models kept up: field accuracy 43.8% -> 54.1% (+10.3pp) with 7 of 7 models improving -- and after two blind weeks, both ETH reversals finally found callers.",
  "evidence_level": "observation"
 },
 "tables": {
  "leaderboard": {
   "rows": [
    {
     "model": "claude-opus-5",
     "n": 672,
     "hit_rate": 0.5908,
     "wilson_95": [
      0.5532,
      0.6273
     ],
     "coverage": 0.5053,
     "insufficient": false
    },
    {
     "model": "claude-fable-5",
     "n": 779,
     "hit_rate": 0.5648,
     "wilson_95": [
      0.5298,
      0.5992
     ],
     "coverage": 0.5857,
     "insufficient": false
    },
    {
     "model": "gemini-3.1-pro",
     "n": 798,
     "hit_rate": 0.5414,
     "wilson_95": [
      0.5067,
      0.5756
     ],
     "coverage": 0.6005,
     "insufficient": false
    },
    {
     "model": "gpt-5.6-sol",
     "n": 688,
     "hit_rate": 0.5363,
     "wilson_95": [
      0.499,
      0.5733
     ],
     "coverage": 0.5173,
     "insufficient": false
    },
    {
     "model": "qwen-3.8-max",
     "n": 706,
     "hit_rate": 0.5227,
     "wilson_95": [
      0.4858,
      0.5593
     ],
     "coverage": 0.5511,
     "insufficient": false
    },
    {
     "model": "deepseek-v4-pro",
     "n": 777,
     "hit_rate": 0.5161,
     "wilson_95": [
      0.481,
      0.5511
     ],
     "coverage": 0.5842,
     "insufficient": false
    },
    {
     "model": "grok-4.5",
     "n": 710,
     "hit_rate": 0.5141,
     "wilson_95": [
      0.4773,
      0.5507
     ],
     "coverage": 0.5338,
     "insufficient": false
    }
   ],
   "title_awarded": false,
   "title_rule": ">=5pp gap AND non-overlapping 95% CI, N>=10",
   "movement_vs_prior_week": [
    {
     "model": "claude-opus-5",
     "hit_rate_issue2_published_pct": 41.5,
     "hit_rate_issue3": 0.5908,
     "delta_pp": 17.5,
     "rank_issue2": 7,
     "rank_issue3": 1
    },
    {
     "model": "claude-fable-5",
     "hit_rate_issue2_published_pct": 41.7,
     "hit_rate_issue3": 0.5648,
     "delta_pp": 14.7,
     "rank_issue2": 6,
     "rank_issue3": 2
    },
    {
     "model": "gemini-3.1-pro",
     "hit_rate_issue2_published_pct": 47.0,
     "hit_rate_issue3": 0.5414,
     "delta_pp": 7.1,
     "rank_issue2": 1,
     "rank_issue3": 3
    },
    {
     "model": "gpt-5.6-sol",
     "hit_rate_issue2_published_pct": 44.2,
     "hit_rate_issue3": 0.5363,
     "delta_pp": 9.4,
     "rank_issue2": 2,
     "rank_issue3": 4
    },
    {
     "model": "qwen-3.8-max",
     "hit_rate_issue2_published_pct": 44.1,
     "hit_rate_issue3": 0.5227,
     "delta_pp": 8.2,
     "rank_issue2": 3,
     "rank_issue3": 5
    },
    {
     "model": "deepseek-v4-pro",
     "hit_rate_issue2_published_pct": 42.5,
     "hit_rate_issue3": 0.5161,
     "delta_pp": 9.1,
     "rank_issue2": 5,
     "rank_issue3": 6
    },
    {
     "model": "grok-4.5",
     "hit_rate_issue2_published_pct": 44.0,
     "hit_rate_issue3": 0.5141,
     "delta_pp": 7.4,
     "rank_issue2": 4,
     "rank_issue3": 7
    }
   ],
   "top2_gap_pp": 2.6,
   "note": "No weekly title awarded (third issue running): 2.6pp gap, overlapping 95% CIs. claude-opus-5 leads descriptively. Deltas are computed on unrounded rates."
  },
  "ticker": {
   "rows": [
    {
     "symbol": "BTC",
     "n": 1118,
     "hit_rate": 0.5751,
     "wilson_95": [
      0.5459,
      0.6038
     ],
     "issue2_hit_rate_pct": 44.0
    },
    {
     "symbol": "SOL",
     "n": 1036,
     "hit_rate": 0.5434,
     "wilson_95": [
      0.513,
      0.5736
     ],
     "issue2_hit_rate_pct": 38.9
    },
    {
     "symbol": "BNB",
     "n": 932,
     "hit_rate": 0.5397,
     "wilson_95": [
      0.5076,
      0.5715
     ],
     "issue2_hit_rate_pct": 49.3
    },
    {
     "symbol": "ETH",
     "n": 1074,
     "hit_rate": 0.5279,
     "wilson_95": [
      0.498,
      0.5576
     ],
     "issue2_hit_rate_pct": 35.6
    },
    {
     "symbol": "XRP",
     "n": 970,
     "hit_rate": 0.5124,
     "wilson_95": [
      0.4809,
      0.5437
     ],
     "issue2_hit_rate_pct": 48.5
    }
   ],
   "best": "BTC",
   "hardest": "XRP",
   "best_vs_hardest_ci_overlap": false,
   "all_above_51pct": true
  },
  "pairs_top": [
   {
    "model": "claude-opus-5",
    "symbol": "BNB",
    "n": 126,
    "hit_rate": 0.6032
   },
   {
    "model": "grok-4.5",
    "symbol": "BTC",
    "n": 141,
    "hit_rate": 0.6028
   },
   {
    "model": "gemini-3.1-pro",
    "symbol": "BTC",
    "n": 175,
    "hit_rate": 0.5943
   },
   {
    "model": "claude-opus-5",
    "symbol": "ETH",
    "n": 138,
    "hit_rate": 0.5942
   },
   {
    "model": "claude-opus-5",
    "symbol": "SOL",
    "n": 137,
    "hit_rate": 0.5912
   },
   {
    "model": "claude-opus-5",
    "symbol": "XRP",
    "n": 119,
    "hit_rate": 0.5882
   }
  ],
  "pairs_worst": [
   {
    "model": "qwen-3.8-max",
    "symbol": "ETH",
    "n": 140,
    "hit_rate": 0.4929
   },
   {
    "model": "grok-4.5",
    "symbol": "ETH",
    "n": 159,
    "hit_rate": 0.4906
   },
   {
    "model": "deepseek-v4-pro",
    "symbol": "ETH",
    "n": 168,
    "hit_rate": 0.4821
   },
   {
    "model": "qwen-3.8-max",
    "symbol": "XRP",
    "n": 144,
    "hit_rate": 0.4792
   },
   {
    "model": "grok-4.5",
    "symbol": "XRP",
    "n": 135,
    "hit_rate": 0.4519
   }
  ],
  "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": [
    {
     "symbol": "ETH",
     "t": "2026-08-22T00:00:00+00:00",
     "new_side": "short",
     "move_8h_pct": -3.46,
     "n_callers": 1,
     "first_caller": {
      "model": "gemini-3.1-pro",
      "slot": "2026-08-22T00:01:00+00:00",
      "fh": "4h",
      "tf": "1h",
      "confidence": 60
     },
     "caller_models": [
      "gemini-3.1-pro"
     ]
    },
    {
     "symbol": "ETH",
     "t": "2026-08-23T08:00:00+00:00",
     "new_side": "long",
     "move_8h_pct": 2.14,
     "n_callers": 3,
     "first_caller": {
      "model": "claude-fable-5",
      "slot": "2026-08-23T00:01:00+00:00",
      "fh": "1d",
      "tf": "1d",
      "confidence": 62
     },
     "caller_models": [
      "claude-fable-5",
      "claude-opus-5",
      "deepseek-v4-pro"
     ]
    }
   ],
   "scope_v1": "BTC/ETH only",
   "status": "ok"
  },
  "cross_tf": {
   "fh_4h_tf_4h_vs_1h": {
    "agree": {
     "n": 575,
     "hit_rate": 0.6122,
     "wilson_95": [
      0.5717,
      0.6511
     ],
     "by_regime": {
      "trend": {
       "n": 455,
       "hit_rate": 0.6484
      },
      "flat": {
       "n": 120,
       "hit_rate": 0.475
      }
     }
    },
    "disagree": {
     "n": 41,
     "hit_rate": 0.4146,
     "wilson_95": [
      0.2776,
      0.5663
     ],
     "by_regime": {
      "trend": {
       "n": 39,
       "hit_rate": 0.4103
      },
      "flat": {
       "n": 2,
       "hit_rate": 0.5
      }
     }
    },
    "mixed_pairs": 223,
    "base": {
     "n": 840,
     "hit_rate": 0.606
    },
    "lift_pp": 0.6
   },
   "fh_1d_tf_1d_vs_4h": {
    "agree": {
     "n": 133,
     "hit_rate": 0.7594,
     "wilson_95": [
      0.6801,
      0.8241
     ],
     "by_regime": {
      "trend": {
       "n": 109,
       "hit_rate": 0.7431
      },
      "flat": {
       "n": 24,
       "hit_rate": 0.8333
      }
     }
    },
    "disagree": {
     "n": 5,
     "hit_rate": 0.4,
     "wilson_95": [
      0.1176,
      0.7693
     ],
     "by_regime": {
      "trend": {
       "n": 4,
       "hit_rate": 0.5
      },
      "flat": {
       "n": 1,
       "hit_rate": 0.0
      }
     }
    },
    "mixed_pairs": 33,
    "base": {
     "n": 171,
     "hit_rate": 0.7135
    },
    "lift_pp": 4.6
   }
  },
  "cross_fh": {
   "fh_4h_confirmed_by_1h": {
    "agree": {
     "n": 508,
     "hit_rate": 0.6004,
     "wilson_95": [
      0.5572,
      0.6421
     ],
     "by_regime": {
      "trend": {
       "n": 404,
       "hit_rate": 0.646
      },
      "flat": {
       "n": 104,
       "hit_rate": 0.4231
      }
     }
    },
    "disagree": {
     "n": 42,
     "hit_rate": 0.4762,
     "wilson_95": [
      0.3336,
      0.6228
     ],
     "by_regime": {
      "trend": {
       "n": 34,
       "hit_rate": 0.4706
      },
      "flat": {
       "n": 8,
       "hit_rate": 0.5
      }
     }
    },
    "mixed_pairs": 288,
    "base": {
     "n": 840,
     "hit_rate": 0.606
    },
    "lift_pp": -0.6
   },
   "fh_1d_confirmed_by_4h": {
    "agree": {
     "n": 100,
     "hit_rate": 0.74,
     "wilson_95": [
      0.6463,
      0.816
     ],
     "by_regime": {
      "trend": {
       "n": 84,
       "hit_rate": 0.7143
      },
      "flat": {
       "n": 16,
       "hit_rate": 0.875
      }
     }
    },
    "disagree": {
     "n": 11,
     "hit_rate": 0.7273,
     "wilson_95": [
      0.4343,
      0.9025
     ],
     "by_regime": {
      "trend": {
       "n": 9,
       "hit_rate": 0.7778
      },
      "flat": {
       "n": 2,
       "hit_rate": 0.5
      }
     }
    },
    "mixed_pairs": 60,
    "base": {
     "n": 171,
     "hit_rate": 0.7135
    },
    "lift_pp": 2.7
   }
  },
  "regime_days": {
   "2026-08-17": {
    "move_pct": 2.55,
    "regime": "trend"
   },
   "2026-08-18": {
    "move_pct": 0.21,
    "regime": "flat"
   },
   "2026-08-19": {
    "move_pct": 7.82,
    "regime": "trend"
   },
   "2026-08-20": {
    "move_pct": 5.07,
    "regime": "trend"
   },
   "2026-08-21": {
    "move_pct": 7.26,
    "regime": "trend"
   },
   "2026-08-22": {
    "move_pct": -1.67,
    "regime": "trend"
   },
   "2026-08-23": {
    "move_pct": 0.69,
    "regime": "flat"
   }
  },
  "side_mix": [
   {
    "model": "claude-fable-5",
    "n": 1330,
    "long": 0.5226,
    "short": 0.0632,
    "sideways": 0.4143,
    "ls_ratio": 8.27
   },
   {
    "model": "claude-opus-5",
    "n": 1330,
    "long": 0.4594,
    "short": 0.0459,
    "sideways": 0.4947,
    "ls_ratio": 10.01
   },
   {
    "model": "deepseek-v4-pro",
    "n": 1330,
    "long": 0.4662,
    "short": 0.118,
    "sideways": 0.4158,
    "ls_ratio": 3.95
   },
   {
    "model": "gemini-3.1-pro",
    "n": 1329,
    "long": 0.4575,
    "short": 0.143,
    "sideways": 0.3995,
    "ls_ratio": 3.2
   },
   {
    "model": "gpt-5.6-sol",
    "n": 1330,
    "long": 0.3835,
    "short": 0.1338,
    "sideways": 0.4827,
    "ls_ratio": 2.87
   },
   {
    "model": "grok-4.5",
    "n": 1330,
    "long": 0.3519,
    "short": 0.182,
    "sideways": 0.4662,
    "ls_ratio": 1.93
   },
   {
    "model": "qwen-3.8-max",
    "n": 1281,
    "long": 0.4543,
    "short": 0.0968,
    "sideways": 0.4489,
    "ls_ratio": 4.69
   }
  ],
  "long_short_ratio_field": {
   "value": 4.99,
   "method": "mean of the 7 per-model long-share / short-share ratios"
  },
  "consensus_skew": {
   "cells_ge5_same_side": 593,
   "n_mature": 3683,
   "hit_rate": 0.5444
  },
  "fail_of_week": {
   "model": "gemini-3.1-pro",
   "symbol": "XRP",
   "side": "long",
   "confidence": 85,
   "slot": "2026-08-21T16:01:00+00:00",
   "fh": "4h",
   "tf": "1h",
   "exit_reason": "sl",
   "pnl_net_usd": -3.1,
   "cross_reference": "XRP was the week's hardest ticker (51.2%) and the asset with the largest mean |1d| move (6.65%); the call was stopped out rather than expiring."
  },
  "counters": {
   "forecasts_total": 9590,
   "ok_in_gate": 9260,
   "invalid": 53,
   "out_of_gate": 277,
   "out_of_gate_by_fh": {
    "1w": 209,
    "1m": 68
   },
   "mature": 9260,
   "mature_directional": 5130,
   "mature_sideways": 4130,
   "pending_next_issue": 0,
   "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
    }
   ]
  },
  "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": 1.0,
   "claude-fable-5": 1.0,
   "qwen-3.8-max": 0.962,
   "grok-4.5": 1.0,
   "deepseek-v4-pro": 1.0,
   "gemini-3.1-pro": 0.9993,
   "gpt-5.6-sol": 1.0
  },
  "calibration_bridge": {
   "best_calibrated_model": "claude-opus-5",
   "brier": 0.2419,
   "note": "First issue where the hit-rate leader and the best-calibrated model are the same model: claude-opus-5 (59.1% hit, Brier 0.2419, gap +2.2pp). Issue #2's best-calibrated model qwen-3.8-max is 3rd by Brier and 5th by hit-rate."
  }
 },
 "key_findings": [
  "OBSERVATION -- No weekly title again. claude-opus-5 leads descriptively at 59.1% [55.3%, 62.7%] after the field's biggest jump (+17.5pp w/w), but the gap to #2 (claude-fable-5, 56.5%) is 2.6pp with overlapping CIs. All 7 models improved w/w.",
  "Every ticker was readable: BTC most readable (57.5%, n=1,118), XRP hardest (51.2%) -- the first week where all 5 assets cleared 51%. Best pair claude-opus-5 x BNB 60.3% (n=126); worst grok-4.5 x XRP 45.2% (n=135).",
  "The reversal blind spot broke: both ETH turns found callers -- gemini-3.1-pro first on the Aug 22 drop (-3.46%, 1 caller), claude-fable-5 first on the Aug 23 rebound (+2.14%, 3 callers).",
  "Self-agreement turned mildly positive: cross-TF/FH lifts -0.6 to +4.6pp (issue #2: -18.5 to +0.2pp). On 5 trend days 4h TF-agreement hit 64.8% (n=455) vs 47.5% flat (n=120)."
 ],
 "market_check": {
  "label": "MARKET CHECK · OBSERVATION (two adjacent calendar weeks)",
  "text": "OBSERVATION — the tape sped up and accuracy followed: mean |1d move| 0.73% -> 4.28% (483% rel), BTC realized vol 19.3% -> 58.7% (ann., hourly); field directional accuracy 43.8% -> 54.1% (+10.3pp), 7 of 7 models improved, sim win-rate up for 7 of 7, field sim PnL -$527 -> +$889 (adjacent calendar weeks Aug 10-16 vs Aug 17-23; descriptive, one pair of weeks, not a claim).",
  "robustness": "Robustness: raw price-sign accuracy 40.1% -> 53.5% — consistent with the trade-based hit rule.",
  "weeks": {
   "A": {
    "days": "2026-08-10..2026-08-16",
    "slots": [
     "2026-08-10T00:00:00+00:00",
     "2026-08-17T00:00:00+00:00"
    ],
    "cutoff": "2026-08-17T16:00:00+00:00"
   },
   "B": {
    "days": "2026-08-17..2026-08-23",
    "slots": [
     "2026-08-17T00:00:00+00:00",
     "2026-08-24T00:00:00+00:00"
    ],
    "cutoff": "2026-08-24T16:00:00+00:00"
   }
  },
  "price_source": "crypto_spot/1h@:00",
  "accuracy_field": {
   "A": {
    "n": 3670,
    "hit_rate": 0.4379,
    "wilson_95": [
     0.4219,
     0.454
    ]
   },
   "B": {
    "n": 5130,
    "hit_rate": 0.5405,
    "wilson_95": [
     0.5269,
     0.5541
    ]
   },
   "delta_pp": 10.3
  },
  "accuracy_per_model": [
   {
    "model": "claude-opus-5",
    "A": {
     "n": 361,
     "hit_rate": 0.4155,
     "wilson_95": [
      0.3658,
      0.467
     ]
    },
    "B": {
     "n": 672,
     "hit_rate": 0.5908,
     "wilson_95": [
      0.5532,
      0.6273
     ]
    },
    "delta_pp": 17.5
   },
   {
    "model": "claude-fable-5",
    "A": {
     "n": 472,
     "hit_rate": 0.4174,
     "wilson_95": [
      0.3737,
      0.4624
     ]
    },
    "B": {
     "n": 779,
     "hit_rate": 0.5648,
     "wilson_95": [
      0.5298,
      0.5992
     ]
    },
    "delta_pp": 14.7
   },
   {
    "model": "gpt-5.6-sol",
    "A": {
     "n": 636,
     "hit_rate": 0.4418,
     "wilson_95": [
      0.4037,
      0.4807
     ]
    },
    "B": {
     "n": 688,
     "hit_rate": 0.5363,
     "wilson_95": [
      0.499,
      0.5733
     ]
    },
    "delta_pp": 9.4
   },
   {
    "model": "deepseek-v4-pro",
    "A": {
     "n": 454,
     "hit_rate": 0.4251,
     "wilson_95": [
      0.3805,
      0.471
     ]
    },
    "B": {
     "n": 777,
     "hit_rate": 0.5161,
     "wilson_95": [
      0.481,
      0.5511
     ]
    },
    "delta_pp": 9.1
   },
   {
    "model": "qwen-3.8-max",
    "A": {
     "n": 572,
     "hit_rate": 0.4406,
     "wilson_95": [
      0.4004,
      0.4815
     ]
    },
    "B": {
     "n": 706,
     "hit_rate": 0.5227,
     "wilson_95": [
      0.4858,
      0.5593
     ]
    },
    "delta_pp": 8.2
   },
   {
    "model": "grok-4.5",
    "A": {
     "n": 620,
     "hit_rate": 0.4403,
     "wilson_95": [
      0.4017,
      0.4796
     ]
    },
    "B": {
     "n": 710,
     "hit_rate": 0.5141,
     "wilson_95": [
      0.4773,
      0.5507
     ]
    },
    "delta_pp": 7.4
   },
   {
    "model": "gemini-3.1-pro",
    "A": {
     "n": 555,
     "hit_rate": 0.4703,
     "wilson_95": [
      0.4291,
      0.5119
     ]
    },
    "B": {
     "n": 798,
     "hit_rate": 0.5414,
     "wilson_95": [
      0.5067,
      0.5756
     ]
    },
    "delta_pp": 7.1
   }
  ],
  "raw_sign_field": {
   "A": {
    "n_scored": 3632,
    "hit_rate": 0.4009
   },
   "B": {
    "n_scored": 5118,
    "hit_rate": 0.5348
   }
  },
  "abs_move_1d": {
   "A": 0.734,
   "B": 4.283,
   "delta_pct_rel": 483.5
  },
  "btc_realized_vol_ann_pct_hourly": {
   "A": 19.26,
   "B": 58.72
  },
  "trading_field": {
   "A": {
    "n_trades": 3670,
    "wr": 0.2965,
    "pnl_net_usd": -527.07,
    "pnl_gross_usd": -160.07
   },
   "B": {
    "n_trades": 5130,
    "wr": 0.4626,
    "pnl_net_usd": 889.37,
    "pnl_gross_usd": 1402.37
   }
  },
  "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": 10.3,
   "field_pnl_net": {
    "A": -527.07,
    "B": 889.37
   },
   "abs_move_delta": {
    "1h": {
     "A": 0.181,
     "B": 0.541,
     "delta_pct_rel": 198.9
    },
    "4h": {
     "A": 0.367,
     "B": 1.314,
     "delta_pct_rel": 258.0
    },
    "1d": {
     "A": 0.734,
     "B": 4.283,
     "delta_pct_rel": 483.5
    }
   },
   "btc_vol_ann_pct": {
    "A": 19.26,
    "B": 58.72
   },
   "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": "no lineage stitching needed: the grok 4.5->4.6 flip (2026-08-24 09:22 UTC) is after this window -- weeks A and B are pure grok-4.5 (verified: 0 grok-4.6 rows in the pull)"
 },
 "why_it_matters": "MarketMania scores 7 models 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. Issue #3 is the series' first live-tape week -- 5 trend days against issue #2's 1 -- so every week-over-week movement here is a movement across regimes as well as across weeks.",
 "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.",
 "practical_implications": [
  "Do not read this week's leaderboard as a skill ranking: no title was awarded, the top CIs overlap, and the two biggest jumps (+17.5pp, +14.7pp) came from the two models that were last and second-to-last a week earlier.",
  "Treat per-ticker readability as weekly weather. Three issues, three different best tickers (SOL -> BNB -> BTC) and the two-week 'ETH is hardest' pattern broke.",
  "Self-agreement stopped being a penalty but is not yet a booster: pooled lifts -0.6 to +4.6pp with overlapping CIs, and the reversal result is two events. Carry the regime split into the monthly test, do not act on it."
 ],
 "limitations": [
  "Single week (Aug 17-23, 2026 UTC). Descriptive for this window only; no claim about next week or any model's underlying skill. This window's regime is the opposite of issue #2's: 5 trend days of 7 against 1 of 7.",
  "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. Four events across three issues cannot characterise detector performance either way.",
  "Cross-TF and cross-FH disagreement cells are still small (n=5, 11, 41, 42); the n=5 cell is 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.",
  "qwen-3.8-max ran a 96.20% ok-rate this window; its mature pool is 1,281 against 1,330 for the other six models. Models in this window: claude-fable-5, claude-opus-5, deepseek-v4-pro, gemini-3.1-pro, gpt-5.6-sol, grok-4.5, qwen-3.8-max. Series density and lineage notes (wave 3): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Aug 17-23) daily coverage is PARTIAL by design: the 1w series has the Mon Aug 17 anchor plus daily slots on Aug 22-23 only, and the 1M series has a daily slot on Aug 23 only; both sit outside this report's FH gate (1h/4h/1d) and appear only in the exclusions counter (1w 209, 1M 68). (2) After the report window — from Aug 24, 2026 — the grok line runs Grok 4.6; every grok forecast in this window and in the week-2 comparison is grok-4.5. (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 this issue, after an audit found the raw table mixes two exchanges; issue #2 row is as published.",
  "Research-to-date counter pinned from this issue: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Aug 24 16:00 UTC). Issue #2 printed 23,458 under an earlier, unpinned definition; treat cross-issue counter deltas across the pin as definitional, not additive."
 ],
 "notes": {
  "series_density_and_lineage_wave3": "Series density and lineage notes (wave 3): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Aug 17-23) daily coverage is PARTIAL by design: the 1w series has the Mon Aug 17 anchor plus daily slots on Aug 22-23 only, and the 1M series has a daily slot on Aug 23 only; both sit outside this report's FH gate (1h/4h/1d) and appear only in the exclusions counter (1w 209, 1M 68). (2) After the report window — from Aug 24, 2026 — the grok line runs Grok 4.6; every grok forecast in this window and in the week-2 comparison is grok-4.5. (3) qwen-3.8-max succeeded qwen-3.7-max on Aug 5, 2026 (fully before this window).",
  "grok_era": {
   "ids_in_window": [
    "grok-4.5"
   ],
   "n_grok45": 1370,
   "n_grok46": 0,
   "note": "After the report window — from Aug 24, 2026 — the grok line runs Grok 4.6; every grok forecast in this window and in the week-2 comparison is grok-4.5"
  },
  "model_ids_line": [
   "claude-fable-5",
   "claude-opus-5",
   "deepseek-v4-pro",
   "gemini-3.1-pro",
   "gpt-5.6-sol",
   "grok-4.5",
   "qwen-3.8-max"
  ],
  "week_over_week_note": "Week-over-week columns compare back-to-back windows: Aug 10-16 (issue #2, and week A of this issue's alive slice) vs Aug 17-23 (this issue). \"Was\" values are the numbers published in issue #2; deltas are computed on unrounded rates.",
  "research_to_date_pin": "Research-to-date counter pinned from this issue: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Aug 24 16:00 UTC). Issue #2 printed 23,458 under an earlier, unpinned definition; treat cross-issue counter deltas across the pin as definitional, not additive.",
  "market_state_audit": "Market-state row is computed on a single-exchange (binance) daily candle series this issue, after an audit found the raw table mixes two exchanges; issue #2 row is as published.",
  "engine": "Engine 1.1 has powered the sandbox since Aug 18, i.e. from day 2 of 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 #3. Weekly Model Watch is a living series. Issue #2's open questions -- would a third reversal repeat the blind spot, does SOL's readability bounce back, and does the trend-day agreement premium reappear? -- closed 'no' (both ETH turns found callers), 'yes' (38.9% -> 54.3%) and 'yes' (64.8% trend vs 47.5% flat on 4h TF-agreement, now on a readable split). After the report window — from Aug 24, 2026 — the grok line runs Grok 4.6; every grok forecast in this window and in the week-2 comparison is grok-4.5. Engine 1.1 has powered the sandbox since Aug 18, i.e. from day 2 of this window; no cross-engine PnL comparisons are claimed.",
 "testing_next": [
  "Next issue: does the leaderboard reshuffle again when the tape calms, or is claude-opus-5's +17.5pp the start of something? Does the reversal detector find callers on a non-ETH turn?",
  "Does the every-ticker-above-51% floor survive a flat week?",
  "Monthly test (Sep 2): cross-TF/FH lifts with regime control across mixed weeks (trend vs. flat), block bootstrap."
 ],
 "related_research": [
  {
   "title": "Consensus Watch #3",
   "url": "https://marketmania.ai/research/reports/consensus-watch-2026-08-17.pdf"
  },
  {
   "title": "Weekly Calibration #3",
   "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-08-17.pdf"
  },
  {
   "title": "Weekly Model Watch #2",
   "url": "https://marketmania.ai/research/reports/model-watch-2026-08-10.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": 5130
  },
  "platform": {
   "as_of_cutoff": "2026-08-24",
   "resolved_forecasts": 33809,
   "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": 11,
   "models_tracked_detail": "7 current + 4 archived",
   "assets": 5,
   "forecast_horizons": 5,
   "cadence": "hourly",
   "published_research_reports": 13
  },
  "source": "weekly_metrics_2026-08-17.json",
  "pin_note": "Research-to-date counter pinned from this issue: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Aug 24 16:00 UTC). Issue #2 printed 23,458 under an earlier, unpinned definition; treat cross-issue counter deltas across the pin as definitional, not additive."
 },
 "citation": {
  "bibtex_key": "mm_modelwatch_2026w34",
  "title": "Weekly Model Watch #3: weekly leaderboard, ticker/pair reads and cross-confirmation, Aug 17-23 2026",
  "author": "MarketMania Research",
  "year": 2026,
  "month": "August",
  "day": 26,
  "url": "https://marketmania.ai/research/reports/model-watch-2026-08-17.pdf",
  "note": "Methodology v1.1 (2026-08-10), hash e66c7e8c864a2233; window Aug 17-23, 2026 UTC; source weekly_metrics_2026-08-17.json"
 },
 "site_entry": {
  "slug": "model-watch-2026-08-17",
  "series": "weekly",
  "seriesLabel": "Weekly · Model Watch",
  "date": "August 26, 2026",
  "title": "Weekly Model Watch #3",
  "summary": "5,130 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 59.1% (+17.5pp w/w, the field's biggest jump) with overlapping CIs. BTC took most-readable (57.5%) and every ticker cleared 51% for the first time in the series. After two blind weeks, both ETH reversals found callers: gemini-3.1-pro first on the Aug 22 drop, claude-fable-5 first on the Aug 23 rebound. Field accuracy rose 43.8% -> 54.1% (+10.3pp), 7 of 7 models improved.",
  "stats": [
   "5,130 directional calls",
   "both ETH turns called",
   "field +10.3pp w/w"
  ],
  "files": {
   "pdf": "/research/reports/model-watch-2026-08-17.pdf",
   "md": "/research/reports/model-watch-2026-08-17.md",
   "json": "/research/reports/model-watch-2026-08-17.json"
  }
 },
 "social": {
  "telegram": {
   "photo_caption_html": "📊 <b>Weekly Model Watch #3</b> — weekly series (window Aug 17–23)\n\nWho led, what was readable, who saw the turn, does self-agreement help? 5,130 directional calls, 7 models:\n• <b>No weekly title again</b> — claude-opus-5 leads at <b>59.1%</b> (+17.5pp w/w, the field's biggest jump), but the CI still overlaps #2\n• Tickers: <b>BTC</b> most readable (57.5%); XRP hardest at 51.2% — first week with every ticker above 51%\n• Reversals: <b>both ETH turns called</b> — gemini-3.1-pro first on the Aug 22 drop, claude-fable-5 first on the Aug 23 rebound (weeks 1-2: zero callers)\n• Market check: field accuracy 43.8% -> 54.1% (+10.3pp), 7 of 7 improved; |1d| move 0.73% -> 4.28%\n\nNote: after this report window — from Aug 24 — the grok line runs Grok 4.6; every grok call in this window is grok-4.5\n\n📄 <a href=\"https://marketmania.ai/research/reports/model-watch-2026-08-17.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 #3 — full report (PDF).\nWeb copy: <a href=\"https://marketmania.ai/research/reports/model-watch-2026-08-17.pdf\">model-watch-2026-08-17.pdf</a> · machine-readable: <a href=\"https://marketmania.ai/research/reports/model-watch-2026-08-17.json\">JSON</a> · <a href=\"https://marketmania.ai/research\">all research</a>\n\n#cryptotrading #LLM #AI #crypto #trading #models #research",
   "caption_len": 1015,
   "document_caption_len": 390,
   "limit": 1024
  },
  "x": {
   "main": "Weekly Model Watch #3 is out.\n\nThe market moved and the models kept up: field accuracy 43.8% -> 54.1%, 7 of 7 models improved w/w. And after two blind weeks — both ETH reversals found callers.\n\nFull report: https://marketmania.ai/research/reports/model-watch-2026-08-17.pdf\n\n#AI #Crypto #Research #LLM",
   "main_tco_len": 258,
   "reply": "Hit-rate, w/w:\ngemini-3.1: 47.0 -> 54.1\ngpt-5.6: 44.2 -> 53.6\nqwen-3.8: 44.1 -> 52.3\ngrok-4.5: 44.0 -> 51.4\ndeepseek: 42.5 -> 51.6\nfable-5: 41.7 -> 56.5\nopus-5: 41.5 -> 59.1\nField: 43.8 -> 54.1. Seven of seven improved. Wilson CIs; methodology v1.1.\nData: https://marketmania.ai/research/reports/model-watch-2026-08-17.json",
   "reply_tco_len": 279,
   "limit_tco": 280,
   "replies_max": 1
  }
 }
}