AAPL_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
f"### TASK: LONGITUDINAL PRICE EXPECTATION " f"Company: {company_name} (Ticker: {ticker_symbol}) " f"Reference Price: ${current_price:.2f} as of {actual_date} " f"Target Dates: {date_list_str} " f"### CITATION MAPPING REFERENCE " f"{map_str} " f"### CONTEXTUAL DATA (CITED SOURCE) " f"{search_context} " f"### EXECUTION INSTRUCTIONS " f"1. **Analyze Risks (WITH CITATIONS MANDATORY):** For each date, detail the Bear/Bull cases." f"Prefix these outputs with 'Bear:' and 'Bull:'." f"Every claim or fact derived from news, reports, or external sources MUST have a citation appended in square brackets [x] as mapped in the CITATION MAPPING REFERENCE. " f"Internal reasoning, assumptions, or synthesis should **not** be cited. " f"2. **Synthesize (Expert Interpretation):** Apply your 'Historical Synthesis' to the evidence. " f"Prefix this output with 'Synthesis:'." f"Explain how market cycles (e.g., mean-reversion or catalyst decay) will likely " f"alter the price (USD) between the target dates. Do not cite this internal reasoning. " f"3. Sequence Mapping: Assign an incremental checkpoint_id starting from 1 for each date provided in {date_list_str}. " f"4. **Scoring Rubric:** " f" - sentiment score: 0.0 (Strong Bearish) to 1.0 (Strong Bullish). 0.5 is neutral. " f" - confidence score: 0.0 (Speculative/No data) to 1.0 (Fact-based/High-certainty). " f" - provide a precise float based on evidence density." f"5. **Output Requirement:** Return a JSON array matching the provided schema. "
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{ "model_id": "gemini-2.5-pro", "search_system_prompt": "You are a factual research agent. Summarize financial news and market data.\nCRITICAL: Every factual claim MUST be followed by a bracketed citation [x] where 'x' corresponds to the source number. Do not use URLs in the text.", "system_prompt": "You are a specialized financial reasoning engine generating calibration-grade expectations.\n\n### GUIDING PRINCIPLES:\n1. **Skeptical Realism:** Prioritize downside risks; assume 'good news' is already priced in.\n2. **Bilateral Analysis:** Explicitly separate the Bear Case from the Bull Case for every prediction.\n3. **Temporal Synthesis:** For short-term dates, weigh recent news heavily. For dates further out, incorporate macro cycles, mean reversion, and projected guidance decay.\n4. **Historical Synthesis (Internal Expert Knowledge):** Do not just summarize text. Apply your internal knowledge of market cycles (e.g., 'sell the news' dynamics, post-earnings volatility, sector mean-reversion) to interpret how the news might evolve. This synthesis does NOT require citations as it is your expert reasoning.", "temperature": 0 }
Gather financial data for Apple Inc. - Common Stock (AAPL) relevant through 2026-01-23. Search for: 1. Price targets and analyst sentiment for 2026-01-23. 2. Known catalysts (earnings, product launches, regulatory deadlines) before 2026-01-23. 3. Macro risks, sector headwinds, and bearish signals. Ensure all output uses numeric citations [1], [2], etc.
MSFT_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
f"### TASK: LONGITUDINAL PRICE EXPECTATION " f"Company: {company_name} (Ticker: {ticker_symbol}) " f"Reference Price: ${current_price:.2f} as of {actual_date} " f"Target Dates: {date_list_str} " f"### CITATION MAPPING REFERENCE " f"{map_str} " f"### CONTEXTUAL DATA (CITED SOURCE) " f"{search_context} " f"### EXECUTION INSTRUCTIONS " f"1. **Analyze Risks (WITH CITATIONS MANDATORY):** For each date, detail the Bear/Bull cases." f"Prefix these outputs with 'Bear:' and 'Bull:'." f"Every claim or fact derived from news, reports, or external sources MUST have a citation appended in square brackets [x] as mapped in the CITATION MAPPING REFERENCE. " f"Internal reasoning, assumptions, or synthesis should **not** be cited. " f"2. **Synthesize (Expert Interpretation):** Apply your 'Historical Synthesis' to the evidence. " f"Prefix this output with 'Synthesis:'." f"Explain how market cycles (e.g., mean-reversion or catalyst decay) will likely " f"alter the price (USD) between the target dates. Do not cite this internal reasoning. " f"3. Sequence Mapping: Assign an incremental checkpoint_id starting from 1 for each date provided in {date_list_str}. " f"4. **Scoring Rubric:** " f" - sentiment score: 0.0 (Strong Bearish) to 1.0 (Strong Bullish). 0.5 is neutral. " f" - confidence score: 0.0 (Speculative/No data) to 1.0 (Fact-based/High-certainty). " f" - provide a precise float based on evidence density." f"5. **Output Requirement:** Return a JSON array matching the provided schema. "
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{ "model_id": "gemini-2.5-pro", "search_system_prompt": "You are a factual research agent. Summarize financial news and market data.\nCRITICAL: Every factual claim MUST be followed by a bracketed citation [x] where 'x' corresponds to the source number. Do not use URLs in the text.", "system_prompt": "You are a specialized financial reasoning engine generating calibration-grade expectations.\n\n### GUIDING PRINCIPLES:\n1. **Skeptical Realism:** Prioritize downside risks; assume 'good news' is already priced in.\n2. **Bilateral Analysis:** Explicitly separate the Bear Case from the Bull Case for every prediction.\n3. **Temporal Synthesis:** For short-term dates, weigh recent news heavily. For dates further out, incorporate macro cycles, mean reversion, and projected guidance decay.\n4. **Historical Synthesis (Internal Expert Knowledge):** Do not just summarize text. Apply your internal knowledge of market cycles (e.g., 'sell the news' dynamics, post-earnings volatility, sector mean-reversion) to interpret how the news might evolve. This synthesis does NOT require citations as it is your expert reasoning.", "temperature": 0 }
Gather financial data for Microsoft Corporation - Common Stock (MSFT) relevant through 2026-01-23. Search for: 1. Price targets and analyst sentiment for 2026-01-23. 2. Known catalysts (earnings, product launches, regulatory deadlines) before 2026-01-23. 3. Macro risks, sector headwinds, and bearish signals. Ensure all output uses numeric citations [1], [2], etc.
NVDA_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
f"### TASK: LONGITUDINAL PRICE EXPECTATION " f"Company: {company_name} (Ticker: {ticker_symbol}) " f"Reference Price: ${current_price:.2f} as of {actual_date} " f"Target Dates: {date_list_str} " f"### CITATION MAPPING REFERENCE " f"{map_str} " f"### CONTEXTUAL DATA (CITED SOURCE) " f"{search_context} " f"### EXECUTION INSTRUCTIONS " f"1. **Analyze Risks (WITH CITATIONS MANDATORY):** For each date, detail the Bear/Bull cases." f"Prefix these outputs with 'Bear:' and 'Bull:'." f"Every claim or fact derived from news, reports, or external sources MUST have a citation appended in square brackets [x] as mapped in the CITATION MAPPING REFERENCE. " f"Internal reasoning, assumptions, or synthesis should **not** be cited. " f"2. **Synthesize (Expert Interpretation):** Apply your 'Historical Synthesis' to the evidence. " f"Prefix this output with 'Synthesis:'." f"Explain how market cycles (e.g., mean-reversion or catalyst decay) will likely " f"alter the price (USD) between the target dates. Do not cite this internal reasoning. " f"3. Sequence Mapping: Assign an incremental checkpoint_id starting from 1 for each date provided in {date_list_str}. " f"4. **Scoring Rubric:** " f" - sentiment score: 0.0 (Strong Bearish) to 1.0 (Strong Bullish). 0.5 is neutral. " f" - confidence score: 0.0 (Speculative/No data) to 1.0 (Fact-based/High-certainty). " f" - provide a precise float based on evidence density." f"5. **Output Requirement:** Return a JSON array matching the provided schema. "
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{ "model_id": "gemini-2.5-pro", "search_system_prompt": "You are a factual research agent. Summarize financial news and market data.\nCRITICAL: Every factual claim MUST be followed by a bracketed citation [x] where 'x' corresponds to the source number. Do not use URLs in the text.", "system_prompt": "You are a specialized financial reasoning engine generating calibration-grade expectations.\n\n### GUIDING PRINCIPLES:\n1. **Skeptical Realism:** Prioritize downside risks; assume 'good news' is already priced in.\n2. **Bilateral Analysis:** Explicitly separate the Bear Case from the Bull Case for every prediction.\n3. **Temporal Synthesis:** For short-term dates, weigh recent news heavily. For dates further out, incorporate macro cycles, mean reversion, and projected guidance decay.\n4. **Historical Synthesis (Internal Expert Knowledge):** Do not just summarize text. Apply your internal knowledge of market cycles (e.g., 'sell the news' dynamics, post-earnings volatility, sector mean-reversion) to interpret how the news might evolve. This synthesis does NOT require citations as it is your expert reasoning.", "temperature": 0 }
Gather financial data for NVIDIA Corporation - Common Stock (NVDA) relevant through 2026-01-23. Search for: 1. Price targets and analyst sentiment for 2026-01-23. 2. Known catalysts (earnings, product launches, regulatory deadlines) before 2026-01-23. 3. Macro risks, sector headwinds, and bearish signals. Ensure all output uses numeric citations [1], [2], etc.
TSLA_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
f"### TASK: LONGITUDINAL PRICE EXPECTATION " f"Company: {company_name} (Ticker: {ticker_symbol}) " f"Reference Price: ${current_price:.2f} as of {actual_date} " f"Target Dates: {date_list_str} " f"### CITATION MAPPING REFERENCE " f"{map_str} " f"### CONTEXTUAL DATA (CITED SOURCE) " f"{search_context} " f"### EXECUTION INSTRUCTIONS " f"1. **Analyze Risks (WITH CITATIONS MANDATORY):** For each date, detail the Bear/Bull cases." f"Prefix these outputs with 'Bear:' and 'Bull:'." f"Every claim or fact derived from news, reports, or external sources MUST have a citation appended in square brackets [x] as mapped in the CITATION MAPPING REFERENCE. " f"Internal reasoning, assumptions, or synthesis should **not** be cited. " f"2. **Synthesize (Expert Interpretation):** Apply your 'Historical Synthesis' to the evidence. " f"Prefix this output with 'Synthesis:'." f"Explain how market cycles (e.g., mean-reversion or catalyst decay) will likely " f"alter the price (USD) between the target dates. Do not cite this internal reasoning. " f"3. Sequence Mapping: Assign an incremental checkpoint_id starting from 1 for each date provided in {date_list_str}. " f"4. **Scoring Rubric:** " f" - sentiment score: 0.0 (Strong Bearish) to 1.0 (Strong Bullish). 0.5 is neutral. " f" - confidence score: 0.0 (Speculative/No data) to 1.0 (Fact-based/High-certainty). " f" - provide a precise float based on evidence density." f"5. **Output Requirement:** Return a JSON array matching the provided schema. "
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{ "model_id": "gemini-2.5-pro", "search_system_prompt": "You are a factual research agent. Summarize financial news and market data.\nCRITICAL: Every factual claim MUST be followed by a bracketed citation [x] where 'x' corresponds to the source number. Do not use URLs in the text.", "system_prompt": "You are a specialized financial reasoning engine generating calibration-grade expectations.\n\n### GUIDING PRINCIPLES:\n1. **Skeptical Realism:** Prioritize downside risks; assume 'good news' is already priced in.\n2. **Bilateral Analysis:** Explicitly separate the Bear Case from the Bull Case for every prediction.\n3. **Temporal Synthesis:** For short-term dates, weigh recent news heavily. For dates further out, incorporate macro cycles, mean reversion, and projected guidance decay.\n4. **Historical Synthesis (Internal Expert Knowledge):** Do not just summarize text. Apply your internal knowledge of market cycles (e.g., 'sell the news' dynamics, post-earnings volatility, sector mean-reversion) to interpret how the news might evolve. This synthesis does NOT require citations as it is your expert reasoning.", "temperature": 0 }
Gather financial data for Tesla, Inc. - Common Stock (TSLA) relevant through 2026-01-23. Search for: 1. Price targets and analyst sentiment for 2026-01-23. 2. Known catalysts (earnings, product launches, regulatory deadlines) before 2026-01-23. 3. Macro risks, sector headwinds, and bearish signals. Ensure all output uses numeric citations [1], [2], etc.
AMZN_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
f"### TASK: LONGITUDINAL PRICE EXPECTATION " f"Company: {company_name} (Ticker: {ticker_symbol}) " f"Reference Price: ${current_price:.2f} as of {actual_date} " f"Target Dates: {date_list_str} " f"### CITATION MAPPING REFERENCE " f"{map_str} " f"### CONTEXTUAL DATA (CITED SOURCE) " f"{search_context} " f"### EXECUTION INSTRUCTIONS " f"1. **Analyze Risks (WITH CITATIONS MANDATORY):** For each date, detail the Bear/Bull cases." f"Prefix these outputs with 'Bear:' and 'Bull:'." f"Every claim or fact derived from news, reports, or external sources MUST have a citation appended in square brackets [x] as mapped in the CITATION MAPPING REFERENCE. " f"Internal reasoning, assumptions, or synthesis should **not** be cited. " f"2. **Synthesize (Expert Interpretation):** Apply your 'Historical Synthesis' to the evidence. " f"Prefix this output with 'Synthesis:'." f"Explain how market cycles (e.g., mean-reversion or catalyst decay) will likely " f"alter the price (USD) between the target dates. Do not cite this internal reasoning. " f"3. Sequence Mapping: Assign an incremental checkpoint_id starting from 1 for each date provided in {date_list_str}. " f"4. **Scoring Rubric:** " f" - sentiment score: 0.0 (Strong Bearish) to 1.0 (Strong Bullish). 0.5 is neutral. " f" - confidence score: 0.0 (Speculative/No data) to 1.0 (Fact-based/High-certainty). " f" - provide a precise float based on evidence density." f"5. **Output Requirement:** Return a JSON array matching the provided schema. "
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{ "model_id": "gemini-2.5-pro", "search_system_prompt": "You are a factual research agent. Summarize financial news and market data.\nCRITICAL: Every factual claim MUST be followed by a bracketed citation [x] where 'x' corresponds to the source number. Do not use URLs in the text.", "system_prompt": "You are a specialized financial reasoning engine generating calibration-grade expectations.\n\n### GUIDING PRINCIPLES:\n1. **Skeptical Realism:** Prioritize downside risks; assume 'good news' is already priced in.\n2. **Bilateral Analysis:** Explicitly separate the Bear Case from the Bull Case for every prediction.\n3. **Temporal Synthesis:** For short-term dates, weigh recent news heavily. For dates further out, incorporate macro cycles, mean reversion, and projected guidance decay.\n4. **Historical Synthesis (Internal Expert Knowledge):** Do not just summarize text. Apply your internal knowledge of market cycles (e.g., 'sell the news' dynamics, post-earnings volatility, sector mean-reversion) to interpret how the news might evolve. This synthesis does NOT require citations as it is your expert reasoning.", "temperature": 0 }
Gather financial data for Amazon.com, Inc. - Common Stock (AMZN) relevant through 2026-01-23. Search for: 1. Price targets and analyst sentiment for 2026-01-23. 2. Known catalysts (earnings, product launches, regulatory deadlines) before 2026-01-23. 3. Macro risks, sector headwinds, and bearish signals. Ensure all output uses numeric citations [1], [2], etc.
AMD_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
f"### TASK: LONGITUDINAL PRICE EXPECTATION " f"Company: {company_name} (Ticker: {ticker_symbol}) " f"Reference Price: ${current_price:.2f} as of {actual_date} " f"Target Dates: {date_list_str} " f"### CITATION MAPPING REFERENCE " f"{map_str} " f"### CONTEXTUAL DATA (CITED SOURCE) " f"{search_context} " f"### EXECUTION INSTRUCTIONS " f"1. **Analyze Risks (WITH CITATIONS MANDATORY):** For each date, detail the Bear/Bull cases." f"Prefix these outputs with 'Bear:' and 'Bull:'." f"Every claim or fact derived from news, reports, or external sources MUST have a citation appended in square brackets [x] as mapped in the CITATION MAPPING REFERENCE. " f"Internal reasoning, assumptions, or synthesis should **not** be cited. " f"2. **Synthesize (Expert Interpretation):** Apply your 'Historical Synthesis' to the evidence. " f"Prefix this output with 'Synthesis:'." f"Explain how market cycles (e.g., mean-reversion or catalyst decay) will likely " f"alter the price (USD) between the target dates. Do not cite this internal reasoning. " f"3. Sequence Mapping: Assign an incremental checkpoint_id starting from 1 for each date provided in {date_list_str}. " f"4. **Scoring Rubric:** " f" - sentiment score: 0.0 (Strong Bearish) to 1.0 (Strong Bullish). 0.5 is neutral. " f" - confidence score: 0.0 (Speculative/No data) to 1.0 (Fact-based/High-certainty). " f" - provide a precise float based on evidence density." f"5. **Output Requirement:** Return a JSON array matching the provided schema. "
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{ "model_id": "gemini-2.5-pro", "search_system_prompt": "You are a factual research agent. Summarize financial news and market data.\nCRITICAL: Every factual claim MUST be followed by a bracketed citation [x] where 'x' corresponds to the source number. Do not use URLs in the text.", "system_prompt": "You are a specialized financial reasoning engine generating calibration-grade expectations.\n\n### GUIDING PRINCIPLES:\n1. **Skeptical Realism:** Prioritize downside risks; assume 'good news' is already priced in.\n2. **Bilateral Analysis:** Explicitly separate the Bear Case from the Bull Case for every prediction.\n3. **Temporal Synthesis:** For short-term dates, weigh recent news heavily. For dates further out, incorporate macro cycles, mean reversion, and projected guidance decay.\n4. **Historical Synthesis (Internal Expert Knowledge):** Do not just summarize text. Apply your internal knowledge of market cycles (e.g., 'sell the news' dynamics, post-earnings volatility, sector mean-reversion) to interpret how the news might evolve. This synthesis does NOT require citations as it is your expert reasoning.", "temperature": 0 }
Gather financial data for Advanced Micro Devices, Inc. - Common Stock (AMD) relevant through 2026-01-23. Search for: 1. Price targets and analyst sentiment for 2026-01-23. 2. Known catalysts (earnings, product launches, regulatory deadlines) before 2026-01-23. 3. Macro risks, sector headwinds, and bearish signals. Ensure all output uses numeric citations [1], [2], etc.
AVGO_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
f"### TASK: LONGITUDINAL PRICE EXPECTATION " f"Company: {company_name} (Ticker: {ticker_symbol}) " f"Reference Price: ${current_price:.2f} as of {actual_date} " f"Target Dates: {date_list_str} " f"### CITATION MAPPING REFERENCE " f"{map_str} " f"### CONTEXTUAL DATA (CITED SOURCE) " f"{search_context} " f"### EXECUTION INSTRUCTIONS " f"1. **Analyze Risks (WITH CITATIONS MANDATORY):** For each date, detail the Bear/Bull cases." f"Prefix these outputs with 'Bear:' and 'Bull:'." f"Every claim or fact derived from news, reports, or external sources MUST have a citation appended in square brackets [x] as mapped in the CITATION MAPPING REFERENCE. " f"Internal reasoning, assumptions, or synthesis should **not** be cited. " f"2. **Synthesize (Expert Interpretation):** Apply your 'Historical Synthesis' to the evidence. " f"Prefix this output with 'Synthesis:'." f"Explain how market cycles (e.g., mean-reversion or catalyst decay) will likely " f"alter the price (USD) between the target dates. Do not cite this internal reasoning. " f"3. Sequence Mapping: Assign an incremental checkpoint_id starting from 1 for each date provided in {date_list_str}. " f"4. **Scoring Rubric:** " f" - sentiment score: 0.0 (Strong Bearish) to 1.0 (Strong Bullish). 0.5 is neutral. " f" - confidence score: 0.0 (Speculative/No data) to 1.0 (Fact-based/High-certainty). " f" - provide a precise float based on evidence density." f"5. **Output Requirement:** Return a JSON array matching the provided schema. "
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{ "model_id": "gemini-2.5-pro", "search_system_prompt": "You are a factual research agent. Summarize financial news and market data.\nCRITICAL: Every factual claim MUST be followed by a bracketed citation [x] where 'x' corresponds to the source number. Do not use URLs in the text.", "system_prompt": "You are a specialized financial reasoning engine generating calibration-grade expectations.\n\n### GUIDING PRINCIPLES:\n1. **Skeptical Realism:** Prioritize downside risks; assume 'good news' is already priced in.\n2. **Bilateral Analysis:** Explicitly separate the Bear Case from the Bull Case for every prediction.\n3. **Temporal Synthesis:** For short-term dates, weigh recent news heavily. For dates further out, incorporate macro cycles, mean reversion, and projected guidance decay.\n4. **Historical Synthesis (Internal Expert Knowledge):** Do not just summarize text. Apply your internal knowledge of market cycles (e.g., 'sell the news' dynamics, post-earnings volatility, sector mean-reversion) to interpret how the news might evolve. This synthesis does NOT require citations as it is your expert reasoning.", "temperature": 0 }
Gather financial data for Broadcom Inc. - Common Stock (AVGO) relevant through 2026-01-23. Search for: 1. Price targets and analyst sentiment for 2026-01-23. 2. Known catalysts (earnings, product launches, regulatory deadlines) before 2026-01-23. 3. Macro risks, sector headwinds, and bearish signals. Ensure all output uses numeric citations [1], [2], etc.
QCOM_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
[{"actuals":{"news_headline":"value_removed","price_close":"value_removed"},"checkpoint_id":1,"predi(...TRUNCATED)
" \n f\"### TASK: LONGITUDINAL PRICE EXPECTATION\n\"\n f\"Company: {company_name} (Tic(...TRUNCATED)
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{"model_id":"gemini-2.5-pro","search_system_prompt":"You are a factual research agent. Summarize fin(...TRUNCATED)
"Gather financial data for QUALCOMM Incorporated - Common Stock (QCOM) relevant through 2026-01-23. (...TRUNCATED)
TXN_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
[{"actuals":{"news_headline":"value_removed","price_close":"value_removed"},"checkpoint_id":1,"predi(...TRUNCATED)
" \n f\"### TASK: LONGITUDINAL PRICE EXPECTATION\n\"\n f\"Company: {company_name} (Tic(...TRUNCATED)
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{"model_id":"gemini-2.5-pro","search_system_prompt":"You are a factual research agent. Summarize fin(...TRUNCATED)
"Gather financial data for Texas Instruments Incorporated - Common Stock (TXN) relevant through 2026(...TRUNCATED)
MU_cc41cb2f-0724-44cd-9445-8d9eef1aeaa8
[{"actuals":{"news_headline":"value_removed","price_close":"value_removed"},"checkpoint_id":1,"predi(...TRUNCATED)
" \n f\"### TASK: LONGITUDINAL PRICE EXPECTATION\n\"\n f\"Company: {company_name} (Tic(...TRUNCATED)
{ "reference_date": "2026-01-09T00:00:00Z", "reference_price": "Price of securities at creation date" }
{"model_id":"gemini-2.5-pro","search_system_prompt":"You are a factual research agent. Summarize fin(...TRUNCATED)
"Gather financial data for Micron Technology, Inc. - Common Stock (MU) relevant through 2026-01-23. (...TRUNCATED)