{"id":1133,"date":"2025-06-15T13:46:38","date_gmt":"2025-06-15T13:46:38","guid":{"rendered":"https:\/\/www.nemeslab.com\/?p=1133"},"modified":"2025-10-22T18:49:25","modified_gmt":"2025-10-22T18:49:25","slug":"making-sense-of-the-literature-deluge","status":"publish","type":"post","link":"https:\/\/www.nemeslab.com\/hu\/making-sense-of-the-literature-deluge\/","title":{"rendered":"Coping with the flood of new papers"},"content":{"rendered":"

We\u2019ve just released on GitHub<\/a> an improved version of the RSS feed searcher powering our group\u2019s “Daily Papers<\/a>” page. With so many literature tools around, like Google Scholar or various AI-powered platforms, you might think researchers are already covered. But there\u2019s still a big gap when it comes to following everything<\/strong> newly published in your research area.<\/p>\n\n\n\n

These days, scientific literature grows so rapidly that crucial papers easily slip through unnoticed, even with all the tools at our disposal. Decades ago, it was manageable to track all new articles from arXiv\u2019s cond-mat feed or selected journals, but today that’s nearly impossible without spending every waking hour reading. But, just because it’s hard doesn’t mean we can’t drink from the firehose. You just have to turn the flood into a trickle… or a managable stream of new papers.<\/p>\n\n\n\n

For the past five years or so, our group tackled this by filtering RSS feeds using the strength and versatility of regular expressions<\/a> to pick out relevant articles. Now, we\u2019ve upgraded this lightweight Python tool, with a ranking algorithm and fulltext summarization of arXiv preprints. It is available on GitHub.<\/p>\n\n\n\n

The tool fetches articles daily, filters them based on your specific interests (easily configured in YAML text files), and provides neat HTML summaries. Furthemore, it now integrates OpenAI\u2019s language models API to automatically summarize the selected preprints, saving even more of your time. If you’ve never used regular expressions before, ask your friendly LLM chatbot to cook one up for you based on your keywords.<\/p>\n\n\n\n

Check it out here:
\ud83d\udc49 paper firehose<\/a>, technical details in the readme on Github<\/p>\n\n\n\n

<\/p>","protected":false},"excerpt":{"rendered":"

We\u2019ve just released on GitHub an improved version of the RSS feed searcher powering our group\u2019s “Daily Papers” page. With so many literature tools around, like Google Scholar or various AI-powered platforms, you might think researchers are already covered. But there\u2019s still a big gap when it comes to following everything newly published in your […]<\/p>\n","protected":false},"author":1,"featured_media":1134,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"footnotes":""},"categories":[24],"tags":[41,43,44,42],"post_formats":[],"class_list":["post-1133","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-ai","tag-journals","tag-literature-search","tag-llm"],"guten_post_layout_featured_media_urls":{"full":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2.png",1229,586,false],"thumbnail":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-150x150.png",150,150,true],"medium":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-300x143.png",300,143,true],"medium_large":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-768x366.png",640,305,true],"large":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-1024x488.png",640,305,true],"1536x1536":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2.png",1229,586,false],"2048x2048":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2.png",1229,586,false],"trp-custom-language-flag":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-18x9.png",18,9,true],"guten_post_layout_landscape_large":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-1200x586.png",1200,586,true],"guten_post_layout_portrait_large":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-1200x586.png",1200,586,true],"guten_post_layout_square_large":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-1200x586.png",1200,586,true],"guten_post_layout_landscape":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-600x400.png",600,400,true],"guten_post_layout_portrait":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-600x586.png",600,586,true],"guten_post_layout_square":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-600x586.png",600,586,true],"sciencexlite-blog-thumb":["https:\/\/www.nemeslab.com\/wp-content\/uploads\/2025\/06\/firehose-meme-2-100x80.png",100,80,true]},"_links":{"self":[{"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/posts\/1133","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/comments?post=1133"}],"version-history":[{"count":6,"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/posts\/1133\/revisions"}],"predecessor-version":[{"id":1202,"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/posts\/1133\/revisions\/1202"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/media\/1134"}],"wp:attachment":[{"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/media?parent=1133"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/categories?post=1133"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/tags?post=1133"},{"taxonomy":"post_format","embeddable":true,"href":"https:\/\/www.nemeslab.com\/hu\/wp-json\/wp\/v2\/post_formats?post=1133"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}