Paper Citation Record · LEDGER

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety

As of 21 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2608.13304.

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

pith.paper-citation-record.v1
2608.13304 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T14:12:28.473434Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

46 of 46 outbound references displayed

verified exact2
verified fuzzy9
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9b8a67bf-7cd3-45e2-bfe7-67bd7f040adc · outbound

This paper cites Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.323410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97354491-ad63-49f5-b84f-1015b6355b72 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in Neural Information Processing Systems , volume=

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.329570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2de20a36-b891-457d-b87b-c383671b4e83 · outbound

This paper cites Invariant Risk Minimization.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Invariant Risk Minimization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.333237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd2e7f94-33b0-4e35-9bba-b0f516457dde · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Constitutional AI: Harmlessness from AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.336772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da153312-d524-4ee3-aabe-de876a85c9bc · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.340232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3169123b-3119-4a71-b625-c39d90b2a089 · outbound

This paper cites International Conference on Learning Representations , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety International Conference on Learning Representations , volume=

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.975192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 06120b13-6b41-4d7c-a3ce-313404f98b82 · outbound

This paper cites 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.348535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe7c96a7-e548-4d36-85dc-35f1540b9683 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.352375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1732f4de-e3f7-48e6-a487-20841a7b14d7 · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.356256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f97c4c-f1c5-4c09-b886-96b2e9f8adc1 · outbound

This paper cites International Conference on Learning Representations , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety International Conference on Learning Representations , volume=

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.961433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c14cb657-1c79-4886-91ba-abf8b8dd313f · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.363257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c336fd-7446-4029-9116-791251096cb6 · outbound

This paper cites The Llama 3 Herd of Models.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.366342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78679640-7e1d-4a8b-91c8-891e967954f0 · outbound

This paper cites Advances in neural information processing systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in neural information processing systems , volume=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.369488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f63d237d-694f-40b3-91a0-71eecb706527 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Measuring Massive Multitask Language Understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.372250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 807c0567-1311-43d2-8362-47f692a53ac4 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.375474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4816d49b-e5be-4569-854a-60741ee7d0b2 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in Neural Information Processing Systems , volume=

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.378989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86b0100d-926b-4919-b829-b1ee10dd32d9 · outbound

This paper cites Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining , pages=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining , pages=

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.941122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7903d8cc-00b4-43cb-93ae-3ccbd56bdbeb · outbound

This paper cites International Conference on Learning Representations , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety International Conference on Learning Representations , volume=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.384928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9198c1-0bad-41b0-a41b-04f7d82d1266 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.387665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eaef203-e547-4026-ab80-5a7f1ed1d536 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in Neural Information Processing Systems , volume=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.391343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e624d8e-17e8-4c9f-b802-eec9fe520552 · outbound

This paper cites Advances in neural information processing systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in neural information processing systems , volume=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.394560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8e84fa7-8f57-48ae-8948-a015970e3c81 · outbound

This paper cites Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.397390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a354e311-12e8-4b7c-8170-1feebaa57509 · outbound

This paper cites International Conference on Learning Representations , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety International Conference on Learning Representations , volume=

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.910625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f89062d1-fdab-4597-b0e5-cb01905b2242 · outbound

This paper cites Advances in neural information processing systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in neural information processing systems , volume=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.403982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdee1468-d2eb-457e-aa41-1b9f02e0c4fb · outbound

This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.406905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aec5d0a9-107a-4e68-8603-97cc997c3182 · outbound

This paper cites Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.410434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54785673-4401-4543-96f5-6fbcff5a866a · outbound

This paper cites arXiv preprint arXiv:2510.01088 , year=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety arXiv preprint arXiv:2510.01088 , year=

Reference 27

Resolution: verified exact; raw_fallback, observed 2026-08-14T14:12:28.709868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8041ce5d-4190-49a0-88ed-613ccdc69b84 · outbound

This paper cites do anything now.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety do anything now

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.416849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f0079cb-03bb-41fb-9f6a-958af737b8dc · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in Neural Information Processing Systems , volume=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.419700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c74e5fba-8f42-44f0-a855-a35f0cf62ba1 · outbound

This paper cites 2023 , publisher=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety 2023 , publisher=

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.422498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e55f52f-0bf2-4e43-8455-e9abd80dd40b · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.425550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e715314-ab13-4c74-a64e-f00630d317c7 · outbound

This paper cites Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.428776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55d282ef-cc6e-4111-af68-c2c3f080eeab · outbound

This paper cites Advances in neural information processing systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in neural information processing systems , volume=

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.432367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ff73026-1da2-443e-abe8-1ac1e16d4ce6 · outbound

This paper cites IEEE Transactions on Image Processing , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety IEEE Transactions on Image Processing , volume=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.871862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b9c76bd1-ed02-45c1-9c41-03d357e73ae5 · outbound

This paper cites Nature Machine Intelligence , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Nature Machine Intelligence , volume=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.438701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca387344-c9ff-4634-a74c-0ea94bd3cc1e · outbound

This paper cites International Conference on Learning Representations , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety International Conference on Learning Representations , volume=

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.857324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 08d54f6e-969b-477e-84b4-09a858bdb077 · outbound

This paper cites FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.445065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7814da34-bd66-4db7-9a68-759d44aff9ee · outbound

This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.448051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda27cdc-6550-41c8-a596-644a57cfcc91 · outbound

This paper cites Proceedings of the 31st International Conference on Computational Linguistics , pages=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Proceedings of the 31st International Conference on Computational Linguistics , pages=

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.842329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8885a504-5351-4932-a052-135c6ec83a4f · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , pages=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Findings of the Association for Computational Linguistics: ACL 2025 , pages=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.454021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a2d8aba-da77-4b2c-987c-dda0a8fa4a76 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.456910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e112e15a-69d8-4d94-9977-e387602d34bf · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.459777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3b77a98-795d-45d8-842d-db682d6a57b3 · outbound

This paper cites Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking

Reference 43

Resolution: verified exact; doi, observed 2026-08-14T14:12:28.497283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 41268f89-688f-4aaf-af12-31433f44b349 · outbound

This paper cites 2023 , howpublished =.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety 2023 , howpublished =

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.823879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 805dd500-05aa-4ece-9b46-7b98a4e924ed · outbound

This paper cites Advances in neural information processing systems , volume=.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Advances in neural information processing systems , volume=

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.470119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca9d742f-4247-49ae-923d-d9065fc2d156 · outbound

This paper cites 2024 , url =.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety 2024 , url =

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T14:12:28.810208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

No inbound Pith citation observations are available.