Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T14:37:19.775024Z
Paper Citation Record · LEDGER
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
As of 19 August 2026, this Paper Citation Record lists 86 of 86 outbound references and 7 inbound Pith citation observations for arXiv:2507.18576.
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 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T10:46:10.926476Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Reference resolution
86 of 86 outbound references displayed
- verified exact3
- verified fuzzy36
- unresolved47
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 14113f65-d8d5-486f-b5e5-712978b5e74c · outbound
This paper cites Traininglanguagemodelstoreasonefficiently.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Traininglanguagemodelstoreasonefficiently
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:18.942038Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b5b181f7-0515-4e43-add9-e15a1ad9fc68 · outbound
This paper cites Monitoringreasoningmodelsfor misbehaviorandtherisksofpromotingobfuscation,2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Monitoringreasoningmodelsfor misbehaviorandtherisksofpromotingobfuscation,2025
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:18.964743Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 11ed3197-923f-4b7f-bb17-4ccb639edcae · outbound
This paper cites The Structural Safety Generalization Problem.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law The Structural Safety Generalization Problem
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-08-06T14:37:22.792786Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 53bb6b69-1acf-4f68-8e73-7402d5ac84c4 · outbound
This paper cites xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:18.997782Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 92d25331-a577-4e63-84df-bc2e5004c45a · outbound
This paper cites ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.007904Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a28afeac-96b8-4a3d-b7ae-f0db15a4bc71 · outbound
This paper cites Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.016033Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 95769e10-fb61-4195-8ff9-d7c4f577d0bb · outbound
This paper cites Tensocial dimensionsofconversationsandrelationships.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Tensocial dimensionsofconversationsandrelationships
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.027039Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a855dbf3-1936-4255-8ffb-2b16a7239d31 · outbound
This paper cites Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.033109Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7df927b7-b6e8-40ea-b6b2-e4cbc3ca62fd · outbound
This paper cites MM-IFEngine: Towards Multimodal Instruction Following.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law MM-IFEngine: Towards Multimodal Instruction Following
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.038128Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 44939cc4-f5be-443c-ab60-5967aa5713e8 · outbound
This paper cites Rethinkingbottlenecksinsafetyfine-tuningofvision languagemodels.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Rethinkingbottlenecksinsafetyfine-tuningofvision languagemodels
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.046224Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b121ac60-e2cc-4638-8084-873d122e4e80 · outbound
This paper cites Emergent Response Planning in LLMs.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Emergent Response Planning in LLMs
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.053536Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1786d7bb-51c9-4630-aa93-52ef0bd1c9b1 · outbound
This paper cites Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.061499Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bed636aa-eb08-4651-b219-5d66fe3ad340 · outbound
This paper cites Areal: Alarge-scaleasynchronous reinforcementlearningsystemforlanguagereasoning,2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Areal: Alarge-scaleasynchronous reinforcementlearningsystemforlanguagereasoning,2025
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.072700Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d757932-4ff4-4177-83f6-589dc79e3d49 · outbound
This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.094739Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3a61089b-fe39-4cd6-b94f-eaeb9ca22457 · outbound
This paper cites CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.114061Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d489acd7-2d0b-49d0-9da4-ace4308af32a · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.127731Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d21200ae-bd5e-42c5-b54f-a360260412a6 · outbound
This paper cites Wildguard: Openone-stopmoderationtoolsforsafetyrisks,jailbreaks, andrefusalsofLLMs.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Wildguard: Openone-stopmoderationtoolsforsafetyrisks,jailbreaks, andrefusalsofLLMs
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.135715Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c62a976-9bed-4d1b-ae55-39569c8d6fcd · outbound
This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.141103Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9ced33e2-7b96-4b2b-ae17-c40328ef2a17 · outbound
This paper cites Rethinking with Retrieval: Faithful Large Language Model Inference.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Rethinking with Retrieval: Faithful Large Language Model Inference
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.145574Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c19413c5-3bf5-4dc3-a7e2-87ce2945554a · outbound
This paper cites Aligningaiwithsharedhumanvalues.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Aligningaiwithsharedhumanvalues
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.150005Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e692892-61fc-4f9d-abdc-d65ba2e78b7f · outbound
This paper cites Constructinga multi-hopQAdatasetforcomprehensiveevaluationofreasoningsteps.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Constructinga multi-hopQAdatasetforcomprehensiveevaluationofreasoningsteps
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.154560Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1fc13f29-1278-4a65-a3cf-2d4543b45fa1 · outbound
This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.159431Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eca19066-b99d-4015-8c65-bdb044da12c8 · outbound
This paper cites Flames: Benchmarking Value Alignment of LLMs in Chinese.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Flames: Benchmarking Value Alignment of LLMs in Chinese
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.163901Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c50e4869-965b-422e-bf54-526f409381ff · outbound
This paper cites Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.168529Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ea09f5e1-7f5d-4282-ba48-6a5389c98710 · outbound
This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.173063Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8ccee5c1-cb35-4416-a4ab-5a3e06f8de7d · outbound
This paper cites OpenAI o1 System Card.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law OpenAI o1 System Card
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.177955Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f1885b8a-5d31-47af-9157-c2ccff287489 · outbound
This paper cites Moralbench: Moralevaluationofllms.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Moralbench: Moralevaluationofllms
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.329723Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b251effc-877e-4481-8464-055748701496 · outbound
This paper cites RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.186707Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e36324b4-f6ff-4989-b0a3-de9d1e8c1fc3 · outbound
This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.191149Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 069b188c-4146-459a-acd2-30888ebee44c · outbound
This paper cites Whencanllmsactually correcttheirownmistakes? acriticalsurveyofself-correctionofllms.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Whencanllmsactually correcttheirownmistakes? acriticalsurveyofself-correctionofllms
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.305978Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 5ed17549-dae4-4519-9df4-afd5707d11bd · outbound
This paper cites Vl-rewardbench: Achallenging benchmarkforvision-languagegenerativerewardmodels,2024.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Vl-rewardbench: Achallenging benchmarkforvision-languagegenerativerewardmodels,2024
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.266074Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4f410e6b-02f2-49bd-9601-a4c6b2a48af8 · outbound
This paper cites SALAD-bench: Ahierarchicalandcomprehensivesafetybenchmarkforlargelanguage models.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law SALAD-bench: Ahierarchicalandcomprehensivesafetybenchmarkforlargelanguage models
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.243024Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 0a56b148-4bcc-4ef3-b2d4-fb9358c2d249 · outbound
This paper cites T2isafety: Benchmarkforassessingfairness,toxicity,andprivacyinimagegeneration.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law T2isafety: Benchmarkforassessingfairness,toxicity,andprivacyinimagegeneration
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.229033Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation bb3dedc3-eb33-4f11-94a7-a70669150b28 · outbound
This paper cites More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.222997Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4006dd7a-151a-436f-8338-b2b5a790df55 · outbound
This paper cites Thechinesedatasetdistilledfromdeepseek-r1-671b.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Thechinesedatasetdistilledfromdeepseek-r1-671b
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.194738Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 1bb9a16b-9643-4ed7-8f8d-dd0894eec232 · outbound
This paper cites Mm-safetybench: A benchmarkforsafetyevaluationofmultimodallargelanguagemodels.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Mm-safetybench: A benchmarkforsafetyevaluationofmultimodallargelanguagemodels
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.174462Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a91993b5-362a-4d00-85be-af49f5cb9aae · outbound
This paper cites Inference-timelanguage modelalignmentviaintegratedvalueguidance.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Inference-timelanguage modelalignmentviaintegratedvalueguidance
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.156098Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8448f995-b58c-4283-9f93-9b853126b25e · outbound
This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Understanding R1-Zero-Like Training: A Critical Perspective
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.247371Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 67ea0d4b-d411-4eca-9e66-9a754f06b37a · outbound
This paper cites CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.252096Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d4c20061-39cc-43e1-86ec-8bfa97ee3fae · outbound
This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.256406Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 93631d9c-d201-4d1c-8be9-bd341bce840e · outbound
This paper cites X-boundary: Establishingexactsafety boundarytoshieldllmsfrommulti-turnjailbreakswithoutcompromisingusability.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law X-boundary: Establishingexactsafety boundarytoshieldllmsfrommulti-turnjailbreakswithoutcompromisingusability
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.261110Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0a5da4ac-339d-4944-9911-399477d5af9d · outbound
This paper cites Jailbreakv-28k: A benchmarkforassessingtherobustnessofmultimodallargelanguagemodelsagainstjailbreak attacks,2024.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Jailbreakv-28k: A benchmarkforassessingtherobustnessofmultimodallargelanguagemodelsagainstjailbreak attacks,2024
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.063529Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation db925682-3266-4893-9bb8-42e513d355bd · outbound
This paper cites Reasoningaboutuncertainty: Doreasoningmodelsknowwhentheydon’tknow?,2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Reasoningaboutuncertainty: Doreasoningmodelsknowwhentheydon’tknow?,2025
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:25.027823Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 126d05fc-153e-4a05-8a7d-989dc2ebb344 · outbound
This paper cites Controlleddecodingfrom languagemodels.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Controlleddecodingfrom languagemodels
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.997313Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 20069732-073d-48c4-aa21-900fddc669bc · outbound
This paper cites Ano(nd)differencealgorithmanditsvariations.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Ano(nd)differencealgorithmanditsvariations
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.971803Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8fdaed9c-3a14-468e-9c67-09de3873d2b9 · outbound
This paper cites Safe policiesforreinforcementlearningviaprimal-dualmethods.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Safe policiesforreinforcementlearningviaprimal-dualmethods
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.910964Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a5ea8639-17e6-4a71-8831-9f44ccece170 · outbound
This paper cites Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.346785Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1651f689-e43b-416e-88a5-1ecbfcf19a73 · outbound
This paper cites Asurveyofefficientreasoningforlargereasoningmodels: Language,multimodality,andbeyond.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Asurveyofefficientreasoningforlargereasoningmodels: Language,multimodality,andbeyond
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.353092Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation de2d6105-4cd0-4891-81d7-83cdb6a73d7c · outbound
This paper cites X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.404740Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4dc3f415-07b2-4007-95ec-bcbc2f2ac67e · outbound
This paper cites Gpqa: Agraduate-levelgoogle-proofq&a benchmark.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Gpqa: Agraduate-levelgoogle-proofq&a benchmark
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.872217Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 31479709-6d8c-4c15-b30a-fd05fe8c72b8 · outbound
This paper cites Llmsknowtheirvulnerabilities: Uncoversafetygapsthroughnatural distributionshifts.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Llmsknowtheirvulnerabilities: Uncoversafetygapsthroughnatural distributionshifts
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.428115Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation df9436d6-8106-4d82-aa3f-340498da4229 · outbound
This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.436595Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 55fb0989-9c54-4028-8526-a11e9d7d45ab · outbound
This paper cites Evaluatingthemoralbeliefsencodedin llms.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Evaluatingthemoralbeliefsencodedin llms
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.845973Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 185bbd59-95b3-4404-ab5e-c8bb3e3df76b · outbound
This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law HybridFlow: A Flexible and Efficient RLHF Framework
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.445412Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 19323d27-54d1-43c1-b620-40efa875ae85 · outbound
This paper cites Assessmentofmultimodallargelanguagemodelsin alignmentwithhumanvalues,2024.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Assessmentofmultimodallargelanguagemodelsin alignmentwithhumanvalues,2024
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.785802Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c92f2e52-01c0-40c9-a0f1-d345136765c8 · outbound
This paper cites R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.453561Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 755ccb8b-4b8a-48af-86f8-3194ee5a22b2 · outbound
This paper cites Astatisticalinterpretationoftermspecificityanditsapplicationinretrieval.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Astatisticalinterpretationoftermspecificityanditsapplicationinretrieval
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.763905Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 6949e637-fc14-4027-8401-8b574820b81c · outbound
This paper cites Judgebench: Abenchmarkforevaluatingllm-based judges,2024.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Judgebench: Abenchmarkforevaluatingllm-based judges,2024
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.706935Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f169b135-52c0-4f30-8381-122082f9688a · outbound
This paper cites Notallcorrectanswersareequal: Whyyourdistillationsourcematters,2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Notallcorrectanswersareequal: Whyyourdistillationsourcematters,2025
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.673649Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 05f9e515-b38b-480a-b0dd-c30003ef91dd · outbound
This paper cites Musique: Multihopquestionsviasingle-hopquestioncomposition.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Musique: Multihopquestionsviasingle-hopquestioncomposition
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.632089Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f3c296d3-290b-4809-9422-5c9e6715ac8a · outbound
This paper cites Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.480378Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 98385709-f5a1-47da-8d2a-69ffe6b03a1f · outbound
This paper cites Jailbroken: Howdoesllmsafetytraining fail? Advances in Neural Information Processing Systems,36:80079–80110,2023.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Jailbroken: Howdoesllmsafetytraining fail? Advances in Neural Information Processing Systems,36:80079–80110,2023
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.603582Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation bf746eee-f06c-41a1-8684-9116719c6a80 · outbound
This paper cites Chain-of-thoughtpromptingelicitsreasoninginlargelanguagemodels.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Chain-of-thoughtpromptingelicitsreasoninginlargelanguagemodels
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.564558Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8ec6924f-0019-420d-84fd-60ef250ecee4 · outbound
This paper cites Mimo: Unlockingthereasoningpotentialoflanguagemodel–from pretrainingtoposttraining,2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Mimo: Unlockingthereasoningpotentialoflanguagemodel–from pretrainingtoposttraining,2025
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.494753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b54f7d1b-4216-4d06-a2e8-a4f2c057a4ae · outbound
This paper cites Cvalues: Measuringthe valuesofchineselargelanguagemodelsfromsafetytoresponsibility,2023.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Cvalues: Measuringthe valuesofchineselargelanguagemodelsfromsafetytoresponsibility,2023
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.421712Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f66aede8-4e66-4a7d-905d-569da437ed35 · outbound
This paper cites MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.511149Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8a91095-f19d-4741-9bb8-29c498bcb447 · outbound
This paper cites Towardsai-45 ◦law: Aroadmapto trustworthyagi.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Towardsai-45 ◦law: Aroadmapto trustworthyagi
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.326024Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 567b353b-a197-4453-b5a9-1de84677abfc · outbound
This paper cites R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Reference 68
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.522772Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 010d5fae-dee3-4c1e-9938-87e6fb01b7ba · outbound
This paper cites The Alignment Trap: Complexity Barriers.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law The Alignment Trap: Complexity Barriers
Reference 69
- Resolution
- verified exact
- local_arxiv, observed 2026-08-06T14:37:20.488895Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation e8941d9e-6a8b-4ece-82c3-3e9d5cf8461c · outbound
This paper cites Omnibal: Towardsfastinstruction-tuningforvision-languagemodelsviaomniverse computationbalance.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Omnibal: Towardsfastinstruction-tuningforvision-languagemodelsviaomniverse computationbalance
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.224745Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9cce3c40-41bc-4898-8ec4-0d816116fcab · outbound
This paper cites Hierarchicalbalancepacking: Towardsefficientsupervised fine-tuningforlong-contextllm,2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Hierarchicalbalancepacking: Towardsefficientsupervised fine-tuningforlong-contextllm,2025
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:24.115281Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8c44e399-fccd-4437-8315-03a40fafb11d · outbound
This paper cites Deepspeed-chat: Easy,fastandaffordablerlhftrainingof chatgpt-likemodelsatallscales,2023.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Deepspeed-chat: Easy,fastandaffordablerlhftrainingof chatgpt-likemodelsatallscales,2023
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.953165Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation ff4e2b1e-947a-4af9-b762-dd0d9dc4c223 · outbound
This paper cites Multimodalrewardbench: Holisticevaluationofrewardmodelsforvisionlanguagemodels,2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Multimodalrewardbench: Holisticevaluationofrewardmodelsforvisionlanguagemodels,2025
Reference 73
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.857913Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation d999c314-9c39-412d-a88e-ed884d663583 · outbound
This paper cites Dapo: An open-sourcellmreinforcementlearningsystematscale,2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Dapo: An open-sourcellmreinforcementlearningsystematscale,2025
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.762272Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 0d88267e-3df0-48db-a724-aaa7d6b63f7c · outbound
This paper cites MMMU:Amassivemulti-disciplinemultimodal understandingandreasoningbenchmarkforexpertagi.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law MMMU:Amassivemulti-disciplinemultimodal understandingandreasoningbenchmarkforexpertagi
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.704802Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation dd6468e9-c53d-49ec-a208-df3dfba823dc · outbound
This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Reference 76
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.566771Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9fc21db0-3ea1-4847-ab37-aa5e108b0cb8 · outbound
This paper cites Gaia: Aglobal,multi-modal,multi-scalevision-languagedatasetforremotesensingimageanalysis.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Gaia: Aglobal,multi-modal,multi-scalevision-languagedatasetforremotesensingimageanalysis
Reference 77
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.571469Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9bf62d37-bacf-46c9-9528-1e292c4f2fe2 · outbound
This paper cites GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking
Reference 78
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.575834Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 47763068-2314-4923-b065-1994b3bc10c1 · outbound
This paper cites Explainabilityforlargelanguagemodels: Asurvey.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Explainabilityforlargelanguagemodels: Asurvey
Reference 79
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.617331Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation e7667d3c-c0e8-4ba2-9f66-3d17de589bb4 · outbound
This paper cites Sglang: Efficientexecutionofstructuredlanguagemodelprograms,2024.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Sglang: Efficientexecutionofstructuredlanguagemodelprograms,2024
Reference 80
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.572663Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation cfcbd294-772b-4809-a627-cea278fce9be · outbound
This paper cites Streamrl: Scalable,heterogeneous,andelasticrlforllmswithdisaggregatedstreamgeneration, 2025.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Streamrl: Scalable,heterogeneous,andelasticrlforllmswithdisaggregatedstreamgeneration, 2025
Reference 81
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.491800Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 49bfd11e-72bd-4149-b511-dca2c5cda3f0 · outbound
This paper cites Instruction-Following Evaluation for Large Language Models.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Instruction-Following Evaluation for Large Language Models
Reference 82
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.675213Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bde0e658-1def-4854-8835-15d908ee292a · outbound
This paper cites Multimodal Situational Safety.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Multimodal Situational Safety
Reference 83
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:37:19.704746Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f4434d3a-eca2-48b8-aaa3-02a43ae00108 · outbound
This paper cites Weak-to-strong search: Alignlargelanguagemodelsviasearchingoversmalllanguagemodels.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Weak-to-strong search: Alignlargelanguagemodelsviasearchingoversmalllanguagemodels
Reference 84
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.417351Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation bb102302-8d7b-4017-b9de-edae00d31d06 · outbound
This paper cites GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation
Reference 85
- Resolution
- verified exact
- local_arxiv, observed 2026-08-06T14:37:19.857208Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 3f46b593-cdaf-49a9-aad1-c359613cd83e · outbound
This paper cites Safety fine-tuningat(almost)nocost: Abaselineforvisionlargelanguagemodels.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law Safety fine-tuningat(almost)nocost: Abaselineforvisionlargelanguagemodels
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T14:37:23.306080Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Pith citing papers
Observation 4abfd7fe-5cb2-482c-9ca5-042db629d440 · inbound
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond cites this paper.
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 2026-08-18T06:34:40.430872+00:00.
Observation 997ccac7-8a02-4cac-8459-74b3e02b510c · inbound
Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration cites this paper.
Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T22:35:52.012574Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f79dac7d-2bab-4b7e-829a-2e38944d53e4 · inbound
Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment cites this paper.
Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T16:21:07.551130Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2af52fbd-8fe1-4e5e-a31b-c1acd19042ce · inbound
DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning cites this paper.
DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Reference 47
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T06:04:21.413639Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 5197de4c-e4cf-4f38-bfaa-04841ea201a2 · inbound
ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators cites this paper.
ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T15:28:33.635352Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 34def933-9562-4343-859e-b6b38b16463d · inbound
ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators cites this paper.
ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Reference 14
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-03T15:28:33.373544Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation ca17c6d0-acac-4bae-81d0-3f8c83fd01ac · inbound
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning cites this paper.
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Reference 104
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:46:10.926476Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.