Paper Citation Record · LEDGER

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration

As of 19 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2608.05741.

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

pith.paper-citation-record.v1
2608.05741 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:38:42.394326Z

measured 38 of 38 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 2026-08-12T19:12:39.585287Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-12T19:12:39.623746Z

Reference resolution

37 of 37 outbound references displayed

verified exact1
verified fuzzy18
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3a739dfc-1386-4efb-8867-ee651674a37b · outbound

This paper cites Generating sentiment-preserving fake online reviews using neural language models and their human-and machine-based detection.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Generating sentiment-preserving fake online reviews using neural language models and their human-and machine-based detection

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.928660Z

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 d5316dd8-77a0-43dc-8f5a-f236113bb904 · outbound

This paper cites Detecting Fake News Using Machine Learning : A Systematic Literature Review.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Detecting Fake News Using Machine Learning : A Systematic Literature Review

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.484893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62aa8735-faef-4129-8d3d-af896b1eeefe · outbound

This paper cites The Falcon Series of Open Language Models.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration The Falcon Series of Open Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.491221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a76c5e-381b-464a-a34c-d0d0b125ffab · outbound

This paper cites Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.497537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57f79b15-0c29-4fab-b807-c1ff88c2234f · outbound

This paper cites Language models are few-shot learners.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Language models are few-shot learners

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.503811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a192335-e63a-4117-8aaf-54bcedc59bf2 · outbound

This paper cites Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Index.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Index

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.509625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2423fd24-8839-4a74-9f47-a46a746dcc46 · outbound

This paper cites On the Possibilities of AI-Generated Text Detection.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration On the Possibilities of AI-Generated Text Detection

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.549764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01334681-3c41-4caf-8870-f59ae1b2819f · outbound

This paper cites All that’s ‘human’is not gold: Evaluating human evaluation of generated text.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration All that’s ‘human’is not gold: Evaluating human evaluation of generated text

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.851749Z

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 a152ba26-361d-4760-8fc0-d15b37c15939 · outbound

This paper cites Raid: A shared benchmark for robust evaluation of machine-generated text detectors.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Raid: A shared benchmark for robust evaluation of machine-generated text detectors

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.831916Z

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 7d478fe1-7342-4685-8e2f-f7496cb52abe · outbound

This paper cites Gltr: Statistical detection and visualization of generated text.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Gltr: Statistical detection and visualization of generated text

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.814855Z

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 7564c225-cb5e-4ad5-aea4-2fdbc96d23f1 · outbound

This paper cites The Llama 3 Herd of Models.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.627617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30ea3e85-60b6-4de8-a9c7-bebc8a5ac68d · outbound

This paper cites How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.632706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec01277a-e3ae-43a2-8bdb-e40c1af8146b · outbound

This paper cites Biscope: Ai-generated text detection by checking memorization of preceding tokens.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Biscope: Ai-generated text detection by checking memorization of preceding tokens

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.743995Z

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 4a7a1cc5-4488-4f81-94e6-cb0e3c5bd302 · outbound

This paper cites Detective: Detecting ai-generated text via multi-level contrastive learning.Advances in Neural Information Processing Systems, 37:88320–88347, 2024.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Detective: Detecting ai-generated text via multi-level contrastive learning.Advances in Neural Information Processing Systems, 37:88320–88347, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.701092Z

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 53c2d5eb-f391-412f-9ecf-51cd31665082 · outbound

This paper cites Spotting LLMs with binoculars: Zero-shot detection of machine-generated text.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Spotting LLMs with binoculars: Zero-shot detection of machine-generated text

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.659377Z

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 44878a39-c5d9-4eca-9ff7-c7aac23747b0 · outbound

This paper cites Unifying human and statistical evaluation for natural language generation.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Unifying human and statistical evaluation for natural language generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.730009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3285b5f-a792-493a-8179-e50b03eeefe0 · outbound

This paper cites DETree: Detecting human–ai collaborative texts via tree-structured hierarchical representation learning.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration DETree: Detecting human–ai collaborative texts via tree-structured hierarchical representation learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.592933Z

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 7a5f26fd-7926-4263-ad62-ea10640e7cdb · outbound

This paper cites Radar: Robust ai-text detection via adversarial learning.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Radar: Robust ai-text detection via adversarial learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.553225Z

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 8d0a19d3-9c7f-4aa0-bebf-b5bb8cf5a318 · outbound

This paper cites Automatic detection of generated text is easiest when humans are fooled.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Automatic detection of generated text is easiest when humans are fooled

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.873327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34486066-b314-41dc-9f0e-89c8f352c1dd · outbound

This paper cites Mage: Machine-generated text detection in the wild.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Mage: Machine-generated text detection in the wild

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.477413Z

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 2ca46068-241d-4cab-952c-d55f766eef75 · outbound

This paper cites Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:41.883720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71e6f87e-3db4-4585-85da-a9ce45a1fa25 · outbound

This paper cites Meta Llama 3.1 model card.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Meta Llama 3.1 model card

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.460821Z

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 d9dd1a24-a061-4694-92de-533d5388b71b · outbound

This paper cites Meta Llama 3.2 model card.https://github.com/meta-llama/llama-models/blob/main/models/ llama3_2/MODEL_CARD.md, 2024.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Meta Llama 3.2 model card.https://github.com/meta-llama/llama-models/blob/main/models/ llama3_2/MODEL_CARD.md, 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.402541Z

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 4abfcb1c-969c-40be-ab44-26c8f473d6df · outbound

This paper cites Meta Llama 3 model card.https://github.com/meta-llama/llama-models/blob/main/models/ llama3/MODEL_CARD.md, 2024.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Meta Llama 3 model card.https://github.com/meta-llama/llama-models/blob/main/models/ llama3/MODEL_CARD.md, 2024

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.351905Z

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 67f193fb-e347-4925-9b24-bb0122876d56 · outbound

This paper cites Detectgpt: Zero-shot machine-generated text detection using probability curvature.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Detectgpt: Zero-shot machine-generated text detection using probability curvature

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.335818Z

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 64574703-735b-4b3a-83fb-bcd2bb9ed047 · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:42.105096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f498333-ed25-4c47-ab04-8a665032908f · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741, 2023.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741, 2023

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:42.110093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0dfbb97-e66d-4d5b-b480-774b6f435339 · outbound

This paper cites Release Strategies and the Social Impacts of Language Models.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Release Strategies and the Social Impacts of Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:42.116398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 269472da-4f00-4dcd-8d30-67e5920712a7 · outbound

This paper cites Deep kernel relative test for machine-generated text detection.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Deep kernel relative test for machine-generated text detection

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:42.121957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cb756e9-0e83-42f7-9277-5588ef92f78d · outbound

This paper cites Detectllm: Leveraging log rank information for zero-shot detection of machine-generated text.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Detectllm: Leveraging log rank information for zero-shot detection of machine-generated text

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.222827Z

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 83eb36ef-38eb-4648-962e-f326eccbfab7 · outbound

This paper cites Authorship attribution for neural text generation.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Authorship attribution for neural text generation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.169223Z

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 ebec266f-dd64-4de5-b66c-863fc993aa33 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:42.247352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0bb859d-ad16-4982-b984-e00161f44bbb · outbound

This paper cites Detectrl: Benchmarking llm-generated text detection in real-world scenarios.Advances in Neural Information Processing Systems, 37:100369–100401, 2024.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Detectrl: Benchmarking llm-generated text detection in real-world scenarios.Advances in Neural Information Processing Systems, 37:100369–100401, 2024

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.140894Z

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 bb536b3e-72bd-4a6e-815c-04d951200594 · outbound

This paper cites Training-free LLM-generated Text Detection by Mining Token Probability Sequences.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Training-free LLM-generated Text Detection by Mining Token Probability Sequences

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:42.257622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a717c1f1-f462-44ae-858d-c6009360bc84 · outbound

This paper cites Qwen2.5 Technical Report.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Qwen2.5 Technical Report

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T14:38:42.263679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7fd3de7-8b64-4d00-83e2-ed8028913eea · outbound

This paper cites Reliably bounding false positives: A zero-shot machine-generated text detection framework via multiscaled conformal prediction.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Reliably bounding false positives: A zero-shot machine-generated text detection framework via multiscaled conformal prediction

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:38:43.089262Z

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 96194a54-7636-4456-b7af-cb8b4964defc · outbound

This paper cites You are a helpful and reliable AI assistant. Answer clearly and avoid unsupported claims.

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration You are a helpful and reliable AI assistant. Answer clearly and avoid unsupported claims

Reference 37

Resolution: verified exact; raw_fallback, observed 2026-08-15T14:38:42.741810Z

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 c61f56d1-52d7-4c15-af90-05791eb72529 · inbound

EVIL-Detect for NLPCC 2026 Shared Task 6: LLM-Generated Text Detection cites this paper.

EVIL-Detect for NLPCC 2026 Shared Task 6: LLM-Generated Text Detection Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-08-12T19:12:39.630619Z

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.