Working on chemistry? What if you could search chemistry findings instead of papers?</p>\n<p>We turned 147,000 papers into <strong>2.4 million searchable claims</strong>, making it possible to find results, compare evidence, and surface contradictions.</p>\n<p>Try AskChem: 🔎 <a href=\"https://askchem.org\" rel=\"nofollow\">https://askchem.org</a></p>\n<p>Everything is open:<br>🤗 <a href=\"https://huggingface.co/datasets/bing-yan/askchem\">https://huggingface.co/datasets/bing-yan/askchem</a><br>💻 <a href=\"https://github.com/bingyan4science/askchem\" rel=\"nofollow\">https://github.com/bingyan4science/askchem</a></p>\n","updatedAt":"2026-07-31T02:23:49.731Z","author":{"_id":"634656667393804ce0d8c268","avatarUrl":"/avatars/1625843226d2c1611419dfb5de16722f.svg","fullname":"Bing Yan","name":"bing-yan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8358682990074158},"editors":["bing-yan"],"editorAvatarUrls":["/avatars/1625843226d2c1611419dfb5de16722f.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.28618","authors":[{"_id":"6a6c01687bd25d8874c070c4","user":{"_id":"634656667393804ce0d8c268","avatarUrl":"/avatars/1625843226d2c1611419dfb5de16722f.svg","isPro":false,"fullname":"Bing Yan","user":"bing-yan","type":"user","name":"bing-yan"},"name":"Bing Yan","status":"claimed_verified","statusLastChangedAt":"2026-07-31T08:45:05.432Z","hidden":false},{"_id":"6a6c01687bd25d8874c070c5","name":"Gregory Wolfe","hidden":false},{"_id":"6a6c01687bd25d8874c070c6","name":"Stefano Martiniani","hidden":false},{"_id":"6a6c01687bd25d8874c070c7","name":"Kyunghyun Cho","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/634656667393804ce0d8c268/p4ftw2yqzwSrQHFsgizJj.mp4"],"publishedAt":"2026-07-30T00:00:00.000Z","submittedOnDailyAt":"2026-07-31T00:00:00.000Z","title":"AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis","submittedOnDailyBy":{"_id":"634656667393804ce0d8c268","avatarUrl":"/avatars/1625843226d2c1611419dfb5de16722f.svg","isPro":false,"fullname":"Bing Yan","user":"bing-yan","type":"user","name":"bing-yan"},"summary":"Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists. As a result, scientists and AI agents need to locate relevant information, verify their provenance, and assemble cross-paper answers manually. We present AskChem, a claim-centered infrastructure for cross-paper chemistry search. AskChem changes the unit of retrieval from the paper to the provenance-carrying claim: each paper is converted into atomic, typed claims, each grounded by a source DOI and a verbatim quote or an explicit evidence locator. Over this shared claim store, AskChem exposes complementary structures for search and synthesis: a stabilized faceted taxonomy for hierarchical retrieval and browsing, an evidence graph linking claims through relations, and an exploratory living taxonomy that situates indexed papers under scientific principles. AskChem currently indexes 2.4M claims from 147K papers and provides a web interface, as well as REST, SDK, and MCP access for AI agents. On AskChem-Bench, grounding a GPT-5.5 reader in AskChem yields 100% resolvable DOIs, compared with 88.3% without retrieval, and the highest citation density among five tested systems. AskChem is live at https://askchem.org.","upvotes":79,"discussionId":"6a6c01697bd25d8874c070c8","projectPage":"https://www.askchem.org","githubRepo":"https://github.com/bingyan4science/askchem","githubRepoAddedBy":"user","githubStars":2,"organization":{"_id":"691d8e884bbe8df0d99462e2","name":"newyorkuniversity","fullname":"New York University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/orNHmPzOQf2_F5UgXPsu5.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"634656667393804ce0d8c268","avatarUrl":"/avatars/1625843226d2c1611419dfb5de16722f.svg","isPro":false,"fullname":"Bing Yan","user":"bing-yan","type":"user"},{"_id":"63081e15a670ed10f9d44229","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63081e15a670ed10f9d44229/w1b9uq-9774bMMgJbSPsS.jpeg","isPro":true,"fullname":"Yuntian Deng","user":"yuntian-deng","type":"user"},{"_id":"6a669854fc9aae3cb525e879","avatarUrl":"/avatars/bff45e6282a5ab5039f85a49b61d6f1b.svg","isPro":false,"fullname":"Aaron Bishop","user":"aaronbishop22","type":"user"},{"_id":"68f1a4e088e256c4ab477152","avatarUrl":"/avatars/e40704b1ebb1b78ccc9577121300793a.svg","isPro":false,"fullname":"Abram Durret","user":"abramdurret","type":"user"},{"_id":"6a669a442a2bb6b063be560f","avatarUrl":"/avatars/4f1f384bd1755af5414f39138c65361e.svg","isPro":false,"fullname":"Adam Grant","user":"adamgrant22","type":"user"},{"_id":"6a481e62a0d7ab44609d9289","avatarUrl":"/avatars/7c4e28f3d231c075e9dd91bd5dfb4ca4.svg","isPro":false,"fullname":"Adji Dieng","user":"adjidieng","type":"user"},{"_id":"6a66973fd2ec8f4c6fa742ec","avatarUrl":"/avatars/bd9cb995fe48ec0c07855f360c89454e.svg","isPro":false,"fullname":"Adrian Olson","user":"adrianolson22","type":"user"},{"_id":"6875be0edec586128138ef1a","avatarUrl":"/avatars/47a2eaacde2e3a5d3588743e919c74d4.svg","isPro":false,"fullname":"Cascade","user":"cascaded","type":"user"},{"_id":"6875c5d3602bdfd2d122b6b9","avatarUrl":"/avatars/3ed27ab0936ba3c14f13cbca986950dd.svg","isPro":false,"fullname":"chen chen","user":"chenchen2","type":"user"},{"_id":"68f1a3bd754424101705a4c4","avatarUrl":"/avatars/4e8b1968bacc01a892f57f2f6e3c08d4.svg","isPro":false,"fullname":"Darius Darius","user":"dariusdarius2","type":"user"},{"_id":"66a017ead2b13e3f33d03725","avatarUrl":"/avatars/17c995158db3365f066f26cd4a3bbe29.svg","isPro":false,"fullname":"Boren Hong","user":"hongb2","type":"user"},{"_id":"68f1a64aa412438414cac393","avatarUrl":"/avatars/7bb2e85d46eb655dc7bff9693879b815.svg","isPro":false,"fullname":"Evelyn Doyle","user":"evelyndoyle","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"691d8e884bbe8df0d99462e2","name":"newyorkuniversity","fullname":"New York University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/orNHmPzOQf2_F5UgXPsu5.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.28618.md","query":{}}">
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
Abstract
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists. As a result, scientists and AI agents need to locate relevant information, verify their provenance, and assemble cross-paper answers manually. We present AskChem, a claim-centered infrastructure for cross-paper chemistry search. AskChem changes the unit of retrieval from the paper to the provenance-carrying claim: each paper is converted into atomic, typed claims, each grounded by a source DOI and a verbatim quote or an explicit evidence locator. Over this shared claim store, AskChem exposes complementary structures for search and synthesis: a stabilized faceted taxonomy for hierarchical retrieval and browsing, an evidence graph linking claims through relations, and an exploratory living taxonomy that situates indexed papers under scientific principles. AskChem currently indexes 2.4M claims from 147K papers and provides a web interface, as well as REST, SDK, and MCP access for AI agents. On AskChem-Bench, grounding a GPT-5.5 reader in AskChem yields 100% resolvable DOIs, compared with 88.3% without retrieval, and the highest citation density among five tested systems. AskChem is live at https://askchem.org.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2607.28618 in a model README.md to link it from this page.
Cite arxiv.org/abs/2607.28618 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.