Paper Citation Record · LEDGER

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis

As of 5 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2605.11664.

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

pith.paper-citation-record.v1
2605.11664 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T01:10:19.056406Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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

25 of 25 outbound references displayed

verified exact10
verified fuzzy9
unresolved4
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 98bd9b8e-5647-4815-9c31-1e49a45e9088 · outbound

This paper cites Many-shot jailbreaking.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Many-shot jailbreaking

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.153649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 113adb3c-9025-4053-872a-dd6347b27fec · outbound

This paper cites Chain-of-lure: A universal jailbreak attack framework using uncon- strained synthetic narratives.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Chain-of-lure: A universal jailbreak attack framework using uncon- strained synthetic narratives

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:52:06.163429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 30b88ccb-7d1f-437a-b43e-3d9fed6200a8 · outbound

This paper cites Jailbreaking black box large language models in twenty queries, in: 2025 IEEE Conference on Secure and Trustworthy Ma- chine Learning (SaTML), IEEE.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Jailbreaking black box large language models in twenty queries, in: 2025 IEEE Conference on Secure and Trustworthy Ma- chine Learning (SaTML), IEEE

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.155470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 00b1c0c5-2394-4282-b13e-7435b6e85286 · outbound

This paper cites En- hancing container security through phase-based system call filtering.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis En- hancing container security through phase-based system call filtering

Reference 4

Resolution: malformed identifier; arxiv_id, observed 2026-05-13T01:52:06.157839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9ec9b13c-3d89-477a-b8c4-2364469c8424 · outbound

This paper cites StruQ: De- fending against prompt injection with structured queries, in: 34th USENIXSecuritySymposium(USENIXSecurity25),USENIXAs- sociation.pp.2383–2400.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis StruQ: De- fending against prompt injection with structured queries, in: 34th USENIXSecuritySymposium(USENIXSecurity25),USENIXAs- sociation.pp.2383–2400

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.151763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4252bbb5-f9f5-492b-b451-04355bf27a84 · outbound

This paper cites ARGS: Alignment as reward-guided search, in: The Twelfth International Conference on Learning Representations.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis ARGS: Alignment as reward-guided search, in: The Twelfth International Conference on Learning Representations

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.139639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0a960c92-ce0d-466f-bcd1-70c801634bf1 · outbound

This paper cites an unresolved cited work.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Unresolved cited work

Reference 7

Resolution: malformed identifier; raw_fallback, observed 2026-05-13T15:37:56.141163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 440878e7-ffaa-445d-a9da-ded061f8ea64 · outbound

This paper cites Evaluating the.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Evaluating the

Reference 8

Resolution: verified exact; doi, observed 2026-05-13T01:11:59.761123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 61e681aa-0296-40ac-86e0-05e1c3852a45 · outbound

This paper cites AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-13T01:52:06.151969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9164322c-79ec-4ce3-accf-0772473f2817 · outbound

This paper cites an unresolved cited work.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Unresolved cited work

Reference 10

Resolution: verified exact; doi, observed 2026-05-13T01:11:59.756994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ce33359b-e118-4989-97fd-78f680407f8b · outbound

This paper cites an unresolved cited work.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-13T15:37:56.136146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6c14c8c0-a788-4f50-bd9e-51798a2d2e18 · outbound

This paper cites an unresolved cited work.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-05-13T15:37:56.134199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8713df86-cf83-4569-8be4-5968870ef5ef · outbound

This paper cites an unresolved cited work.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-05-13T15:37:56.137644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 690f3d4a-f0ec-45b4-a72e-484b83becd53 · outbound

This paper cites Training language models to follow instructions with human feedback, in: Advances in Neural Information Processing Systems, pp.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Training language models to follow instructions with human feedback, in: Advances in Neural Information Processing Systems, pp

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.142888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a84b1c2b-2c62-4fbc-b683-040775c718e4 · outbound

This paper cites Sentence- BERT : Sentence Embeddings using S iamese BERT -Networks.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Sentence- BERT : Sentence Embeddings using S iamese BERT -Networks

Reference 15

Resolution: verified exact; doi, observed 2026-05-13T01:11:59.769102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d8420dee-18f0-408f-8a1e-14635d279381 · outbound

This paper cites ”do anything now.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis ”do anything now

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:11:59.782368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation db43380d-86d4-4aed-9b6f-9f60ebb3f086 · outbound

This paper cites Jailbroken: How does LLM safety training fail?, in: Advances in Neural Information Processing Systems, pp.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Jailbroken: How does LLM safety training fail?, in: Advances in Neural Information Processing Systems, pp

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.146580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6734016a-cc9a-4339-a1bd-6a1e7bc1d6e3 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models, in: Ad- vances in Neural Information Processing Systems, pp.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Chain-of-thought prompting elicits reasoning in large language models, in: Ad- vances in Neural Information Processing Systems, pp

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.132695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a4eec750-f42e-48d8-8b69-1b6efcd2f27f · outbound

This paper cites Instructional segment embedding:ImprovingLLMsafetywithinstructionhierarchy,in:The Thirteenth International Conference on Learning Representations.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Instructional segment embedding:ImprovingLLMsafetywithinstructionhierarchy,in:The Thirteenth International Conference on Learning Representations

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.144827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 11213c14-8d22-408f-8d8a-6e1e527b897c · outbound

This paper cites URL:https://aclanthology.org/2025.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis URL:https://aclanthology.org/2025

Reference 20

Resolution: verified exact; doi, observed 2026-05-13T01:11:59.775046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 03a1d0d3-c46a-4bbb-a0b0-8f988f95b13e · outbound

This paper cites SafeDecoding: Defending against Jailbreak Attacks via Safety -Aware Decoding.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis SafeDecoding: Defending against Jailbreak Attacks via Safety -Aware Decoding

Reference 21

Resolution: verified exact; doi, observed 2026-05-13T01:11:59.765356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 17db23be-703a-449f-87bd-d63f6e515c4f · outbound

This paper cites doi: 10.18653/v1/2024.naacl-long.337.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis doi: 10.18653/v1/2024.naacl-long.337

Reference 22

Resolution: verified exact; doi, observed 2026-05-13T01:11:59.788022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e9f264b8-b038-48ca-b7aa-23da0c1284a6 · outbound

This paper cites LLM-Fuzzer: Scaling assessment of large language model jailbreaks, in: 33rd USENIX Security Symposium (USENIX Security 24), USENIX Association, Philadelphia, PA.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis LLM-Fuzzer: Scaling assessment of large language model jailbreaks, in: 33rd USENIX Security Symposium (USENIX Security 24), USENIX Association, Philadelphia, PA

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T15:37:56.148404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ffff0719-a46f-4a7c-a4ee-fbf055d9f392 · outbound

This paper cites an unresolved cited work.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-05-13T15:37:56.150069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7cce0e09-d51c-486d-adfc-3fbeb799ab6b · outbound

This paper cites an unresolved cited work.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis Unresolved cited work

Reference 25

Resolution: verified exact; doi, observed 2026-05-13T01:11:59.750527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

No inbound Pith citation observations are available.