# config/sources.d/16-universities-research.yaml — universities, research institutes & national labs, # journals / publishers / preprint servers / scholarly infrastructure, funders & science policy. # Authored 2026-09-08. Every sensor below was fetched and parsed with the registry validator; organizations # whose feeds are blocked (403/202 bot management) or simply absent are kept as discover-only entities with a # `notes:` explanation so nobody re-probes them blindly. Extends: arxiv (API Atom feeds), nasa (JPL), esa # (ESA/Webb, ESA/Hubble). sources: # ───────────────────────── extensions of founding-file sources ───────────────────────── - id: arxiv extend: true notes: "arXiv API (export.arxiv.org) — Atom, 50 newest per category; the API asks for ≥ 3–4 s between requests, one sensor per category keeps it polite." sensors: - { name: cs.AI api feed, url: "https://export.arxiv.org/api/query?search_query=cat:cs.AI&sortBy=submittedDate&sortOrder=descending&max_results=50", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } } - { name: cs.LG api feed, url: "https://export.arxiv.org/api/query?search_query=cat:cs.LG&sortBy=submittedDate&sortOrder=descending&max_results=50", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } } - { name: cs.CL api feed, url: "https://export.arxiv.org/api/query?search_query=cat:cs.CL&sortBy=submittedDate&sortOrder=descending&max_results=50", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } } - { name: cs.CR api feed, url: "https://export.arxiv.org/api/query?search_query=cat:cs.CR&sortBy=submittedDate&sortOrder=descending&max_results=50", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } } - { name: econ.EM api feed, url: "https://export.arxiv.org/api/query?search_query=cat:econ.EM&sortBy=submittedDate&sortOrder=descending&max_results=50", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } } - { name: q-fin.ST api feed, url: "https://export.arxiv.org/api/query?search_query=cat:q-fin.ST&sortBy=submittedDate&sortOrder=descending&max_results=50", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } } - id: nasa extend: true aliases: [jpl, jet propulsion laboratory] products: - { name: Jet Propulsion Laboratory, type: service, aliases: [jpl] } sensors: - { name: jpl news feed, url: "https://www.jpl.nasa.gov/feeds/news/", type: RSS, connector: rss, tier: B } - { name: science news feed, url: "https://science.nasa.gov/feed/", type: RSS, connector: rss, tier: B } - id: esa extend: true aliases: [esa webb, esa hubble] sensors: - { name: esa webb news feed, url: "https://esawebb.org/news/feed/", type: RSS, connector: rss, tier: B } - { name: esa hubble news feed, url: "https://esahubble.org/news/feed/", type: RSS, connector: rss, tier: B } # ───────────────────────── universities · United Kingdom & Europe ───────────────────────── - id: cambridge name: University of Cambridge domain: cam.ac.uk categories: [education, research] tier: B weight: 1.2 aliases: [cambridge university] discover: { rss: true, sitemap: false } sensors: - { name: news feed, url: "https://www.cam.ac.uk/news/feed", type: RSS, connector: rss, tier: B } - id: oxford name: University of Oxford domain: ox.ac.uk categories: [education, research] tier: B weight: 1.2 aliases: [oxford university] discover: { rss: false, sitemap: false } notes: "www.ox.ac.uk answers 403 to every non-browser and browser fetch from our network (bot management) — /rss/news and sitemaps unreachable; entity only." - id: imperial-college name: Imperial College London domain: imperial.ac.uk categories: [education, research] tier: B aliases: [imperial] discover: { rss: true, sitemap: false } notes: "No RSS on /news (historic /news/rss/ and /news/feed/ are 404); the only sitemap is the 17 k-URL corporate one — entity only until a feed reappears." - id: ucl name: University College London domain: ucl.ac.uk categories: [education, research] tier: B aliases: [university college london] discover: { rss: false, sitemap: false } notes: "403 on feeds and news sitemap (bot management); entity only." - id: edinburgh name: University of Edinburgh domain: ed.ac.uk categories: [education, research] tier: B aliases: [edinburgh university] discover: { rss: true, sitemap: false } notes: "News hub has no RSS/Atom and no news sitemap (2026-09); entity only." - id: eth-zurich name: ETH Zurich domain: ethz.ch categories: [education, research] tier: B weight: 1.2 aliases: [eth zürich, eth] discover: { rss: false } sensors: - { name: eth news feed, url: "https://ethz.ch/en/news-und-veranstaltungen/eth-news/news/_jcr_content.feed.html", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } } - id: epfl name: EPFL domain: epfl.ch categories: [education, research] tier: B weight: 1.1 aliases: [école polytechnique fédérale de lausanne] discover: { rss: false } sensors: - { name: mediacom news feed, url: "https://actu.epfl.ch/feeds/rss/mediacom/en/", type: RSS, connector: rss, tier: B } - id: tu-munich name: Technical University of Munich domain: tum.de categories: [education, research] tier: B aliases: [tum, technische universität münchen] discover: { rss: false } sensors: - { name: news feed, url: "https://www.tum.de/en/news.rss", type: ATOM, connector: rss, tier: B } - id: lmu-munich name: LMU Munich domain: lmu.de categories: [education, research] tier: B aliases: [ludwig-maximilians-universität, lmu] discover: { rss: false } sensors: - { name: newsroom feed, url: "https://www.lmu.de/en/newsroom/rss-feed-news.xml", type: RSS, connector: rss, tier: B } - id: sorbonne-universite name: Sorbonne Université domain: sorbonne-universite.fr categories: [education, research] tier: B aliases: [sorbonne] discover: { rss: false } sensors: - { name: actualités feed, url: "https://www.sorbonne-universite.fr/rss.xml", type: RSS, connector: rss, tier: B } - id: psl name: Université PSL domain: psl.eu categories: [education, research] tier: B aliases: [paris sciences et lettres] discover: { rss: false } sensors: - { name: actualités feed, url: "https://psl.eu/rss.xml", type: RSS, connector: rss, tier: B } - id: ku-leuven name: KU Leuven domain: kuleuven.be categories: [education, research] tier: B aliases: [leuven] discover: { rss: false } sensors: - { name: news feed, url: "https://nieuws.kuleuven.be/en/content/rss", type: ATOM, connector: rss, tier: B } - id: tu-delft name: TU Delft domain: tudelft.nl categories: [education, research] tier: B aliases: [delft university of technology] discover: { rss: true, sitemap: false } notes: "No RSS on /en/news (2026-09); generic 217-child sitemap only. Entity only." - id: university-of-amsterdam name: University of Amsterdam domain: uva.nl categories: [education, research] tier: B aliases: [uva, universiteit van amsterdam] discover: { rss: false } sensors: - { name: news sitemap, url: "https://www.uva.nl/news-sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 500, maxChildren: 6 } } - id: university-of-copenhagen name: University of Copenhagen domain: ku.dk categories: [education, research] tier: B aliases: [københavns universitet, ucph] discover: { rss: false } sensors: - { name: all news feed, url: "https://news.ku.dk/all_news/?get_rss=1", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: karolinska name: Karolinska Institutet domain: ki.se categories: [education, research, health] tier: B aliases: [karolinska institute] discover: { rss: false } sensors: - { name: latest news feed, url: "https://nyheter.ki.se/latest-news/rss.xml", type: RSS, connector: rss, tier: B } - id: uppsala name: Uppsala University domain: uu.se categories: [education, research] tier: B aliases: [uppsala universitet] discover: { rss: true, sitemap: false } notes: "No RSS on /en/news and no news sitemap (2026-09); entity only." - id: university-of-helsinki name: University of Helsinki domain: helsinki.fi categories: [education, research] tier: B aliases: [helsingin yliopisto] discover: { rss: false } sensors: - { name: news feed, url: "https://www.helsinki.fi/en/rss.xml", type: RSS, connector: rss, tier: B } # ───────────────────────── universities · Asia-Pacific ───────────────────────── - id: university-of-tokyo name: University of Tokyo domain: u-tokyo.ac.jp categories: [education, research] tier: B weight: 1.1 aliases: [utokyo, todai] discover: { rss: true, sitemap: false } notes: "No RSS/Atom on the EN news hub, no sitemap (2026-09); entity only." - id: kyoto-university name: Kyoto University domain: kyoto-u.ac.jp categories: [education, research] tier: B aliases: [kyodai] discover: { rss: false } sensors: - { name: news feed, url: "https://www.kyoto-u.ac.jp/en/rss.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: nus name: National University of Singapore domain: nus.edu.sg categories: [education, research] tier: B weight: 1.1 aliases: [nus singapore] discover: { rss: false } sensors: - { name: news feed, url: "https://news.nus.edu.sg/feed/", type: RSS, connector: rss, tier: B } - id: ntu-singapore name: Nanyang Technological University domain: ntu.edu.sg categories: [education, research] tier: B aliases: [ntu] discover: { rss: true, sitemap: false } notes: "News hub is client-rendered without RSS; no sitemap (2026-09). Entity only." - id: tsinghua name: Tsinghua University domain: tsinghua.edu.cn categories: [education, research] tier: B weight: 1.1 discover: { rss: true, sitemap: false } notes: "No feed on the EN site (2026-09); entity only." - id: peking-university name: Peking University domain: pku.edu.cn categories: [education, research] tier: B weight: 1.1 aliases: [pku, beida] discover: { rss: true, sitemap: false } notes: "No feed on english.pku.edu.cn (2026-09); entity only." - id: hku name: University of Hong Kong domain: hku.hk categories: [education, research] tier: B aliases: [hong kong university] discover: { rss: true, sitemap: false } notes: "Press-release pages have no RSS (rss.hku.hk is the Research Services office, not a feed). Entity only." - id: kaist name: KAIST domain: kaist.ac.kr categories: [education, research] tier: B aliases: [korea advanced institute of science and technology] discover: { rss: false } sensors: - { name: news sitemap, url: "https://news.kaist.ac.kr/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 1500, maxChildren: 4 } } - id: seoul-national-university name: Seoul National University domain: snu.ac.kr categories: [education, research] tier: B aliases: [snu] discover: { rss: true, sitemap: false } notes: "No feed on en.snu.ac.kr (2026-09); entity only." - id: iit-bombay name: IIT Bombay domain: iitb.ac.in categories: [education, research] tier: B aliases: [indian institute of technology bombay] discover: { rss: false } sensors: - { name: news feed, url: "https://www.iitb.ac.in/rss.xml", type: RSS, connector: rss, tier: B } - id: university-of-melbourne name: University of Melbourne domain: unimelb.edu.au categories: [education, research] tier: B aliases: [unimelb, melbourne university] discover: { rss: false, sitemap: false } notes: "403 on newsroom feeds/sitemaps and on pursuit.unimelb.edu.au (bot management); entity only." - id: university-of-sydney name: University of Sydney domain: sydney.edu.au categories: [education, research] tier: B aliases: [usyd] discover: { rss: true, sitemap: false } notes: "No RSS in News & opinion (AEM), no news sitemap (2026-09); entity only." - id: anu name: Australian National University domain: anu.edu.au categories: [education, research] tier: B aliases: [australian national university] discover: { rss: true, sitemap: false } notes: "Newsroom has no RSS (2026-09); generic 76-child sitemap only. Entity only." # ───────────────────────── universities · Canada ───────────────────────── - id: university-of-toronto name: University of Toronto domain: utoronto.ca categories: [education, research] tier: B weight: 1.2 aliases: [u of t, uoft] discover: { rss: false } sensors: - { name: news feed, url: "https://www.utoronto.ca/rss.xml", type: RSS, connector: rss, tier: B } - id: ubc name: University of British Columbia domain: ubc.ca categories: [education, research] tier: B weight: 1.1 aliases: [ubc] discover: { rss: false } sensors: - { name: news feed, url: "https://news.ubc.ca/feed/", type: RSS, connector: rss, tier: B } - id: mcgill name: McGill University domain: mcgill.ca categories: [education, research] tier: B weight: 1.1 aliases: [mcgill] discover: { rss: false } sensors: - { name: news releases feed, url: "https://www.mcgill.ca/newsroom/channels_item/19/rss", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - { name: experts feed, url: "https://www.mcgill.ca/newsroom/channels_item/20/rss", type: RSS, connector: rss, tier: C, config: { maxItems: 30 } } - id: universite-de-montreal name: Université de Montréal domain: umontreal.ca categories: [education, research] tier: B weight: 1.1 aliases: [udem, university of montreal] discover: { rss: false } notes: "UdeMnouvelles offers only a client-rendered RSS builder (/rss) with no static feed URL; the TYPO3 sitemap index of the news site is used instead." sensors: - { name: udemnouvelles sitemap, url: "https://nouvelles.umontreal.ca/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000, maxChildren: 3 } } - id: universite-laval name: Université Laval domain: ulaval.ca categories: [education, research] tier: B aliases: [laval university] discover: { rss: false } sensors: - { name: actualités feed, url: "https://www.ulaval.ca/rss.xml", type: RSS, connector: rss, tier: B } - id: uqam name: Université du Québec à Montréal domain: uqam.ca categories: [education, research] tier: B aliases: [uqam] discover: { rss: false } notes: "actualites.uqam.ca answers 500 on /feed; the press room (salledepresse.uqam.ca) WordPress feed works." sensors: - { name: salle de presse feed, url: "https://salledepresse.uqam.ca/feed/", type: RSS, connector: rss, tier: B } - id: uqo name: Université du Québec en Outaouais domain: uqo.ca categories: [education, research] tier: B aliases: [uqo] discover: { rss: true } sensors: - { name: actualités feed, url: "https://uqo.ca/rss.xml", type: RSS, connector: rss, tier: B } - id: universite-de-sherbrooke name: Université de Sherbrooke domain: usherbrooke.ca categories: [education, research] tier: B aliases: [udes, sherbrooke] discover: { rss: true, sitemap: false } notes: "No RSS under /actualites (2026-09); entity only." - id: polytechnique-montreal name: Polytechnique Montréal domain: polymtl.ca categories: [education, research] tier: B aliases: [poly montréal, polymtl] discover: { rss: false } sensors: - { name: news feed, url: "https://www.polymtl.ca/rss.xml", type: RSS, connector: rss, tier: B } - { name: carrefour actualité feed, url: "https://www.polymtl.ca/carrefour-actualite/rss.xml", type: RSS, connector: rss, tier: C } - id: hec-montreal name: HEC Montréal domain: hec.ca categories: [education, research, finance] tier: B aliases: [hec] discover: { rss: false } sensors: - { name: nouvelles feed, url: "https://www.hec.ca/nouvelles/rss.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: concordia name: Concordia University domain: concordia.ca categories: [education, research] tier: B aliases: [concordia montreal] discover: { rss: true, sitemap: false } notes: "AEM news hub without RSS or news sitemap (2026-09); entity only." - id: ets-montreal name: École de technologie supérieure domain: etsmtl.ca categories: [education, research] tier: C aliases: [éts, ets] discover: { rss: true, sitemap: false } notes: "No RSS on /nouvelles (2026-09); entity only." - id: inrs name: Institut national de la recherche scientifique domain: inrs.ca categories: [education, research] tier: B aliases: [inrs] discover: { rss: false } sensors: - { name: actualités feed, url: "https://inrs.ca/feed/", type: RSS, connector: rss, tier: B } - id: teluq name: Université TÉLUQ domain: teluq.ca categories: [education] tier: C aliases: [téluq, teluq] discover: { rss: true, sitemap: false } notes: "No RSS on /site/nouvelles (2026-09); entity only." - id: uqtr name: Université du Québec à Trois-Rivières domain: uqtr.ca categories: [education, research] tier: B aliases: [uqtr] discover: { rss: false } sensors: - { name: néo uqtr feed, url: "https://neo.uqtr.ca/feed/", type: RSS, connector: rss, tier: B } - id: uqac name: Université du Québec à Chicoutimi domain: uqac.ca categories: [education, research] tier: B aliases: [uqac] discover: { rss: false } sensors: - { name: nouvelles feed, url: "https://www.uqac.ca/feed/", type: RSS, connector: rss, tier: B } - id: uqar name: Université du Québec à Rimouski domain: uqar.ca categories: [education, research] tier: B aliases: [uqar] discover: { rss: false } sensors: - { name: nouvelles feed, url: "https://www.uqar.ca/feed/", type: RSS, connector: rss, tier: B } - id: uqat name: Université du Québec en Abitibi-Témiscamingue domain: uqat.ca categories: [education, research] tier: C aliases: [uqat] discover: { rss: true, sitemap: false } notes: "/feed and /rss.xml are 404 (2026-09); entity only." - id: bishops-university name: Bishop's University domain: ubishops.ca categories: [education] tier: C aliases: [bishop's] discover: { rss: false } sensors: - { name: news feed, url: "https://www.ubishops.ca/feed/", type: RSS, connector: rss, tier: C } - id: university-of-waterloo name: University of Waterloo domain: uwaterloo.ca categories: [education, research, ai] tier: B weight: 1.1 aliases: [waterloo, uwaterloo] discover: { rss: false } sensors: - { name: news feed, url: "https://uwaterloo.ca/rss.xml", type: RSS, connector: rss, tier: B } - id: mcmaster name: McMaster University domain: mcmaster.ca categories: [education, research] tier: B aliases: [mcmaster] discover: { rss: false } sensors: - { name: mcmaster news feed, url: "https://news.mcmaster.ca/feed/", type: RSS, connector: rss, tier: B } - id: university-of-alberta name: University of Alberta domain: ualberta.ca categories: [education, research, ai] tier: B aliases: [ualberta, u of a] discover: { rss: false, sitemap: false } notes: "403 on every feed/sitemap path under /en/news and /folio (bot management); entity only." - id: university-of-calgary name: University of Calgary domain: ucalgary.ca categories: [education, research] tier: B aliases: [ucalgary, u of c] discover: { rss: false } sensors: - { name: news feed, url: "https://ucalgary.ca/news/rss.xml", type: RSS, connector: rss, tier: B } - id: university-of-ottawa name: University of Ottawa domain: uottawa.ca categories: [education, research] tier: B aliases: [uottawa, université d'ottawa] discover: { rss: false } sensors: - { name: news feed, url: "https://www.uottawa.ca/en/rss.xml", type: RSS, connector: rss, tier: B } - id: queens-university name: Queen's University domain: queensu.ca categories: [education, research] tier: B aliases: [queen's, queensu] discover: { rss: false } sensors: - { name: gazette feed, url: "https://www.queensu.ca/gazette/rss.xml", type: RSS, connector: rss, tier: B } - id: western-university name: Western University domain: uwo.ca homepage: https://www.uwo.ca categories: [education, research] tier: B aliases: [western, uwo] discover: { rss: false } sensors: - { name: western news feed, url: "https://news.westernu.ca/feed/", type: RSS, connector: rss, tier: B } - id: dalhousie name: Dalhousie University domain: dal.ca categories: [education, research] tier: B aliases: [dal] discover: { rss: false } sensors: - { name: dal news feed, url: "https://www.dal.ca/news.rss.html", type: RSS, connector: rss, tier: B } - id: sfu name: Simon Fraser University domain: sfu.ca categories: [education, research] tier: B aliases: [sfu] discover: { rss: false } sensors: - { name: sfu news feed, url: "https://www.sfu.ca/content/sfu/sfunews/_jcr_content/main_content/listclf3.feed", type: ATOM, connector: rss, tier: B } - id: university-of-victoria name: University of Victoria domain: uvic.ca categories: [education, research] tier: B aliases: [uvic] discover: { rss: false } sensors: - { name: news feed, url: "https://news.uvic.ca/feed/", type: RSS, connector: rss, tier: B } - id: university-of-manitoba name: University of Manitoba domain: umanitoba.ca categories: [education, research] tier: C aliases: [umanitoba, u of m] discover: { rss: false, sitemap: false } notes: "news.umanitoba.ca returns an HTML shell for /feed and sitemaps (client-rendered); entity only." - id: university-of-saskatchewan name: University of Saskatchewan domain: usask.ca categories: [education, research] tier: B aliases: [usask] discover: { rss: false } sensors: - { name: news feed, url: "https://news.usask.ca/index.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } # ───────────────────────── universities · United States ───────────────────────── - id: princeton name: Princeton University domain: princeton.edu categories: [education, research] tier: B weight: 1.2 discover: { rss: false } sensors: - { name: news feed, url: "https://www.princeton.edu/feed", type: RSS, connector: rss, tier: B } - id: yale name: Yale University domain: yale.edu categories: [education, research] tier: B weight: 1.2 discover: { rss: false } sensors: - { name: yale news feed, url: "https://news.yale.edu/news-rss", type: RSS, connector: rss, tier: B } - id: columbia name: Columbia University domain: columbia.edu categories: [education, research] tier: B weight: 1.2 discover: { rss: false, sitemap: false } notes: "news.columbia.edu answers 403 to feeds and sitemap (bot management); entity only." - id: upenn name: University of Pennsylvania domain: upenn.edu categories: [education, research] tier: B weight: 1.1 aliases: [penn] discover: { rss: false, sitemap: false } notes: "penntoday.upenn.edu answers 403 to feeds and sitemap (bot management); entity only." - id: uchicago name: University of Chicago domain: uchicago.edu categories: [education, research] tier: B weight: 1.1 aliases: [university of chicago] discover: { rss: false } notes: "UChicago News has no RSS; its sitemap index (news-only host) is the sensor." sensors: - { name: news sitemap, url: "https://news.uchicago.edu/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000, maxChildren: 3 } } - id: cornell name: Cornell University domain: cornell.edu categories: [education, research] tier: B weight: 1.1 discover: { rss: false } notes: "Cornell Chronicle only exposes topic feeds (taxonomy/term/*/feed); the Google news sitemap covers everything." sensors: - { name: chronicle news sitemap, url: "https://news.cornell.edu/sitemap-news.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 500 } } - id: johns-hopkins name: Johns Hopkins University domain: jhu.edu categories: [education, research, health] tier: B weight: 1.1 aliases: [jhu, hopkins] discover: { rss: false } sensors: - { name: hub feed, url: "https://hub.jhu.edu/feed/", type: RSS, connector: rss, tier: B } - id: duke name: Duke University domain: duke.edu categories: [education, research] tier: B weight: 1.1 discover: { rss: false } notes: "Duke Today has no RSS; its sitemap index (news-only host) is the sensor." sensors: - { name: duke today sitemap, url: "https://today.duke.edu/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000, maxChildren: 3 } } - id: northwestern name: Northwestern University domain: northwestern.edu categories: [education, research] tier: B discover: { rss: false } sensors: - { name: northwestern now feed, url: "https://news.northwestern.edu/feeds/allStories", type: RSS, connector: rss, tier: B } - id: university-of-michigan name: University of Michigan domain: umich.edu categories: [education, research] tier: B weight: 1.1 aliases: [umich, michigan] discover: { rss: false } sensors: - { name: michigan news feed, url: "https://news.umich.edu/feed/", type: RSS, connector: rss, tier: B } - id: ucla name: UCLA domain: ucla.edu categories: [education, research] tier: B weight: 1.1 aliases: [university of california los angeles] discover: { rss: false } sensors: - { name: newsroom feed, url: "https://newsroom.ucla.edu/rss.xml", type: RSS, connector: rss, tier: B } - id: ucsd name: UC San Diego domain: ucsd.edu categories: [education, research] tier: B aliases: [uc san diego, university of california san diego] discover: { rss: false } notes: "UC San Diego Today has no RSS; its sitemap (news-only host) is the sensor." sensors: - { name: today sitemap, url: "https://today.ucsd.edu/others/sitemap", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000 } } - id: university-of-washington name: University of Washington domain: washington.edu categories: [education, research] tier: B weight: 1.1 aliases: [uw, udub] discover: { rss: false } sensors: - { name: uw news feed, url: "https://www.washington.edu/news/feed/", type: RSS, connector: rss, tier: B } - id: georgia-tech name: Georgia Tech domain: gatech.edu categories: [education, research] tier: B aliases: [georgia institute of technology] discover: { rss: false } sensors: - { name: news feed, url: "https://news.gatech.edu/rss/all", type: RSS, connector: rss, tier: B } - id: ut-austin name: University of Texas at Austin domain: utexas.edu categories: [education, research] tier: B aliases: [ut austin, utexas] discover: { rss: false } sensors: - { name: news feed, url: "https://news.utexas.edu/feed/", type: RSS, connector: rss, tier: B } - id: carnegie-mellon name: Carnegie Mellon University domain: cmu.edu categories: [education, research, ai] tier: B weight: 1.2 aliases: [cmu, carnegie mellon] discover: { rss: false } sensors: - { name: news feed, url: "https://www.cmu.edu/news/feeds/news.rss", type: RSS, connector: rss, tier: B } - id: nyu name: New York University domain: nyu.edu categories: [education, research] tier: B aliases: [nyu] discover: { rss: false, sitemap: false } notes: "nyu.edu answers 202 with an interstitial (bot management) on feeds and sitemap; entity only." - id: usc name: University of Southern California domain: usc.edu categories: [education, research] tier: B aliases: [usc] discover: { rss: false } sensors: - { name: usc today feed, url: "https://today.usc.edu/feed/", type: RSS, connector: rss, tier: B } - id: purdue name: Purdue University domain: purdue.edu categories: [education, research] tier: B discover: { rss: false } sensors: - { name: newsroom feed, url: "https://www.purdue.edu/newsroom/feed/", type: RSS, connector: rss, tier: B } - id: university-of-illinois name: University of Illinois Urbana-Champaign domain: illinois.edu categories: [education, research] tier: B aliases: [uiuc, illinois] discover: { rss: false } sensors: - { name: news bureau feed, url: "https://news.illinois.edu/feed/", type: RSS, connector: rss, tier: B } - id: university-of-wisconsin name: University of Wisconsin–Madison domain: wisc.edu categories: [education, research] tier: B aliases: [uw–madison, wisconsin] discover: { rss: false } sensors: - { name: news feed, url: "https://news.wisc.edu/feed/", type: RSS, connector: rss, tier: B } - id: university-of-minnesota name: University of Minnesota domain: umn.edu categories: [education, research] tier: B aliases: [umn] discover: { rss: false, sitemap: false } notes: "twin-cities.umn.edu answers 403 to feeds and sitemap (bot management); entity only." # ───────────────────────── research institutes & national labs ───────────────────────── - id: cnrs name: CNRS domain: cnrs.fr categories: [research, science] tier: B weight: 1.2 aliases: [centre national de la recherche scientifique] discover: { rss: false } notes: "/en/rss.xml is a stale single-item feed; the FR feed, CNRS News (EN) and CNRS Le journal are live." sensors: - { name: actualités feed, url: "https://www.cnrs.fr/fr/rss.xml", type: RSS, connector: rss, tier: B } - { name: cnrs news feed, url: "https://news.cnrs.fr/rss", type: RSS, connector: rss, tier: B } - { name: le journal feed, url: "https://lejournal.cnrs.fr/rss", type: RSS, connector: rss, tier: C } - id: inria name: Inria domain: inria.fr categories: [research, ai, developer] tier: B weight: 1.1 discover: { rss: false } sensors: - { name: actualités feed, url: "https://www.inria.fr/fr/rss.xml", type: RSS, connector: rss, tier: B } - { name: news feed (en), url: "https://www.inria.fr/en/rss.xml", type: RSS, connector: rss, tier: C } - id: inserm name: Inserm domain: inserm.fr categories: [research, health] tier: B aliases: [institut national de la santé et de la recherche médicale] discover: { rss: false } sensors: - { name: press room feed, url: "https://presse.inserm.fr/en/feed/", type: RSS, connector: rss, tier: B } - { name: site feed, url: "https://www.inserm.fr/feed/", type: RSS, connector: rss, tier: C } - id: cea name: CEA domain: cea.fr categories: [research, energy, science] tier: B aliases: [commissariat à l'énergie atomique et aux énergies alternatives] discover: { rss: true, sitemap: false } notes: "SharePoint site without any RSS endpoint found (2026-09); entity only." - id: fraunhofer name: Fraunhofer-Gesellschaft domain: fraunhofer.de categories: [research, technology] tier: B weight: 1.1 aliases: [fraunhofer] discover: { rss: false } sensors: - { name: press feed, url: "https://www.fraunhofer.de/en/rss/press.rss", type: RSS, connector: rss, tier: B } - id: helmholtz name: Helmholtz Association domain: helmholtz.de categories: [research, science] tier: B aliases: [helmholtz-gemeinschaft] discover: { rss: true, sitemap: false } notes: "Newsroom without RSS (2026-09); entity only." - id: leibniz name: Leibniz Association domain: leibniz-gemeinschaft.de categories: [research, science] tier: B aliases: [leibniz-gemeinschaft, leibniz] discover: { rss: false } sensors: - { name: news feed, url: "https://www.leibniz-gemeinschaft.de/rss.xml", type: RSS, connector: rss, tier: B } - id: riken name: RIKEN domain: riken.jp categories: [research, science] tier: B weight: 1.1 discover: { rss: false } sensors: - { name: press releases feed, url: "https://www.riken.jp/en/feed/press_feed/", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - { name: topics feed, url: "https://www.riken.jp/en/feed/topics_feed/", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } } - id: csiro name: CSIRO domain: csiro.au categories: [research, science] tier: B aliases: [commonwealth scientific and industrial research organisation] discover: { rss: true, sitemap: false } notes: "News hub without RSS and blog.csiro.au feed returns HTML (2026-09); only a 7 k-URL corporate sitemap. Entity only." - id: nrc-canada name: National Research Council Canada domain: nrc.canada.ca categories: [research, government] tier: B aliases: [nrc, cnrc, conseil national de recherches] discover: { rss: true, sitemap: false } notes: "Stories hub has no feed and canada.ca department Atom feeds return the 404 page for NRC (2026-09); entity only." - id: mila name: Mila – Quebec AI Institute domain: mila.quebec categories: [research, ai] tier: B weight: 1.1 aliases: [mila] discover: { rss: false } sensors: - { name: news feed, url: "https://mila.quebec/en/rss.xml", type: RSS, connector: rss, tier: B } - id: vector-institute name: Vector Institute domain: vectorinstitute.ai categories: [research, ai] tier: B aliases: [vector] discover: { rss: false } sensors: - { name: news feed, url: "https://vectorinstitute.ai/feed/", type: RSS, connector: rss, tier: B } - id: amii name: Amii domain: amii.ca categories: [research, ai] tier: C aliases: [alberta machine intelligence institute] discover: { rss: true, sitemap: false } notes: "Client-rendered site with no feed (2026-09); entity only." - id: ivado name: IVADO domain: ivado.ca categories: [research, ai] tier: C discover: { rss: false } sensors: - { name: news feed, url: "https://ivado.ca/en/feed/", type: RSS, connector: rss, tier: C } - id: cifar name: CIFAR domain: cifar.ca categories: [research, ai, funding] tier: B aliases: [canadian institute for advanced research] discover: { rss: false } sensors: - { name: news feed, url: "https://cifar.ca/feed/", type: RSS, connector: rss, tier: B } - id: ai2 name: Allen Institute for AI domain: allenai.org categories: [research, ai] tier: B weight: 1.1 aliases: [ai2, allen ai] products: - { name: OLMo, type: AI_model, aliases: [olmo] } - { name: Semantic Scholar, type: service, aliases: [semantic scholar] } discover: { rss: false } notes: "Semantic Scholar (an AI2 product) has no public news feed; blog.semanticscholar.org does not resolve." sensors: - { name: blog feed, url: "https://allenai.org/rss.xml", type: RSS, connector: rss, tier: B } - { name: medium blog feed, url: "https://medium.com/feed/ai2-blog", type: RSS, connector: rss, tier: C } - id: broad-institute name: Broad Institute domain: broadinstitute.org categories: [research, health] tier: B aliases: [broad] discover: { rss: false } sensors: - { name: news feed, url: "https://www.broadinstitute.org/rss.xml", type: RSS, connector: rss, tier: B } - id: salk-institute name: Salk Institute domain: salk.edu categories: [research, health] tier: C aliases: [salk] discover: { rss: false } sensors: - { name: news feed, url: "https://www.salk.edu/feed/", type: RSS, connector: rss, tier: C } - id: scripps-research name: Scripps Research domain: scripps.edu categories: [research, health] tier: C discover: { rss: true, sitemap: false } notes: "/rss returns a valid but empty WordPress feed (2026-09); entity only." - id: hhmi name: Howard Hughes Medical Institute domain: hhmi.org categories: [research, health, funding] tier: B aliases: [hhmi] discover: { rss: true, sitemap: false } notes: "/rss.xml is an empty channel and the news hub has no feed (2026-09); entity only." - id: wellcome name: Wellcome domain: wellcome.org categories: [research, health, funding] tier: B aliases: [wellcome trust] discover: { rss: false, sitemap: false } notes: "wellcome.org answers 202 with a bot-management interstitial on every path; entity only." - id: sanger-institute name: Wellcome Sanger Institute domain: sanger.ac.uk categories: [research, health] tier: C aliases: [sanger] discover: { rss: false } sensors: - { name: news feed, url: "https://www.sanger.ac.uk/feed/", type: RSS, connector: rss, tier: C } - id: embl name: EMBL domain: embl.org categories: [research, science] tier: B weight: 1.1 aliases: [european molecular biology laboratory] discover: { rss: false } sensors: - { name: news feed, url: "https://www.embl.org/news/feed/", type: RSS, connector: rss, tier: B } - id: francis-crick-institute name: Francis Crick Institute domain: crick.ac.uk categories: [research, health] tier: B aliases: [the crick] discover: { rss: false, sitemap: false } notes: "403 on feeds and sitemap (bot management); entity only." - id: institut-pasteur name: Institut Pasteur domain: pasteur.fr categories: [research, health] tier: B weight: 1.1 aliases: [pasteur] discover: { rss: true, sitemap: false } notes: "/rss.xml, /fr/rss.xml and /en/rss.xml are valid but empty channels (2026-09); entity only." - id: weizmann-institute name: Weizmann Institute of Science domain: weizmann.ac.il categories: [research, science] tier: B aliases: [weizmann] discover: { rss: false } sensors: - { name: compass feed, url: "https://www.weizmann.ac.il/WeizmannCompass/rss.xml", type: RSS, connector: rss, tier: B } - { name: wis wander feed, url: "https://wis-wander.weizmann.ac.il/rss.xml", type: RSS, connector: rss, tier: C } - id: perimeter-institute name: Perimeter Institute domain: perimeterinstitute.ca categories: [research, science] tier: C aliases: [perimeter] discover: { rss: true, sitemap: false } notes: "/rss.xml is an empty channel; no sitemap (2026-09). Entity only." - id: santa-fe-institute name: Santa Fe Institute domain: santafe.edu categories: [research, science] tier: C aliases: [sfi] discover: { rss: false } sensors: - { name: news feed, url: "https://www.santafe.edu/news-center/feed/", type: RSS, connector: rss, tier: C } - id: argonne name: Argonne National Laboratory domain: anl.gov categories: [research, science, energy] tier: B aliases: [argonne] discover: { rss: false, sitemap: false } notes: "anl.gov answers 403 to feeds and sitemap (bot management); entity only." - id: oak-ridge name: Oak Ridge National Laboratory domain: ornl.gov categories: [research, science, energy] tier: B aliases: [ornl, oak ridge] discover: { rss: false } sensors: - { name: news feed, url: "https://www.ornl.gov/rss.xml", type: RSS, connector: rss, tier: B } - id: los-alamos name: Los Alamos National Laboratory domain: lanl.gov categories: [research, science] tier: B aliases: [lanl, los alamos] discover: { rss: true, sitemap: false } notes: "No feed on /media/news and discover.lanl.gov does not resolve (2026-09); only a 1.8 k-URL corporate sitemap. Entity only." - id: lawrence-livermore name: Lawrence Livermore National Laboratory domain: llnl.gov categories: [research, science] tier: B aliases: [llnl, livermore] discover: { rss: true, sitemap: false } notes: "/rss.xml is an empty channel and /news/rss.xml returns HTML (2026-09); entity only." - id: lawrence-berkeley name: Lawrence Berkeley National Laboratory domain: lbl.gov categories: [research, science, energy] tier: B aliases: [berkeley lab, lbnl] discover: { rss: false } sensors: - { name: news center feed, url: "https://newscenter.lbl.gov/feed/", type: RSS, connector: rss, tier: B } - id: brookhaven name: Brookhaven National Laboratory domain: bnl.gov categories: [research, science] tier: B aliases: [bnl] discover: { rss: true, sitemap: false } notes: "Newsroom without RSS and no sitemap (2026-09); entity only." - id: fermilab name: Fermilab domain: fnal.gov categories: [research, science] tier: B aliases: [fermi national accelerator laboratory] discover: { rss: false } sensors: - { name: news feed, url: "https://news.fnal.gov/feed/", type: RSS, connector: rss, tier: B } - id: slac name: SLAC National Accelerator Laboratory domain: slac.stanford.edu categories: [research, science] tier: B aliases: [slac] discover: { rss: false } sensors: - { name: news feed, url: "https://www6.slac.stanford.edu/rss.xml", type: RSS, connector: rss, tier: B } - id: pnnl name: Pacific Northwest National Laboratory domain: pnnl.gov categories: [research, science, energy] tier: B aliases: [pnnl] discover: { rss: true, sitemap: false } notes: "/rss.xml is an empty channel and /news/rss.xml is 403 (2026-09); entity only." - id: sandia name: Sandia National Laboratories domain: sandia.gov categories: [research, science, cyber] tier: B aliases: [sandia labs] discover: { rss: false } sensors: - { name: news releases feed, url: "https://newsreleases.sandia.gov/feed/", type: RSS, connector: rss, tier: B } - { name: news feed, url: "https://www.sandia.gov/news/feed/", type: RSS, connector: rss, tier: C } - id: ncar name: NCAR / UCAR domain: ucar.edu categories: [research, climate, weather] tier: B aliases: [national center for atmospheric research, ucar] discover: { rss: false } sensors: - { name: news feed, url: "https://news.ucar.edu/rss.xml", type: RSS, connector: rss, tier: B } - id: woods-hole name: Woods Hole Oceanographic Institution domain: whoi.edu categories: [research, climate, science] tier: B aliases: [whoi] discover: { rss: false } sensors: - { name: news feed, url: "https://www.whoi.edu/feed/", type: RSS, connector: rss, tier: B } - id: scripps-oceanography name: Scripps Institution of Oceanography domain: scripps.ucsd.edu categories: [research, climate, science] tier: B aliases: [scripps oceanography] discover: { rss: false } sensors: - { name: news feed, url: "https://scripps.ucsd.edu/news/feed", type: RSS, connector: rss, tier: B } - id: alfred-wegener-institute name: Alfred Wegener Institute domain: awi.de categories: [research, climate, science] tier: C aliases: [awi] discover: { rss: true, sitemap: false } notes: "Press pages without RSS (2026-09); entity only." - id: triumf name: TRIUMF domain: triumf.ca categories: [research, science] tier: C discover: { rss: false } sensors: - { name: news feed, url: "https://triumf.ca/feed", type: RSS, connector: rss, tier: C } - id: snolab name: SNOLAB domain: snolab.ca categories: [research, science] tier: C discover: { rss: false } sensors: - { name: news feed, url: "https://www.snolab.ca/news/feed/", type: RSS, connector: rss, tier: C } - id: canadian-light-source name: Canadian Light Source domain: lightsource.ca categories: [research, science] tier: C aliases: [cls] discover: { rss: true, sitemap: false } notes: "Only sector news pages (HTML) — no RSS found (2026-09); entity only." - id: eso name: European Southern Observatory domain: eso.org categories: [research, space, science] tier: B weight: 1.1 aliases: [eso] discover: { rss: false } sensors: - { name: news feed, url: "https://www.eso.org/public/news/feed/", type: RSS, connector: rss, tier: B } - { name: announcements feed, url: "https://feeds.feedburner.com/EsoAnnouncements", type: RSS, connector: rss, tier: C } - { name: blog feed, url: "https://www.eso.org/public/blog/feed/", type: RSS, connector: rss, tier: C } - id: nrao name: National Radio Astronomy Observatory domain: nrao.edu categories: [research, space, science] tier: B aliases: [nrao] discover: { rss: false } sensors: - { name: news feed, url: "https://public.nrao.edu/news/feed/", type: RSS, connector: rss, tier: B } - id: noirlab name: NSF NOIRLab domain: noirlab.edu categories: [research, space, science] tier: B aliases: [noirlab] discover: { rss: false } sensors: - { name: news feed, url: "https://noirlab.edu/public/news/feed/", type: RSS, connector: rss, tier: B } - id: stsci name: Space Telescope Science Institute domain: stsci.edu categories: [research, space, science] tier: B aliases: [stsci, webb telescope, hubble] products: - { name: James Webb Space Telescope, type: product, aliases: [jwst, webb] } - { name: Hubble Space Telescope, type: product, aliases: [hubble] } discover: { rss: false, sitemap: false } notes: "webbtelescope.org / hubblesite.org now point to science.nasa.gov/feed/ (covered on nasa) and the ESA/Webb + ESA/Hubble feeds are on esa; STScI itself publishes no feed." # ───────────────────────── journals, publishers, preprints, scholarly infrastructure ───────────────────────── - id: cell-press name: Cell Press domain: cell.com categories: [research, science, health] tier: B weight: 1.1 aliases: [cell] products: - { name: Cell, type: product } discover: { rss: false } sensors: - { name: cell current issue feed, url: "https://www.cell.com/cell/current.rss", type: RSS, connector: rss, tier: B } - { name: cell in press feed, url: "https://www.cell.com/cell/inpress.rss", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: the-lancet name: The Lancet domain: thelancet.com categories: [research, health] tier: B weight: 1.2 aliases: [lancet] discover: { rss: false } sensors: - { name: current issue feed, url: "https://www.thelancet.com/rssfeed/lancet_current.xml", type: RSS, connector: rss, tier: B } - { name: online first feed, url: "https://www.thelancet.com/rssfeed/lancet_online.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: nejm name: New England Journal of Medicine domain: nejm.org categories: [research, health] tier: B weight: 1.2 aliases: [nejm] discover: { rss: false } sensors: - { name: current issue feed, url: "https://www.nejm.org/action/showFeed?type=etoc&feed=rss&jc=nejm", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: jama name: JAMA Network domain: jamanetwork.com categories: [research, health] tier: B weight: 1.1 aliases: [jama] discover: { rss: false } sensors: - { name: jama current issue feed, url: "https://jamanetwork.com/rss/site_3/67.xml", type: RSS, connector: rss, tier: B } - { name: jama online first feed, url: "https://jamanetwork.com/rss/site_3/onlineFirst_67.xml", type: RSS, connector: rss, tier: B } - id: bmj name: The BMJ domain: bmj.com categories: [research, health] tier: B weight: 1.1 aliases: [british medical journal] discover: { rss: false } sensors: - { name: recent articles feed, url: "https://www.bmj.com/rss/recent.xml", type: RSS, connector: rss, tier: B } - id: pnas name: PNAS domain: pnas.org categories: [research, science] tier: B weight: 1.1 aliases: [proceedings of the national academy of sciences] discover: { rss: false } sensors: - { name: current issue feed, url: "https://www.pnas.org/action/showFeed?type=etoc&feed=rss&jc=pnas", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: plos name: PLOS domain: plos.org categories: [research, science] tier: B aliases: [public library of science] products: - { name: PLOS ONE, type: product, aliases: [plos one] } - { name: PLOS Biology, type: product } discover: { rss: false } sensors: - { name: plos one feed, url: "https://journals.plos.org/plosone/feed/atom", type: ATOM, connector: rss, tier: B } - { name: plos biology feed, url: "https://journals.plos.org/plosbiology/feed/atom", type: ATOM, connector: rss, tier: C } - { name: blog feed, url: "https://theplosblog.plos.org/feed/", type: RSS, connector: rss, tier: C } - id: elife name: eLife domain: elifesciences.org categories: [research, science] tier: B discover: { rss: false } sensors: - { name: recent articles feed, url: "https://elifesciences.org/rss/recent.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - { name: ahead of print feed, url: "https://elifesciences.org/rss/ahead.xml", type: RSS, connector: rss, tier: C } - id: frontiers name: Frontiers domain: frontiersin.org categories: [research, science] tier: B aliases: [frontiers media] discover: { rss: false } sensors: - { name: news feed, url: "https://www.frontiersin.org/news/rss", type: RSS, connector: rss, tier: B } - { name: frontiers in ai feed, url: "https://www.frontiersin.org/journals/artificial-intelligence/rss", type: RSS, connector: rss, tier: C } - id: elsevier name: Elsevier domain: elsevier.com categories: [research, media] tier: B weight: 1.1 products: - { name: ScienceDirect, type: service } - { name: Scopus, type: service } discover: { rss: true, sitemap: false } notes: "No RSS on Elsevier Connect / press releases and no sitemap (2026-09); entity only." - id: wiley name: Wiley domain: wiley.com categories: [research, media] tier: B aliases: [john wiley & sons] discover: { rss: false, sitemap: false } notes: "newsroom.wiley.com answers 403 to feeds (bot management); entity only." - id: acm name: ACM domain: acm.org categories: [research, developer, standards] tier: B aliases: [association for computing machinery] products: - { name: Turing Award, type: product, aliases: [acm turing award] } - { name: Communications of the ACM, type: product, aliases: [cacm] } discover: { rss: false, sitemap: false } notes: "acm.org, cacm.acm.org and awards.acm.org all answer 403 to feeds (bot management); entity only." - id: ieee-spectrum name: IEEE Spectrum domain: spectrum.ieee.org categories: [research, technology, ai, media] tier: B weight: 1.1 aliases: [ieee] discover: { rss: false } sensors: - { name: all articles feed, url: "https://spectrum.ieee.org/feeds/feed.rss", type: RSS, connector: rss, tier: B } - { name: ai topic feed, url: "https://spectrum.ieee.org/feeds/topic/artificial-intelligence.rss", type: RSS, connector: rss, tier: C } - id: biorxiv name: bioRxiv domain: biorxiv.org categories: [research, science, health] tier: B weight: 1.1 llm: false discover: { rss: false } notes: "High-volume preprint stream — heuristics only. Subject feeds: connect.biorxiv.org/biorxiv_xml.php?subject=." sensors: - { name: all preprints feed, url: "https://connect.biorxiv.org/biorxiv_xml.php?subject=all", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - { name: neuroscience feed, url: "https://connect.biorxiv.org/biorxiv_xml.php?subject=neuroscience", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } } - { name: bioinformatics feed, url: "https://connect.biorxiv.org/biorxiv_xml.php?subject=bioinformatics", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } } - id: medrxiv name: medRxiv domain: medrxiv.org categories: [research, health] tier: B weight: 1.1 llm: false discover: { rss: false } notes: "High-volume preprint stream — heuristics only." sensors: - { name: all preprints feed, url: "https://connect.medrxiv.org/medrxiv_xml.php?subject=all", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - { name: infectious diseases feed, url: "https://connect.medrxiv.org/medrxiv_xml.php?subject=infectious_diseases", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } } - { name: epidemiology feed, url: "https://connect.medrxiv.org/medrxiv_xml.php?subject=epidemiology", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } } - id: chemrxiv name: ChemRxiv domain: chemrxiv.org categories: [research, science] tier: C discover: { rss: false, sitemap: false } notes: "Cambridge Open Engage answers 403 to the RSS and public API (bot management); entity only." - id: ssrn name: SSRN domain: ssrn.com categories: [research, finance] tier: C aliases: [social science research network] discover: { rss: false, sitemap: false } notes: "ssrn.com and papers.ssrn.com answer 403 (bot management); entity only." - id: nber name: National Bureau of Economic Research domain: nber.org categories: [research, finance, statistics] tier: B weight: 1.2 aliases: [nber] discover: { rss: false } sensors: - { name: new working papers feed, url: "https://www.nber.org/rss/new.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - { name: releases feed, url: "https://www.nber.org/rss/releases.xml", type: RSS, connector: rss, tier: C } - id: repec name: RePEc domain: repec.org categories: [research, finance] tier: C aliases: [research papers in economics, ideas repec] discover: { rss: false } sensors: - { name: blog feed, url: "https://blog.repec.org/feed/", type: RSS, connector: rss, tier: C } - id: retraction-watch name: Retraction Watch domain: retractionwatch.com categories: [research, media] tier: B discover: { rss: false } sensors: - { name: posts feed, url: "https://retractionwatch.com/feed/", type: RSS, connector: rss, tier: B } - id: crossref name: Crossref domain: crossref.org categories: [research, infrastructure, open-data] tier: B weight: 1.1 products: - { name: Crossref REST API, type: API } discover: { rss: false, status: true } sensors: - { name: status, url: "https://status.crossref.org/api/v2/summary.json", type: STATUSPAGE, connector: statuspage, tier: S } - { name: blog feed, url: "https://www.crossref.org/blog/index.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: orcid name: ORCID domain: orcid.org categories: [research, infrastructure] tier: B discover: { rss: false } sensors: - { name: news feed, url: "https://info.orcid.org/feed/", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } } - id: doaj name: DOAJ domain: doaj.org categories: [research, open-data] tier: C aliases: [directory of open access journals] discover: { rss: false } sensors: - { name: new journals feed, url: "https://doaj.org/feed", type: ATOM, connector: rss, tier: C, config: { maxItems: 50 } } - { name: blog feed, url: "https://blog.doaj.org/feed/", type: RSS, connector: rss, tier: C } - id: zenodo name: Zenodo domain: zenodo.org categories: [research, open-data, infrastructure] tier: B products: - { name: Zenodo REST API, type: API } discover: { rss: false, sitemap: false } notes: "Candidate sensor: jsonlist on https://zenodo.org/api/records?sort=mostrecent&size=25 (itemsPath hits.hits, keyField id, titleField metadata.title, urlField links.self_html, dateField created, llm: false). The API answered 504 Gateway Time-out on every attempt on 2026-09-08 and blog.zenodo.org has no feed — entity only until the API is healthy." - id: center-for-open-science name: Center for Open Science domain: cos.io categories: [research, infrastructure] tier: B aliases: [cos, osf, open science framework] products: - { name: OSF, type: service, aliases: [open science framework] } discover: { rss: false, status: true } sensors: - { name: osf status, url: "https://status.cos.io/api/v2/summary.json", type: STATUSPAGE, connector: statuspage, tier: S } - { name: blog feed, url: "https://www.cos.io/blog/rss.xml", type: RSS, connector: rss, tier: C } - id: figshare name: Figshare domain: figshare.com categories: [research, infrastructure] tier: B discover: { rss: false, status: true } notes: "Blog answers 202 (bot management); the status page is the only sensor." sensors: - { name: status, url: "https://status.figshare.com/api/v2/summary.json", type: STATUSPAGE, connector: statuspage, tier: S } - id: dryad name: Dryad domain: datadryad.org categories: [research, open-data] tier: C discover: { rss: false } sensors: - { name: blog feed, url: "https://blog.datadryad.org/feed", type: RSS, connector: rss, tier: C } - id: europe-pmc name: Europe PMC domain: europepmc.org categories: [research, health, open-data] tier: B llm: false products: - { name: Europe PMC REST API, type: API } discover: { rss: false } notes: "europepmc.org RSS is 403; the EBI REST search (newest preprints, SRC:PPR) is polled instead — heuristics only." sensors: - { name: newest preprints api, url: "https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=SRC:PPR&sort=P_PDATE_D%20desc&format=json&pageSize=25", type: REST_API, connector: jsonlist, tier: B, config: { itemsPath: resultList.result, keyField: id, titleField: title, urlTemplate: "https://europepmc.org/article/PPR/{key}", dateField: firstPublicationDate, maxItems: 25 } } # ───────────────────────── funders & science policy ───────────────────────── - id: erc name: European Research Council domain: erc.europa.eu categories: [research, funding, government] tier: B weight: 1.1 aliases: [erc] discover: { rss: false } sensors: - { name: news feed, url: "https://erc.europa.eu/rss.xml", type: RSS, connector: rss, tier: B } - id: cordis name: CORDIS / Horizon Europe domain: cordis.europa.eu categories: [research, funding, government] tier: B aliases: [cordis, horizon europe] discover: { rss: false, sitemap: false } notes: "/rss/en/news returns HTML (feed discontinued); entity only." - id: ukri name: UK Research and Innovation domain: ukri.org categories: [research, funding, government] tier: B weight: 1.1 aliases: [ukri] discover: { rss: false } sensors: - { name: news feed, url: "https://www.ukri.org/news/feed/", type: RSS, connector: rss, tier: B } - id: dfg name: Deutsche Forschungsgemeinschaft domain: dfg.de categories: [research, funding] tier: B aliases: [dfg, german research foundation] discover: { rss: false } sensors: - { name: press releases feed, url: "https://www.dfg.de/service/rss/en/324778/feed.rss", type: RSS, connector: rss, tier: B } - id: anr name: Agence nationale de la recherche domain: anr.fr categories: [research, funding, government] tier: B aliases: [anr] discover: { rss: false } notes: "The generic /rss/ is empty; the calls-for-proposals feed (/rss/?aap) is live." sensors: - { name: appels à projets feed, url: "https://anr.fr/rss/?aap", type: RSS, connector: rss, tier: B } - id: nserc name: NSERC domain: nserc-crsng.gc.ca categories: [research, funding, government] tier: B aliases: [crsng, natural sciences and engineering research council] discover: { rss: false, sitemap: false } notes: "Classic ASP site without RSS; canada.ca department Atom feed returns the 404 page (2026-09). Entity only." - id: sshrc name: SSHRC domain: sshrc-crsh.canada.ca categories: [research, funding, government] tier: C aliases: [crsh, social sciences and humanities research council] discover: { rss: true, sitemap: false } notes: "No feed found after the move to sshrc-crsh.canada.ca (2026-09); entity only." - id: cihr name: CIHR domain: cihr-irsc.gc.ca categories: [research, funding, health, government] tier: C aliases: [irsc, canadian institutes of health research] discover: { rss: false, sitemap: false } notes: "Site links to a canada.ca Atom feed that returns the 404 page (2026-09); entity only." - id: frq name: Fonds de recherche du Québec domain: frq.gouv.qc.ca categories: [research, funding, government] tier: B aliases: [frq, frqnt, frqs, frqsc] discover: { rss: false } sensors: - { name: actualités feed, url: "https://frq.gouv.qc.ca/feed/", type: RSS, connector: rss, tier: B } - { name: news feed (en), url: "https://frq.gouv.qc.ca/en/feed/", type: RSS, connector: rss, tier: C } - id: genome-canada name: Genome Canada domain: genomecanada.ca categories: [research, funding, health] tier: C discover: { rss: false } sensors: - { name: news feed, url: "https://genomecanada.ca/feed/", type: RSS, connector: rss, tier: C } - id: cfi name: Canada Foundation for Innovation domain: innovation.ca categories: [research, funding, government] tier: C aliases: [cfi, fci] discover: { rss: false } sensors: - { name: news feed, url: "https://www.innovation.ca/rss.xml", type: RSS, connector: rss, tier: C } - id: gates-foundation name: Gates Foundation domain: gatesfoundation.org categories: [funding, health, ngo] tier: B weight: 1.1 aliases: [bill & melinda gates foundation] discover: { rss: false, sitemap: false } notes: "Media center without RSS; only a 1.1 k-URL corporate sitemap (2026-09). Entity only." - id: czi name: Chan Zuckerberg Initiative domain: chanzuckerberg.com categories: [funding, research, health] tier: B aliases: [czi] discover: { rss: false } sensors: - { name: newsroom feed, url: "https://chanzuckerberg.com/newsroom/feed/", type: RSS, connector: rss, tier: B } - id: simons-foundation name: Simons Foundation domain: simonsfoundation.org categories: [funding, research, science] tier: B discover: { rss: false } sensors: - { name: news feed, url: "https://www.simonsfoundation.org/feed/", type: RSS, connector: rss, tier: B } - id: sloan-foundation name: Alfred P. Sloan Foundation domain: sloan.org categories: [funding, research] tier: C aliases: [sloan] discover: { rss: false, sitemap: false } notes: "sloan.org answers 403 to feeds (bot management); entity only." - id: templeton-foundation name: John Templeton Foundation domain: templeton.org categories: [funding, research] tier: C aliases: [templeton] discover: { rss: true, sitemap: false } notes: "/feed is a valid but empty WordPress channel (2026-09); entity only." - id: jst name: Japan Science and Technology Agency domain: jst.go.jp categories: [research, funding, government] tier: C aliases: [jst] discover: { rss: true, sitemap: false } notes: "No RSS on the EN site (2026-09); entity only." - id: nsfc name: National Natural Science Foundation of China domain: nsfc.gov.cn categories: [research, funding, government] tier: C aliases: [nsfc] discover: { rss: true, sitemap: false } notes: "No feed on the EN site (2026-09); entity only." - id: arc-australia name: Australian Research Council domain: arc.gov.au categories: [research, funding, government] tier: C aliases: [arc] discover: { rss: false, sitemap: false } notes: "arc.gov.au drops connections from our network (geo/bot filtering, 2026-09); entity only." - id: royal-society name: Royal Society domain: royalsociety.org categories: [research, science] tier: B weight: 1.1 discover: { rss: false, sitemap: false } notes: "royalsociety.org and royalsocietypublishing.org answer 403 to feeds and sitemap (bot management); entity only." - id: national-academies name: National Academies of Sciences, Engineering, and Medicine domain: nationalacademies.org categories: [research, science, government] tier: B weight: 1.1 aliases: [nasem, national academies press] discover: { rss: false } notes: "The news hub has no RSS; the National Academies Press new-titles Atom feed is the sensor." sensors: - { name: nap new titles feed, url: "https://nap.nationalacademies.org/rss/new.xml", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } } - id: aaas name: AAAS domain: aaas.org categories: [research, science] tier: B aliases: [american association for the advancement of science, eurekalert] discover: { rss: true, sitemap: false } notes: "aaas.org news has no RSS and EurekAlert! removed its RSS feeds (2026-09); Science journal is the separate `science` source. Entity only." - id: nobel-prize name: Nobel Prize domain: nobelprize.org categories: [research, science] tier: B weight: 1.2 aliases: [nobel, nobel foundation] discover: { rss: false } sensors: - { name: news feed, url: "https://www.nobelprize.org/feed/", type: RSS, connector: rss, tier: B } - id: breakthrough-prize name: Breakthrough Prize domain: breakthroughprize.org categories: [research, science] tier: C discover: { rss: true, sitemap: false } notes: "No RSS on /News (2026-09); entity only." - id: imu name: International Mathematical Union domain: mathunion.org categories: [research, science] tier: C aliases: [fields medal] products: - { name: Fields Medal, type: product } discover: { rss: true, sitemap: false } notes: "No RSS on imu-news (2026-09); entity only." - id: kavli-foundation name: Kavli Foundation domain: kavlifoundation.org categories: [funding, science] tier: C aliases: [kavli prize] discover: { rss: true, sitemap: false } notes: "No RSS on kavlifoundation.org or kavliprize.org (2026-09); entity only." - id: wolf-foundation name: Wolf Foundation domain: wolffund.org.il categories: [research, science] tier: C aliases: [wolf prize] discover: { rss: false } sensors: - { name: news feed, url: "https://wolffund.org.il/feed/", type: RSS, connector: rss, tier: C }