Paper Citation Record · LEDGER

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization

As of 19 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 1 inbound Pith citation observation for arXiv:2607.05861.

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

pith.paper-citation-record.v1
2607.05861 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-08T22:25:35.119625Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T07:07:43.937980Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

27 of 27 outbound references displayed

verified exact19
verified fuzzy4
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f78885e2-a5d1-43c7-bcb4-82db19fde026 · outbound

This paper cites Improving text-to-image generation with input-side inference-time scaling.arXiv preprint arXiv:2510.12041, 2025a.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Improving text-to-image generation with input-side inference-time scaling.arXiv preprint arXiv:2510.12041, 2025a

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-08T22:25:39.488004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4172036c-25e3-4fa3-a7d6-3ce61867d503 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.498423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 439de9c2-ba8c-4d7a-babb-2af5d81b7bc4 · outbound

This paper cites Simpleqa verified: A reliable factuality benchmark to measure parametric knowledge.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Simpleqa verified: A reliable factuality benchmark to measure parametric knowledge

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-08T22:25:39.515791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 378ae87d-3737-4926-9fb5-67d5ee7c0ad9 · outbound

This paper cites Your models have thought enough: Training large reasoning models to stop overthinking.arXiv preprint arXiv:2509.23392,.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Your models have thought enough: Training large reasoning models to stop overthinking.arXiv preprint arXiv:2509.23392,

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-08T22:25:39.502352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5626b2da-b009-4083-a6a5-b40232e5cb46 · outbound

This paper cites DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.512464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 212e8307-e81a-479c-a1aa-106cd0950245 · outbound

This paper cites T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.476832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 79c9d6de-ad71-41fa-b4ea-f910e311639d · outbound

This paper cites OpenAI o1 System Card.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization OpenAI o1 System Card

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.519029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 97309de7-fb92-4a8f-9b92-3f424bfca6ce · outbound

This paper cites Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.525478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ef48be6c-b42c-4735-bc2a-826ba7a60f0c · outbound

This paper cites an unresolved cited work.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-07-08T22:25:39.579426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4e574cb2-ac5b-4bed-b051-d2b58a9a6bfb · outbound

This paper cites an unresolved cited work.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-07-08T22:25:39.581612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 14bb2cb9-c0cb-4a25-8be8-8f4093ddb6df · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.521701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ae6a39f5-3cca-4c85-af88-d055964d0cfc · outbound

This paper cites Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.495002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 11939e0f-e700-4b7a-896e-822373b2318d · outbound

This paper cites Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.516771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3131f75a-e836-4b65-9e7d-5f7bd9109e76 · outbound

This paper cites AdapThink: Adaptive Thinking Preferences for Reasoning Language Model.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.518829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e5bc2b48-05af-47df-9f1d-0dd8583bdf76 · outbound

This paper cites Unsafe by reciprocity: How generation-understanding coupling undermines safety in unified multimodal models.arXiv preprint arXiv:2603.27332,.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Unsafe by reciprocity: How generation-understanding coupling undermines safety in unified multimodal models.arXiv preprint arXiv:2603.27332,

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-08T22:25:39.484751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 26238231-4439-42e6-b9b2-6e29b052237f · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.508664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d1dda002-d588-4465-9f9e-8b1129edf6d2 · outbound

This paper cites Measuring short-form factuality in large language models.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Measuring short-form factuality in large language models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.472828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3ddcd1b4-7d39-4b69-9707-b3622cd61e72 · outbound

This paper cites Qwen3 Technical Report.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Qwen3 Technical Report

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.494724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dc8f9468-bfc5-4825-9119-4b989cd0c30f · outbound

This paper cites Hotpotqa: A dataset for diverse, explainable multi-hop question answering.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Hotpotqa: A dataset for diverse, explainable multi-hop question answering

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:25:39.583408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5d2ff7b9-f1d2-465b-bcd3-d1115e9ac8f4 · outbound

This paper cites Are Reasoning Models More Prone to Hallucination?.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Are Reasoning Models More Prone to Hallucination?

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T22:25:39.514165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c6683de8-a772-4165-857f-8bd5b86c4256 · outbound

This paper cites Hallurnn: Mitigating hallucinations via recurrent cross-layer reasoning in large vision-language models.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Hallurnn: Mitigating hallucinations via recurrent cross-layer reasoning in large vision-language models

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-08T22:25:39.473432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 96dae197-bff3-4abd-8b7a-dada2a6c2ff1 · outbound

This paper cites Unraveling hallucination in large reasoning models: A topological perspective.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Unraveling hallucination in large reasoning models: A topological perspective

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:25:39.575179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1a8b30ef-032d-4beb-99f5-a9cdfb02e038 · outbound

This paper cites Progressive-Hint Prompting Improves Reasoning in Large Language Models.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Progressive-Hint Prompting Improves Reasoning in Large Language Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.491495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 06880647-70f8-45c1-84dd-bd54ffdf7cbb · outbound

This paper cites Parallel-probe: Towards efficient parallel thinking via 2d probing.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Parallel-probe: Towards efficient parallel thinking via 2d probing

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-08T22:25:39.505727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 92d0ab6c-4e9d-4e3a-8c3d-ea00a32bdf90 · outbound

This paper cites A”, “B”, or “C.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization A”, “B”, or “C

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:25:39.583597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b13bbe99-e567-4f84-b560-4a158f8b55aa · outbound

This paper cites it is possible that.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization it is possible that

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:25:39.579230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7a77d263-d036-4094-8f32-6d536bf31ae0 · outbound

This paper cites an unresolved cited work.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization Unresolved cited work

Reference 27

Resolution: malformed identifier; raw_fallback, observed 2026-07-08T22:25:39.586035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 015346d0-d947-4438-ae35-7f953e4d6a52 · inbound

Visual Contrastive Self-Distillation cites this paper.

Visual Contrastive Self-Distillation Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T07:07:43.937980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.