{"id":9283,"date":"2025-10-28T16:36:34","date_gmt":"2025-10-28T21:36:34","guid":{"rendered":"https:\/\/scottaaronson.blog\/?p=9283"},"modified":"2025-10-28T16:36:34","modified_gmt":"2025-10-28T21:36:34","slug":"an-experimental-program-for-ai-powered-feedback-at-stoc-guest-post-from-david-woodruff","status":"publish","type":"post","link":"https:\/\/scottaaronson.blog\/?p=9283","title":{"rendered":"An Experimental Program for AI-Powered Feedback at\u00a0STOC: Guest Post from David Woodruff"},"content":{"rendered":"\n<p>This year for\u00a0<a href=\"https:\/\/acm-stoc.org\/stoc2026\/\">STOC<\/a>, we decided to run an experiment to explore the use of Large Language Models in the theoretical computer science community, and we&#8217;re inviting the entire community to participate.<\/p>\n\n\n\n<p>We\u2014a team from the&nbsp;STOC&nbsp;PC\u2014are offering authors the chance to get automated pre-submission feedback from an advanced, Gemini-based LLM tool that&#8217;s been optimized for checking mathematical rigor. The goal is simple: to provide constructive suggestions and, potentially, help find technical mistakes&nbsp;<em>before<\/em>&nbsp;the paper goes to the PC. Some important points:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>This is 100% optional and opt-in.<\/strong><strong><br><\/strong><\/li>\n\n\n\n<li><strong>The reviews generated WILL NOT be passed on to the PC.<\/strong> They are for your eyes only.<br><\/li>\n\n\n\n<li><strong>Data Privacy is Our #1 Commitment.<\/strong> We commit that your submitted paper will <strong>NOT be logged,<\/strong> stored, or used for training.<br><\/li>\n\n\n\n<li>Please do not publicly share these reviews without contacting the organizing team first.<\/li>\n<\/ul>\n\n\n\n<p>This tool is specifically optimized for checking a paper&#8217;s&nbsp;<em>mathematical rigor<\/em>. It&#8217;s a hopefully useful way to check the correctness of your arguments. Note that sometimes it does not possess external, area-specific knowledge (like &#8220;folklore&#8221; results). This means it may flag sections that rely on unstated assumptions, or it might find simple omissions or typos.<\/p>\n\n\n\n<p>Nevertheless, we hope you&#8217;ll find this feedback valuable for improving the paper&#8217;s overall clarity and completeness.<\/p>\n\n\n\n<p>If you&#8217;re submitting to&nbsp;STOC, we encourage you to opt-in. You&#8217;ll get (we hope) useful feedback, and you&#8217;ll be providing invaluable data as we assess this tool for future theory conferences.<\/p>\n\n\n\n<p>The deadline to opt-in on the HotCRP submission form is&nbsp;<strong>November 1 (5pm EST)<\/strong>.<\/p>\n\n\n\n<p>You can read the full &#8220;Terms of Participation&#8221; (including all privacy and confidentiality details) at the link below.<\/p>\n\n\n\n<p>This experiment is being run by PC members David Woodruff (CMU) and Rajesh Jayaram (Google), as well as Vincent Cohen-Addad (Google) and Jon Schneider (Google).<\/p>\n\n\n\n<p>We&#8217;re excited to offer this resource to the community.<\/p>\n\n\n\n<p>Please see the\u00a0STOC\u00a0Call for Papers <a href=\"https:\/\/acm-stoc.org\/stoc2026\/stoc2026-cfp.html\">here<\/a> and specific details on the experiment <a href=\"https:\/\/acm-stoc.org\/stoc2026\/stoc2026-LLM_feedback.html\">here<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This year for\u00a0STOC, we decided to run an experiment to explore the use of Large Language Models in the theoretical computer science community, and we&#8217;re inviting the entire community to participate. We\u2014a team from the&nbsp;STOC&nbsp;PC\u2014are offering authors the chance to get automated pre-submission feedback from an advanced, Gemini-based LLM tool that&#8217;s been optimized for checking [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"advanced_seo_description":"","jetpack_seo_html_title":"","jetpack_seo_noindex":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"_wpas_customize_per_network":false},"categories":[31,5],"tags":[],"class_list":["post-9283","post","type-post","status-publish","format-standard","hentry","category-announcements","category-complexity"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=\/wp\/v2\/posts\/9283","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=9283"}],"version-history":[{"count":1,"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=\/wp\/v2\/posts\/9283\/revisions"}],"predecessor-version":[{"id":9284,"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=\/wp\/v2\/posts\/9283\/revisions\/9284"}],"wp:attachment":[{"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=9283"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=9283"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/scottaaronson.blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=9283"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}