TypeScript 55.4%
Python 43.2%
SQL 1.2%
1# config/sources.d/16-universities-research.yaml — universities, research institutes & national labs,2# journals / publishers / preprint servers / scholarly infrastructure, funders & science policy.3# Authored 2026-09-08. Every sensor below was fetched and parsed with the registry validator; organizations4# whose feeds are blocked (403/202 bot management) or simply absent are kept as discover-only entities with a5# `notes:` explanation so nobody re-probes them blindly. Extends: arxiv (API Atom feeds), nasa (JPL), esa6# (ESA/Webb, ESA/Hubble).7sources:8 # ───────────────────────── extensions of founding-file sources ─────────────────────────9 - id: arxiv10 extend: true11 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."12 sensors:13 - { 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 } }14 - { 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 } }15 - { 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 } }16 - { 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 } }17 - { 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 } }18 - { 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 } }19 - id: nasa20 extend: true21 aliases: [jpl, jet propulsion laboratory]22 products:23 - { name: Jet Propulsion Laboratory, type: service, aliases: [jpl] }24 sensors:25 - { name: jpl news feed, url: "https://www.jpl.nasa.gov/feeds/news/", type: RSS, connector: rss, tier: B }26 - { name: science news feed, url: "https://science.nasa.gov/feed/", type: RSS, connector: rss, tier: B }27 - id: esa28 extend: true29 aliases: [esa webb, esa hubble]30 sensors:31 - { name: esa webb news feed, url: "https://esawebb.org/news/feed/", type: RSS, connector: rss, tier: B }32 - { name: esa hubble news feed, url: "https://esahubble.org/news/feed/", type: RSS, connector: rss, tier: B }3334 # ───────────────────────── universities · United Kingdom & Europe ─────────────────────────35 - id: cambridge36 name: University of Cambridge37 domain: cam.ac.uk38 categories: [education, research]39 tier: B40 weight: 1.241 aliases: [cambridge university]42 discover: { rss: true, sitemap: false }43 sensors:44 - { name: news feed, url: "https://www.cam.ac.uk/news/feed", type: RSS, connector: rss, tier: B }45 - id: oxford46 name: University of Oxford47 domain: ox.ac.uk48 categories: [education, research]49 tier: B50 weight: 1.251 aliases: [oxford university]52 discover: { rss: false, sitemap: false }53 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."54 - id: imperial-college55 name: Imperial College London56 domain: imperial.ac.uk57 categories: [education, research]58 tier: B59 aliases: [imperial]60 discover: { rss: true, sitemap: false }61 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."62 - id: ucl63 name: University College London64 domain: ucl.ac.uk65 categories: [education, research]66 tier: B67 aliases: [university college london]68 discover: { rss: false, sitemap: false }69 notes: "403 on feeds and news sitemap (bot management); entity only."70 - id: edinburgh71 name: University of Edinburgh72 domain: ed.ac.uk73 categories: [education, research]74 tier: B75 aliases: [edinburgh university]76 discover: { rss: true, sitemap: false }77 notes: "News hub has no RSS/Atom and no news sitemap (2026-09); entity only."78 - id: eth-zurich79 name: ETH Zurich80 domain: ethz.ch81 categories: [education, research]82 tier: B83 weight: 1.284 aliases: [eth zürich, eth]85 discover: { rss: false }86 sensors:87 - { 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 } }88 - id: epfl89 name: EPFL90 domain: epfl.ch91 categories: [education, research]92 tier: B93 weight: 1.194 aliases: [école polytechnique fédérale de lausanne]95 discover: { rss: false }96 sensors:97 - { name: mediacom news feed, url: "https://actu.epfl.ch/feeds/rss/mediacom/en/", type: RSS, connector: rss, tier: B }98 - id: tu-munich99 name: Technical University of Munich100 domain: tum.de101 categories: [education, research]102 tier: B103 aliases: [tum, technische universität münchen]104 discover: { rss: false }105 sensors:106 - { name: news feed, url: "https://www.tum.de/en/news.rss", type: ATOM, connector: rss, tier: B }107 - id: lmu-munich108 name: LMU Munich109 domain: lmu.de110 categories: [education, research]111 tier: B112 aliases: [ludwig-maximilians-universität, lmu]113 discover: { rss: false }114 sensors:115 - { name: newsroom feed, url: "https://www.lmu.de/en/newsroom/rss-feed-news.xml", type: RSS, connector: rss, tier: B }116 - id: sorbonne-universite117 name: Sorbonne Université118 domain: sorbonne-universite.fr119 categories: [education, research]120 tier: B121 aliases: [sorbonne]122 discover: { rss: false }123 sensors:124 - { name: actualités feed, url: "https://www.sorbonne-universite.fr/rss.xml", type: RSS, connector: rss, tier: B }125 - id: psl126 name: Université PSL127 domain: psl.eu128 categories: [education, research]129 tier: B130 aliases: [paris sciences et lettres]131 discover: { rss: false }132 sensors:133 - { name: actualités feed, url: "https://psl.eu/rss.xml", type: RSS, connector: rss, tier: B }134 - id: ku-leuven135 name: KU Leuven136 domain: kuleuven.be137 categories: [education, research]138 tier: B139 aliases: [leuven]140 discover: { rss: false }141 sensors:142 - { name: news feed, url: "https://nieuws.kuleuven.be/en/content/rss", type: ATOM, connector: rss, tier: B }143 - id: tu-delft144 name: TU Delft145 domain: tudelft.nl146 categories: [education, research]147 tier: B148 aliases: [delft university of technology]149 discover: { rss: true, sitemap: false }150 notes: "No RSS on /en/news (2026-09); generic 217-child sitemap only. Entity only."151 - id: university-of-amsterdam152 name: University of Amsterdam153 domain: uva.nl154 categories: [education, research]155 tier: B156 aliases: [uva, universiteit van amsterdam]157 discover: { rss: false }158 sensors:159 - { name: news sitemap, url: "https://www.uva.nl/news-sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 500, maxChildren: 6 } }160 - id: university-of-copenhagen161 name: University of Copenhagen162 domain: ku.dk163 categories: [education, research]164 tier: B165 aliases: [københavns universitet, ucph]166 discover: { rss: false }167 sensors:168 - { name: all news feed, url: "https://news.ku.dk/all_news/?get_rss=1", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }169 - id: karolinska170 name: Karolinska Institutet171 domain: ki.se172 categories: [education, research, health]173 tier: B174 aliases: [karolinska institute]175 discover: { rss: false }176 sensors:177 - { name: latest news feed, url: "https://nyheter.ki.se/latest-news/rss.xml", type: RSS, connector: rss, tier: B }178 - id: uppsala179 name: Uppsala University180 domain: uu.se181 categories: [education, research]182 tier: B183 aliases: [uppsala universitet]184 discover: { rss: true, sitemap: false }185 notes: "No RSS on /en/news and no news sitemap (2026-09); entity only."186 - id: university-of-helsinki187 name: University of Helsinki188 domain: helsinki.fi189 categories: [education, research]190 tier: B191 aliases: [helsingin yliopisto]192 discover: { rss: false }193 sensors:194 - { name: news feed, url: "https://www.helsinki.fi/en/rss.xml", type: RSS, connector: rss, tier: B }195196 # ───────────────────────── universities · Asia-Pacific ─────────────────────────197 - id: university-of-tokyo198 name: University of Tokyo199 domain: u-tokyo.ac.jp200 categories: [education, research]201 tier: B202 weight: 1.1203 aliases: [utokyo, todai]204 discover: { rss: true, sitemap: false }205 notes: "No RSS/Atom on the EN news hub, no sitemap (2026-09); entity only."206 - id: kyoto-university207 name: Kyoto University208 domain: kyoto-u.ac.jp209 categories: [education, research]210 tier: B211 aliases: [kyodai]212 discover: { rss: false }213 sensors:214 - { name: news feed, url: "https://www.kyoto-u.ac.jp/en/rss.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }215 - id: nus216 name: National University of Singapore217 domain: nus.edu.sg218 categories: [education, research]219 tier: B220 weight: 1.1221 aliases: [nus singapore]222 discover: { rss: false }223 sensors:224 - { name: news feed, url: "https://news.nus.edu.sg/feed/", type: RSS, connector: rss, tier: B }225 - id: ntu-singapore226 name: Nanyang Technological University227 domain: ntu.edu.sg228 categories: [education, research]229 tier: B230 aliases: [ntu]231 discover: { rss: true, sitemap: false }232 notes: "News hub is client-rendered without RSS; no sitemap (2026-09). Entity only."233 - id: tsinghua234 name: Tsinghua University235 domain: tsinghua.edu.cn236 categories: [education, research]237 tier: B238 weight: 1.1239 discover: { rss: true, sitemap: false }240 notes: "No feed on the EN site (2026-09); entity only."241 - id: peking-university242 name: Peking University243 domain: pku.edu.cn244 categories: [education, research]245 tier: B246 weight: 1.1247 aliases: [pku, beida]248 discover: { rss: true, sitemap: false }249 notes: "No feed on english.pku.edu.cn (2026-09); entity only."250 - id: hku251 name: University of Hong Kong252 domain: hku.hk253 categories: [education, research]254 tier: B255 aliases: [hong kong university]256 discover: { rss: true, sitemap: false }257 notes: "Press-release pages have no RSS (rss.hku.hk is the Research Services office, not a feed). Entity only."258 - id: kaist259 name: KAIST260 domain: kaist.ac.kr261 categories: [education, research]262 tier: B263 aliases: [korea advanced institute of science and technology]264 discover: { rss: false }265 sensors:266 - { name: news sitemap, url: "https://news.kaist.ac.kr/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 1500, maxChildren: 4 } }267 - id: seoul-national-university268 name: Seoul National University269 domain: snu.ac.kr270 categories: [education, research]271 tier: B272 aliases: [snu]273 discover: { rss: true, sitemap: false }274 notes: "No feed on en.snu.ac.kr (2026-09); entity only."275 - id: iit-bombay276 name: IIT Bombay277 domain: iitb.ac.in278 categories: [education, research]279 tier: B280 aliases: [indian institute of technology bombay]281 discover: { rss: false }282 sensors:283 - { name: news feed, url: "https://www.iitb.ac.in/rss.xml", type: RSS, connector: rss, tier: B }284 - id: university-of-melbourne285 name: University of Melbourne286 domain: unimelb.edu.au287 categories: [education, research]288 tier: B289 aliases: [unimelb, melbourne university]290 discover: { rss: false, sitemap: false }291 notes: "403 on newsroom feeds/sitemaps and on pursuit.unimelb.edu.au (bot management); entity only."292 - id: university-of-sydney293 name: University of Sydney294 domain: sydney.edu.au295 categories: [education, research]296 tier: B297 aliases: [usyd]298 discover: { rss: true, sitemap: false }299 notes: "No RSS in News & opinion (AEM), no news sitemap (2026-09); entity only."300 - id: anu301 name: Australian National University302 domain: anu.edu.au303 categories: [education, research]304 tier: B305 aliases: [australian national university]306 discover: { rss: true, sitemap: false }307 notes: "Newsroom has no RSS (2026-09); generic 76-child sitemap only. Entity only."308309 # ───────────────────────── universities · Canada ─────────────────────────310 - id: university-of-toronto311 name: University of Toronto312 domain: utoronto.ca313 categories: [education, research]314 tier: B315 weight: 1.2316 aliases: [u of t, uoft]317 discover: { rss: false }318 sensors:319 - { name: news feed, url: "https://www.utoronto.ca/rss.xml", type: RSS, connector: rss, tier: B }320 - id: ubc321 name: University of British Columbia322 domain: ubc.ca323 categories: [education, research]324 tier: B325 weight: 1.1326 aliases: [ubc]327 discover: { rss: false }328 sensors:329 - { name: news feed, url: "https://news.ubc.ca/feed/", type: RSS, connector: rss, tier: B }330 - id: mcgill331 name: McGill University332 domain: mcgill.ca333 categories: [education, research]334 tier: B335 weight: 1.1336 aliases: [mcgill]337 discover: { rss: false }338 sensors:339 - { name: news releases feed, url: "https://www.mcgill.ca/newsroom/channels_item/19/rss", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }340 - { name: experts feed, url: "https://www.mcgill.ca/newsroom/channels_item/20/rss", type: RSS, connector: rss, tier: C, config: { maxItems: 30 } }341 - id: universite-de-montreal342 name: Université de Montréal343 domain: umontreal.ca344 categories: [education, research]345 tier: B346 weight: 1.1347 aliases: [udem, university of montreal]348 discover: { rss: false }349 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."350 sensors:351 - { name: udemnouvelles sitemap, url: "https://nouvelles.umontreal.ca/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000, maxChildren: 3 } }352 - id: universite-laval353 name: Université Laval354 domain: ulaval.ca355 categories: [education, research]356 tier: B357 aliases: [laval university]358 discover: { rss: false }359 sensors:360 - { name: actualités feed, url: "https://www.ulaval.ca/rss.xml", type: RSS, connector: rss, tier: B }361 - id: uqam362 name: Université du Québec à Montréal363 domain: uqam.ca364 categories: [education, research]365 tier: B366 aliases: [uqam]367 discover: { rss: false }368 notes: "actualites.uqam.ca answers 500 on /feed; the press room (salledepresse.uqam.ca) WordPress feed works."369 sensors:370 - { name: salle de presse feed, url: "https://salledepresse.uqam.ca/feed/", type: RSS, connector: rss, tier: B }371 - id: uqo372 name: Université du Québec en Outaouais373 domain: uqo.ca374 categories: [education, research]375 tier: B376 aliases: [uqo]377 discover: { rss: true }378 sensors:379 - { name: actualités feed, url: "https://uqo.ca/rss.xml", type: RSS, connector: rss, tier: B }380 - id: universite-de-sherbrooke381 name: Université de Sherbrooke382 domain: usherbrooke.ca383 categories: [education, research]384 tier: B385 aliases: [udes, sherbrooke]386 discover: { rss: true, sitemap: false }387 notes: "No RSS under /actualites (2026-09); entity only."388 - id: polytechnique-montreal389 name: Polytechnique Montréal390 domain: polymtl.ca391 categories: [education, research]392 tier: B393 aliases: [poly montréal, polymtl]394 discover: { rss: false }395 sensors:396 - { name: news feed, url: "https://www.polymtl.ca/rss.xml", type: RSS, connector: rss, tier: B }397 - { name: carrefour actualité feed, url: "https://www.polymtl.ca/carrefour-actualite/rss.xml", type: RSS, connector: rss, tier: C }398 - id: hec-montreal399 name: HEC Montréal400 domain: hec.ca401 categories: [education, research, finance]402 tier: B403 aliases: [hec]404 discover: { rss: false }405 sensors:406 - { name: nouvelles feed, url: "https://www.hec.ca/nouvelles/rss.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }407 - id: concordia408 name: Concordia University409 domain: concordia.ca410 categories: [education, research]411 tier: B412 aliases: [concordia montreal]413 discover: { rss: true, sitemap: false }414 notes: "AEM news hub without RSS or news sitemap (2026-09); entity only."415 - id: ets-montreal416 name: École de technologie supérieure417 domain: etsmtl.ca418 categories: [education, research]419 tier: C420 aliases: [éts, ets]421 discover: { rss: true, sitemap: false }422 notes: "No RSS on /nouvelles (2026-09); entity only."423 - id: inrs424 name: Institut national de la recherche scientifique425 domain: inrs.ca426 categories: [education, research]427 tier: B428 aliases: [inrs]429 discover: { rss: false }430 sensors:431 - { name: actualités feed, url: "https://inrs.ca/feed/", type: RSS, connector: rss, tier: B }432 - id: teluq433 name: Université TÉLUQ434 domain: teluq.ca435 categories: [education]436 tier: C437 aliases: [téluq, teluq]438 discover: { rss: true, sitemap: false }439 notes: "No RSS on /site/nouvelles (2026-09); entity only."440 - id: uqtr441 name: Université du Québec à Trois-Rivières442 domain: uqtr.ca443 categories: [education, research]444 tier: B445 aliases: [uqtr]446 discover: { rss: false }447 sensors:448 - { name: néo uqtr feed, url: "https://neo.uqtr.ca/feed/", type: RSS, connector: rss, tier: B }449 - id: uqac450 name: Université du Québec à Chicoutimi451 domain: uqac.ca452 categories: [education, research]453 tier: B454 aliases: [uqac]455 discover: { rss: false }456 sensors:457 - { name: nouvelles feed, url: "https://www.uqac.ca/feed/", type: RSS, connector: rss, tier: B }458 - id: uqar459 name: Université du Québec à Rimouski460 domain: uqar.ca461 categories: [education, research]462 tier: B463 aliases: [uqar]464 discover: { rss: false }465 sensors:466 - { name: nouvelles feed, url: "https://www.uqar.ca/feed/", type: RSS, connector: rss, tier: B }467 - id: uqat468 name: Université du Québec en Abitibi-Témiscamingue469 domain: uqat.ca470 categories: [education, research]471 tier: C472 aliases: [uqat]473 discover: { rss: true, sitemap: false }474 notes: "/feed and /rss.xml are 404 (2026-09); entity only."475 - id: bishops-university476 name: Bishop's University477 domain: ubishops.ca478 categories: [education]479 tier: C480 aliases: [bishop's]481 discover: { rss: false }482 sensors:483 - { name: news feed, url: "https://www.ubishops.ca/feed/", type: RSS, connector: rss, tier: C }484 - id: university-of-waterloo485 name: University of Waterloo486 domain: uwaterloo.ca487 categories: [education, research, ai]488 tier: B489 weight: 1.1490 aliases: [waterloo, uwaterloo]491 discover: { rss: false }492 sensors:493 - { name: news feed, url: "https://uwaterloo.ca/rss.xml", type: RSS, connector: rss, tier: B }494 - id: mcmaster495 name: McMaster University496 domain: mcmaster.ca497 categories: [education, research]498 tier: B499 aliases: [mcmaster]500 discover: { rss: false }501 sensors:502 - { name: mcmaster news feed, url: "https://news.mcmaster.ca/feed/", type: RSS, connector: rss, tier: B }503 - id: university-of-alberta504 name: University of Alberta505 domain: ualberta.ca506 categories: [education, research, ai]507 tier: B508 aliases: [ualberta, u of a]509 discover: { rss: false, sitemap: false }510 notes: "403 on every feed/sitemap path under /en/news and /folio (bot management); entity only."511 - id: university-of-calgary512 name: University of Calgary513 domain: ucalgary.ca514 categories: [education, research]515 tier: B516 aliases: [ucalgary, u of c]517 discover: { rss: false }518 sensors:519 - { name: news feed, url: "https://ucalgary.ca/news/rss.xml", type: RSS, connector: rss, tier: B }520 - id: university-of-ottawa521 name: University of Ottawa522 domain: uottawa.ca523 categories: [education, research]524 tier: B525 aliases: [uottawa, université d'ottawa]526 discover: { rss: false }527 sensors:528 - { name: news feed, url: "https://www.uottawa.ca/en/rss.xml", type: RSS, connector: rss, tier: B }529 - id: queens-university530 name: Queen's University531 domain: queensu.ca532 categories: [education, research]533 tier: B534 aliases: [queen's, queensu]535 discover: { rss: false }536 sensors:537 - { name: gazette feed, url: "https://www.queensu.ca/gazette/rss.xml", type: RSS, connector: rss, tier: B }538 - id: western-university539 name: Western University540 domain: uwo.ca541 homepage: https://www.uwo.ca542 categories: [education, research]543 tier: B544 aliases: [western, uwo]545 discover: { rss: false }546 sensors:547 - { name: western news feed, url: "https://news.westernu.ca/feed/", type: RSS, connector: rss, tier: B }548 - id: dalhousie549 name: Dalhousie University550 domain: dal.ca551 categories: [education, research]552 tier: B553 aliases: [dal]554 discover: { rss: false }555 sensors:556 - { name: dal news feed, url: "https://www.dal.ca/news.rss.html", type: RSS, connector: rss, tier: B }557 - id: sfu558 name: Simon Fraser University559 domain: sfu.ca560 categories: [education, research]561 tier: B562 aliases: [sfu]563 discover: { rss: false }564 sensors:565 - { name: sfu news feed, url: "https://www.sfu.ca/content/sfu/sfunews/_jcr_content/main_content/listclf3.feed", type: ATOM, connector: rss, tier: B }566 - id: university-of-victoria567 name: University of Victoria568 domain: uvic.ca569 categories: [education, research]570 tier: B571 aliases: [uvic]572 discover: { rss: false }573 sensors:574 - { name: news feed, url: "https://news.uvic.ca/feed/", type: RSS, connector: rss, tier: B }575 - id: university-of-manitoba576 name: University of Manitoba577 domain: umanitoba.ca578 categories: [education, research]579 tier: C580 aliases: [umanitoba, u of m]581 discover: { rss: false, sitemap: false }582 notes: "news.umanitoba.ca returns an HTML shell for /feed and sitemaps (client-rendered); entity only."583 - id: university-of-saskatchewan584 name: University of Saskatchewan585 domain: usask.ca586 categories: [education, research]587 tier: B588 aliases: [usask]589 discover: { rss: false }590 sensors:591 - { name: news feed, url: "https://news.usask.ca/index.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }592593 # ───────────────────────── universities · United States ─────────────────────────594 - id: princeton595 name: Princeton University596 domain: princeton.edu597 categories: [education, research]598 tier: B599 weight: 1.2600 discover: { rss: false }601 sensors:602 - { name: news feed, url: "https://www.princeton.edu/feed", type: RSS, connector: rss, tier: B }603 - id: yale604 name: Yale University605 domain: yale.edu606 categories: [education, research]607 tier: B608 weight: 1.2609 discover: { rss: false }610 sensors:611 - { name: yale news feed, url: "https://news.yale.edu/news-rss", type: RSS, connector: rss, tier: B }612 - id: columbia613 name: Columbia University614 domain: columbia.edu615 categories: [education, research]616 tier: B617 weight: 1.2618 discover: { rss: false, sitemap: false }619 notes: "news.columbia.edu answers 403 to feeds and sitemap (bot management); entity only."620 - id: upenn621 name: University of Pennsylvania622 domain: upenn.edu623 categories: [education, research]624 tier: B625 weight: 1.1626 aliases: [penn]627 discover: { rss: false, sitemap: false }628 notes: "penntoday.upenn.edu answers 403 to feeds and sitemap (bot management); entity only."629 - id: uchicago630 name: University of Chicago631 domain: uchicago.edu632 categories: [education, research]633 tier: B634 weight: 1.1635 aliases: [university of chicago]636 discover: { rss: false }637 notes: "UChicago News has no RSS; its sitemap index (news-only host) is the sensor."638 sensors:639 - { name: news sitemap, url: "https://news.uchicago.edu/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000, maxChildren: 3 } }640 - id: cornell641 name: Cornell University642 domain: cornell.edu643 categories: [education, research]644 tier: B645 weight: 1.1646 discover: { rss: false }647 notes: "Cornell Chronicle only exposes topic feeds (taxonomy/term/*/feed); the Google news sitemap covers everything."648 sensors:649 - { name: chronicle news sitemap, url: "https://news.cornell.edu/sitemap-news.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 500 } }650 - id: johns-hopkins651 name: Johns Hopkins University652 domain: jhu.edu653 categories: [education, research, health]654 tier: B655 weight: 1.1656 aliases: [jhu, hopkins]657 discover: { rss: false }658 sensors:659 - { name: hub feed, url: "https://hub.jhu.edu/feed/", type: RSS, connector: rss, tier: B }660 - id: duke661 name: Duke University662 domain: duke.edu663 categories: [education, research]664 tier: B665 weight: 1.1666 discover: { rss: false }667 notes: "Duke Today has no RSS; its sitemap index (news-only host) is the sensor."668 sensors:669 - { name: duke today sitemap, url: "https://today.duke.edu/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000, maxChildren: 3 } }670 - id: northwestern671 name: Northwestern University672 domain: northwestern.edu673 categories: [education, research]674 tier: B675 discover: { rss: false }676 sensors:677 - { name: northwestern now feed, url: "https://news.northwestern.edu/feeds/allStories", type: RSS, connector: rss, tier: B }678 - id: university-of-michigan679 name: University of Michigan680 domain: umich.edu681 categories: [education, research]682 tier: B683 weight: 1.1684 aliases: [umich, michigan]685 discover: { rss: false }686 sensors:687 - { name: michigan news feed, url: "https://news.umich.edu/feed/", type: RSS, connector: rss, tier: B }688 - id: ucla689 name: UCLA690 domain: ucla.edu691 categories: [education, research]692 tier: B693 weight: 1.1694 aliases: [university of california los angeles]695 discover: { rss: false }696 sensors:697 - { name: newsroom feed, url: "https://newsroom.ucla.edu/rss.xml", type: RSS, connector: rss, tier: B }698 - id: ucsd699 name: UC San Diego700 domain: ucsd.edu701 categories: [education, research]702 tier: B703 aliases: [uc san diego, university of california san diego]704 discover: { rss: false }705 notes: "UC San Diego Today has no RSS; its sitemap (news-only host) is the sensor."706 sensors:707 - { name: today sitemap, url: "https://today.ucsd.edu/others/sitemap", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000 } }708 - id: university-of-washington709 name: University of Washington710 domain: washington.edu711 categories: [education, research]712 tier: B713 weight: 1.1714 aliases: [uw, udub]715 discover: { rss: false }716 sensors:717 - { name: uw news feed, url: "https://www.washington.edu/news/feed/", type: RSS, connector: rss, tier: B }718 - id: georgia-tech719 name: Georgia Tech720 domain: gatech.edu721 categories: [education, research]722 tier: B723 aliases: [georgia institute of technology]724 discover: { rss: false }725 sensors:726 - { name: news feed, url: "https://news.gatech.edu/rss/all", type: RSS, connector: rss, tier: B }727 - id: ut-austin728 name: University of Texas at Austin729 domain: utexas.edu730 categories: [education, research]731 tier: B732 aliases: [ut austin, utexas]733 discover: { rss: false }734 sensors:735 - { name: news feed, url: "https://news.utexas.edu/feed/", type: RSS, connector: rss, tier: B }736 - id: carnegie-mellon737 name: Carnegie Mellon University738 domain: cmu.edu739 categories: [education, research, ai]740 tier: B741 weight: 1.2742 aliases: [cmu, carnegie mellon]743 discover: { rss: false }744 sensors:745 - { name: news feed, url: "https://www.cmu.edu/news/feeds/news.rss", type: RSS, connector: rss, tier: B }746 - id: nyu747 name: New York University748 domain: nyu.edu749 categories: [education, research]750 tier: B751 aliases: [nyu]752 discover: { rss: false, sitemap: false }753 notes: "nyu.edu answers 202 with an interstitial (bot management) on feeds and sitemap; entity only."754 - id: usc755 name: University of Southern California756 domain: usc.edu757 categories: [education, research]758 tier: B759 aliases: [usc]760 discover: { rss: false }761 sensors:762 - { name: usc today feed, url: "https://today.usc.edu/feed/", type: RSS, connector: rss, tier: B }763 - id: purdue764 name: Purdue University765 domain: purdue.edu766 categories: [education, research]767 tier: B768 discover: { rss: false }769 sensors:770 - { name: newsroom feed, url: "https://www.purdue.edu/newsroom/feed/", type: RSS, connector: rss, tier: B }771 - id: university-of-illinois772 name: University of Illinois Urbana-Champaign773 domain: illinois.edu774 categories: [education, research]775 tier: B776 aliases: [uiuc, illinois]777 discover: { rss: false }778 sensors:779 - { name: news bureau feed, url: "https://news.illinois.edu/feed/", type: RSS, connector: rss, tier: B }780 - id: university-of-wisconsin781 name: University of Wisconsin–Madison782 domain: wisc.edu783 categories: [education, research]784 tier: B785 aliases: [uw–madison, wisconsin]786 discover: { rss: false }787 sensors:788 - { name: news feed, url: "https://news.wisc.edu/feed/", type: RSS, connector: rss, tier: B }789 - id: university-of-minnesota790 name: University of Minnesota791 domain: umn.edu792 categories: [education, research]793 tier: B794 aliases: [umn]795 discover: { rss: false, sitemap: false }796 notes: "twin-cities.umn.edu answers 403 to feeds and sitemap (bot management); entity only."797798 # ───────────────────────── research institutes & national labs ─────────────────────────799 - id: cnrs800 name: CNRS801 domain: cnrs.fr802 categories: [research, science]803 tier: B804 weight: 1.2805 aliases: [centre national de la recherche scientifique]806 discover: { rss: false }807 notes: "/en/rss.xml is a stale single-item feed; the FR feed, CNRS News (EN) and CNRS Le journal are live."808 sensors:809 - { name: actualités feed, url: "https://www.cnrs.fr/fr/rss.xml", type: RSS, connector: rss, tier: B }810 - { name: cnrs news feed, url: "https://news.cnrs.fr/rss", type: RSS, connector: rss, tier: B }811 - { name: le journal feed, url: "https://lejournal.cnrs.fr/rss", type: RSS, connector: rss, tier: C }812 - id: inria813 name: Inria814 domain: inria.fr815 categories: [research, ai, developer]816 tier: B817 weight: 1.1818 discover: { rss: false }819 sensors:820 - { name: actualités feed, url: "https://www.inria.fr/fr/rss.xml", type: RSS, connector: rss, tier: B }821 - { name: news feed (en), url: "https://www.inria.fr/en/rss.xml", type: RSS, connector: rss, tier: C }822 - id: inserm823 name: Inserm824 domain: inserm.fr825 categories: [research, health]826 tier: B827 aliases: [institut national de la santé et de la recherche médicale]828 discover: { rss: false }829 sensors:830 - { name: press room feed, url: "https://presse.inserm.fr/en/feed/", type: RSS, connector: rss, tier: B }831 - { name: site feed, url: "https://www.inserm.fr/feed/", type: RSS, connector: rss, tier: C }832 - id: cea833 name: CEA834 domain: cea.fr835 categories: [research, energy, science]836 tier: B837 aliases: [commissariat à l'énergie atomique et aux énergies alternatives]838 discover: { rss: true, sitemap: false }839 notes: "SharePoint site without any RSS endpoint found (2026-09); entity only."840 - id: fraunhofer841 name: Fraunhofer-Gesellschaft842 domain: fraunhofer.de843 categories: [research, technology]844 tier: B845 weight: 1.1846 aliases: [fraunhofer]847 discover: { rss: false }848 sensors:849 - { name: press feed, url: "https://www.fraunhofer.de/en/rss/press.rss", type: RSS, connector: rss, tier: B }850 - id: helmholtz851 name: Helmholtz Association852 domain: helmholtz.de853 categories: [research, science]854 tier: B855 aliases: [helmholtz-gemeinschaft]856 discover: { rss: true, sitemap: false }857 notes: "Newsroom without RSS (2026-09); entity only."858 - id: leibniz859 name: Leibniz Association860 domain: leibniz-gemeinschaft.de861 categories: [research, science]862 tier: B863 aliases: [leibniz-gemeinschaft, leibniz]864 discover: { rss: false }865 sensors:866 - { name: news feed, url: "https://www.leibniz-gemeinschaft.de/rss.xml", type: RSS, connector: rss, tier: B }867 - id: riken868 name: RIKEN869 domain: riken.jp870 categories: [research, science]871 tier: B872 weight: 1.1873 discover: { rss: false }874 sensors:875 - { name: press releases feed, url: "https://www.riken.jp/en/feed/press_feed/", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }876 - { name: topics feed, url: "https://www.riken.jp/en/feed/topics_feed/", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } }877 - id: csiro878 name: CSIRO879 domain: csiro.au880 categories: [research, science]881 tier: B882 aliases: [commonwealth scientific and industrial research organisation]883 discover: { rss: true, sitemap: false }884 notes: "News hub without RSS and blog.csiro.au feed returns HTML (2026-09); only a 7 k-URL corporate sitemap. Entity only."885 - id: nrc-canada886 name: National Research Council Canada887 domain: nrc.canada.ca888 categories: [research, government]889 tier: B890 aliases: [nrc, cnrc, conseil national de recherches]891 discover: { rss: true, sitemap: false }892 notes: "Stories hub has no feed and canada.ca department Atom feeds return the 404 page for NRC (2026-09); entity only."893 - id: mila894 name: Mila – Quebec AI Institute895 domain: mila.quebec896 categories: [research, ai]897 tier: B898 weight: 1.1899 aliases: [mila]900 discover: { rss: false }901 sensors:902 - { name: news feed, url: "https://mila.quebec/en/rss.xml", type: RSS, connector: rss, tier: B }903 - id: vector-institute904 name: Vector Institute905 domain: vectorinstitute.ai906 categories: [research, ai]907 tier: B908 aliases: [vector]909 discover: { rss: false }910 sensors:911 - { name: news feed, url: "https://vectorinstitute.ai/feed/", type: RSS, connector: rss, tier: B }912 - id: amii913 name: Amii914 domain: amii.ca915 categories: [research, ai]916 tier: C917 aliases: [alberta machine intelligence institute]918 discover: { rss: true, sitemap: false }919 notes: "Client-rendered site with no feed (2026-09); entity only."920 - id: ivado921 name: IVADO922 domain: ivado.ca923 categories: [research, ai]924 tier: C925 discover: { rss: false }926 sensors:927 - { name: news feed, url: "https://ivado.ca/en/feed/", type: RSS, connector: rss, tier: C }928 - id: cifar929 name: CIFAR930 domain: cifar.ca931 categories: [research, ai, funding]932 tier: B933 aliases: [canadian institute for advanced research]934 discover: { rss: false }935 sensors:936 - { name: news feed, url: "https://cifar.ca/feed/", type: RSS, connector: rss, tier: B }937 - id: ai2938 name: Allen Institute for AI939 domain: allenai.org940 categories: [research, ai]941 tier: B942 weight: 1.1943 aliases: [ai2, allen ai]944 products:945 - { name: OLMo, type: AI_model, aliases: [olmo] }946 - { name: Semantic Scholar, type: service, aliases: [semantic scholar] }947 discover: { rss: false }948 notes: "Semantic Scholar (an AI2 product) has no public news feed; blog.semanticscholar.org does not resolve."949 sensors:950 - { name: blog feed, url: "https://allenai.org/rss.xml", type: RSS, connector: rss, tier: B }951 - { name: medium blog feed, url: "https://medium.com/feed/ai2-blog", type: RSS, connector: rss, tier: C }952 - id: broad-institute953 name: Broad Institute954 domain: broadinstitute.org955 categories: [research, health]956 tier: B957 aliases: [broad]958 discover: { rss: false }959 sensors:960 - { name: news feed, url: "https://www.broadinstitute.org/rss.xml", type: RSS, connector: rss, tier: B }961 - id: salk-institute962 name: Salk Institute963 domain: salk.edu964 categories: [research, health]965 tier: C966 aliases: [salk]967 discover: { rss: false }968 sensors:969 - { name: news feed, url: "https://www.salk.edu/feed/", type: RSS, connector: rss, tier: C }970 - id: scripps-research971 name: Scripps Research972 domain: scripps.edu973 categories: [research, health]974 tier: C975 discover: { rss: true, sitemap: false }976 notes: "/rss returns a valid but empty WordPress feed (2026-09); entity only."977 - id: hhmi978 name: Howard Hughes Medical Institute979 domain: hhmi.org980 categories: [research, health, funding]981 tier: B982 aliases: [hhmi]983 discover: { rss: true, sitemap: false }984 notes: "/rss.xml is an empty channel and the news hub has no feed (2026-09); entity only."985 - id: wellcome986 name: Wellcome987 domain: wellcome.org988 categories: [research, health, funding]989 tier: B990 aliases: [wellcome trust]991 discover: { rss: false, sitemap: false }992 notes: "wellcome.org answers 202 with a bot-management interstitial on every path; entity only."993 - id: sanger-institute994 name: Wellcome Sanger Institute995 domain: sanger.ac.uk996 categories: [research, health]997 tier: C998 aliases: [sanger]999 discover: { rss: false }1000 sensors:1001 - { name: news feed, url: "https://www.sanger.ac.uk/feed/", type: RSS, connector: rss, tier: C }1002 - id: embl1003 name: EMBL1004 domain: embl.org1005 categories: [research, science]1006 tier: B1007 weight: 1.11008 aliases: [european molecular biology laboratory]1009 discover: { rss: false }1010 sensors:1011 - { name: news feed, url: "https://www.embl.org/news/feed/", type: RSS, connector: rss, tier: B }1012 - id: francis-crick-institute1013 name: Francis Crick Institute1014 domain: crick.ac.uk1015 categories: [research, health]1016 tier: B1017 aliases: [the crick]1018 discover: { rss: false, sitemap: false }1019 notes: "403 on feeds and sitemap (bot management); entity only."1020 - id: institut-pasteur1021 name: Institut Pasteur1022 domain: pasteur.fr1023 categories: [research, health]1024 tier: B1025 weight: 1.11026 aliases: [pasteur]1027 discover: { rss: true, sitemap: false }1028 notes: "/rss.xml, /fr/rss.xml and /en/rss.xml are valid but empty channels (2026-09); entity only."1029 - id: weizmann-institute1030 name: Weizmann Institute of Science1031 domain: weizmann.ac.il1032 categories: [research, science]1033 tier: B1034 aliases: [weizmann]1035 discover: { rss: false }1036 sensors:1037 - { name: compass feed, url: "https://www.weizmann.ac.il/WeizmannCompass/rss.xml", type: RSS, connector: rss, tier: B }1038 - { name: wis wander feed, url: "https://wis-wander.weizmann.ac.il/rss.xml", type: RSS, connector: rss, tier: C }1039 - id: perimeter-institute1040 name: Perimeter Institute1041 domain: perimeterinstitute.ca1042 categories: [research, science]1043 tier: C1044 aliases: [perimeter]1045 discover: { rss: true, sitemap: false }1046 notes: "/rss.xml is an empty channel; no sitemap (2026-09). Entity only."1047 - id: santa-fe-institute1048 name: Santa Fe Institute1049 domain: santafe.edu1050 categories: [research, science]1051 tier: C1052 aliases: [sfi]1053 discover: { rss: false }1054 sensors:1055 - { name: news feed, url: "https://www.santafe.edu/news-center/feed/", type: RSS, connector: rss, tier: C }1056 - id: argonne1057 name: Argonne National Laboratory1058 domain: anl.gov1059 categories: [research, science, energy]1060 tier: B1061 aliases: [argonne]1062 discover: { rss: false, sitemap: false }1063 notes: "anl.gov answers 403 to feeds and sitemap (bot management); entity only."1064 - id: oak-ridge1065 name: Oak Ridge National Laboratory1066 domain: ornl.gov1067 categories: [research, science, energy]1068 tier: B1069 aliases: [ornl, oak ridge]1070 discover: { rss: false }1071 sensors:1072 - { name: news feed, url: "https://www.ornl.gov/rss.xml", type: RSS, connector: rss, tier: B }1073 - id: los-alamos1074 name: Los Alamos National Laboratory1075 domain: lanl.gov1076 categories: [research, science]1077 tier: B1078 aliases: [lanl, los alamos]1079 discover: { rss: true, sitemap: false }1080 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."1081 - id: lawrence-livermore1082 name: Lawrence Livermore National Laboratory1083 domain: llnl.gov1084 categories: [research, science]1085 tier: B1086 aliases: [llnl, livermore]1087 discover: { rss: true, sitemap: false }1088 notes: "/rss.xml is an empty channel and /news/rss.xml returns HTML (2026-09); entity only."1089 - id: lawrence-berkeley1090 name: Lawrence Berkeley National Laboratory1091 domain: lbl.gov1092 categories: [research, science, energy]1093 tier: B1094 aliases: [berkeley lab, lbnl]1095 discover: { rss: false }1096 sensors:1097 - { name: news center feed, url: "https://newscenter.lbl.gov/feed/", type: RSS, connector: rss, tier: B }1098 - id: brookhaven1099 name: Brookhaven National Laboratory1100 domain: bnl.gov1101 categories: [research, science]1102 tier: B1103 aliases: [bnl]1104 discover: { rss: true, sitemap: false }1105 notes: "Newsroom without RSS and no sitemap (2026-09); entity only."1106 - id: fermilab1107 name: Fermilab1108 domain: fnal.gov1109 categories: [research, science]1110 tier: B1111 aliases: [fermi national accelerator laboratory]1112 discover: { rss: false }1113 sensors:1114 - { name: news feed, url: "https://news.fnal.gov/feed/", type: RSS, connector: rss, tier: B }1115 - id: slac1116 name: SLAC National Accelerator Laboratory1117 domain: slac.stanford.edu1118 categories: [research, science]1119 tier: B1120 aliases: [slac]1121 discover: { rss: false }1122 sensors:1123 - { name: news feed, url: "https://www6.slac.stanford.edu/rss.xml", type: RSS, connector: rss, tier: B }1124 - id: pnnl1125 name: Pacific Northwest National Laboratory1126 domain: pnnl.gov1127 categories: [research, science, energy]1128 tier: B1129 aliases: [pnnl]1130 discover: { rss: true, sitemap: false }1131 notes: "/rss.xml is an empty channel and /news/rss.xml is 403 (2026-09); entity only."1132 - id: sandia1133 name: Sandia National Laboratories1134 domain: sandia.gov1135 categories: [research, science, cyber]1136 tier: B1137 aliases: [sandia labs]1138 discover: { rss: false }1139 sensors:1140 - { name: news releases feed, url: "https://newsreleases.sandia.gov/feed/", type: RSS, connector: rss, tier: B }1141 - { name: news feed, url: "https://www.sandia.gov/news/feed/", type: RSS, connector: rss, tier: C }1142 - id: ncar1143 name: NCAR / UCAR1144 domain: ucar.edu1145 categories: [research, climate, weather]1146 tier: B1147 aliases: [national center for atmospheric research, ucar]1148 discover: { rss: false }1149 sensors:1150 - { name: news feed, url: "https://news.ucar.edu/rss.xml", type: RSS, connector: rss, tier: B }1151 - id: woods-hole1152 name: Woods Hole Oceanographic Institution1153 domain: whoi.edu1154 categories: [research, climate, science]1155 tier: B1156 aliases: [whoi]1157 discover: { rss: false }1158 sensors:1159 - { name: news feed, url: "https://www.whoi.edu/feed/", type: RSS, connector: rss, tier: B }1160 - id: scripps-oceanography1161 name: Scripps Institution of Oceanography1162 domain: scripps.ucsd.edu1163 categories: [research, climate, science]1164 tier: B1165 aliases: [scripps oceanography]1166 discover: { rss: false }1167 sensors:1168 - { name: news feed, url: "https://scripps.ucsd.edu/news/feed", type: RSS, connector: rss, tier: B }1169 - id: alfred-wegener-institute1170 name: Alfred Wegener Institute1171 domain: awi.de1172 categories: [research, climate, science]1173 tier: C1174 aliases: [awi]1175 discover: { rss: true, sitemap: false }1176 notes: "Press pages without RSS (2026-09); entity only."1177 - id: triumf1178 name: TRIUMF1179 domain: triumf.ca1180 categories: [research, science]1181 tier: C1182 discover: { rss: false }1183 sensors:1184 - { name: news feed, url: "https://triumf.ca/feed", type: RSS, connector: rss, tier: C }1185 - id: snolab1186 name: SNOLAB1187 domain: snolab.ca1188 categories: [research, science]1189 tier: C1190 discover: { rss: false }1191 sensors:1192 - { name: news feed, url: "https://www.snolab.ca/news/feed/", type: RSS, connector: rss, tier: C }1193 - id: canadian-light-source1194 name: Canadian Light Source1195 domain: lightsource.ca1196 categories: [research, science]1197 tier: C1198 aliases: [cls]1199 discover: { rss: true, sitemap: false }1200 notes: "Only sector news pages (HTML) — no RSS found (2026-09); entity only."1201 - id: eso1202 name: European Southern Observatory1203 domain: eso.org1204 categories: [research, space, science]1205 tier: B1206 weight: 1.11207 aliases: [eso]1208 discover: { rss: false }1209 sensors:1210 - { name: news feed, url: "https://www.eso.org/public/news/feed/", type: RSS, connector: rss, tier: B }1211 - { name: announcements feed, url: "https://feeds.feedburner.com/EsoAnnouncements", type: RSS, connector: rss, tier: C }1212 - { name: blog feed, url: "https://www.eso.org/public/blog/feed/", type: RSS, connector: rss, tier: C }1213 - id: nrao1214 name: National Radio Astronomy Observatory1215 domain: nrao.edu1216 categories: [research, space, science]1217 tier: B1218 aliases: [nrao]1219 discover: { rss: false }1220 sensors:1221 - { name: news feed, url: "https://public.nrao.edu/news/feed/", type: RSS, connector: rss, tier: B }1222 - id: noirlab1223 name: NSF NOIRLab1224 domain: noirlab.edu1225 categories: [research, space, science]1226 tier: B1227 aliases: [noirlab]1228 discover: { rss: false }1229 sensors:1230 - { name: news feed, url: "https://noirlab.edu/public/news/feed/", type: RSS, connector: rss, tier: B }1231 - id: stsci1232 name: Space Telescope Science Institute1233 domain: stsci.edu1234 categories: [research, space, science]1235 tier: B1236 aliases: [stsci, webb telescope, hubble]1237 products:1238 - { name: James Webb Space Telescope, type: product, aliases: [jwst, webb] }1239 - { name: Hubble Space Telescope, type: product, aliases: [hubble] }1240 discover: { rss: false, sitemap: false }1241 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."12421243 # ───────────────────────── journals, publishers, preprints, scholarly infrastructure ─────────────────────────1244 - id: cell-press1245 name: Cell Press1246 domain: cell.com1247 categories: [research, science, health]1248 tier: B1249 weight: 1.11250 aliases: [cell]1251 products:1252 - { name: Cell, type: product }1253 discover: { rss: false }1254 sensors:1255 - { name: cell current issue feed, url: "https://www.cell.com/cell/current.rss", type: RSS, connector: rss, tier: B }1256 - { name: cell in press feed, url: "https://www.cell.com/cell/inpress.rss", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }1257 - id: the-lancet1258 name: The Lancet1259 domain: thelancet.com1260 categories: [research, health]1261 tier: B1262 weight: 1.21263 aliases: [lancet]1264 discover: { rss: false }1265 sensors:1266 - { name: current issue feed, url: "https://www.thelancet.com/rssfeed/lancet_current.xml", type: RSS, connector: rss, tier: B }1267 - { name: online first feed, url: "https://www.thelancet.com/rssfeed/lancet_online.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }1268 - id: nejm1269 name: New England Journal of Medicine1270 domain: nejm.org1271 categories: [research, health]1272 tier: B1273 weight: 1.21274 aliases: [nejm]1275 discover: { rss: false }1276 sensors:1277 - { 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 } }1278 - id: jama1279 name: JAMA Network1280 domain: jamanetwork.com1281 categories: [research, health]1282 tier: B1283 weight: 1.11284 aliases: [jama]1285 discover: { rss: false }1286 sensors:1287 - { name: jama current issue feed, url: "https://jamanetwork.com/rss/site_3/67.xml", type: RSS, connector: rss, tier: B }1288 - { name: jama online first feed, url: "https://jamanetwork.com/rss/site_3/onlineFirst_67.xml", type: RSS, connector: rss, tier: B }1289 - id: bmj1290 name: The BMJ1291 domain: bmj.com1292 categories: [research, health]1293 tier: B1294 weight: 1.11295 aliases: [british medical journal]1296 discover: { rss: false }1297 sensors:1298 - { name: recent articles feed, url: "https://www.bmj.com/rss/recent.xml", type: RSS, connector: rss, tier: B }1299 - id: pnas1300 name: PNAS1301 domain: pnas.org1302 categories: [research, science]1303 tier: B1304 weight: 1.11305 aliases: [proceedings of the national academy of sciences]1306 discover: { rss: false }1307 sensors:1308 - { 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 } }1309 - id: plos1310 name: PLOS1311 domain: plos.org1312 categories: [research, science]1313 tier: B1314 aliases: [public library of science]1315 products:1316 - { name: PLOS ONE, type: product, aliases: [plos one] }1317 - { name: PLOS Biology, type: product }1318 discover: { rss: false }1319 sensors:1320 - { name: plos one feed, url: "https://journals.plos.org/plosone/feed/atom", type: ATOM, connector: rss, tier: B }1321 - { name: plos biology feed, url: "https://journals.plos.org/plosbiology/feed/atom", type: ATOM, connector: rss, tier: C }1322 - { name: blog feed, url: "https://theplosblog.plos.org/feed/", type: RSS, connector: rss, tier: C }1323 - id: elife1324 name: eLife1325 domain: elifesciences.org1326 categories: [research, science]1327 tier: B1328 discover: { rss: false }1329 sensors:1330 - { name: recent articles feed, url: "https://elifesciences.org/rss/recent.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }1331 - { name: ahead of print feed, url: "https://elifesciences.org/rss/ahead.xml", type: RSS, connector: rss, tier: C }1332 - id: frontiers1333 name: Frontiers1334 domain: frontiersin.org1335 categories: [research, science]1336 tier: B1337 aliases: [frontiers media]1338 discover: { rss: false }1339 sensors:1340 - { name: news feed, url: "https://www.frontiersin.org/news/rss", type: RSS, connector: rss, tier: B }1341 - { name: frontiers in ai feed, url: "https://www.frontiersin.org/journals/artificial-intelligence/rss", type: RSS, connector: rss, tier: C }1342 - id: elsevier1343 name: Elsevier1344 domain: elsevier.com1345 categories: [research, media]1346 tier: B1347 weight: 1.11348 products:1349 - { name: ScienceDirect, type: service }1350 - { name: Scopus, type: service }1351 discover: { rss: true, sitemap: false }1352 notes: "No RSS on Elsevier Connect / press releases and no sitemap (2026-09); entity only."1353 - id: wiley1354 name: Wiley1355 domain: wiley.com1356 categories: [research, media]1357 tier: B1358 aliases: [john wiley & sons]1359 discover: { rss: false, sitemap: false }1360 notes: "newsroom.wiley.com answers 403 to feeds (bot management); entity only."1361 - id: acm1362 name: ACM1363 domain: acm.org1364 categories: [research, developer, standards]1365 tier: B1366 aliases: [association for computing machinery]1367 products:1368 - { name: Turing Award, type: product, aliases: [acm turing award] }1369 - { name: Communications of the ACM, type: product, aliases: [cacm] }1370 discover: { rss: false, sitemap: false }1371 notes: "acm.org, cacm.acm.org and awards.acm.org all answer 403 to feeds (bot management); entity only."1372 - id: ieee-spectrum1373 name: IEEE Spectrum1374 domain: spectrum.ieee.org1375 categories: [research, technology, ai, media]1376 tier: B1377 weight: 1.11378 aliases: [ieee]1379 discover: { rss: false }1380 sensors:1381 - { name: all articles feed, url: "https://spectrum.ieee.org/feeds/feed.rss", type: RSS, connector: rss, tier: B }1382 - { name: ai topic feed, url: "https://spectrum.ieee.org/feeds/topic/artificial-intelligence.rss", type: RSS, connector: rss, tier: C }1383 - id: biorxiv1384 name: bioRxiv1385 domain: biorxiv.org1386 categories: [research, science, health]1387 tier: B1388 weight: 1.11389 llm: false1390 discover: { rss: false }1391 notes: "High-volume preprint stream — heuristics only. Subject feeds: connect.biorxiv.org/biorxiv_xml.php?subject=<slug>."1392 sensors:1393 - { name: all preprints feed, url: "https://connect.biorxiv.org/biorxiv_xml.php?subject=all", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }1394 - { name: neuroscience feed, url: "https://connect.biorxiv.org/biorxiv_xml.php?subject=neuroscience", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } }1395 - { name: bioinformatics feed, url: "https://connect.biorxiv.org/biorxiv_xml.php?subject=bioinformatics", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } }1396 - id: medrxiv1397 name: medRxiv1398 domain: medrxiv.org1399 categories: [research, health]1400 tier: B1401 weight: 1.11402 llm: false1403 discover: { rss: false }1404 notes: "High-volume preprint stream — heuristics only."1405 sensors:1406 - { name: all preprints feed, url: "https://connect.medrxiv.org/medrxiv_xml.php?subject=all", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }1407 - { name: infectious diseases feed, url: "https://connect.medrxiv.org/medrxiv_xml.php?subject=infectious_diseases", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } }1408 - { name: epidemiology feed, url: "https://connect.medrxiv.org/medrxiv_xml.php?subject=epidemiology", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } }1409 - id: chemrxiv1410 name: ChemRxiv1411 domain: chemrxiv.org1412 categories: [research, science]1413 tier: C1414 discover: { rss: false, sitemap: false }1415 notes: "Cambridge Open Engage answers 403 to the RSS and public API (bot management); entity only."1416 - id: ssrn1417 name: SSRN1418 domain: ssrn.com1419 categories: [research, finance]1420 tier: C1421 aliases: [social science research network]1422 discover: { rss: false, sitemap: false }1423 notes: "ssrn.com and papers.ssrn.com answer 403 (bot management); entity only."1424 - id: nber1425 name: National Bureau of Economic Research1426 domain: nber.org1427 categories: [research, finance, statistics]1428 tier: B1429 weight: 1.21430 aliases: [nber]1431 discover: { rss: false }1432 sensors:1433 - { name: new working papers feed, url: "https://www.nber.org/rss/new.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }1434 - { name: releases feed, url: "https://www.nber.org/rss/releases.xml", type: RSS, connector: rss, tier: C }1435 - id: repec1436 name: RePEc1437 domain: repec.org1438 categories: [research, finance]1439 tier: C1440 aliases: [research papers in economics, ideas repec]1441 discover: { rss: false }1442 sensors:1443 - { name: blog feed, url: "https://blog.repec.org/feed/", type: RSS, connector: rss, tier: C }1444 - id: retraction-watch1445 name: Retraction Watch1446 domain: retractionwatch.com1447 categories: [research, media]1448 tier: B1449 discover: { rss: false }1450 sensors:1451 - { name: posts feed, url: "https://retractionwatch.com/feed/", type: RSS, connector: rss, tier: B }1452 - id: crossref1453 name: Crossref1454 domain: crossref.org1455 categories: [research, infrastructure, open-data]1456 tier: B1457 weight: 1.11458 products:1459 - { name: Crossref REST API, type: API }1460 discover: { rss: false, status: true }1461 sensors:1462 - { name: status, url: "https://status.crossref.org/api/v2/summary.json", type: STATUSPAGE, connector: statuspage, tier: S }1463 - { name: blog feed, url: "https://www.crossref.org/blog/index.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }1464 - id: orcid1465 name: ORCID1466 domain: orcid.org1467 categories: [research, infrastructure]1468 tier: B1469 discover: { rss: false }1470 sensors:1471 - { name: news feed, url: "https://info.orcid.org/feed/", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }1472 - id: doaj1473 name: DOAJ1474 domain: doaj.org1475 categories: [research, open-data]1476 tier: C1477 aliases: [directory of open access journals]1478 discover: { rss: false }1479 sensors:1480 - { name: new journals feed, url: "https://doaj.org/feed", type: ATOM, connector: rss, tier: C, config: { maxItems: 50 } }1481 - { name: blog feed, url: "https://blog.doaj.org/feed/", type: RSS, connector: rss, tier: C }1482 - id: zenodo1483 name: Zenodo1484 domain: zenodo.org1485 categories: [research, open-data, infrastructure]1486 tier: B1487 products:1488 - { name: Zenodo REST API, type: API }1489 discover: { rss: false, sitemap: false }1490 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."1491 - id: center-for-open-science1492 name: Center for Open Science1493 domain: cos.io1494 categories: [research, infrastructure]1495 tier: B1496 aliases: [cos, osf, open science framework]1497 products:1498 - { name: OSF, type: service, aliases: [open science framework] }1499 discover: { rss: false, status: true }1500 sensors:1501 - { name: osf status, url: "https://status.cos.io/api/v2/summary.json", type: STATUSPAGE, connector: statuspage, tier: S }1502 - { name: blog feed, url: "https://www.cos.io/blog/rss.xml", type: RSS, connector: rss, tier: C }1503 - id: figshare1504 name: Figshare1505 domain: figshare.com1506 categories: [research, infrastructure]1507 tier: B1508 discover: { rss: false, status: true }1509 notes: "Blog answers 202 (bot management); the status page is the only sensor."1510 sensors:1511 - { name: status, url: "https://status.figshare.com/api/v2/summary.json", type: STATUSPAGE, connector: statuspage, tier: S }1512 - id: dryad1513 name: Dryad1514 domain: datadryad.org1515 categories: [research, open-data]1516 tier: C1517 discover: { rss: false }1518 sensors:1519 - { name: blog feed, url: "https://blog.datadryad.org/feed", type: RSS, connector: rss, tier: C }1520 - id: europe-pmc1521 name: Europe PMC1522 domain: europepmc.org1523 categories: [research, health, open-data]1524 tier: B1525 llm: false1526 products:1527 - { name: Europe PMC REST API, type: API }1528 discover: { rss: false }1529 notes: "europepmc.org RSS is 403; the EBI REST search (newest preprints, SRC:PPR) is polled instead — heuristics only."1530 sensors:1531 - { 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 } }15321533 # ───────────────────────── funders & science policy ─────────────────────────1534 - id: erc1535 name: European Research Council1536 domain: erc.europa.eu1537 categories: [research, funding, government]1538 tier: B1539 weight: 1.11540 aliases: [erc]1541 discover: { rss: false }1542 sensors:1543 - { name: news feed, url: "https://erc.europa.eu/rss.xml", type: RSS, connector: rss, tier: B }1544 - id: cordis1545 name: CORDIS / Horizon Europe1546 domain: cordis.europa.eu1547 categories: [research, funding, government]1548 tier: B1549 aliases: [cordis, horizon europe]1550 discover: { rss: false, sitemap: false }1551 notes: "/rss/en/news returns HTML (feed discontinued); entity only."1552 - id: ukri1553 name: UK Research and Innovation1554 domain: ukri.org1555 categories: [research, funding, government]1556 tier: B1557 weight: 1.11558 aliases: [ukri]1559 discover: { rss: false }1560 sensors:1561 - { name: news feed, url: "https://www.ukri.org/news/feed/", type: RSS, connector: rss, tier: B }1562 - id: dfg1563 name: Deutsche Forschungsgemeinschaft1564 domain: dfg.de1565 categories: [research, funding]1566 tier: B1567 aliases: [dfg, german research foundation]1568 discover: { rss: false }1569 sensors:1570 - { name: press releases feed, url: "https://www.dfg.de/service/rss/en/324778/feed.rss", type: RSS, connector: rss, tier: B }1571 - id: anr1572 name: Agence nationale de la recherche1573 domain: anr.fr1574 categories: [research, funding, government]1575 tier: B1576 aliases: [anr]1577 discover: { rss: false }1578 notes: "The generic /rss/ is empty; the calls-for-proposals feed (/rss/?aap) is live."1579 sensors:1580 - { name: appels à projets feed, url: "https://anr.fr/rss/?aap", type: RSS, connector: rss, tier: B }1581 - id: nserc1582 name: NSERC1583 domain: nserc-crsng.gc.ca1584 categories: [research, funding, government]1585 tier: B1586 aliases: [crsng, natural sciences and engineering research council]1587 discover: { rss: false, sitemap: false }1588 notes: "Classic ASP site without RSS; canada.ca department Atom feed returns the 404 page (2026-09). Entity only."1589 - id: sshrc1590 name: SSHRC1591 domain: sshrc-crsh.canada.ca1592 categories: [research, funding, government]1593 tier: C1594 aliases: [crsh, social sciences and humanities research council]1595 discover: { rss: true, sitemap: false }1596 notes: "No feed found after the move to sshrc-crsh.canada.ca (2026-09); entity only."1597 - id: cihr1598 name: CIHR1599 domain: cihr-irsc.gc.ca1600 categories: [research, funding, health, government]1601 tier: C1602 aliases: [irsc, canadian institutes of health research]1603 discover: { rss: false, sitemap: false }1604 notes: "Site links to a canada.ca Atom feed that returns the 404 page (2026-09); entity only."1605 - id: frq1606 name: Fonds de recherche du Québec1607 domain: frq.gouv.qc.ca1608 categories: [research, funding, government]1609 tier: B1610 aliases: [frq, frqnt, frqs, frqsc]1611 discover: { rss: false }1612 sensors:1613 - { name: actualités feed, url: "https://frq.gouv.qc.ca/feed/", type: RSS, connector: rss, tier: B }1614 - { name: news feed (en), url: "https://frq.gouv.qc.ca/en/feed/", type: RSS, connector: rss, tier: C }1615 - id: genome-canada1616 name: Genome Canada1617 domain: genomecanada.ca1618 categories: [research, funding, health]1619 tier: C1620 discover: { rss: false }1621 sensors:1622 - { name: news feed, url: "https://genomecanada.ca/feed/", type: RSS, connector: rss, tier: C }1623 - id: cfi1624 name: Canada Foundation for Innovation1625 domain: innovation.ca1626 categories: [research, funding, government]1627 tier: C1628 aliases: [cfi, fci]1629 discover: { rss: false }1630 sensors:1631 - { name: news feed, url: "https://www.innovation.ca/rss.xml", type: RSS, connector: rss, tier: C }1632 - id: gates-foundation1633 name: Gates Foundation1634 domain: gatesfoundation.org1635 categories: [funding, health, ngo]1636 tier: B1637 weight: 1.11638 aliases: [bill & melinda gates foundation]1639 discover: { rss: false, sitemap: false }1640 notes: "Media center without RSS; only a 1.1 k-URL corporate sitemap (2026-09). Entity only."1641 - id: czi1642 name: Chan Zuckerberg Initiative1643 domain: chanzuckerberg.com1644 categories: [funding, research, health]1645 tier: B1646 aliases: [czi]1647 discover: { rss: false }1648 sensors:1649 - { name: newsroom feed, url: "https://chanzuckerberg.com/newsroom/feed/", type: RSS, connector: rss, tier: B }1650 - id: simons-foundation1651 name: Simons Foundation1652 domain: simonsfoundation.org1653 categories: [funding, research, science]1654 tier: B1655 discover: { rss: false }1656 sensors:1657 - { name: news feed, url: "https://www.simonsfoundation.org/feed/", type: RSS, connector: rss, tier: B }1658 - id: sloan-foundation1659 name: Alfred P. Sloan Foundation1660 domain: sloan.org1661 categories: [funding, research]1662 tier: C1663 aliases: [sloan]1664 discover: { rss: false, sitemap: false }1665 notes: "sloan.org answers 403 to feeds (bot management); entity only."1666 - id: templeton-foundation1667 name: John Templeton Foundation1668 domain: templeton.org1669 categories: [funding, research]1670 tier: C1671 aliases: [templeton]1672 discover: { rss: true, sitemap: false }1673 notes: "/feed is a valid but empty WordPress channel (2026-09); entity only."1674 - id: jst1675 name: Japan Science and Technology Agency1676 domain: jst.go.jp1677 categories: [research, funding, government]1678 tier: C1679 aliases: [jst]1680 discover: { rss: true, sitemap: false }1681 notes: "No RSS on the EN site (2026-09); entity only."1682 - id: nsfc1683 name: National Natural Science Foundation of China1684 domain: nsfc.gov.cn1685 categories: [research, funding, government]1686 tier: C1687 aliases: [nsfc]1688 discover: { rss: true, sitemap: false }1689 notes: "No feed on the EN site (2026-09); entity only."1690 - id: arc-australia1691 name: Australian Research Council1692 domain: arc.gov.au1693 categories: [research, funding, government]1694 tier: C1695 aliases: [arc]1696 discover: { rss: false, sitemap: false }1697 notes: "arc.gov.au drops connections from our network (geo/bot filtering, 2026-09); entity only."1698 - id: royal-society1699 name: Royal Society1700 domain: royalsociety.org1701 categories: [research, science]1702 tier: B1703 weight: 1.11704 discover: { rss: false, sitemap: false }1705 notes: "royalsociety.org and royalsocietypublishing.org answer 403 to feeds and sitemap (bot management); entity only."1706 - id: national-academies1707 name: National Academies of Sciences, Engineering, and Medicine1708 domain: nationalacademies.org1709 categories: [research, science, government]1710 tier: B1711 weight: 1.11712 aliases: [nasem, national academies press]1713 discover: { rss: false }1714 notes: "The news hub has no RSS; the National Academies Press new-titles Atom feed is the sensor."1715 sensors:1716 - { name: nap new titles feed, url: "https://nap.nationalacademies.org/rss/new.xml", type: ATOM, connector: rss, tier: B, config: { maxItems: 50 } }1717 - id: aaas1718 name: AAAS1719 domain: aaas.org1720 categories: [research, science]1721 tier: B1722 aliases: [american association for the advancement of science, eurekalert]1723 discover: { rss: true, sitemap: false }1724 notes: "aaas.org news has no RSS and EurekAlert! removed its RSS feeds (2026-09); Science journal is the separate `science` source. Entity only."1725 - id: nobel-prize1726 name: Nobel Prize1727 domain: nobelprize.org1728 categories: [research, science]1729 tier: B1730 weight: 1.21731 aliases: [nobel, nobel foundation]1732 discover: { rss: false }1733 sensors:1734 - { name: news feed, url: "https://www.nobelprize.org/feed/", type: RSS, connector: rss, tier: B }1735 - id: breakthrough-prize1736 name: Breakthrough Prize1737 domain: breakthroughprize.org1738 categories: [research, science]1739 tier: C1740 discover: { rss: true, sitemap: false }1741 notes: "No RSS on /News (2026-09); entity only."1742 - id: imu1743 name: International Mathematical Union1744 domain: mathunion.org1745 categories: [research, science]1746 tier: C1747 aliases: [fields medal]1748 products:1749 - { name: Fields Medal, type: product }1750 discover: { rss: true, sitemap: false }1751 notes: "No RSS on imu-news (2026-09); entity only."1752 - id: kavli-foundation1753 name: Kavli Foundation1754 domain: kavlifoundation.org1755 categories: [funding, science]1756 tier: C1757 aliases: [kavli prize]1758 discover: { rss: true, sitemap: false }1759 notes: "No RSS on kavlifoundation.org or kavliprize.org (2026-09); entity only."1760 - id: wolf-foundation1761 name: Wolf Foundation1762 domain: wolffund.org.il1763 categories: [research, science]1764 tier: C1765 aliases: [wolf prize]1766 discover: { rss: false }1767 sensors:1768 - { name: news feed, url: "https://wolffund.org.il/feed/", type: RSS, connector: rss, tier: C }1769