ug. The problem with XML::Simple is that it doesn't return a consistent format unless you disable everything it considers an advantage. It's no longer using XML::LibXML, and it's much faster.

For good measure, I used Text::CSV_XS for output.

use strict;
use warnings;

use Text::CSV_XS qw( );
use XML::LibXML  qw( );

my $csv = Text::CSV_XS->new({ binary => 1, eol => $/ });

my $parser = XML::LibXML->new();
my $doc = $parser->parse_file('infile.xml');
my $root = $doc->documentElement();

for my $doc_node ( $root->findnodes('/results/document') ) {
    my @doc_fields = map $doc_node->getAttribute($_),
        qw( datetime id sourcecategory schemeversion );

    my @rec_nodes = $doc_node->findnodes('record');
    if (!@rec_nodes) {
        $csv->print(*STDOUT, \@doc_fields);
        next;
    }

    for my $rec_node ( @rec_nodes ) {
        $csv->print(*STDOUT, [
            @doc_fields,
            map $rec_node->findvalue("$_/text()"),
                qw( sentence-number data-class group )
        ]);
    }
}
[download]