[{"data":1,"prerenderedAt":311},["ShallowReactive",2],{"project-48840207":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":5,"maker":10,"posted_at":11,"year":12,"points":13,"comments":14,"rank_in_year":15,"shown_in_year":16,"top":17,"tier":18,"category":19,"subcategory":20,"format":21,"keywords":22,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":43,"post_text":45,"what":46,"said":100,"maker_in_thread":183,"shape":195,"grid":199,"attempts":272,"same_week":273,"maker_shows":34,"maker_hidden":303,"reader_version":304,"card":305},"48840207","tomesphere.com","I mapped 8.5M research papers into an interactive atlas","title","Show HN: I mapped 8.5M research papers into an interactive atlas","https:\u002F\u002Ftomesphere.com\u002Fatlas","leonickson",1783563804,2026,85,28,797,4366,19,"notable","learning_science","research paper discovery","web_app",[23,24,25,26,27],"research papers","citation graph","paper visualization","literature search","mcp server","mixed",0.065,{"positive":31,"neutral":32,"mixed":33,"critical":34},4,6,1,3,14,{"execution":37,"idea":38,"design":40,"performance":42},{"positive":33,"critical":33},{"positive":33,"critical":39},2,{"positive":33,"critical":41},0,{"positive":41,"critical":41},[44,33,33,34,41,41,41,41,44,34,41,34,41,34,41,41,41,41,34,44,33,41,34,41,44,41,34,41],5,"Reading a paper means opening a PDF, then hunting separately for the code, the citations, whether it replicated, and what genes\u002Fdrugs it touches. I spent a few months trying to fix that.\n\nTwo parts:\n\n1. The map: I embedded 8.5M papers (arXiv, PubMed Central, bioRxiv, medRxiv), ran UMAP to lay them out in 2D, and render them with a WebGL scatterplot. Every dot is a paper — click it for an LLM TLDR, key findings, citations, peer reviews (where they exist), and similar work. Zoom in and the clusters are labeled by topic.\n\n2. Rich paper pages + an MCP server: each paper is rebuilt with linked gene",{"problem":47,"audience":53,"pricing":61,"motivation":68,"time_to_build":72,"stack":76,"openness":97,"stage":98,"team_size":99},{"value":48,"source":49,"evidence":50},"Reading papers requires hunting separately for code, citations, replication status and linked genes, drugs and trials.","maker",[51],{"id":52},"post",{"value":54,"source":55,"evidence":56},"Researchers reading scientific papers, and agents working with papers.","inferred",[57,58],{"id":52},{"id":59,"by":10,"text":60},"48851770","It is all open, bulk-downloadable sources. Here are some links. ``` - arXiv: bulk on S3 (https:\u002F\u002Finfo.arxiv.org\u002Fhelp\u002Fbulk_data_s3.html) - PubMed Central Open Access: AWS Open…",{"value":62,"source":49,"evidence":63},"Free to explore, no signup; business model undecided.",[64,65],{"id":52},{"id":66,"by":10,"text":67},"48853114","Hello, 1. Yes, I am working on it, I will soon release it for Firefox and Safari (by this weekend). 2. For now I am just trying to see what people want, may be the business model…",{"value":69,"source":49,"evidence":70},"Make reading papers less fragmented by linking code, citations, entities and trials.",[71],{"id":52},{"value":73,"source":49,"evidence":74},"A few months.",[75],{"id":52},[77,81,85,89,93],{"value":78,"source":49,"evidence":79},"Next.js",[80],{"id":52},{"value":82,"source":49,"evidence":83},"Postgres (Neon)",[84],{"id":52},{"value":86,"source":49,"evidence":87},"Cloudflare R2",[88],{"id":52},{"value":90,"source":49,"evidence":91},"UMAP\u002FHDBSCAN",[92],{"id":52},{"value":94,"source":49,"evidence":95},"WebGL",[96],{"id":52},"free","launched","unknown",{"praise":101,"objections":117,"requests":137,"questions":156,"alternatives":168},[102,110],{"value":103,"source":104,"evidence":105},"Useful for jumping between arXiv, GitHub and peer reviews.","commenter",[106],{"id":107,"by":108,"text":109},"48895210","Jahnavi_Aleti","Jumping between arXiv, GitHub, and peer reviews is such a real pain. The “copy page as markdown for your LLM” feature is especially useful.Curious how accurate the entity linking…",{"value":111,"source":104,"evidence":112},"Fun way to explore a corpus.",[113],{"id":114,"by":115,"text":116},"48850507","specproc","I love them! It's a really nice, fun way to explore a corpus. Cosmograph for this sort of thing is great, it supports graphs as well as 2D projections, and is blazing fast. That…",[118,126],{"value":119,"source":104,"evidence":120},"Map visualizations may have little use beyond looking cool.",[121,125],{"id":122,"by":123,"text":124},"48850230","murkt","I remember similar kind of visualization from a decade ago, called paperscape. Looked cool, worked on clustering using citations and references. Never got any idea on any use…",{"id":114,"by":115,"text":116},{"value":127,"source":104,"evidence":128},"Title search and search-to-map filtering don't work well yet.",[129,133],{"id":130,"by":131,"text":132},"48851927","goodwillhunting","this is fun! even for casual users. I searched \"James Webb\" and got 'James Webb Space Telescope: data, problems, and resolution A. D. Dolgov · 2023 · 1 cites' as my first result,…",{"id":134,"by":135,"text":136},"48850250","gavinray","Neat! Two questions I had after using it: 1) Is there a way to filter the visual atlas by the search term? For instance, I searched \"ribosome\" and it gave me a list, but I…",[138,145,149],{"value":139,"source":104,"evidence":140},"Firefox extension support.",[141],{"id":142,"by":143,"text":144},"48852283","GymInMeCricket","I see there is a Chrome extension, but I have not used Chrome since their adblocker blocker announcement. Is a Firefox extension planned? Also, what is the business model? Is…",{"value":146,"source":104,"evidence":147},"Filter the map by search term.",[148],{"id":134,"by":135,"text":136},{"value":150,"source":104,"evidence":151},"Show relationships between nearby papers.",[152],{"id":153,"by":154,"text":155},"48868405","rahulb0802","I really like the clustering aspect of this. It would be cool if there was a way to articulate some sort of relationship between two adjacent or nearby papers in this tool.",[157,161],{"value":158,"source":104,"evidence":159},"How accurate is entity linking for genes and diseases?",[160],{"id":107,"by":108,"text":109},{"value":162,"source":104,"evidence":163},"Where are the papers sourced from?",[164],{"id":165,"by":166,"text":167},"48851522","vignyBot","Just curious where do you source all those papers?",[169,175,179],{"value":170,"source":104,"evidence":171},"ResearchRabbit, Connected Papers, Litmaps",[172],{"id":173,"by":135,"text":174},"48850629","ResearchRabbit is free and has this feature! https:\u002F\u002Fwww.researchrabbit.ai\u002F ConnectedPapers also has this but they started to limit unless you pay:…",{"value":176,"source":104,"evidence":177},"Paperclip MCP",[178],{"id":134,"by":135,"text":136},{"value":180,"source":104,"evidence":181},"Paperscape",[182],{"id":122,"by":123,"text":124},{"comments":184,"answered":32,"key":185},11,[186,189,192],{"id":187,"text":188},"48851200","Hi, I love the genre too. Cosmograph is wonderful, I did try it, but because of its license restriction I could not use it for this project. I do agree that beyond an initial…",{"id":190,"text":191},"48850952","Hello, I agree with you, viz are just cool and might not really have a usecase. In this project map is not the product, it is 1 of 4 parts and to be honest the least important.…",{"id":193,"text":194},"48851615","The project has four parts, and I think you may have used the search in the navigation bar. That search is for the paper page (detailed information about that specific paper).…",{"commenters":196,"max_depth":31,"maker_replies":184,"first_comment_mins":197,"lifespan_hours":198},17,953,135,[200,202,204,207,209,211,213,216,217,221,223,225,229,232,234,235,237,241,244,247,250,253,256,261,263,268,270,271],[107,41,44,201,108,41],"project\u002Fpositive\u002Fexecution",[122,33,33,203,123,41],"project\u002Fcritical\u002Fidea",[205,33,33,203,206,41],"48850261","addycb",[114,33,34,208,115,41],"project\u002Fmixed\u002Fidea",[187,33,41,210,10,33],"maker\u002Fneutral\u002Fidea",[173,33,41,212,135,41],"other\u002Fneutral\u002Fidea",[214,33,41,212,215,41],"48852379","aziis98",[190,33,41,210,10,33],[218,33,44,219,220,41],"48880075","project\u002Fpositive\u002Fidea","figassis",[134,39,34,222,135,41],"project\u002Fneutral\u002Fdesign",[193,39,41,224,10,33],"maker\u002Fneutral\u002Fdesign",[226,34,34,227,228,41],"48852470","project\u002Fneutral\u002Fperformance","ColinEberhardt",[230,34,41,231,10,33],"48852993","maker\u002Fneutral\u002Fnone",[142,31,34,233,143,41],"project\u002Fneutral\u002Fnone",[66,31,41,231,10,33],[236,31,41,231,10,33],"48909738",[238,44,41,239,240,41],"48853174","other\u002Fneutral\u002Fnone","mfscholar",[242,44,41,243,10,33],"48853377","other\u002Fneutral\u002Fdesign",[245,32,34,222,246,41],"48853299","hadi121",[153,248,44,249,154,41],7,"project\u002Fpositive\u002Fdesign",[130,251,33,252,131,41],8,"project\u002Fcritical\u002Fexecution",[254,251,41,255,10,33],"48853025","maker\u002Fneutral\u002Fexecution",[257,258,34,259,260,41],"48863820",9,"project\u002Fneutral\u002Fexecution","Kerbonut",[262,258,41,255,10,33],"48872049",[264,265,44,266,267,41],"48852088",10,"project\u002Fpositive\u002Fnone","VinayUPrabhu",[269,265,41,231,10,33],"48853355",[165,184,34,233,166,41],[59,184,41,201,10,33],[],[274,279,284,288,293,298],{"id":275,"name":276,"points":277,"category":278},"48845049","18 Words",1160,"games",{"id":280,"name":281,"points":282,"category":283},"48842459","colibri",937,"ai",{"id":285,"name":286,"points":287,"category":278},"48896286","Super Dario",397,{"id":289,"name":290,"points":291,"category":292},"48875377","Ant",330,"languages",{"id":294,"name":295,"points":296,"category":297},"48883305","Juggler",280,"dev_tools",{"id":299,"name":300,"points":301,"category":302},"48926939","Firefox in WebAssembly",273,"creative",false,"v2",{"id":306,"name":5,"line":6,"ai":303,"cat":19,"year":12,"points":13,"comments":14,"rec":28,"s":307,"top":17,"kw":308,"maker":10,"domain":5,"tier":18,"attempts":41,"strip":309,"url":9,"mix":310,"praise":103,"objection":119,"sub":20},48840207,0.07,[23,24,25,26,27],"5113000053030300003510305030",[31,32,33,34],1794036704545]