Paper Citation Record · LEDGER

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training

As of 7 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 1 inbound Pith citation observation for arXiv:2508.02186.

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

pith.paper-citation-record.v1
2508.02186 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T05:08:12.800621Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T17:17:44.826139Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-28T17:22:25.112597Z

Reference resolution

31 of 31 outbound references displayed

verified exact1
verified fuzzy13
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 521ba75a-1329-4cd3-8f8d-ac40f3e50fdb · outbound

This paper cites OpenAI o1 System Card.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training OpenAI o1 System Card

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:10.190896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40eaebf6-edc1-49c4-91ca-0bf36c606893 · outbound

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

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:10.256798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1eaec9f-8804-40ec-999b-ae1ddea56737 · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:10.374721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a327b30d-25c0-410c-ac2a-6739cbc9a188 · outbound

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

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:10.498742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2230aad-aa95-4a74-98f9-df858b7527ff · outbound

This paper cites Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-06T05:08:13.098887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fab89506-7469-4de6-ab70-cddda240ce39 · outbound

This paper cites On reasoning strength planning in large reasoning models,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training On reasoning strength planning in large reasoning models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:15.343009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5ed0d81d-c867-47f4-adfa-3c9d21dd653a · outbound

This paper cites Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:10.743319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8858b52a-37b7-43a8-8586-e097cd95e7ea · outbound

This paper cites Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:10.807715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 485334e8-46cf-4e65-9298-00594d41d28e · outbound

This paper cites O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:10.890536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d05e6839-a82d-400a-8666-1d909cd41412 · outbound

This paper cites Training language models to reason effi- ciently,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Training language models to reason effi- ciently,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:15.210401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9c2925d9-1ba6-46d9-beec-995c06c1c312 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Chain-of-thought prompting elicits reasoning in large language models,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:11.039341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fb219ad-9146-41ce-8b08-f42b54d63bdd · outbound

This paper cites Reasoning with language model prompting: A survey,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Reasoning with language model prompting: A survey,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:15.034304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 88ebd071-3832-41d0-b71f-3cda71f6fc44 · outbound

This paper cites Dast: Difficulty-adaptive slow-thinking for large reasoning models,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Dast: Difficulty-adaptive slow-thinking for large reasoning models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:14.806853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ded8afa0-bb66-4199-8e42-bfb85be62ee5 · outbound

This paper cites Think When You Need: Self-Adaptive Chain-of-Thought Learning.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Think When You Need: Self-Adaptive Chain-of-Thought Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:11.326869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eca2c49-f8f5-4cb1-8350-007051668f10 · outbound

This paper cites Token-budget- aware llm reasoning,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Token-budget- aware llm reasoning,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:14.624532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cd454ec8-313d-4a27-aefd-16d204ee7e9e · outbound

This paper cites Can language models learn to skip steps?.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Can language models learn to skip steps?

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:14.482819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f6c42539-1989-485b-9672-74ad5a52148b · outbound

This paper cites Cot-valve: Length- compressible chain-of-thought tuning,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Cot-valve: Length- compressible chain-of-thought tuning,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:14.306792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dc59d6e1-9e2a-43e6-a6ce-631fc02fa798 · outbound

This paper cites Data-efficient rein- forcement learning for complex nonlinear systems,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Data-efficient rein- forcement learning for complex nonlinear systems,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:14.144549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c2c3d6d9-8ffb-4831-a490-47ee413b30a5 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:11.793313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90cb4fe0-b8d8-4a98-adc4-35de0af72969 · outbound

This paper cites ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:11.890551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4466a45-860c-4843-ac05-09dab89649c4 · outbound

This paper cites Optimizing Length Compression in Large Reasoning Models.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Optimizing Length Compression in Large Reasoning Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:11.949845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6915e61-61a0-4f32-a12b-f985863a2d14 · outbound

This paper cites Learn to reason efficiently with adaptive length-based reward shaping,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Learn to reason efficiently with adaptive length-based reward shaping,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:14.016628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9801a469-2c31-4c57-9b23-11cecbb294cf · outbound

This paper cites A survey on reinforcement learning for recommender systems,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training A survey on reinforcement learning for recommender systems,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:13.855457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation adcddd72-8f26-4a80-82e7-625eca13fe55 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:12.229405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a138f5a-c56c-491b-9adc-c90a4f345df9 · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Livecodebench: Holistic and contamination free evaluation of large language models for code,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:13.680744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3b018bbb-1ba5-45df-a54a-81943378ccf4 · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Hybridflow: A flexible and efficient rlhf framework,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:12.403992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d80eb73d-4078-4f53-a4f7-a30aba153225 · outbound

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

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:12.506419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31478fc7-1122-402e-a4c7-8698150747b5 · outbound

This paper cites Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:13.513040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 63786440-f1d6-4606-b1ff-0d1a3c1875ed · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Training Verifiers to Solve Math Word Problems

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:12.656410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e2aa0cd-210c-4cb7-a7ed-892c32d24fc0 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Measuring Mathematical Problem Solving With the MATH Dataset

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T05:08:12.721234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0524808-5450-43a3-a900-f615b561182c · outbound

This paper cites Mind the gap: Bridging thought leap for improved chain-of-thought tuning,.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Mind the gap: Bridging thought leap for improved chain-of-thought tuning,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:08:13.277511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 351497bb-0519-4a31-bf97-51810c72946f · inbound

CEAR: Certified Ensemble Adversarial Robustness in DNNs cites this paper.

CEAR: Certified Ensemble Adversarial Robustness in DNNs Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:22:25.114443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.