Separate italic title content from publisher status notices

paper_atlas/collectors/aamas2026.py

@@ -84,13 +84,15 @@ def parse_contents(html, evidence):
         if page in seen_pages:
             raise ValueError('Repeated publisher page ID')
         seen_pages.add(page)
-        title = clean(one([n for n in node.walk() if n.tag == 'strong'], 'paper title').text())
+        title_node = one([n for n in node.walk() if n.tag == 'strong'], 'paper title')
+        title = clean(title_node.text())
         if not title:
             raise ValueError('Empty paper title')
         authors, affiliations = parse_authors(node)
         link = one([n for n in node.walk() if n.tag == 'a' and 'href' in n.attrs], 'paper link')
         href = link.attrs['href']
-        retractions = [clean(n.text()) for n in link.walk() if n.tag == 'i']
+        title_nodes = {id(n) for n in title_node.walk()}
+        retractions = [clean(n.text()) for n in link.walk() if n.tag == 'i' and id(n) not in title_nodes]
         heading, publication_format, track, _ = SECTIONS[section]
         counts[section] += 1
         metadata = {'publisher_page': page, 'section_url': URL, 'section_anchor': section,