Pith. sign in

Paper Citation Record · LEDGER

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors

As of 12 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2505.15337.

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

pith.paper-citation-record.v1
2505.15337 v3

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:22:31.544367Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

15 of 15 outbound references displayed

  • verified exact0
  • verified fuzzy7
  • unresolved6
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 59496089-f7a6-4da5-aba2-4ba8e5fcc346 · outbound

This paper cites Often difficult or impossible to understand.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Often difficult or impossible to understand

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:22:32.541203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:31.096186Z digest=sha256:79a9b1cba69080418406900220caa69b1468cc43d12d44f92f14b3e61bdb07d8

Observation 466e75e2-0a03-47f5-8868-15848f299495 · outbound

This paper cites Requires effort to understand in places.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Requires effort to understand in places

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:22:32.673930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:31.009236Z digest=sha256:a5da4a51daa361dc509817898bd83d2af61b22f4ebecaf3e3deefd174c1d263d

Observation 9cbd1d7f-ae07-4703-bc4c-9f6e5fb7db2a · outbound

This paper cites Some grammatical errors or awkward constructions occasionally disrupt flow.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Some grammatical errors or awkward constructions occasionally disrupt flow

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:22:32.905859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:30.941157Z digest=sha256:6753bd66a711a28284b5f03558248fcba861a2da77a0cdc81994e3ff53445d95

Observation 98822f04-6b6a-41a5-8581-0c4bfd2951f2 · outbound

This paper cites May contain 1-2 subtle non-native phrasings, but remains highly readable.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors May contain 1-2 subtle non-native phrasings, but remains highly readable

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:22:33.144496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:30.820236Z digest=sha256:c1726619880e97ce33b712b1d02fad605a6b57254d6a5d4abc669957ee8a4b1e

Observation b4e23e5e-cbdc-4f1e-a0d0-2211e80a70a0 · outbound

This paper cites Grammar, word choice, and sentence structure appear completely native with zero awkwardness.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Grammar, word choice, and sentence structure appear completely native with zero awkwardness

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:22:33.444300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:30.740939Z digest=sha256:b29babb97eabf5b973d1ea9dc5197ec4effb23870814f7a696355ed5b324eec4

Observation 257a68e5-139f-421c-bdba-6f19928f5dc2 · outbound

This paper cites an unresolved cited work.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Unresolved cited work

Reference 10

Resolution
unresolved
raw_fallback, observed 2026-08-07T15:22:32.415408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:31.154852Z digest=sha256:3cf8c80901ff7113abd26cc5225ee2c863e16fbfa2133eb7c3053e0ef4b6ed60

Observation 73696569-83b3-4adf-b2ab-f374d0e0227a · outbound

This paper cites an unresolved cited work.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Unresolved cited work

Reference 11

Resolution
unresolved
raw_fallback, observed 2026-08-07T15:22:32.274204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:31.257813Z digest=sha256:2d65f3bbfedb56c48bacce32ce8a649bf29217f325b313f02a1f41fda1cb32f7

Observation 4a38413e-c248-4a18-9e30-56ff18ee8aee · outbound

This paper cites The deadline got pushed back because of unexpected tech issues.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors The deadline got pushed back because of unexpected tech issues

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:22:32.211597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:31.340760Z digest=sha256:6f8bf1b35ff0b42aa7d73235cd3c68f886b4dbde55ac0fbd6772fcd0adf2f764

Observation 227e1f50-9125-4ea1-b6b7-7d37cae6ce2d · outbound

This paper cites an unresolved cited work.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Unresolved cited work

Reference 13

Resolution
unresolved
raw_fallback, observed 2026-08-07T15:22:32.160555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:31.385258Z digest=sha256:2e1fe3d9cfc01fc1e3179cb66e51c86edc924e54614ae07a72590623634f4266

Observation 2a542af6-6a08-40d5-b837-bdfc9aa28715 · outbound

This paper cites an unresolved cited work.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-07T15:22:32.080381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:31.450546Z digest=sha256:8123c12c1690809264cb579d6bd5f8ad37199e3d1bb0f5eb03b260f81c63a8d4

Observation 892b344f-d2c2-485c-a6b1-a1c0b0d31412 · outbound

This paper cites The project deadline was extended due to unforeseen technical challenges.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors The project deadline was extended due to unforeseen technical challenges

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:22:31.950105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:31.544367Z digest=sha256:84e424ec51def09e44b500c5ad839f37688f2490b7acf9692414dcddf99b0169

Observation dce83e80-6e92-4c68-bc4a-673872c1828d · outbound

This paper cites in the tone of an AI assis- tant.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors in the tone of an AI assis- tant

Reference 2002

Resolution
malformed identifier
raw_fallback, observed 2026-08-07T15:22:33.735516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:30.669499Z digest=sha256:92f3e22dde968f219c1ef92ffedfc8d226fcd41d66c71aad5ca9f13dd77a6704

Observation f6725b2b-cd91-477e-b2ef-ad3298e166ca · outbound

This paper cites Unifying Human and Statistical Evaluation for Natural Language Generation.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Unifying Human and Statistical Evaluation for Natural Language Generation

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-07T15:22:30.546016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:22:30.546016Z digest=sha256:2f5b26b154ff431cfffa0e2db95c8bf0389d685500ea9ab61be3c94964a9ffe9

Observation 5ae75b80-5561-4946-a60c-547779fc8d26 · outbound

This paper cites MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds

Reference 2024

Resolution
metadata mismatch
local_arxiv, observed 2026-08-07T15:22:31.705805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-07T15:22:30.606261Z digest=sha256:f078907d9fa74a0ca736466704bee02fb711c83602ddfc55f5b2ee6a79cb5252

Observation f533ded2-5323-4e8e-81f6-cf624e33332a · outbound

This paper cites Sebastian Gehrmann, Hendrik Strobelt, and Alexan- der M Rush.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Sebastian Gehrmann, Hendrik Strobelt, and Alexan- der M Rush

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-07T15:22:30.488359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:22:30.488359Z digest=sha256:0266bd88c63ead072db9d8a41409738bb73a2bcbf297c42a8f2a58b0bf97445c

Pith citing papers

No inbound Pith citation observations are available.