Claim · 2025-01-22 · publication · Stated in source · Supported

The paper introduces two reasoning models, DeepSeek-R1-Zero and DeepSeek-R1, which it calls its first-generation reasoning models.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

DeepSeek-R1 research report → states its contribution → The paper introduces two reasoning models, DeepSeek-R1-Zero and DeepSeek-R1, which it calls its first-generation reasoning models.

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

DeepSeek-R1 research reportstates its contribution ↓The paper introduces two reasoning models, DeepSeek-R1-Zero and DeepSeek-R1, which it calls its first-generation reasoning models.

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2025-01-22 · publication Records dated 2025 →

Scope and limitsThe paper's own description of its contribution; not an assessment of it.

The evidence 01

primary sourceSupports the claim

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

arXiv · 2025-01-22

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.”

Location in source arXiv v1, PDF p. 1, abstract

Machine-checked · 2026-10-31

Source details and check notes

Authors: DeepSeek-AI
Version: arXiv:2501.12948v1, submitted 22 January 2025 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 52d8ca3ac93e88cef9944e1fd03b0e04aec5954495a8250fb2fadf8fa20a4dad). The first page prints the collective byline “DeepSeek-AI”; contributors listed elsewhere in the text are not recorded as authors.
Version date: 2025-01-22
Canonical address: Open the canonical source ↗
Accessed: 2026-10-28
Language: English (en)
Attribution: DeepSeek-AI, “DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning”, 2025-01-22.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, key papers (research/key-papers). The quotation (9 words) matched the text retrieved for the candidate pack on 2026-10-28 (research/key-papers/verification.json). Matching ignored differences of whitespace, case, quotation marks, dashes and line-break hyphens, so the source’s typography can differ. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. A paper or other publication describes its own contribution, quoted from the expression the record names, usually its abstract or introduction. The record is the document’s own description, not an assessment: a claim of priority or novelty it contains is the document’s claim, flagged as such, and says nothing about earlier or later work.

Date. Date of the arXiv version quoted, submitted 22 January 2025 (UTC); later versions may word it differently.

Record ID kp-states-deepseek-r1-incentivizing-reasoning-capability-2025-1