Paper Citation Record · LEDGER

BeamClean: Language Aware Embedding Reconstruction

As of 16 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 1 inbound Pith citation observation for arXiv:2505.13758.

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

pith.paper-citation-record.v1
2505.13758 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:15:06.181858Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:55:48.859664Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T04:55:49.088584Z

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy1
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1b739dcd-b212-4153-8558-76266306ca6e · outbound

This paper cites Split-and-Denoise: Protect large language model inference with local differential privacy.

BeamClean: Language Aware Embedding Reconstruction Split-and-Denoise: Protect large language model inference with local differential privacy

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.128863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 559f8268-40b7-47fb-b115-3ed31a36e7a6 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

BeamClean: Language Aware Embedding Reconstruction Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.141642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63ba8537-c565-442d-8438-5b5f81c18ca4 · outbound

This paper cites GPT-4 Technical Report.

BeamClean: Language Aware Embedding Reconstruction GPT-4 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.144908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f7eb49-b141-4782-89c4-9d7f4da47999 · outbound

This paper cites Large Language Models Can Be Strong Differentially Private Learners.

BeamClean: Language Aware Embedding Reconstruction Large Language Models Can Be Strong Differentially Private Learners

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.148604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d5cef1e-a4e4-4fb1-a96f-614d400f152e · outbound

This paper cites Differentially Private Fine-tuning of Language Models.

BeamClean: Language Aware Embedding Reconstruction Differentially Private Fine-tuning of Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.153078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8f81c91-46a4-4530-a17a-5b6c42c69a84 · outbound

This paper cites Privacy-preserving prompt tuning for large language model services.arXiv preprint arXiv:2305.06212,.

BeamClean: Language Aware Embedding Reconstruction Privacy-preserving prompt tuning for large language model services.arXiv preprint arXiv:2305.06212,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.157101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1359fb16-1d1d-4ef4-95fe-426bc0bd7ee7 · outbound

This paper cites Text Embeddings Reveal (Almost) As Much As Text.

BeamClean: Language Aware Embedding Reconstruction Text Embeddings Reveal (Almost) As Much As Text

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.165027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e608541a-4ca4-4f13-b620-2c1874c3d5ba · outbound

This paper cites an unresolved cited work.

BeamClean: Language Aware Embedding Reconstruction Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:15:06.469431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d4b6b90d-d5ff-4a3e-84ae-f3615d3c232e · outbound

This paper cites URLhttp://dx.doi.org/10.1145/3576915.3616592.

BeamClean: Language Aware Embedding Reconstruction URLhttp://dx.doi.org/10.1145/3576915.3616592

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.171292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7904ef13-f96e-4a3d-954c-141a32fc19cc · outbound

This paper cites Discrete variant.Replacing continuous Laplace noise by thegeometric(discrete Laplace) distribution yields the universally utility -maximizing geometric mechanism Ghosh et al.

BeamClean: Language Aware Embedding Reconstruction Discrete variant.Replacing continuous Laplace noise by thegeometric(discrete Laplace) distribution yields the universally utility -maximizing geometric mechanism Ghosh et al

Reference 2006

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:15:06.458393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fb3f8106-c2ae-4896-b841-c2e4bc01160c · outbound

This paper cites InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline.

BeamClean: Language Aware Embedding Reconstruction InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.161254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e01c108-23ee-43a4-a13c-03c14862885f · outbound

This paper cites GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.

BeamClean: Language Aware Embedding Reconstruction GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.174242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e009dc8b-ea71-4afe-8108-231b94a91fa4 · outbound

This paper cites doi: 10.18653/v1/2021.trustnlp-1.3.

BeamClean: Language Aware Embedding Reconstruction doi: 10.18653/v1/2021.trustnlp-1.3

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.137859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce8cead9-7318-4cd3-8e51-bc25579ae271 · outbound

This paper cites A Split-and-Privatize Framework for Large Language Model Fine-Tuning.

BeamClean: Language Aware Embedding Reconstruction A Split-and-Privatize Framework for Large Language Model Fine-Tuning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.133168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24d38592-7ba2-49ed-adfc-0c85e54eaf21 · outbound

This paper cites PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles.

BeamClean: Language Aware Embedding Reconstruction PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T20:15:06.178285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 287a0dc6-137a-423d-8125-81f9d96e4f16 · inbound

Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform cites this paper.

Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform BeamClean: Language Aware Embedding Reconstruction

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-07T04:55:49.095358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.