{"uid":"cap_pas6Sfk40n7Ic8_tuBeCx","slug":"2s-io-a117a582","name":"2s.io Scientific Literature Search","description":"Unified scientific literature search across arXiv (preprints), PubMed (biomedical), and Semantic Scholar (cross-field, with citation counts). Returns a flat array of papers with stable schema: source, sourceId, doi, title, authors, abstract, year, publishedAt, citationCount, url, pdfUrl. Partial failures surface in the errors array rather than failing the whole call. Optional filters: since (YYYY-MM-DD), sources (subset), limit (max 20 per source).","url":"https://2s.io/api/papers/search","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","queryParams"],"properties":{"type":{"const":"http"},"method":{"const":"GET"},"queryParams":{"type":"object","required":["q"],"properties":{"q":{"type":"string","maxLength":500,"minLength":1},"limit":{"type":"integer","default":10,"maximum":20,"minimum":1},"since":{"type":"string"},"sources":{"type":"string"}},"additionalProperties":false}}}}},"responseSchema":null,"example":{"request":{"input":{"type":"http","method":"GET","queryParams":{"q":"machine learning","limit":10}}},"response":{"data":{"ok":true,"meta":{"query":"machine learning","errors":[{"source":"semantic-scholar","message":"semantic-scholar HTTP 429"},{"source":"arxiv","message":"This operation was aborted"}],"sources":["arxiv","pubmed","semantic-scholar"],"attribution":[{"url":"https://arxiv.org/help/api/terms-of-use","source":"arxiv","license":"arXiv non-exclusive license — terms permit programmatic access"},{"url":"https://www.nlm.nih.gov/databases/download/pubmed_medline.html","source":"pubmed","license":"Public domain (US government work)"},{"url":"https://www.semanticscholar.org/product/api/license","source":"semantic-scholar","license":"CC0 1.0 (metadata)"}]},"items":[{"doi":"10.1111/joim.12822","url":"https://pubmed.ncbi.nlm.nih.gov/30102808/","year":2018,"title":"eDoctor: machine learning and the future of medicine.","pdfUrl":null,"source":"pubmed","authors":["Handelman GS","Kok HK","Chandra RV","Razavi AH","Lee MJ","Asadi H"],"abstract":null,"sourceId":"30102808","publishedAt":"2018 Dec","citationCount":null},{"doi":"10.23736/S2724-5683.21.05709-4","url":"https://pubmed.ncbi.nlm.nih.gov/34338485/","year":2022,"title":"Machine learning for cardiology.","pdfUrl":null,"source":"pubmed","authors":["Arfat Y","Mittone G","Esposito R","Cantalupo B","DE Ferrari GM","Aldinucci M"],"abstract":null,"sourceId":"34338485","publishedAt":"2022 Feb","citationCount":null},{"doi":"10.1016/j.beth.2020.05.002","url":"https://pubmed.ncbi.nlm.nih.gov/32800297/","year":2020,"title":"Supervised Machine Learning: A Brief Primer.","pdfUrl":null,"source":"pubmed","authors":["Jiang T","Gradus JL","Rosellini AJ"],"abstract":null,"sourceId":"32800297","publishedAt":"2020 Sep","citationCount":null},{"doi":"10.1016/j.drudis.2021.09.007","url":"https://pubmed.ncbi.nlm.nih.gov/34560276/","year":2022,"title":"Machine-learning methods for ligand-protein molecular docking.","pdfUrl":null,"source":"pubmed","authors":["Crampon K","Giorkallos A","Deldossi M","Baud S","Steffenel LA"],"abstract":null,"sourceId":"34560276","publishedAt":"2022 Jan","citationCount":null},{"doi":"10.1146/annurev-clinpsy-032816-045037","url":"https://pubmed.ncbi.nlm.nih.gov/29401044/","year":2018,"title":"Machine Learning Approaches for Clinical Psychology and Psychiatry.","pdfUrl":null,"source":"pubmed","authors":["Dwyer DB","Falkai P","Koutsouleris N"],"abstract":null,"sourceId":"29401044","publishedAt":"2018 May 7","citationCount":null},{"doi":"10.1161/HYPERTENSIONAHA.124.19468","url":"https://pubmed.ncbi.nlm.nih.gov/38380541/","year":2024,"title":"AI, Machine Learning, and ChatGPT in Hypertension.","pdfUrl":null,"source":"pubmed","authors":["Layton AT"],"abstract":null,"sourceId":"38380541","publishedAt":"2024 Apr","citationCount":null},{"doi":"10.1002/adma.202102703","url":"https://pubmed.ncbi.nlm.nih.gov/34617632/","year":2022,"title":"Machine Learning-Driven Biomaterials Evolution.","pdfUrl":null,"source":"pubmed","authors":["Suwardi A","Wang F","Xue K","Han MY","Teo P","Wang P","Wang S","Liu Y","Ye E","Li Z","Loh XJ"],"abstract":null,"sourceId":"34617632","publishedAt":"2022 Jan","citationCount":null},{"doi":"10.1016/S2352-3026(20)30121-6","url":"https://pubmed.ncbi.nlm.nih.gov/32589980/","year":2020,"title":"Machine learning in haematological malignancies.","pdfUrl":null,"source":"pubmed","authors":["Radakovich N","Nagy M","Nazha A"],"abstract":null,"sourceId":"32589980","publishedAt":"2020 Jul","citationCount":null},{"doi":"10.1007/s10529-024-03499-8","url":"https://pubmed.ncbi.nlm.nih.gov/38902585/","year":2024,"title":"Machine learning: an advancement in biochemical engineering.","pdfUrl":null,"source":"pubmed","authors":["Saha R","Chauhan A","Rastogi Verma S"],"abstract":null,"sourceId":"38902585","publishedAt":"2024 Aug","citationCount":null},{"doi":"10.1111/ijlh.14110","url":"https://pubmed.ncbi.nlm.nih.gov/37257440/","year":2023,"title":"Applied machine learning in hematopathology.","pdfUrl":null,"source":"pubmed","authors":["Dehkharghanian T","Mu Y","Tizhoosh HR","Campbell CJV"],"abstract":null,"sourceId":"37257440","publishedAt":"2023 Jun","citationCount":null}],"total":10,"source":{"url":"https://2s.io/papers/search","license":"Mixed open licenses; see meta.attribution","provider":"2s.io aggregation over arXiv + PubMed + Semantic Scholar"}},"meta":{"cost":{"usd":0.0024,"tier":0},"caller":"x402","version":null,"endpoint":"papers.search","settlement":{"txHash":"0x927d1a4f29b9c6e7b53619cff0292ec81f58d7b14005e77c1bbe1d5290cd62cd","network":"eip155:8453","success":true}}}},"exampleRequest":{"q":"machine learning","limit":10},"tags":["x402"],"displayCostAmount":"0.0024","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.0024/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_oxIbvz4gYKcZxn2VxNFrc","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.006","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Search for academic papers across arXiv, PubMed, and Semantic Scholar simultaneously, returning a unified flat list with source, DOI, title, authors, abstract, year, citation count, and PDF links.","exampleAgentPrompt":"Search for up to 15 papers on CRISPR gene editing published since 2022, pulling from arXiv, PubMed, and Semantic Scholar so I can see citation counts and grab PDF links.","exampleUseCases":null,"resultDescription":"A flat JSON array of papers, each with fields: source (arXiv/PubMed/Semantic Scholar), sourceId, doi, title, authors, abstract, year, publishedAt, citationCount, url, and pdfUrl. Partial source failures are surfaced in a separate errors array rather than aborting the whole response.","failureModes":["One or more upstream sources (arXiv, PubMed, Semantic Scholar) unavailable — partial results returned with errors array populated","Query string too long (>500 chars) — 400 validation error","Invalid 'since' date format (not YYYY-MM-DD) — 400 validation error","limit exceeds 20 — 400 validation error","No results found for query — empty array returned","Payment not provided or insufficient — 402 Payment Required"],"whenToPreferThis":"Use this endpoint when you need to search academic literature across multiple scientific databases simultaneously and want a unified, stable schema with citation counts and PDF links. Prefer it over individual API calls to arXiv, PubMed, or Semantic Scholar when you want aggregated cross-domain results in a single call with graceful partial-failure handling.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:52:12.262Z","isFirstParty":false}