{% extends "base.html" %}

{% block title %}
{% trans website_name = super() %}About {{ website_name }}{% endtrans %}
{% endblock %}

{% block main %}
<h1>{% trans %}About Internet Archive Scholar{% endtrans %}</h1>
<p><i>
  {% trans %}See also: <a href="{{ lang_prefix }}/help">User Guide</a> which lists some bugs and known issues{% endtrans %}
</i>

<a name="howitworks"></a>
<h3>{% trans %}How It Works{% endtrans %}</h3>

<p>{% trans %}Content in this search index comes in one of three forms:{% endtrans %}

<ul>
  <li>{% trans %}<b>public web content</b> as preserved in <a href="https://web.archive.org">The Wayback Machine</a> and <a href="https://archive-it.org">Archive-It</a> partner collections{% endtrans %}
  <li>{% trans %}<b>digitized print materials</b> from paper and microform collections{% endtrans %}
  <li>{% trans %}<b>general materials</b> from <a href="https://archive.org">archive.org collections</a>, including collaborations with partners{% endtrans %}
</ul>

<p>{% trans url="https://www.youtube.com/watch?v=PARqfbYIdXQ" %}This <a href="{{ url }}">2019 FORCE11 conference presentation</a> gives an overview of the technical infrastructure and goals of the project overall.{% endtrans %}

<a name="sources"></a>
<h3>{% trans %}Content Sources{% endtrans %}</h3>

<p>{% trans %}Metadata comes from <a href="https://fatcat.wiki">fatcat.wiki</a>, an open
user-editable catalog of scholarly work. It should be possible to track and
attribute the provenance of content and metadata in all cases. Please
<a href="#contact">contact us</a> if you have questions.{% endtrans %}

<a name="tdm"></a>
<h3>{% trans %}Text and Data Mining{% endtrans %}</h3>

<p>{% trans %}We intend to provide researcher access to the full corpus for text and data
mining purposes. Derived datasets may also be posted publicly for analysis, for
example a citation graph or N-gram frequencies by year. If you are interested
or would like to see specific datasets made available, please contact us.{% endtrans %}

<p>{% trans %}Currently snapshots of the full fatcat metadata corpus and upstream metadata sources are uploaded periodically to the <a href="https://archive.org/details/ia_biblio_metadata">Bulk Bibliographic Metadata</a> collection on archive.org.{% endtrans %}

{% trans %}Read more in <a href="https://guide.fatcat.wiki/bulk_exports.html">the Fatcat Guide</a>.{% endtrans %}

<a name="contact"></a>
<h3>{% trans %}Contact Information{% endtrans %}</h3>

<p>
{% trans url="https://archive.org/about/contact.php" %}The organizational contact information for the Internet Archive is listed at <a href="{{ url }}">{{ url }}</a>.{% endtrans %}

{% trans email="webservices@archive.org" %}Queries about this search service and the fatcat catalog can be directed to <a href="mailto:{{ email }}">{{ email }}</a>.{% endtrans %}

{% trans url="https://gitter.im/internetarchive/fatcat" %}There is a public chat channel at <a href="{{ url }}">{{ url }}</a>.{% endtrans %}


{% endblock %}