Paper Citation Record · LEDGER

Libra: Large Chinese-based Safeguard for AI Content

As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2507.21929.

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

pith.paper-citation-record.v1
2507.21929 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:17:38.753696Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

37 of 37 outbound references displayed

verified exact0
verified fuzzy5
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 479579ee-879d-41ee-bcde-92e38988968b · outbound

This paper cites GPT-4 Technical Report.

Libra: Large Chinese-based Safeguard for AI Content GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.632043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2717c16e-5aff-42fe-b504-ea4ed8d533cb · outbound

This paper cites Claude-3 Model Card1 (2024).

Libra: Large Chinese-based Safeguard for AI Content Claude-3 Model Card1 (2024)

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:17:39.073888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9f62e5b9-66f9-4892-9ce0-82d93517871c · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Libra: Large Chinese-based Safeguard for AI Content A General Language Assistant as a Laboratory for Alignment

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.638752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1382a3a-1d53-4a38-94c2-1529e0ac34ec · outbound

This paper cites In: Proceedings of the 26th annual international conference on machine learning.

Libra: Large Chinese-based Safeguard for AI Content In: Proceedings of the 26th annual international conference on machine learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.642617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff59c55b-07b2-4cd9-a6f3-e62dceb32978 · outbound

This paper cites In: Proceed- ings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region.

Libra: Large Chinese-based Safeguard for AI Content In: Proceed- ings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:17:39.059617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4a6b7539-6e06-4798-8bf7-6f1d441f1970 · outbound

This paper cites Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model.

Libra: Large Chinese-based Safeguard for AI Content Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.650062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc8e66d-7568-4640-bbb0-a56f2761026b · outbound

This paper cites LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions.

Libra: Large Chinese-based Safeguard for AI Content LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.653512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 136bcd82-410a-4977-9243-58df5a5f1f00 · outbound

This paper cites NExtLong: Toward Effective Long-Context Training without Long Documents.

Libra: Large Chinese-based Safeguard for AI Content NExtLong: Toward Effective Long-Context Training without Long Documents

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.656970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b54d9ee7-1675-406f-9fd5-ca2eec46de03 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

Libra: Large Chinese-based Safeguard for AI Content AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.660420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b23d923-fb9a-45b2-9e6d-cf79ef6937c9 · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

Libra: Large Chinese-based Safeguard for AI Content Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.663630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6bd10ca-1b1a-4e1f-8dc6-596a1db9706c · outbound

This paper cites WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.

Libra: Large Chinese-based Safeguard for AI Content WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.666916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c93aad8-82b6-4d7d-b186-06f86cf404c1 · outbound

This paper cites In: Proceedings of the AAAI Conference on Artificial Intelligence.

Libra: Large Chinese-based Safeguard for AI Content In: Proceedings of the AAAI Conference on Artificial Intelligence

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:17:39.050906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 975eaf68-f009-4aab-931d-9fe066bfd407 · outbound

This paper cites GPT-4o System Card.

Libra: Large Chinese-based Safeguard for AI Content GPT-4o System Card

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.673817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9299ee83-44bc-4628-8e41-0eac91cd7080 · outbound

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

Libra: Large Chinese-based Safeguard for AI Content Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.676661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 656dcaaf-d62e-41e1-85d5-2af6807166cd · outbound

This paper cites Advances in Neural Information Processing Systems 36, 24678–24704 (2023).

Libra: Large Chinese-based Safeguard for AI Content Advances in Neural Information Processing Systems 36, 24678–24704 (2023)

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:17:39.041309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8496057-405a-400c-b566-dc5deab73992 · outbound

This paper cites From System 1 to System 2: A Survey of Reasoning Large Language Models.

Libra: Large Chinese-based Safeguard for AI Content From System 1 to System 2: A Survey of Reasoning Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.683475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2cb920b-edb2-46e2-89d0-42c46bd58ec8 · outbound

This paper cites Task Oriented In-Domain Data Augmentation.

Libra: Large Chinese-based Safeguard for AI Content Task Oriented In-Domain Data Augmentation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.686519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ce4099e-64e1-4d5f-bb86-20d23d32d5b1 · outbound

This paper cites SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning.

Libra: Large Chinese-based Safeguard for AI Content SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.690339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8931d49a-fabd-42e7-9820-d0c202a20bee · outbound

This paper cites From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models.

Libra: Large Chinese-based Safeguard for AI Content From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.693434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c6d2218-9ac7-427f-86e3-294f03af0bbd · outbound

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

Libra: Large Chinese-based Safeguard for AI Content HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.696503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4093c14-bee1-4cca-9516-90ccde7d5b27 · outbound

This paper cites AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications.

Libra: Large Chinese-based Safeguard for AI Content AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.700638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b16ebd34-448b-436c-9fe3-8fc75f3a99b4 · outbound

This paper cites Safety Assessment of Chinese Large Language Models.

Libra: Large Chinese-based Safeguard for AI Content Safety Assessment of Chinese Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.703912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1984abf-f671-4cc5-abf4-f80d41bc3c12 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Libra: Large Chinese-based Safeguard for AI Content Gemini: A Family of Highly Capable Multimodal Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.707357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6cac63-9ec1-49f2-9976-0503a909c395 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Libra: Large Chinese-based Safeguard for AI Content Gemma 2: Improving Open Language Models at a Practical Size

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.710745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb929ba7-e09d-47ff-bf1f-80a20e7b18b1 · outbound

This paper cites an unresolved cited work.

Libra: Large Chinese-based Safeguard for AI Content Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:17:39.031414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ad542f9f-c3b6-4b6c-b327-2ff583173770 · outbound

This paper cites Qwen2.5 Technical Report.

Libra: Large Chinese-based Safeguard for AI Content Qwen2.5 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.717360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e6ec922-c540-4707-8652-749344f1a28b · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

Libra: Large Chinese-based Safeguard for AI Content Yi: Open Foundation Models by 01.AI

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.720449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19459666-c808-4256-ad47-b371b450ae70 · outbound

This paper cites CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning.

Libra: Large Chinese-based Safeguard for AI Content CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.723583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c693db93-0998-45c9-8dc5-8cddb27429c5 · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

Libra: Large Chinese-based Safeguard for AI Content ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.726761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d29e842-6805-42d9-8e58-2f3ecfebcfd5 · outbound

This paper cites ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors.

Libra: Large Chinese-based Safeguard for AI Content ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.729765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a78411c-8c9e-466b-9d32-671d75f9d9a2 · outbound

This paper cites an unresolved cited work.

Libra: Large Chinese-based Safeguard for AI Content Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:17:39.022962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5dfb52da-6572-4445-b72e-fce07a988d96 · outbound

This paper cites an unresolved cited work.

Libra: Large Chinese-based Safeguard for AI Content Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:17:39.013710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bb3eb86d-52c7-4ddf-9172-2ab02f972875 · outbound

This paper cites an unresolved cited work.

Libra: Large Chinese-based Safeguard for AI Content Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:17:39.004303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 23e9d929-8955-4db5-9cc9-cbfa9c6ede43 · outbound

This paper cites an unresolved cited work.

Libra: Large Chinese-based Safeguard for AI Content Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:17:38.994741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7ea16d53-8c11-4740-b625-911b667a02a3 · outbound

This paper cites an unresolved cited work.

Libra: Large Chinese-based Safeguard for AI Content Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:17:38.985698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 84055a0b-4e05-4ed7-8bbe-2b8bc27a94c9 · outbound

This paper cites an unresolved cited work.

Libra: Large Chinese-based Safeguard for AI Content Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:17:38.975974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b878c253-9aef-46e3-b611-b0e8da7532bc · outbound

This paper cites Analysis.

Libra: Large Chinese-based Safeguard for AI Content Analysis

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:17:38.966618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.