<?xml version='1.0' encoding='utf-8'?>
<?xml-stylesheet type="text/xsl" href="/v2/static/oai2.xsl"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-10-15T13:50:52Z</responseDate>
  <request identifier="oai:figshare.com:article/34035683" metadataPrefix="oai_dc" verb="GetRecord">https://api.figshare.com/v2/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:figshare.com:article/34035683</identifier>
        <datestamp>2026-09-30T17:36:56Z</datestamp>
        <setSpec>category_7</setSpec>
        <setSpec>category_45</setSpec>
        <setSpec>category_734</setSpec>
        <setSpec>category_931</setSpec>
        <setSpec>category_106</setSpec>
        <setSpec>category_132</setSpec>
        <setSpec>portal_5</setSpec>
        <setSpec>item_type_3</setSpec>
        <setSpec>month_year_09_2026</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"  xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>&lt;p&gt;Trading performance (January 2022–December 2023, 498 days). returns net of transaction costs. the S&amp;P 500 compound annualized return is computed from total return index data:  in 2022 and +26.3% in 2023, yielding  (Source: S&amp;P Dow Jones Indices). see Experimental Setup for complete protocol details.&lt;/p&gt;</dc:title>
          <dc:creator>Hong He (221185)</dc:creator>
          <dc:creator>Xinhai Li (191514)</dc:creator>
          <dc:subject>Medicine</dc:subject>
          <dc:subject>Sociology</dc:subject>
          <dc:subject>Biological Sciences not elsewhere classified</dc:subject>
          <dc:subject>Information Systems not elsewhere classified</dc:subject>
          <dc:subject>Science Policy</dc:subject>
          <dc:subject>Infectious Diseases</dc:subject>
          <dc:subject>three key innovations</dc:subject>
          <dc:subject>strictly chronological train</dc:subject>
          <dc:subject>shape investor behavior</dc:subject>
          <dc:subject>scale temporal fusion</dc:subject>
          <dc:subject>relevant historical patterns</dc:subject>
          <dc:subject>random walk benchmarks</dc:subject>
          <dc:subject>effect size analysis</dc:subject>
          <dc:subject>bootstrap confidence intervals</dc:subject>
          <dc:subject>aware temporal alignment</dc:subject>
          <dc:subject>article without using</dc:subject>
          <dc:subject>ablation studies reveal</dc:subject>
          <dc:subject>2022 &amp;# 8211</dc:subject>
          <dc:subject>2013 &amp;# 8211</dc:subject>
          <dc:subject>time fusion architecture</dc:subject>
          <dc:subject>preventing information leakage</dc:subject>
          <dc:subject>future market information</dc:subject>
          <dc:subject>price autocorrelation vanishes</dc:subject>
          <dc:subject>scale financial news</dc:subject>
          <dc:subject>using large models</dc:subject>
          <dc:subject>time series forecasting</dc:subject>
          <dc:subject>financial news</dc:subject>
          <dc:subject>series models</dc:subject>
          <dc:subject>advanced time</dc:subject>
          <dc:subject>market reaction</dc:subject>
          <dc:subject>level forecasting</dc:subject>
          <dc:subject>financial narratives</dc:subject>
          <dc:subject>series prediction</dc:subject>
          <dc:subject>series data</dc:subject>
          <dc:subject>work demonstrates</dc:subject>
          <dc:subject>text publication</dc:subject>
          <dc:subject>testing ).</dc:subject>
          <dc:subject>test splits</dc:subject>
          <dc:subject>stfa ),</dc:subject>
          <dc:subject>sentiment annotations</dc:subject>
          <dc:subject>semantic information</dc:subject>
          <dc:subject>return prediction</dc:subject>
          <dc:subject>predictive accuracy</dc:subject>
          <dc:subject>multimodal sources</dc:subject>
          <dc:subject>multimodal baselines</dc:subject>
          <dc:subject>liquidity stocks</dc:subject>
          <dc:subject>generated independently</dc:subject>
          <dc:subject>experiments demonstrate</dc:subject>
          <dc:subject>deep learning</dc:subject>
          <dc:subject>based sentiment</dc:subject>
          <dc:subject>balance accuracy</dc:subject>
          <dc:description>&lt;p&gt;Trading performance (January 2022–December 2023, 498 days). returns net of transaction costs. the S&amp;P 500 compound annualized return is computed from total return index data:  in 2022 and +26.3% in 2023, yielding  (Source: S&amp;P Dow Jones Indices). see Experimental Setup for complete protocol details.&lt;/p&gt;</dc:description>
          <dc:date>2026-09-30T17:36:43Z</dc:date>
          <dc:type>Dataset</dc:type>
          <dc:type>Dataset</dc:type>
          <dc:identifier>10.1371/journal.pone.0356139.t004</dc:identifier>
          <dc:relation>https://figshare.com/articles/dataset/_p_Trading_performance_January_2022_December_2023_498_days_returns_net_of_transaction_costs_the_S_P_500_compound_annualized_return_is_computed_from_total_return_index_data_in_2022_and_26_3_in_2023_yielding_Source_S_P_Dow_Jones_Indices_see_E/34035683</dc:relation>
          <dc:rights>CC BY 4.0</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
