{"data":{"slug":"deepseek-r1-paper","etype":"paper","name":"DeepSeek-R1 — Reasoning via RL (2025)","cat":"Reasoning","subtitle":"The open recipe for reasoning models — a Nature cover, from a hedge fund's lab.","summary":"The R1 report showed reasoning emerging from pure reinforcement learning on verifiable problems (R1-Zero), then a practical pipeline mixing SFT and RL — published openly with weights while Western labs kept their recipes closed. It democratized the o1 breakthrough within weeks and later ran as Nature's cover paper.","attrs":null,"kf":null,"aliases":["R1 paper"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://arxiv.org/abs/2501.12948","label":"arXiv 2501.12948"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T07:57:46+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}