Paper Citation Record · LEDGER

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

As of 24 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 2 inbound Pith citation observations for arXiv:2501.17030.

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

pith.paper-citation-record.v1
2501.17030 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T05:05:01.269473Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:50:12.427431Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T15:59:41.195117Z

Reference resolution

21 of 21 outbound references displayed

verified exact0
verified fuzzy17
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 31c8ab8e-1d47-43db-8686-eb16c03313d6 · outbound

This paper cites an unresolved cited work.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-10T05:05:01.785904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ab578b07-dcaf-4e0b-936a-3bcfc330ff2f · outbound

This paper cites an unresolved cited work.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-10T05:05:01.765138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 116f0772-e6d7-492b-acb3-9975bd43de23 · outbound

This paper cites A survey of reinforcement learning from human feedback, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies A survey of reinforcement learning from human feedback, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.746055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1d97cb7f-1ed0-49fa-ac70-b7e5926ed309 · outbound

This paper cites an unresolved cited work.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-10T05:05:01.724319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bf6030c7-23ab-4f9b-9378-6967f3319124 · outbound

This paper cites A survey on knowledge distillation of large language m odels, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies A survey on knowledge distillation of large language m odels, 2024

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.706390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fe8a78d5-a66e-4ec3-8031-b8df746f6cd5 · outbound

This paper cites an unresolved cited work.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-10T05:05:01.682226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b8072c70-2e3f-4e8c-ba4c-d045863e50aa · outbound

This paper cites Ai alignment through r einforcement learning from human feedback? contradictions and limitations, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Ai alignment through r einforcement learning from human feedback? contradictions and limitations, 2024

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.652320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 04f5af42-5c1d-4a86-ac80-0446af801e1a · outbound

This paper cites Making harmful behaviors unlearnable for large language models, 2023.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Making harmful behaviors unlearnable for large language models, 2023

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.630621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 01e4d683-b0ca-4d4e-a9cf-05f371b640b4 · outbound

This paper cites Reinforcement learning enhanced llms: A su rvey, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Reinforcement learning enhanced llms: A su rvey, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.610895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7d49c436-a5f7-4f2a-a103-691e2bca5197 · outbound

This paper cites Harmful ﬁne-tuning attacks and defenses for large language models: A survey, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Harmful ﬁne-tuning attacks and defenses for large language models: A survey, 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.593102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 194398b7-781d-44ec-b522-a9f1e9467b56 · outbound

This paper cites Rlaif vs.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Rlaif vs

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.574782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bebbc818-4e1b-4dcf-95a9-82f42aebfe2c · outbound

This paper cites Safety-awar e ﬁne-tuning of large language models, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Safety-awar e ﬁne-tuning of large language models, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.555204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d9ea1634-02e3-4156-b906-28df3de31eaa · outbound

This paper cites Reinfo rcing thinking through reasoning-enhanced reward models, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Reinfo rcing thinking through reasoning-enhanced reward models, 2024

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.534376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c2ab986f-092b-4b24-b03e-847b9bbc8efb · outbound

This paper cites Learning and forgetting unsafe examples in large language models, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Learning and forgetting unsafe examples in large language models, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.514599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a479a1f7-77b0-4096-9c38-96cb9eaab9ee · outbound

This paper cites U nlock the correlation between supervised ﬁne- tuning and reinforcement learning in training code large la nguage models, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies U nlock the correlation between supervised ﬁne- tuning and reinforcement learning in training code large la nguage models, 2024

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.492275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 384eaee3-e832-488d-b94d-28ca5a5ec35a · outbound

This paper cites Q-sft: Q-lea rning for language models via supervised ﬁne-tuning, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Q-sft: Q-lea rning for language models via supervised ﬁne-tuning, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.471308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bbb3a527-114c-458b-9c92-b8f88b161636 · outbound

This paper cites Superhf: Supervised iterative learning from human feedbac k, 2023.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Superhf: Supervised iterative learning from human feedbac k, 2023

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.437648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 60786ee8-b584-423d-88cb-e60596daf280 · outbound

This paper cites Reinforcement learning ﬁne-tuning of language models is biased towards more extractable features, 2023.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Reinforcement learning ﬁne-tuning of language models is biased towards more extractable features, 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.409808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1950a342-4a06-495c-ba88-e7a994f7c3af · outbound

This paper cites A closer look at the limitat ions of instruction tuning, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies A closer look at the limitat ions of instruction tuning, 2024

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.385895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 19b95f18-8d05-46cb-bc42-d5cfb8818056 · outbound

This paper cites Mitigating forgetting in llm supervised ﬁne-tuning and pre ference learning, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Mitigating forgetting in llm supervised ﬁne-tuning and pre ference learning, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.365546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bcaec5dd-67fe-445b-83f8-6a9c48200214 · outbound

This paper cites Supervised ﬁne-tuning as inverse reinforceme nt learning, 2024.

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies Supervised ﬁne-tuning as inverse reinforceme nt learning, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T05:05:01.333092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 38c0dfef-a61f-4d89-9103-1c632de164db · inbound

DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models cites this paper.

DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:50:12.427431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c8e444-b67c-4f7e-a612-4da9aa17c510 · inbound

Reasoning LLMs in the Medical Domain: A Literature Survey cites this paper.

Reasoning LLMs in the Medical Domain: A Literature Survey Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-08-05T15:59:41.202035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.