Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-16T11:54:13.359465Z
Paper Citation Record · LEDGER
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
As of 20 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 5 inbound Pith citation observations for arXiv:2504.14452.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-08T20:08:57.322125Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Reference resolution
48 of 48 outbound references displayed
- verified exact0
- verified fuzzy13
- unresolved34
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 60442e38-aa72-4a0d-a33c-dc5565b34a8d · outbound
This paper cites Measuring non-adversarial reproduction of training data in large language models.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Measuring non-adversarial reproduction of training data in large language models
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.308651Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 45600956-3e15-4dce-8f47-36ee27bb5847 · outbound
This paper cites Llama 3 model card.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Llama 3 model card
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.094004Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4f4367a8-162d-4a7d-b8c8-ac7c0089c8af · outbound
This paper cites Emergent and predictable memorization in large language models.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Emergent and predictable memorization in large language models
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.099253Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3e754891-6566-4068-ac49-4340a230fe16 · outbound
This paper cites Elephants never forget: Memorization and learning of tabular data in large language models.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Elephants never forget: Memorization and learning of tabular data in large language models
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.266376Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation d65ef4e2-e7ef-4ae2-a615-fa0d54fd4f31 · outbound
This paper cites Smith, Yejin Choi, and Hannaneh Hajishirzi.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Smith, Yejin Choi, and Hannaneh Hajishirzi
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.247493Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 8db054e8-44b9-4969-afb1-2a8c5c48c891 · outbound
This paper cites an unresolved cited work.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Unresolved cited work
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.117113Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 16a1946b-e546-4e85-8695-771af4f32749 · outbound
This paper cites The secret sharer: evaluating and testing unintended memorization in neural networks.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data The secret sharer: evaluating and testing unintended memorization in neural networks
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.228722Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7e348123-1fba-4929-9e39-723eeeadda12 · outbound
This paper cites Extracting training data from large language models.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Extracting training data from large language models
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.211084Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 3230de1b-14f2-46da-9191-7883cedff428 · outbound
This paper cites Quantifying memorization across neural language models.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Quantifying memorization across neural language models
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.133727Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 040140a9-1aeb-4d8c-8419-414a83e164b0 · outbound
This paper cites C opy B ench: Measuring literal and non-literal reproduction of copyright-protected text in language model generation.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data C opy B ench: Measuring literal and non-literal reproduction of copyright-protected text in language model generation
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.138857Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34dfd986-3a25-4e5f-af02-eb87974faaba · outbound
This paper cites Mind the privacy unit! user-level differential privacy for language model fine-tuning.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Mind the privacy unit! user-level differential privacy for language model fine-tuning
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.167228Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 85019146-ef5f-4476-bc19-cf853851f388 · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Training Verifiers to Solve Math Word Problems
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.150138Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4817619f-045e-4c84-80fe-15388621bb81 · outbound
This paper cites Hashimoto.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Hashimoto
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.156672Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ad0420e3-aa44-4d54-a6bc-69020732201a · outbound
This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.162223Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c88e9e81-b93e-4556-8f2a-0643945ea6df · outbound
This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data The Pile: An 800GB Dataset of Diverse Text for Language Modeling
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.167828Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0ab230a6-ef3f-408b-af77-0a2052e9c285 · outbound
This paper cites Foundation models and fair use.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Foundation models and fair use
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.173572Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c4f0bec4-f36f-478e-a492-30fa090b1f53 · outbound
This paper cites Measuring massive multitask language understanding.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Measuring massive multitask language understanding
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.178935Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7d440d75-9490-4f8b-a94a-d29e2b2bfc64 · outbound
This paper cites Lo RA : Low-rank adaptation of large language models.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Lo RA : Low-rank adaptation of large language models
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.183946Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a2692415-98ad-47c9-b4fe-0ecfaefc8d29 · outbound
This paper cites Demystifying Verbatim Memorization in Large Language Models.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Demystifying Verbatim Memorization in Large Language Models
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.190277Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 65c44cd8-d216-4591-8365-f1a44f831735 · outbound
This paper cites Proactive privacy amnesia for large language models: Safeguarding PII with negligible impact on model utility.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Proactive privacy amnesia for large language models: Safeguarding PII with negligible impact on model utility
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.098095Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 60dcb794-01a2-46d6-811a-74a6cd75569f · outbound
This paper cites Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.201192Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 976c0750-164b-4110-8150-a99a49cbe996 · outbound
This paper cites Do language models plagiarize? In Proceedings of the ACM Web Conference 2023, WWW '23, pp.\ 3637–3647, New York, NY, USA, 2023.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Do language models plagiarize? In Proceedings of the ACM Web Conference 2023, WWW '23, pp.\ 3637–3647, New York, NY, USA, 2023
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.206972Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4dc31253-d0a3-4a38-81df-13c9c065059e · outbound
This paper cites Hashimoto.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Hashimoto
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.212490Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8a276843-b3db-41af-9021-b6df3a90ad70 · outbound
This paper cites Infini-gram: Scaling unbounded n-gram language models to a trillion tokens.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Infini-gram: Scaling unbounded n-gram language models to a trillion tokens
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.057959Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e1ad022a-34d6-474a-a9bd-6f7cffb9be17 · outbound
This paper cites SHIELD : Evaluation and defense strategies for copyright compliance in LLM text generation.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data SHIELD : Evaluation and defense strategies for copyright compliance in LLM text generation
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.223305Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 578bf052-fdd1-4cc3-8e2a-128f14a270c8 · outbound
This paper cites AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.229201Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dc7fc16f-b3fc-4442-b286-3070d6e7e88f · outbound
This paper cites An adversarial perspective on machine unlearning for AI safety.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data An adversarial perspective on machine unlearning for AI safety
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.040487Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7aef4625-373c-4269-9772-48d2d1bd3573 · outbound
This paper cites Smith, and Yanai Elazar.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Smith, and Yanai Elazar
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.240745Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5e6dd183-b9d7-4a43-91d5-5936978c865d · outbound
This paper cites Smith, and Luke Zettlemoyer.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Smith, and Luke Zettlemoyer
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:14.018443Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 00ee90b5-5691-4b36-b6f7-55294935bcb0 · outbound
This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations, 2024.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations, 2024
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.252620Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 58cbf1fd-717c-4a81-a0f6-2609d04d7de9 · outbound
This paper cites Qwen2.5: A party of foundation models, September 2024.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Qwen2.5: A party of foundation models, September 2024
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.258067Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a372f06c-93f1-4b17-b0ad-3b39acfb9074 · outbound
This paper cites Direct preference optimization: Your language model is secretly a reward model.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Direct preference optimization: Your language model is secretly a reward model
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.263458Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c89c70d3-164a-45b0-8874-c33fe1e55440 · outbound
This paper cites The language barrier: Dissecting safety challenges of LLM s in multilingual contexts.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data The language barrier: Dissecting safety challenges of LLM s in multilingual contexts
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.268980Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 59f41274-fc6e-4337-9049-667cf714c4ad · outbound
This paper cites Safer-instruct: Aligning language models with automated preference data.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Safer-instruct: Aligning language models with automated preference data
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.275264Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4ef953a-1e4c-44c1-bae5-388620299c96 · outbound
This paper cites Smith, and Chiyuan Zhang.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Smith, and Chiyuan Zhang
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:13.963926Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 48c9165c-36c5-430f-b100-078f8fd431d9 · outbound
This paper cites Dolma: an open corpus of three trillion tokens for language model pretraining research.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Dolma: an open corpus of three trillion tokens for language model pretraining research
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.286792Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5e5d2486-29d5-4697-bab6-0513b47fda78 · outbound
This paper cites Mitigating Memorization in LLMs using Activation Steering.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Mitigating Memorization in LLMs using Activation Steering
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.292758Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 293eff2c-08a5-423f-be98-abace1fa3ddc · outbound
This paper cites Challenging BIG -bench tasks and whether chain-of-thought can solve them.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Challenging BIG -bench tasks and whether chain-of-thought can solve them
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.298587Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 70402b85-ef6b-403a-838b-67a0688338e6 · outbound
This paper cites Generalization v.s.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Generalization v.s
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:13.932781Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation f78663c9-6a5f-4265-b100-8704268ef877 · outbound
This paper cites Smith, Chiyuan Zhang, Luke Zettlemoyer, Kai Li, and Peter Henderson.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Smith, Chiyuan Zhang, Luke Zettlemoyer, Kai Li, and Peter Henderson
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-16T11:54:13.913422Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a24f28bf-4b95-4edd-a2f5-da7977d2c870 · outbound
This paper cites DEPN : Detecting and editing privacy neurons in pretrained language models.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data DEPN : Detecting and editing privacy neurons in pretrained language models
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.316996Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1de13a09-f027-42d6-acd0-36a437ec335b · outbound
This paper cites On Memorization of Large Language Models in Logical Reasoning.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data On Memorization of Large Language Models in Logical Reasoning
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.323025Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e16929f4-c97e-45e5-ab7b-e875e8e6d098 · outbound
This paper cites Evaluating large language models at evaluating instruction following.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Evaluating large language models at evaluating instruction following
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.328502Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b0345459-6bee-45e9-8a02-8b447c0a1097 · outbound
This paper cites Negative preference optimization: From catastrophic collapse to effective unlearning.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Negative preference optimization: From catastrophic collapse to effective unlearning
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.334304Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 99fd69d5-2804-42a0-8d36-b6d99b444737 · outbound
This paper cites write newline.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data write newline
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.339736Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a5f0cb7b-7651-4941-9844-b2da57dcd198 · outbound
This paper cites @esa (Ref.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data @esa (Ref
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.346918Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3fe6fb67-205c-4d91-bb69-5e0028684321 · outbound
This paper cites an unresolved cited work.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Unresolved cited work
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:54:13.352803Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7d769909-3a85-4328-9d28-51a3ce23ef46 · outbound
This paper cites rejected.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data rejected
Reference 48
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-16T11:54:13.359465Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 3142da95-84b7-45da-9503-ac79ab796a6d · inbound
A Lightweight Method to Disrupt Memorized Sequences in LLM cites this paper.
A Lightweight Method to Disrupt Memorized Sequences in LLM ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-08T20:08:57.322125Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 44529817-3cf0-42c8-885c-76b44e28e9f8 · inbound
GhazalBench: Evaluating LLM Understanding and Canonical Surface-Form Access in Persian Ghazals cites this paper.
GhazalBench: Evaluating LLM Understanding and Canonical Surface-Form Access in Persian Ghazals ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T03:53:36.446835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2e023a48-09fe-455b-8c18-fe298c8a7bdb · inbound
Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs cites this paper.
Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T12:06:01.925289Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation db03da17-49ad-4312-aa6a-6a7725f487ac · inbound
Prompt Governance? On Governing Technologies Governed by Natural Language cites this paper.
Prompt Governance? On Governing Technologies Governed by Natural Language ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
Reference 54
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T08:25:32.770331Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e348474e-c286-4a39-bdd6-f989b6efd401 · inbound
Output Vector Editing for Memorization Mitigation in Large Language Models cites this paper.
Output Vector Editing for Memorization Mitigation in Large Language Models ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
Reference 49
- Resolution
- verified exact
- arxiv_id, observed 2026-06-26T21:30:02.972376Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.