Arena run #400

You are an Arena strategy executor. You must follow the strategy rules strictly and output ONLY valid JSON. You are NOT allowed to invent prices, fundamentals, earnings dates, or sentiment. If a field is null/empty, treat it as unknown. You are a constrained selector (no narrative).

{"task": "stage1_universe_scan", "region": "US", "strategy": {"key": "meanrev-v1", "name": "Two-Stage LLM Mean-Reversion (Arena v1)", "rules": {"max_positions": 10, "max_buys_per_run": 2, "avoid_overtrading": true, "max_sells_per_run": 2, "max_gross_leverage": 3.0, "fixed_position_size": 3000.0, "universe_symbols_eu": [], "universe_symbols_us": []}}, "selection_rules": {"horizon": "2-10 trading days", "target": "short-term mean reversion in liquid equities", "constraints": ["Select exactly 5 candidates", "Avoid earnings within 5 trading days (if known)", "Avoid highly binary/event-driven moves (if known)", "Avoid sector concentration: max 1 per sector unless clearly justified (sector may be unknown)"]}, "universe": [{"symbol": "TRN_CFD.UK", "name": "TRAINLINE PLC", "sector": "", "last_price": 206.0, "change_1d_pct": -12.93322062552832, "distance_from_ma200_pct": -22.557701091522887, "distance_from_ma50_pct": -12.560104316644482, "volatility_20d_pct": 131.09279103846345, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "VCT_CFD.UK", "name": "VICTREX PLC", "sector": "", "last_price": 695.0, "change_1d_pct": -0.42979942693409656, "distance_from_ma200_pct": -3.2784163489814833, "distance_from_ma50_pct": 6.2434457730395465, "volatility_20d_pct": 118.65826330943554, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "SYNT_CFD.UK", "name": "SYNTHOMER PLC", "sector": "", "last_price": 20.2, "change_1d_pct": -32.666666666666664, "distance_from_ma200_pct": -73.62254515017194, "distance_from_ma50_pct": -61.002505878582646, "volatility_20d_pct": 362.0742865046256, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "DLN_CFD.UK", "name": "DERWENT LONDON PLC", "sector": "", "last_price": 1953.0, "change_1d_pct": 10.401356698699837, "distance_from_ma200_pct": 5.069478604951705, "distance_from_ma50_pct": 12.150447212111025, "volatility_20d_pct": 115.39088732649292, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "CRDA_CFD.UK", "name": "CRODA INTERNATIONAL PLC", "sector": "", "last_price": 3121.0, "change_1d_pct": 13.367235742826011, "distance_from_ma200_pct": 10.093851216079353, "distance_from_ma50_pct": 9.83246554776207, "volatility_20d_pct": 109.18178749390499, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "RHIM_CFD.UK", "name": "", "sector": "", "last_price": 2960.0, "change_1d_pct": 9.023941068139973, "distance_from_ma200_pct": 12.939755835694466, "distance_from_ma50_pct": 17.95826987098712, "volatility_20d_pct": 137.0123103901981, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "BLND_CFD.UK", "name": "BRITISH LAND CO PLC", "sector": "", "last_price": 400.4, "change_1d_pct": -3.4715525554484206, "distance_from_ma200_pct": 6.86656372352572, "distance_from_ma50_pct": -0.2590673575129543, "volatility_20d_pct": 90.47340329611018, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "BBY_CFD.UK", "name": "BALFOUR BEATTY PLC", "sector": "", "last_price": 759.18, "change_1d_pct": 5.222453222453205, "distance_from_ma200_pct": 33.313724414201815, "distance_from_ma50_pct": 8.832962232591, "volatility_20d_pct": 54.25956465831767, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "BIG_CFD.FR", "name": "Bigben Interactive", "sector": "", "last_price": 0.473, "change_1d_pct": -40.65244667503137, "distance_from_ma200_pct": -57.481044006670004, "distance_from_ma50_pct": -45.84258856396987, "volatility_20d_pct": 245.7660340614924, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "DCC_CFD.UK", "name": "DCC PLC", "sector": "", "last_price": 5080.0, "change_1d_pct": 16.08775137111518, "distance_from_ma200_pct": 5.470412938362834, "distance_from_ma50_pct": 5.336155457586478, "volatility_20d_pct": 94.82279659179201, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "IMI_CFD.UK", "name": "IMI PLC", "sector": "", "last_price": 2828.0, "change_1d_pct": 8.26952526799387, "distance_from_ma200_pct": 29.012317870749314, "distance_from_ma50_pct": 11.107007677698544, "volatility_20d_pct": 78.40398881701634, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "RKT_CFD.UK", "name": "", "sector": "", "last_price": 6416.0, "change_1d_pct": -0.773275595422207, "distance_from_ma200_pct": 9.203621104249947, "distance_from_ma50_pct": 1.3697812890090422, "volatility_20d_pct": 53.84159623395557, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "CNA_CFD.UK", "name": "CENTRICA PLC", "sector": "", "last_price": 189.9, "change_1d_pct": -3.6040609137055757, "distance_from_ma200_pct": 12.694478089261874, "distance_from_ma50_pct": 4.223265003704624, "volatility_20d_pct": 4354.2492559168495, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "ATG_CFD.UK", "name": "AUCTION TECHNOLOGY GROUP", "sector": "", "last_price": 316.5, "change_1d_pct": 3.770491803278686, "distance_from_ma200_pct": null, "distance_from_ma50_pct": 2.606496790507684, "volatility_20d_pct": 3869.8570945036245, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "CSGP_CFD.US", "name": "CoStar Group Inc", "sector": "", "last_price": 44.99, "change_1d_pct": -0.08882966910948031, "distance_from_ma200_pct": null, "distance_from_ma50_pct": -27.832637164507577, "volatility_20d_pct": 6517.0730512753025, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "BRBY_CFD.UK", "name": "BURBERRY GROUP PLC", "sector": "", "last_price": 1174.5, "change_1d_pct": -0.550381033022862, "distance_from_ma200_pct": null, "distance_from_ma50_pct": -4.69118971687319, "volatility_20d_pct": 4100.463229875871, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}, {"symbol": "COTY_CFD.US", "name": "Coty Inc", "sector": "", "last_price": 2.65, "change_1d_pct": -0.7490636704119868, "distance_from_ma200_pct": null, "distance_from_ma50_pct": -12.425644415069403, "volatility_20d_pct": 7661.46272234243, "market_cap_usd": null, "avg_daily_volume_usd": null, "days_to_next_earnings": null, "earnings_confirmed": null, "news_sentiment_score": null, "news_headlines_last_3": [], "data_quality_note": "snapshot_ok_prices_technicals_only"}], "output_schema": {"selected_stocks": [{"symbol": "string", "mean_reversion_score": "integer 0-100", "selection_reason": "short, concrete, indicator-based"}], "rejected_common_reasons": ["string"]}}

{
  "raw": {
    "id": "gen-1772565864-gvH6fZVjPWf76erc8ncK",
    "model": "google/gemini-3-pro-preview-20251117",
    "usage": {
      "cost": 0.056184,
      "is_byok": false,
      "cost_details": {
        "upstream_inference_cost": 0.056184,
        "upstream_inference_prompt_cost": 0.008412,
        "upstream_inference_completions_cost": 0.047772
      },
      "total_tokens": 8187,
      "prompt_tokens": 4206,
      "completion_tokens": 3981,
      "prompt_tokens_details": {
        "audio_tokens": 0,
        "video_tokens": 0,
        "cached_tokens": 0,
        "cache_write_tokens": 0
      },
      "completion_tokens_details": {
        "audio_tokens": 0,
        "image_tokens": 0,
        "reasoning_tokens": 3839
      }
    },
    "object": "chat.completion",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "{\n  \"task\": \"stage1_universe_scan\",\n  \"region\": \"US\",\n  \"strategy\": {\n    \"key\": \"meanrev-v1\",\n    \"name\": \"Two-Stage LLM Mean-Reversion (Arena v1)\",\n    \"rules\": {\n      \"max_positions\": 10,\n      \"max_buys_per_run\": 2,\n      \"avoid_overtrading\": true,\n      \"max_sells_per_run\": 2,\n      \"max_gross_leverage\": 3.0,\n      \"fixed_position_size\": ",
          "refusal": null,
          "reasoning": "**Contemplating Stock Selection**\n\nI'm now zeroing in on the core challenge: pinpointing the 5 optimal stocks. The \"Two-Stage LLM Mean-Reversion (Arena v1)\" strategy is my guide. I'm focusing on the mean-reversion signals and the universe of stocks to make the most informed picks.\n\n\n**Defining Mean-Reversion Criteria**\n\nI'm now refining the mean-reversion scoring. I'm focusing on the interplay of `change_1d_pct`, and `distance_from_ma200_pct`, and `distance_from_ma50_pct`. The universe includes mixed regions, but the instructions specify US. I'm considering how to weight each factor for my final selection.\n\n\n**Scoring and Ranking Stocks**\n\nI am now weighting the factors for the mean-reversion score, taking into account `change_1d_pct`, and the distances from the MA's. Given the mixed US/EU universe, I will prioritize US stocks if possible, but the selection constraint is key. I'll flag high-volatility candidates to avoid \"binary events,\" as instructed.\n\n\n**Formulating the Selection Criteria**\n\nI'm now prioritizing the selection. Given the mixed US/UK/FR universe and the \"US\" target region, I will favor US stocks, if possible. I'll focus on stocks with significant 1-day changes and distances from MA50 and MA200, but avoid those flagged as highly volatile or likely binary events. I'm building a ranked list based on these factors.\n\n\n**Finalizing Stock Selections**\n\nMy top 5 picks are now locked in: TRN, BLND, CNA, COTY, and CSGP. I carefully weighed the mean-reversion signals, prioritizing US stocks where possible and avoiding high-volatility candidates to align with the safety constraint. I'm now documenting the rationale for each selection.\n\n\n**Refining the Strategy**\n\nI'm now prioritizing the US stocks and evaluating both the degree of oversold conditions and potential for mean reversion. I'm carefully considering volatility and the likelihood of \"binary events\" to minimize risk and adhere to the safety guidelines. I'm leaning toward a core set of candidates.\n\n\n**Prioritizing Safe Selections**\n\nMy latest focus is to prioritize safe candidates, meaning those with more plausible volatility data. I've re-evaluated the high-volatility candidates and will stick to a core set, focusing on US stocks where possible and standard mean-reversion signals for the final five.\n\n\n**Prioritizing Safe Candidates**\n\nI'm now prioritizing the safe candidates within the constraints. I've re-examined the volatility data and eliminated stocks with questionable figures. I'm focusing on US stocks like COTY and CSGP, but will prioritize safe candidates, balancing mean reversion signals and risk mitigation as I build my final five.\n\n\n**Revisiting Volatility Concerns**\n\nI'm now prioritizing the accuracy of the volatility data. The extreme volatility readings for several stocks are likely errors, so I'm focusing on stocks with more believable figures to make the best informed selections. I'm carefully analyzing the data and will make appropriate corrections if the volatility is a scaling error.\n\n\n**Prioritizing Data Accuracy**\n\nI'm now focusing on the data quality, especially the volatility figures, which seem implausibly high for several stocks. This prompted me to revisit the US stock selections, with the intention of making the most informed picks. I will prioritize the data and signals, and pick a core set.\n\n\n**Prioritizing Safe Candidates**\n\nI'm now zeroing in on data accuracy and stock safety. I'm focusing on stocks with believable volatility figures and manageable 1-day percentage changes. Given this refined assessment, I am opting for the less volatile candidates, and will avoid the outlier values that could be a data error.\n\n\n",
          "reasoning_details": [
            {
              "text": "**Contemplating Stock Selection**\n\nI'm now zeroing in on the core challenge: pinpointing the 5 optimal stocks. The \"Two-Stage LLM Mean-Reversion (Arena v1)\" strategy is my guide. I'm focusing on the mean-reversion signals and the universe of stocks to make the most informed picks.\n\n\n**Defining Mean-Reversion Criteria**\n\nI'm now refining the mean-reversion scoring. I'm focusing on the interplay of `change_1d_pct`, and `distance_from_ma200_pct`, and `distance_from_ma50_pct`. The universe includes mixed regions, but the instructions specify US. I'm considering how to weight each factor for my final selection.\n\n\n**Scoring and Ranking Stocks**\n\nI am now weighting the factors for the mean-reversion score, taking into account `change_1d_pct`, and the distances from the MA's. Given the mixed US/EU universe, I will prioritize US stocks if possible, but the selection constraint is key. I'll flag high-volatility candidates to avoid \"binary events,\" as instructed.\n\n\n**Formulating the Selection Criteria**\n\nI'm now prioritizing the selection. Given the mixed US/UK/FR universe and the \"US\" target region, I will favor US stocks, if possible. I'll focus on stocks with significant 1-day changes and distances from MA50 and MA200, but avoid those flagged as highly volatile or likely binary events. I'm building a ranked list based on these factors.\n\n\n**Finalizing Stock Selections**\n\nMy top 5 picks are now locked in: TRN, BLND, CNA, COTY, and CSGP. I carefully weighed the mean-reversion signals, prioritizing US stocks where possible and avoiding high-volatility candidates to align with the safety constraint. I'm now documenting the rationale for each selection.\n\n\n**Refining the Strategy**\n\nI'm now prioritizing the US stocks and evaluating both the degree of oversold conditions and potential for mean reversion. I'm carefully considering volatility and the likelihood of \"binary events\" to minimize risk and adhere to the safety guidelines. I'm leaning toward a core set of candidates.\n\n\n**Prioritizing Safe Selections**\n\nMy latest focus is to prioritize safe candidates, meaning those with more plausible volatility data. I've re-evaluated the high-volatility candidates and will stick to a core set, focusing on US stocks where possible and standard mean-reversion signals for the final five.\n\n\n**Prioritizing Safe Candidates**\n\nI'm now prioritizing the safe candidates within the constraints. I've re-examined the volatility data and eliminated stocks with questionable figures. I'm focusing on US stocks like COTY and CSGP, but will prioritize safe candidates, balancing mean reversion signals and risk mitigation as I build my final five.\n\n\n**Revisiting Volatility Concerns**\n\nI'm now prioritizing the accuracy of the volatility data. The extreme volatility readings for several stocks are likely errors, so I'm focusing on stocks with more believable figures to make the best informed selections. I'm carefully analyzing the data and will make appropriate corrections if the volatility is a scaling error.\n\n\n**Prioritizing Data Accuracy**\n\nI'm now focusing on the data quality, especially the volatility figures, which seem implausibly high for several stocks. This prompted me to revisit the US stock selections, with the intention of making the most informed picks. I will prioritize the data and signals, and pick a core set.\n\n\n**Prioritizing Safe Candidates**\n\nI'm now zeroing in on data accuracy and stock safety. I'm focusing on stocks with believable volatility figures and manageable 1-day percentage changes. Given this refined assessment, I am opting for the less volatile candidates, and will avoid the outlier values that could be a data error.\n\n\n",
              "type": "reasoning.text",
              "index": 0,
              "format": "google-gemini-v1"
            },
            {
              "data": "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",
              "type": "reasoning.encrypted",
              "index": 1,
              "format": "google-gemini-v1"
            }
          ]
        },
        "logprobs": null,
        "finish_reason": "length",
        "native_finish_reason": "MAX_TOKENS"
      }
    ],
    "created": 1772565864,
    "provider": "Google"
  }
}

You are an Arena portfolio manager. You must follow the strategy rules strictly and output ONLY valid JSON. You are NOT allowed to invent prices/fundamentals/news/earnings. If a field is null/empty, treat it as unknown. Avoid overtrading: if changes are marginal, prefer HOLD. Do not churn.

{"task": "stage2_portfolio_management", "region": "US", "strategy": {"key": "meanrev-v1", "name": "Two-Stage LLM Mean-Reversion (Arena v1)", "rules": {"max_positions": 10, "max_buys_per_run": 2, "avoid_overtrading": true, "max_sells_per_run": 2, "max_gross_leverage": 3.0, "fixed_position_size": 3000.0, "universe_symbols_eu": [], "universe_symbols_us": []}}, "portfolio_constraints": {"initial_equity": 10000.0, "max_positions": 10, "fixed_position_size": 3000.0, "max_gross_leverage": 3.0, "overtrading_rules": ["Max 2 SELL actions per run unless risk event forces more", "Max 2 BUY actions per run", "If no clear improvement vs current holdings, output HOLD for everything"]}, "current_portfolio": [{"symbol": "ATE_CFD.FR", "qty": 48.115477145148354, "avg_price": 62.35, "last_price": 59.65, "unrealized_pnl": -129.9117882919007, "opened_at": "2026-02-27T18:23:55.960577+00:00"}, {"symbol": "CABO_CFD.US", "qty": 31.71247357293869, "avg_price": 94.6, "last_price": 108.8, "unrealized_pnl": 450.3171247357295, "opened_at": "2026-02-27T18:23:55.960577+00:00"}, {"symbol": "HIK_CFD.UK", "qty": 2.1306818181818183, "avg_price": 1408.0, "last_price": 1244.0, "unrealized_pnl": -349.4318181818182, "opened_at": "2026-02-26T10:33:24.101894+00:00"}, {"symbol": "LIO_CFD.UK", "qty": 0.0, "avg_price": 250.0, "last_price": 270.0, "unrealized_pnl": 0.0, "opened_at": "2026-02-26T10:33:24.101894+00:00"}, {"symbol": "MKS_CFD.UK", "qty": 7.5452716297786715, "avg_price": 397.6, "last_price": 389.5, "unrealized_pnl": -61.11670020120741, "opened_at": "2026-03-01T10:30:13.622938+00:00"}, {"symbol": "PZC_CFD.UK", "qty": 36.67481662591687, "avg_price": 81.8, "last_price": 81.9, "unrealized_pnl": 3.6674816625919995, "opened_at": "2026-03-01T10:30:13.622938+00:00"}, {"symbol": "UKW_CFD.UK", "qty": 32.48511099079589, "avg_price": 92.35, "last_price": 94.79, "unrealized_pnl": 79.26367081754236, "opened_at": "2026-02-25T17:57:28.313088+00:00"}, {"symbol": "WIZZ_CFD.UK", "qty": 2.3094688221709005, "avg_price": 1299.0, "last_price": 1080.0, "unrealized_pnl": -505.7736720554272, "opened_at": "2026-02-25T17:57:28.313088+00:00"}], "candidates": [], "output_schema": {"actions": {"sell": [{"symbol": "string", "reason": "string"}], "hold": [{"symbol": "string", "reason": "string"}], "buy": [{"symbol": "string", "position_size": "number (currency amount)", "reason": "string"}]}, "portfolio_rationale": "string"}}

{
  "actions": {
    "buy": [],
    "hold": [
      {
        "reason": "Current drawdown is within normal volatility; holding for mean reversion.",
        "symbol": "ATE_CFD.FR"
      },
      {
        "reason": "Significant drawdown (-11%), but holding for potential technical bounce/reversion absent better capital allocation options.",
        "symbol": "HIK_CFD.UK"
      },
      {
        "reason": "Minor fluctuation (-2%); holding.",
        "symbol": "MKS_CFD.UK"
      },
      {
        "reason": "Price is flat relative to entry; holding.",
        "symbol": "PZC_CFD.UK"
      },
      {
        "reason": "Slight profit (+2.6%); holding for further potential upside before reversion.",
        "symbol": "UKW_CFD.UK"
      },
      {
        "reason": "Deep drawdown (-16%), holding for oversold bounce as per mean-reversion logic.",
        "symbol": "WIZZ_CFD.UK"
      }
    ],
    "sell": [
      {
        "reason": "Position has appreciated significantly (+15%), triggering a mean-reversion take-profit signal to lock in gains.",
        "symbol": "CABO_CFD.US"
      }
    ]
  },
  "portfolio_rationale": "The strategy dictates selling strength in a mean-reversion framework. CABO_CFD.US has rallied 15% and is sold to capture profits. Other positions, including those in drawdown like WIZZ and HIK, are held to wait for a reversion to the mean, as no superior buy candidates were provided to rotate capital into."
}

{
  "raw": {
    "id": "gen-1772565864-gvH6fZVjPWf76erc8ncK",
    "model": "google/gemini-3-pro-preview-20251117",
    "usage": {
      "cost": 0.056184,
      "is_byok": false,
      "cost_details": {
        "upstream_inference_cost": 0.056184,
        "upstream_inference_prompt_cost": 0.008412,
        "upstream_inference_completions_cost": 0.047772
      },
      "total_tokens": 8187,
      "prompt_tokens": 4206,
      "completion_tokens": 3981,
      "prompt_tokens_details": {
        "audio_tokens": 0,
        "video_tokens": 0,
        "cached_tokens": 0,
        "cache_write_tokens": 0
      },
      "completion_tokens_details": {
        "audio_tokens": 0,
        "image_tokens": 0,
        "reasoning_tokens": 3839
      }
    },
    "object": "chat.completion",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "{\n  \"task\": \"stage1_universe_scan\",\n  \"region\": \"US\",\n  \"strategy\": {\n    \"key\": \"meanrev-v1\",\n    \"name\": \"Two-Stage LLM Mean-Reversion (Arena v1)\",\n    \"rules\": {\n      \"max_positions\": 10,\n      \"max_buys_per_run\": 2,\n      \"avoid_overtrading\": true,\n      \"max_sells_per_run\": 2,\n      \"max_gross_leverage\": 3.0,\n      \"fixed_position_size\": ",
          "refusal": null,
          "reasoning": "**Contemplating Stock Selection**\n\nI'm now zeroing in on the core challenge: pinpointing the 5 optimal stocks. The \"Two-Stage LLM Mean-Reversion (Arena v1)\" strategy is my guide. I'm focusing on the mean-reversion signals and the universe of stocks to make the most informed picks.\n\n\n**Defining Mean-Reversion Criteria**\n\nI'm now refining the mean-reversion scoring. I'm focusing on the interplay of `change_1d_pct`, and `distance_from_ma200_pct`, and `distance_from_ma50_pct`. The universe includes mixed regions, but the instructions specify US. I'm considering how to weight each factor for my final selection.\n\n\n**Scoring and Ranking Stocks**\n\nI am now weighting the factors for the mean-reversion score, taking into account `change_1d_pct`, and the distances from the MA's. Given the mixed US/EU universe, I will prioritize US stocks if possible, but the selection constraint is key. I'll flag high-volatility candidates to avoid \"binary events,\" as instructed.\n\n\n**Formulating the Selection Criteria**\n\nI'm now prioritizing the selection. Given the mixed US/UK/FR universe and the \"US\" target region, I will favor US stocks, if possible. I'll focus on stocks with significant 1-day changes and distances from MA50 and MA200, but avoid those flagged as highly volatile or likely binary events. I'm building a ranked list based on these factors.\n\n\n**Finalizing Stock Selections**\n\nMy top 5 picks are now locked in: TRN, BLND, CNA, COTY, and CSGP. I carefully weighed the mean-reversion signals, prioritizing US stocks where possible and avoiding high-volatility candidates to align with the safety constraint. I'm now documenting the rationale for each selection.\n\n\n**Refining the Strategy**\n\nI'm now prioritizing the US stocks and evaluating both the degree of oversold conditions and potential for mean reversion. I'm carefully considering volatility and the likelihood of \"binary events\" to minimize risk and adhere to the safety guidelines. I'm leaning toward a core set of candidates.\n\n\n**Prioritizing Safe Selections**\n\nMy latest focus is to prioritize safe candidates, meaning those with more plausible volatility data. I've re-evaluated the high-volatility candidates and will stick to a core set, focusing on US stocks where possible and standard mean-reversion signals for the final five.\n\n\n**Prioritizing Safe Candidates**\n\nI'm now prioritizing the safe candidates within the constraints. I've re-examined the volatility data and eliminated stocks with questionable figures. I'm focusing on US stocks like COTY and CSGP, but will prioritize safe candidates, balancing mean reversion signals and risk mitigation as I build my final five.\n\n\n**Revisiting Volatility Concerns**\n\nI'm now prioritizing the accuracy of the volatility data. The extreme volatility readings for several stocks are likely errors, so I'm focusing on stocks with more believable figures to make the best informed selections. I'm carefully analyzing the data and will make appropriate corrections if the volatility is a scaling error.\n\n\n**Prioritizing Data Accuracy**\n\nI'm now focusing on the data quality, especially the volatility figures, which seem implausibly high for several stocks. This prompted me to revisit the US stock selections, with the intention of making the most informed picks. I will prioritize the data and signals, and pick a core set.\n\n\n**Prioritizing Safe Candidates**\n\nI'm now zeroing in on data accuracy and stock safety. I'm focusing on stocks with believable volatility figures and manageable 1-day percentage changes. Given this refined assessment, I am opting for the less volatile candidates, and will avoid the outlier values that could be a data error.\n\n\n",
          "reasoning_details": [
            {
              "text": "**Contemplating Stock Selection**\n\nI'm now zeroing in on the core challenge: pinpointing the 5 optimal stocks. The \"Two-Stage LLM Mean-Reversion (Arena v1)\" strategy is my guide. I'm focusing on the mean-reversion signals and the universe of stocks to make the most informed picks.\n\n\n**Defining Mean-Reversion Criteria**\n\nI'm now refining the mean-reversion scoring. I'm focusing on the interplay of `change_1d_pct`, and `distance_from_ma200_pct`, and `distance_from_ma50_pct`. The universe includes mixed regions, but the instructions specify US. I'm considering how to weight each factor for my final selection.\n\n\n**Scoring and Ranking Stocks**\n\nI am now weighting the factors for the mean-reversion score, taking into account `change_1d_pct`, and the distances from the MA's. Given the mixed US/EU universe, I will prioritize US stocks if possible, but the selection constraint is key. I'll flag high-volatility candidates to avoid \"binary events,\" as instructed.\n\n\n**Formulating the Selection Criteria**\n\nI'm now prioritizing the selection. Given the mixed US/UK/FR universe and the \"US\" target region, I will favor US stocks, if possible. I'll focus on stocks with significant 1-day changes and distances from MA50 and MA200, but avoid those flagged as highly volatile or likely binary events. I'm building a ranked list based on these factors.\n\n\n**Finalizing Stock Selections**\n\nMy top 5 picks are now locked in: TRN, BLND, CNA, COTY, and CSGP. I carefully weighed the mean-reversion signals, prioritizing US stocks where possible and avoiding high-volatility candidates to align with the safety constraint. I'm now documenting the rationale for each selection.\n\n\n**Refining the Strategy**\n\nI'm now prioritizing the US stocks and evaluating both the degree of oversold conditions and potential for mean reversion. I'm carefully considering volatility and the likelihood of \"binary events\" to minimize risk and adhere to the safety guidelines. I'm leaning toward a core set of candidates.\n\n\n**Prioritizing Safe Selections**\n\nMy latest focus is to prioritize safe candidates, meaning those with more plausible volatility data. I've re-evaluated the high-volatility candidates and will stick to a core set, focusing on US stocks where possible and standard mean-reversion signals for the final five.\n\n\n**Prioritizing Safe Candidates**\n\nI'm now prioritizing the safe candidates within the constraints. I've re-examined the volatility data and eliminated stocks with questionable figures. I'm focusing on US stocks like COTY and CSGP, but will prioritize safe candidates, balancing mean reversion signals and risk mitigation as I build my final five.\n\n\n**Revisiting Volatility Concerns**\n\nI'm now prioritizing the accuracy of the volatility data. The extreme volatility readings for several stocks are likely errors, so I'm focusing on stocks with more believable figures to make the best informed selections. I'm carefully analyzing the data and will make appropriate corrections if the volatility is a scaling error.\n\n\n**Prioritizing Data Accuracy**\n\nI'm now focusing on the data quality, especially the volatility figures, which seem implausibly high for several stocks. This prompted me to revisit the US stock selections, with the intention of making the most informed picks. I will prioritize the data and signals, and pick a core set.\n\n\n**Prioritizing Safe Candidates**\n\nI'm now zeroing in on data accuracy and stock safety. I'm focusing on stocks with believable volatility figures and manageable 1-day percentage changes. Given this refined assessment, I am opting for the less volatile candidates, and will avoid the outlier values that could be a data error.\n\n\n",
              "type": "reasoning.text",
              "index": 0,
              "format": "google-gemini-v1"
            },
            {
              "data": "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",
              "type": "reasoning.encrypted",
              "index": 1,
              "format": "google-gemini-v1"
            }
          ]
        },
        "logprobs": null,
        "finish_reason": "length",
        "native_finish_reason": "MAX_TOKENS"
      }
    ],
    "created": 1772565864,
    "provider": "Google"
  }
}