{ "slug": "weekly-calibration-2026-08-10", "series": "weekly", "series_label": "WEEKLY · CALIBRATION", "issue": 2, "title": "Weekly Calibration #2", "window_start": "2026-08-10T00:00:00+00:00", "window_end": "2026-08-17T00:00:00+00:00", "cutoff": "2026-08-17T16:00:00+00:00", "generated_at": "2026-08-18T08:37:10.727025+00:00", "methodology": "v1.1 (2026-08-10)", "methodology_hash": "e66c7e8c864a2233", "source": "weekly_metrics_2026-08-10.json", "hit_rule": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl", "bibtex_key": "mm_weekly_calibration_2026w33", "market_state": { "panel": "market_state_6p2", "week": { "start": "2026-08-10", "end": "2026-08-17" }, "prev_week": { "start": "2026-08-03", "end": "2026-08-10" }, "generated_utc": "2026-08-19T06:26:44+00:00", "settings_module": "marketmania.settings", "current": { "per_symbol": { "BTC": { "net_pct": -3.08, "days": 7, "quote_vol_usd": 4676300109.0 }, "ETH": { "net_pct": -1.81, "days": 7, "quote_vol_usd": 1799344934.0 }, "SOL": { "net_pct": -2.16, "days": 7, "quote_vol_usd": 545506557.0 }, "BNB": { "net_pct": 0.13, "days": 7, "quote_vol_usd": 373245161.0 }, "XRP": { "net_pct": -3.52, "days": 7, "quote_vol_usd": 357704108.0 } }, "btc_net_pct": -3.08, "realized_vol_ann_pct": 10.03, "vol_n_returns": 7, "avg_daily_range_pct": 1.63, "hivol_days": 0, "hivol_days_of": 7, "volume_top5_usd": 7752100869.0, "volume_symbols_counted": 5, "avg_pairwise_corr": 0.52, "corr_pairs": 10 }, "previous": { "per_symbol": { "BTC": { "net_pct": 2.09, "days": 7, "quote_vol_usd": 4914474500.0 }, "ETH": { "net_pct": 1.34, "days": 7, "quote_vol_usd": 2141079318.0 }, "SOL": { "net_pct": 3.57, "days": 7, "quote_vol_usd": 680571970.0 }, "BNB": { "net_pct": 2.34, "days": 7, "quote_vol_usd": 388062382.0 }, "XRP": { "net_pct": -5.24, "days": 7, "quote_vol_usd": 382877404.0 } }, "btc_net_pct": 2.09, "realized_vol_ann_pct": 11.42, "vol_n_returns": 7, "avg_daily_range_pct": 1.64, "hivol_days": 0, "hivol_days_of": 7, "volume_top5_usd": 8507065574.0, "volume_symbols_counted": 5, "avg_pairwise_corr": 0.4, "corr_pairs": 10 }, "delta": { "btc_net_pct": -5.17, "realized_vol_ann_pct": -1.39, "avg_daily_range_pct": -0.01, "volume_top5_usd_pct": -8.9, "avg_pairwise_corr": 0.12 }, "_debug": { "models": { "Candle": "datalake.Candle", "MetricSnapshot": "datalake.MetricSnapshot", "EtfFlow": "datalake.EtfFlow" }, "candle_fields": [ "close", "exchange", "high", "id", "ingested_at", "low", "market_type", "open", "quote_volume", "source", "symbol", "timeframe", "ts_open", "volume" ], "market_types": [ "commodity", "crypto_futures", "crypto_spot", "forex", "stock" ], "timeframes": [ "1M", "1d", "1h", "1w", "4h" ], "picked": { "market_type": "crypto_spot", "timeframe": "1d", "ohlc": [ "open", "high", "low", "close" ], "qv": "quote_volume", "ts": "ts_open" }, "symbol_map": { "BTC": "BTCUSDT", "ETH": "ETHUSDT", "SOL": "SOLUSDT", "BNB": "BNBUSDT", "XRP": "XRPUSDT" }, "funding_trace": "Traceback (most recent call last):\n File \"/tmp/w73_market_state.py\", line 202, in \n out[\"current\"][\"funding_btc\"] = funding_block(W0, W1)\n ~~~~~~~~~~~~~^^^^^^^^\n File \"/tmp/w73_market_state.py\", line 190, in funding_block\n raise RuntimeError(\"funding field mapping failed: \" + json.dumps(dbg))\nRuntimeError: funding field mapping failed: {\"fields\": [\"exchange\", \"id\", \"market_type\", \"metric\", \"raw\", \"symbol\", \"ts\", \"value_num\"], \"ts\": \"ts\", \"val\": null, \"sym\": \"symbol\", \"symbols_seen\": [\"1000BONKUSDT\", \"1000FLOKIUSDT\", \"1000PEPEUSDT\", \"1000SHIBUSDT\", \"1INCHUSDT\", \"AAVEUSDT\", \"ADAUSDT\", \"ALGOUSDT\", \"ANKRUSDT\", \"APEUSDT\", \"APTUSDT\", \"ARBUSDT\", \"ATOMUSDT\", \"AVAXUSDT\", \"AXSUSDT\", \"BATUSDT\", \"BCHUSDT\", \"BLURUSDT\", \"BNBUSDT\", \"BONKUSDT\", \"BTCUSDT\", \"CAKEUSDT\", \"CELOUSDT\", \"CFXUSDT\", \"CHZUSDT\", \"COMPUSDT\", \"CRVUSDT\", \"DASHUSDT\", \"DOGEUSDT\", \"DOTUSDT\"], \"symbol_used\": \"BTCUSDT\"}\n", "etf_trace": "Traceback (most recent call last):\n File \"/tmp/w73_market_state.py\", line 246, in \n out[\"current\"][\"etf_flow\"] = etf_block(W0, W1)\n ~~~~~~~~~^^^^^^^^\n File \"/tmp/w73_market_state.py\", line 217, in etf_block\n raise RuntimeError(\"etf field mapping failed: \" + json.dumps(dbg))\nRuntimeError: etf field mapping failed: {\"fields\": {\"id\": \"BigAutoField\", \"asset\": \"CharField\", \"fund\": \"CharField\", \"flow_date\": \"DateField\", \"flow_musd\": \"DecimalField\", \"source\": \"CharField\", \"raw\": \"JSONField\", \"first_seen\": \"DateTimeField\", \"last_seen\": \"DateTimeField\"}, \"date\": \"flow_date\", \"asset\": \"asset\", \"val\": null}\n" }, "_errors": [ "funding: RuntimeError('funding field mapping failed: {\"fields\": [\"exchange\", \"id\", \"market_type\", \"metric\", \"raw\", \"symbol\", \"ts\", \"value_num\"], \"ts\": \"ts\", \"val\": null, \"sym\": \"symbol\", \"symbols_seen\": [\"1000BONKUSDT\", \"1000FLOKIUSDT\", \"1000PEPEUSDT\", \"1000SHIBUSDT\", \"1INCHUSDT\", \"AAVEUSDT\", \"ADAUSDT\", \"ALGOUSDT\", \"ANKRUSDT\", \"APEUSDT\", \"APTUSDT\", \"ARBUSDT\", \"ATOMUSDT\", \"AVAXUSDT\", \"AXSUSDT\", \"BATUSDT\", \"BCHUSDT\", \"BLURUSDT\", \"BNBUSDT\", \"BONKUSDT\", \"BTCUSDT\", \"CAKEUSDT\", \"CELOUSDT\", \"CFXUSDT\", \"CHZUSDT\", \"COMPUSDT\", \"CRVUSDT\", \"DASHUSDT\", \"DOGEUSDT\", \"DOTUSDT\"], \"symbol_used\": \"BTCUSDT\"}')", "etf: RuntimeError('etf field mapping failed: {\"fields\": {\"id\": \"BigAutoField\", \"asset\": \"CharField\", \"fund\": \"CharField\", \"flow_date\": \"DateField\", \"flow_musd\": \"DecimalField\", \"source\": \"CharField\", \"raw\": \"JSONField\", \"first_seen\": \"DateTimeField\", \"last_seen\": \"DateTimeField\"}, \"date\": \"flow_date\", \"asset\": \"asset\", \"val\": null}')" ] }, "tables": { "calibration_main": [ { "model": "qwen-3.8-max", "legacy": false, "is_field": false, "n": 572, "coverage": 0.4304, "hit_rate": 0.4406, "mean_conf": 58.2, "gap_pp": 14.1, "brier": 0.2688, "wilson_95": { "lo": 0.4004, "hi": 0.4815 } }, { "model": "grok-4.5", "legacy": false, "is_field": false, "n": 620, "coverage": 0.4662, "hit_rate": 0.4403, "mean_conf": 59.8, "gap_pp": 15.8, "brier": 0.2727, "wilson_95": { "lo": 0.4017, "hi": 0.4796 } }, { "model": "claude-fable-5", "legacy": false, "is_field": false, "n": 472, "coverage": 0.3549, "hit_rate": 0.4174, "mean_conf": 59.8, "gap_pp": 18.1, "brier": 0.2782, "wilson_95": { "lo": 0.3737, "hi": 0.4624 } }, { "model": "claude-opus-5", "legacy": false, "is_field": false, "n": 361, "coverage": 0.2714, "hit_rate": 0.4155, "mean_conf": 60.7, "gap_pp": 19.2, "brier": 0.2814, "wilson_95": { "lo": 0.3658, "hi": 0.467 } }, { "model": "gemini-3.1-pro", "legacy": false, "is_field": false, "n": 555, "coverage": 0.4173, "hit_rate": 0.4703, "mean_conf": 65.4, "gap_pp": 18.4, "brier": 0.2848, "wilson_95": { "lo": 0.4291, "hi": 0.5119 } }, { "model": "deepseek-v4-pro", "legacy": false, "is_field": false, "n": 454, "coverage": 0.3419, "hit_rate": 0.4251, "mean_conf": 60.7, "gap_pp": 18.2, "brier": 0.2879, "wilson_95": { "lo": 0.3805, "hi": 0.471 } }, { "model": "gpt-5.6-sol", "legacy": false, "is_field": false, "n": 636, "coverage": 0.4782, "hit_rate": 0.4418, "mean_conf": 68.2, "gap_pp": 24.0, "brier": 0.309, "wilson_95": { "lo": 0.4037, "hi": 0.4807 } }, { "model": "Field (all models)", "legacy": false, "is_field": true, "n": 3670, "coverage": null, "hit_rate": 0.4379, "mean_conf": 62.0, "gap_pp": 18.3, "brier": 0.2836, "wilson_95": null } ], "buckets": [ { "model": "qwen-3.8-max", "bucket": "50-60", "n": 360, "hit_rate": 0.4583, "mean_conf": 56.5, "insufficient": false, "no_data": false }, { "model": "qwen-3.8-max", "bucket": "60-70", "n": 200, "hit_rate": 0.405, "mean_conf": 62.0, "insufficient": false, "no_data": false }, { "model": "qwen-3.8-max", "bucket": "70-80", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "qwen-3.8-max", "bucket": "80-100", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "qwen-3.8-max", "bucket": "sub-50", "n": 12, "hit_rate": 0.5, "mean_conf": null, "insufficient": false, "no_data": false }, { "model": "grok-4.5", "bucket": "50-60", "n": 367, "hit_rate": 0.4305, "mean_conf": 57.5, "insufficient": false, "no_data": false }, { "model": "grok-4.5", "bucket": "60-70", "n": 251, "hit_rate": 0.4582, "mean_conf": 63.1, "insufficient": false, "no_data": false }, { "model": "grok-4.5", "bucket": "70-80", "n": 2, "hit_rate": 0.0, "mean_conf": 71, "insufficient": true, "no_data": false }, { "model": "grok-4.5", "bucket": "80-100", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "grok-4.5", "bucket": "sub-50", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "claude-fable-5", "bucket": "50-60", "n": 200, "hit_rate": 0.435, "mean_conf": 56.5, "insufficient": false, "no_data": false }, { "model": "claude-fable-5", "bucket": "60-70", "n": 272, "hit_rate": 0.4044, "mean_conf": 62.2, "insufficient": false, "no_data": false }, { "model": "claude-fable-5", "bucket": "70-80", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "claude-fable-5", "bucket": "80-100", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "claude-fable-5", "bucket": "sub-50", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "claude-opus-5", "bucket": "50-60", "n": 108, "hit_rate": 0.4352, "mean_conf": 57.9, "insufficient": false, "no_data": false }, { "model": "claude-opus-5", "bucket": "60-70", "n": 253, "hit_rate": 0.4071, "mean_conf": 61.9, "insufficient": false, "no_data": false }, { "model": "claude-opus-5", "bucket": "70-80", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "claude-opus-5", "bucket": "80-100", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "claude-opus-5", "bucket": "sub-50", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "gemini-3.1-pro", "bucket": "50-60", "n": 5, "hit_rate": 0.4, "mean_conf": 55, "insufficient": true, "no_data": false }, { "model": "gemini-3.1-pro", "bucket": "60-70", "n": 396, "hit_rate": 0.4571, "mean_conf": 62.8, "insufficient": false, "no_data": false }, { "model": "gemini-3.1-pro", "bucket": "70-80", "n": 152, "hit_rate": 0.5066, "mean_conf": 72.3, "insufficient": false, "no_data": false }, { "model": "gemini-3.1-pro", "bucket": "80-100", "n": 2, "hit_rate": 0.5, "mean_conf": 80, "insufficient": true, "no_data": false }, { "model": "gemini-3.1-pro", "bucket": "sub-50", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true }, { "model": "deepseek-v4-pro", "bucket": "50-60", "n": 181, "hit_rate": 0.453, "mean_conf": 56.2, "insufficient": false, "no_data": false }, { "model": "deepseek-v4-pro", "bucket": "60-70", "n": 230, "hit_rate": 0.4217, "mean_conf": 62.5, "insufficient": false, "no_data": false }, { "model": "deepseek-v4-pro", "bucket": "70-80", "n": 38, "hit_rate": 0.2632, "mean_conf": 72.6, "insufficient": false, "no_data": false }, { "model": "deepseek-v4-pro", "bucket": "80-100", "n": 1, "hit_rate": 0.0, "mean_conf": 80, "insufficient": true, "no_data": false }, { "model": "deepseek-v4-pro", "bucket": "sub-50", "n": 4, "hit_rate": 1.0, "mean_conf": null, "insufficient": true, "no_data": false }, { "model": "gpt-5.6-sol", "bucket": "50-60", "n": 1, "hit_rate": 0.0, "mean_conf": 59, "insufficient": true, "no_data": false }, { "model": "gpt-5.6-sol", "bucket": "60-70", "n": 419, "hit_rate": 0.4702, "mean_conf": 65.3, "insufficient": false, "no_data": false }, { "model": "gpt-5.6-sol", "bucket": "70-80", "n": 214, "hit_rate": 0.3925, "mean_conf": 73.7, "insufficient": false, "no_data": false }, { "model": "gpt-5.6-sol", "bucket": "80-100", "n": 2, "hit_rate": 0.0, "mean_conf": 81, "insufficient": true, "no_data": false }, { "model": "gpt-5.6-sol", "bucket": "sub-50", "n": 0, "hit_rate": null, "mean_conf": null, "insufficient": false, "no_data": true } ], "by_fh": [ { "model": "qwen-3.8-max", "fh": "1h", "n": 365, "hit_rate": 0.4548, "flag": null }, { "model": "qwen-3.8-max", "fh": "4h", "n": 180, "hit_rate": 0.4222, "flag": null }, { "model": "qwen-3.8-max", "fh": "1d", "n": 27, "hit_rate": 0.3704, "flag": null }, { "model": "grok-4.5", "fh": "1h", "n": 400, "hit_rate": 0.4625, "flag": null }, { "model": "grok-4.5", "fh": "4h", "n": 190, "hit_rate": 0.4, "flag": null }, { "model": "grok-4.5", "fh": "1d", "n": 30, "hit_rate": 0.4, "flag": null }, { "model": "claude-fable-5", "fh": "1h", "n": 311, "hit_rate": 0.4405, "flag": null }, { "model": "claude-fable-5", "fh": "4h", "n": 132, "hit_rate": 0.3939, "flag": null }, { "model": "claude-fable-5", "fh": "1d", "n": 29, "hit_rate": 0.2759, "flag": null }, { "model": "claude-opus-5", "fh": "1h", "n": 228, "hit_rate": 0.4518, "flag": null }, { "model": "claude-opus-5", "fh": "4h", "n": 107, "hit_rate": 0.3645, "flag": null }, { "model": "claude-opus-5", "fh": "1d", "n": 26, "hit_rate": 0.3077, "flag": null }, { "model": "gemini-3.1-pro", "fh": "1h", "n": 365, "hit_rate": 0.4822, "flag": null }, { "model": "gemini-3.1-pro", "fh": "4h", "n": 161, "hit_rate": 0.4472, "flag": null }, { "model": "gemini-3.1-pro", "fh": "1d", "n": 29, "hit_rate": 0.4483, "flag": null }, { "model": "deepseek-v4-pro", "fh": "1h", "n": 276, "hit_rate": 0.442, "flag": null }, { "model": "deepseek-v4-pro", "fh": "4h", "n": 157, "hit_rate": 0.4204, "flag": null }, { "model": "deepseek-v4-pro", "fh": "1d", "n": 21, "hit_rate": 0.2381, "flag": null }, { "model": "gpt-5.6-sol", "fh": "1h", "n": 401, "hit_rate": 0.4539, "flag": null }, { "model": "gpt-5.6-sol", "fh": "4h", "n": 203, "hit_rate": 0.4138, "flag": null }, { "model": "gpt-5.6-sol", "fh": "1d", "n": 32, "hit_rate": 0.4688, "flag": null } ], "trading": [ { "model": "claude-opus-5", "n_trades": 361, "wr": 0.2909, "pnl_net_usd": -63.19, "pnl_gross_usd": -27.09, "max_dd_usd": -64.58 }, { "model": "deepseek-v4-pro", "n_trades": 454, "wr": 0.2819, "pnl_net_usd": -70.86, "pnl_gross_usd": -25.46, "max_dd_usd": -71.2 }, { "model": "gemini-3.1-pro", "n_trades": 555, "wr": 0.3117, "pnl_net_usd": -71.64, "pnl_gross_usd": -16.14, "max_dd_usd": -72.62 }, { "model": "qwen-3.8-max", "n_trades": 572, "wr": 0.2972, "pnl_net_usd": -72.62, "pnl_gross_usd": -15.42, "max_dd_usd": -77.53 }, { "model": "claude-fable-5", "n_trades": 472, "wr": 0.2818, "pnl_net_usd": -77.13, "pnl_gross_usd": -29.93, "max_dd_usd": -77.13 }, { "model": "grok-4.5", "n_trades": 620, "wr": 0.2968, "pnl_net_usd": -85.46, "pnl_gross_usd": -23.46, "max_dd_usd": -88.68 }, { "model": "gpt-5.6-sol", "n_trades": 636, "wr": 0.3066, "pnl_net_usd": -86.17, "pnl_gross_usd": -22.57, "max_dd_usd": -88.98 } ], "gap_week_over_week": [ { "model": "qwen-3.8-max", "gap_pp_issue1": 15.1, "gap_pp_issue2": 14.1 }, { "model": "grok-4.5", "gap_pp_issue1": 18.3, "gap_pp_issue2": 15.8 }, { "model": "claude-fable-5", "gap_pp_issue1": 19.2, "gap_pp_issue2": 18.1 }, { "model": "deepseek-v4-pro", "gap_pp_issue1": 20.3, "gap_pp_issue2": 18.2 }, { "model": "gemini-3.1-pro", "gap_pp_issue1": 22.2, "gap_pp_issue2": 18.4 }, { "model": "claude-opus-5", "gap_pp_issue1": 20.0, "gap_pp_issue2": 19.2 }, { "model": "gpt-5.6-sol", "gap_pp_issue1": 24.4, "gap_pp_issue2": 24.0 }, { "model": "Field (all models)", "gap_pp_issue1": 20.4, "gap_pp_issue2": 18.3 } ], "counters": { "forecasts_total": 9380, "ok_in_gate": 9307, "invalid": 4, "out_of_gate_1w": 69, "mature": 9307, "mature_directional": 3670, "mature_sideways": 5637, "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 } ] } }, "key_finding": { "label": "KEY FINDING · OBSERVATION (one weekly window)", "text": "Overconfidence eased across the whole field -- every one of the 7 models narrowed its gap, 20.4pp -> 18.3pp pooled -- yet high confidence still ranked nothing, with one exception: gemini-3.1-pro's 70-80 bucket hit 50.7%, the field's first working high-confidence bucket.", "evidence_level": "observation" }, "key_findings": [ "OBSERVATION -- A second flat, hard week. Directional calls hit 43.8% against 62.0 stated mean confidence -- a +18.3pp overconfidence gap (issue #1: +20.4pp). Every model's Brier score again topped 0.25, worse than an uninformative always-50% predictor, for the second week running.", "Every model narrowed its gap week-over-week -- the series' first w/w delta, and it is field-wide: from gemini-3.1-pro's -3.8pp improvement to gpt-5.6-sol's -0.4pp. qwen-3.8-max is best-calibrated again (gap +14.1pp, Brier 0.2688), but the hit-rate lead moved: gemini-3.1-pro tops the field at 47.0% [42.9%, 51.2%].", "Confidence still failed to rank outcomes in the middle of the scale: 4 of the 5 models with sufficient N (>=10) in both 50-60 and 60-70 did not out-hit 50-60 from 60-70 (issue #1: 4 of 6). Higher up, issue #1's inversion flags split: gemini-3.1-pro un-inverted -- its 70-80 bucket hit 50.7% (n=152), the only high-confidence cell in the field above base -- while deepseek-v4-pro's inversion deepened, 35.9% -> 26.3% (n=38).", "Trading stayed uniformly negative -- and got cleaner about it. All 7 models finished net-negative AND gross-negative (issue #1 had one gross-positive outlier); net PnL ran -$63.19 (claude-opus-5, best) to -$86.17 (gpt-5.6-sol, worst)." ], "practical_implications": [ "Stated confidence remains a style signal, not a probability: 4 of 5 sufficient-N models again failed to out-hit their 50-60 bucket from 60-70. Nothing this week changes issue #1's advice.", "The one working high-confidence cell -- gemini-3.1-pro's 70-80 at 50.7% -- is one week old and sits next to deepseek-v4-pro's 26.3% in the same bucket. Treat it as the thing to watch, not a filter to trade.", "The field-wide gap narrowing (all 7 models, first w/w delta of the series) is two data points, not a trend. Whether it is drift toward humility or just this week's regime is exactly what the monthly report will test." ], "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 (a single market wave can move many forecasts together), so read them as a range, not a formal coverage guarantee.", "All 3,670 scored calls sit inside one market regime -- 6 of 7 days this window were flat (|BTC daily move| < 1%). A single week cannot separate a calibration pattern from the week's specific conditions.", "Week-over-week deltas begin with this issue, but two points cannot separate drift from noise -- several issues can. No durability claim is made.", "Models report confidence at discrete levels, not a continuous scale; the 50-60 / 60-70 / 70-80 / 80-100 buckets reflect those natural breakpoints, not an arbitrary binning choice.", "Underlying price series are reconstructed from trade entry prices (median per symbol-slot), not an independent tick feed." ], "platform_note_tpsl": "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. Context, not a finding.", "living_series_note": "Issue #2. Weekly Calibration is a living series; week-over-week deltas begin with this issue. Issue #1's open questions -- does the confidence-bucket inversion persist, and does the 60-70 vs 50-60 non-ranking repeat? -- closed as 'split' and 'yes': gemini-3.1-pro un-inverted its 70-80 bucket, deepseek-v4-pro's inversion deepened, and 4 of 5 sufficient-N models again failed to rank. Engine 1.1 powers the sandbox since Aug 18 (after this window closed); no cross-engine PnL comparisons are claimed.", "testing_next": [ "Next issue: does gemini-3.1-pro's 70-80 bucket keep outperforming at n>150 -- and does deepseek-v4-pro's inversion survive a third week? Does the field-wide gap keep narrowing?", "Monthly test (Sep 2): is the overconfidence gap stable across market regimes (trend vs flat) at monthly n?" ], "related_research": [ { "title": "Consensus Watch #2", "url": "https://marketmania.ai/research/reports/consensus-watch-2026-08-10.pdf" }, { "title": "Weekly Model Watch #2", "url": "https://marketmania.ai/research/reports/model-watch-2026-08-10.pdf" }, { "title": "Config Watch #2", "url": "https://marketmania.ai/research/reports/config-watch-2026-08-12.pdf" }, { "title": "Weekly Calibration #1", "url": "https://marketmania.ai/research/reports/weekly-calibration-2026-08-03.pdf" } ], "related_research_note": "The three weekly reports publish together as one issue each week; Config Watch follows on its own cycle. Direct links are the posting rule from this wave on.", "research_to_date": { "this_report": { "scored_observations": 3670 }, "platform": { "as_of_cutoff": "2026-08-17", "resolved_forecasts": 23458, "since": "2026-07-11", "models_tracked": 9, "models_current_frontier": 7, "models_archived_legacy": 2, "assets": 5, "forecast_horizons": 5, "cadence": "hourly", "published_reports": 9 }, "source": "platform_counters_2026-08-17" } }