Pith. sign in

Paper Citation Record · LEDGER

Get my drift? Catching LLM Task Drift with Activation Deltas

As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 19 inbound Pith citation observations for arXiv:2406.00799.

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

pith.paper-citation-record.v1
2406.00799 v6

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 19 of 19 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T20:36:01.278972Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-10T20:57:34.835399Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation f52f41d0-e120-43c0-9c46-915c932a32de · inbound

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models cites this paper.

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-15T06:08:05.444361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-05-15T06:08:05.386345Z digest=sha256:76bc7e40aaa27518b480bf7201c460e602e23c9ccad9a593018164439687d554

Observation 2b963028-4430-4846-8763-579eb2120d1e · inbound

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents cites this paper.

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-12T20:36:01.278972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T20:36:01.278972Z digest=sha256:5fb1329474cb816a06904c98373eec61b7c582e6d8ea8a6af24a98ee27250198

Observation 9137548e-9d65-4d63-870c-db1024ff4da1 · inbound

Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications cites this paper.

Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-12T15:34:25.895226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:34:25.895226Z digest=sha256:20996d65da1064fb701953fafeaec425e5a8a7d1bb7f4de18c5703a8b091aeae

Observation 5bac9ba5-0724-4c15-8c82-bc4cecbe455e · inbound

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis cites this paper.

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-12T10:47:45.660196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-12T10:47:45.660196Z digest=sha256:81c02fae151112020d50d7b11388560b9ef082a4f9b900226b1514abf9e25a44

Observation ebd8f26f-5dc9-4d52-9ac6-bef8b3335c81 · inbound

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety cites this paper.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-07T10:24:26.300328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:24:26.300328Z digest=sha256:37bd42a7a7edf581a07d9af69970729893ad23ea73bda90b3ddc238ab8dc510d

Observation 7100632c-ff3f-474d-990f-65599ab8012a · inbound

JavelinGuard: Low-Cost Transformer Architectures for LLM Security cites this paper.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T05:41:25.315260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T05:41:25.315260Z digest=sha256:2dcc04678fa381d7f1b877be4864a0a207d0f41e3c0bc5ca1fed6ee42a9f5395

Observation 9aefd09e-afcb-4317-a68a-b5710882db51 · inbound

Design Patterns for Securing LLM Agents against Prompt Injections cites this paper.

Design Patterns for Securing LLM Agents against Prompt Injections Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-07T05:06:14.384486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:06:14.384486Z digest=sha256:0104f75731b08c52f48fc76154f40f6e1702dcee4d2ce23fd77e73c5f3351231

Observation 49627b25-758f-4cfc-97fa-761867b0fdc1 · inbound

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem cites this paper.

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-05-19T08:42:12.803304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-19T08:40:56.186349Z digest=sha256:80b0b57cf1b8d3c2681c89acba36ddc056b512d49abf9b24fe94199c855d8f07

Observation 52e726ee-3ad2-4262-8e5e-a49e8896dd63 · inbound

CORE-KG: An LLM-Driven Knowledge Graph Construction Framework for Human Smuggling Networks cites this paper.

CORE-KG: An LLM-Driven Knowledge Graph Construction Framework for Human Smuggling Networks Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T23:40:57.228636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:40:57.228636Z digest=sha256:185faa77544ca9c34cbae1b3de777aa452e3870d09fdbd31edc6a5f6c534b94b

Observation fb34d00c-f53e-4211-880a-21b8f1ffaf43 · inbound

Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead cites this paper.

Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T21:36:21.976834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:36:21.976834Z digest=sha256:e33fbaacce6523b67a1efd2a0bb91a4acde1edbb7fae7bcf8c3290a06ea4c826

Observation 70deac73-eb39-4506-8e14-af93fb311975 · inbound

Defending Against Prompt Injection With a Few DefensiveTokens cites this paper.

Defending Against Prompt Injection With a Few DefensiveTokens Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T18:32:38.442495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:32:38.442495Z digest=sha256:d9d200b9c7388b0608a1e598af766b445423a607cc73fcb81bfa81ac44178368

Observation 586f8d8a-f0e5-4a8a-a6ff-790b26029a29 · inbound

Quantifying Conversation Drift in MCP via Latent Polytope cites this paper.

Quantifying Conversation Drift in MCP via Latent Polytope Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-05T22:51:28.042439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T22:51:28.042439Z digest=sha256:c1426b73930205191997f83f26c230a9eb7b1be0c68c0fc145b5534825f8a6e3

Observation 9e7d3ba7-4aad-4095-a7b5-3c73f2aaa80f · inbound

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling cites this paper.

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-04T22:01:55.817698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T22:01:55.817698Z digest=sha256:d5ebe1a25832ed2295cb261639009c488adbf54d7f6b6f7be239557fb5beab8f

Observation 673c7633-70fa-40c4-b4f2-b6709a53a326 · inbound

Security Considerations for Artificial Intelligence Agents cites this paper.

Security Considerations for Artificial Intelligence Agents Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-15T12:40:00.273093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-15T12:37:27.153365Z digest=sha256:caab802c9fb2244c44b017defe8975a5e6b802c43a1ca2e3e959eedaa9f73e72

Observation 769188e2-51a6-49ae-afbd-ca61c1abaee0 · inbound

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction cites this paper.

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 16

Resolution
metadata mismatch
arxiv_id, observed 2026-05-14T20:22:55.684511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-05-14T20:20:27.212052Z digest=sha256:cb22daefd6f73ea7764a09f391fd31a92d645c113d1eacdd6d00cdfd15ce8f1d

Observation 208b79ca-417c-428b-9df5-6224b7b3f4aa · inbound

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content cites this paper.

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-06-29T09:13:16.035221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-06-29T09:11:58.843585Z digest=sha256:059d6371fa5672253d719e7fd3c746f650a3e6c3373d83dc5cb855b6d8a6de13

Observation 48c56ddb-b76c-4601-89c9-889d8af80332 · inbound

Measuring What Persists: Conditioning Mechanisms and a Geometric Framework for AI Agent Identity cites this paper.

Measuring What Persists: Conditioning Mechanisms and a Geometric Framework for AI Agent Identity Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-07-04T07:59:39.886546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-06-26T12:26:28.740555Z digest=sha256:08efea3e1e4496203549daaf42ea539520d743bdb2cd40407edc7c844ae16985

Observation e9a6ddf5-6e9d-4975-8ecd-3ad0f97e9dbe · inbound

PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption cites this paper.

PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 32

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T23:47:27.137076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-07-02T23:42:23.695930Z digest=sha256:d32b198a5bfacbaa94057548306e5ed54185df29d77e4857b7e308b5bbf53d0b

Observation 4378fb33-7fba-4141-8afe-b42e1254040a · inbound

When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems cites this paper.

When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 17

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T20:57:34.851213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-07-10T20:55:21.031591Z digest=sha256:c499618b13f4a0bd8ae718efbcd0a7b7dc82f74a5121f9853355b5c69c1aec62