Paper Citation Record · LEDGER

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 27 inbound Pith citation observations for arXiv:2503.10460.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2503.10460 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 27 of 27 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:19:53.921525Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 3a06483f-e30c-4c86-a0d8-fc1f430aa4c1 · inbound

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models cites this paper.

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 191

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T01:29:57.071592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 616e83c4-3352-43ef-b983-289c2dbd6c2a · inbound

Learning to Reason under Off-Policy Guidance cites this paper.

Learning to Reason under Off-Policy Guidance Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T23:17:02.869340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 89e88595-6b82-4a51-ba4e-fabbdd4e0f50 · inbound

Reinforcement Learning for Reasoning in Large Language Models with One Training Example cites this paper.

Reinforcement Learning for Reasoning in Large Language Models with One Training Example Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 43

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T19:51:05.002577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d906625e-03ee-4bc7-90cf-733794c7e472 · inbound

Skywork Open Reasoner 1 Technical Report cites this paper.

Skywork Open Reasoner 1 Technical Report Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T04:26:47.350497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ba84593e-9ae9-4427-8d11-3e07adbfd0b4 · inbound

InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling cites this paper.

InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T22:34:23.988237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c5b6fc67-3e29-4c6a-bd9e-45e90dcbf817 · inbound

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models cites this paper.

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T16:19:53.921525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d205813b-567a-43ec-9793-c23f36ab7807 · inbound

Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM cites this paper.

Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T15:11:01.110314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08fe2101-9ae3-4671-9a47-74cd828efa0a · inbound

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework cites this paper.

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T05:45:04.041310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df28670-0e00-44f9-a3c3-8772a2db9d8a · inbound

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework cites this paper.

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T05:45:04.085149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1c883b7-520d-4b4a-97f1-d8b690a827bc · inbound

Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval cites this paper.

Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T23:23:41.779153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 400fda6c-c35b-4b51-92e0-b5081c768edb · inbound

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training cites this paper.

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T13:31:24.978441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b7b7f24b-3eea-4265-9b27-09e63c6e8bb5 · inbound

The Signal is in the Steps: Local Scoring for Reasoning Data Selection cites this paper.

The Signal is in the Steps: Local Scoring for Reasoning Data Selection Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:16:14.172268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6eb96528-8a20-4626-b3e4-0e81d6459750 · inbound

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation cites this paper.

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 99

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:06:13.802986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 15289bb2-e131-49f9-ae78-6e8beb41fd51 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T05:12:23.662328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation be7e2720-b16e-4fdb-ae74-588e4da07b09 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T20:10:34.891829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a4abdab7-eff5-47e4-8935-3ee46b435881 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.747822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d14952ea-21c3-4e8c-8ef4-34e0280d2194 · inbound

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training cites this paper.

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:48:50.926478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1bf0c8de-d4d5-449c-998f-c000e8621a0d · inbound

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models cites this paper.

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T14:10:13.173355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 09a06dac-043b-4ecc-bfb4-0a1933af2e20 · inbound

Characterizing Model-Native Skills cites this paper.

Characterizing Model-Native Skills Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 73

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:06:19.521433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0e9be8f2-6c0b-4de7-98bb-6803cffdb2a4 · inbound

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost cites this paper.

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 159

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:06:09.755531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5a49ae54-1398-4a86-9a44-d95a03d6c9a1 · inbound

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards cites this paper.

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:46:28.509523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e229cccd-8685-440f-a136-6c54e5289bd3 · inbound

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs cites this paper.

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T02:46:18.839590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1d6efd00-eb3d-4326-8317-629164fefbbe · inbound

Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning cites this paper.

Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 59

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T05:15:02.865013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4a5b6d9-9cbb-40e4-9b29-12e08523d53f · inbound

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance cites this paper.

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:21:09.548667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ae67e4f2-82f4-4c79-bc4f-db0a819cbd93 · inbound

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs cites this paper.

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T17:12:25.200187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 221004fe-29e5-487f-8700-2e681c0208f9 · inbound

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning cites this paper.

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T04:27:36.717007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ec1f147d-143b-4586-bbec-816290c2e37b · inbound

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think cites this paper.

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T13:58:21.051491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.