Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z
Paper Citation Record · LEDGER
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
As of 2 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 2 inbound Pith citation observations for arXiv:2603.01589.
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 2026-08-01T06:32:01.292127+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-01T16:21:25.563051Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
27 of 27 outbound references displayed
- verified exact16
- verified fuzzy2
- unresolved7
- parse uncertain0
- malformed identifier1
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 69bccb58-f08e-485b-ba64-87e140781be5 · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-05-15T18:01:26.341189Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation a0463868-eace-4862-a74e-b46ceda5927a · outbound
This paper cites We split all 125 tasks into two sets,Gated Public Access setand HighRisk Restricted Access set.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond We split all 125 tasks into two sets,Gated Public Access setand HighRisk Restricted Access set
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:01:26.345078Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 50943350-583d-436c-9543-29f2b5d3c95e · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:01:25.541805Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation b2589ea2-7fa2-4c2d-92ff-72d21cafe9ad · outbound
This paper cites Intern-s1: A scientific multimodal foundation model.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Intern-s1: A scientific multimodal foundation model
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:01:25.535498Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 472464fd-c3a2-4519-919b-01ee2029bf4f · outbound
This paper cites Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:01:25.528515Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 0fe1c598-9fcc-4c8e-916e-a273ed8c76d0 · outbound
This paper cites SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T00:47:04.366365Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 7a1ead7c-9d98-424e-8806-31927ff8f8a4 · outbound
This paper cites The Llama 3 Herd of Models.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond The Llama 3 Herd of Models
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:01:25.554485Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation a12b6004-4cd2-4988-88ac-fc6ef244fb63 · outbound
This paper cites 2024 , url =.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond 2024 , url =
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:01:25.521960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 36667f83-b39d-4a1a-bc61-5cc16d782a26 · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-05-15T18:01:26.336964Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 678099fb-4732-426b-b9a1-8f0e79af9e86 · outbound
This paper cites Control Risk for Potential Misuse of Artificial Intelligence in Science.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Control Risk for Potential Misuse of Artificial Intelligence in Science
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:01:25.547934Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 905da372-f9b8-4398-9af3-2bda31f53ec4 · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-05-15T18:01:26.332750Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 6716e6ff-3368-4e39-8e49-7a5bc2dbdcbe · outbound
This paper cites SoSBench: Benchmarking Safety Alignment on Six Scientific Domains.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:01:25.616943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 3d135be1-68bf-4279-b346-7668da1352cb · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 13
- Resolution
- unresolved
- raw_fallback, observed 2026-05-15T18:01:26.319892Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 07eafd48-7b4a-4fcf-8c25-f10411897d8b · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-05-15T18:01:26.315522Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 4abfd7fe-5cb2-482c-9ca5-042db629d440 · outbound
This paper cites SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:01:25.610609Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation c8b38e62-a389-450e-970f-bb5c12691c84 · outbound
This paper cites The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T19:55:50.014661Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 7f150f46-66c7-400c-8f0d-d602b34f1a6e · outbound
This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:01:25.623098Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 7a9f240b-0e1a-4899-9896-482ff365bc62 · outbound
This paper cites Probing and Steering Evaluation Awareness of Language Models.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Probing and Steering Evaluation Awareness of Language Models
Reference 19
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T18:01:25.603359Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation b6022c6a-5560-4088-9723-2352897489c3 · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-05-15T18:01:26.328132Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 614640aa-d0a4-43d6-bf38-ab4e4f7d7006 · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-05-15T18:01:26.323679Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 6bb84f98-db4b-472d-beeb-68fab9f77420 · outbound
This paper cites Qwen3 Technical Report.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Qwen3 Technical Report
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:01:25.596110Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation cee15327-83a4-414a-b92b-f201f669c678 · outbound
This paper cites Accessed: 2026-01-29.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Accessed: 2026-01-29
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:01:26.310950Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 93886e3c-a0e1-4be5-8bce-e27eeb57d4ac · outbound
This paper cites Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:01:25.243853Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation dbee5bae-42ba-40d1-a12f-3e827a123fd9 · outbound
This paper cites SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking
Reference 25
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:01:25.575015Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation f6f258be-97c4-4423-ad54-4beea4f501d0 · outbound
This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:01:25.588604Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation af3b1add-78f6-45e4-a25c-52dd2c13dea4 · outbound
This paper cites Ans.” represent if the questions have corresponding answers. “Rep.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Ans.” represent if the questions have corresponding answers. “Rep
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:01:25.581771Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Observation 0fe6894c-4ced-4bb3-82ff-d16ee20b6920 · outbound
This paper cites an unresolved cited work.
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond Unresolved cited work
Reference 28
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-15T18:01:26.349334Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.
Pith citing papers
Observation affd77b5-38e3-41fb-8a5b-5339ac7598ec · inbound
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs cites this paper.
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T16:21:25.563051Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dfb99e88-fc71-4050-b015-9d7219c9c2a6 · inbound
SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring cites this paper.
SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T14:45:44.097098Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.