Paper Citation Record · LEDGER

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length

As of 9 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 1 inbound Pith citation observation for arXiv:2506.08184.

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

pith.paper-citation-record.v1
2506.08184 v3

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:23:10.981613Z

measured 13 of 13 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-14T22:01:15.475633Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-14T22:03:03.129329Z

Reference resolution

12 of 12 outbound references displayed

verified exact3
verified fuzzy3
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f79b3cf7-21cc-442d-b619-627668f8b47e · outbound

This paper cites write newline.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:23:10.888239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91874de7-89e1-438d-844e-60b107e9411b · outbound

This paper cites In-context learning and induction heads, March 2022.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length In-context learning and induction heads, March 2022

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:23:11.312834Z

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 4d411def-419f-4ff5-85b8-73229e5e3ff8 · outbound

This paper cites D., Thomson, N., and Buchanan, M.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length D., Thomson, N., and Buchanan, M

Reference 3

Resolution: verified exact; doi, observed 2026-08-07T05:23:11.149705Z

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 9039f936-c291-4e4d-938a-9ce654ce5d59 · outbound

This paper cites an unresolved cited work.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length Unresolved cited work

Reference 4

Resolution: verified exact; doi, observed 2026-08-07T05:23:11.120658Z

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 a0dcb979-ab6a-4569-b825-b7764cc7e860 · outbound

This paper cites Working Memory Capacity of ChatGPT : An Empirical Study.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length Working Memory Capacity of ChatGPT : An Empirical Study

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:23:10.929710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7151bf95-2b4d-4b0c-8b6b-7f3fa6f91683 · outbound

This paper cites Does Prompt Formatting Have Any Impact on LLM Performance?.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length Does Prompt Formatting Have Any Impact on LLM Performance?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:23:10.935880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4a1b95-7f32-47ed-acb4-f7deb9a1cdf1 · outbound

This paper cites H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:23:10.942096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad299a9-f35b-4d91-9d30-d9f11b072635 · outbound

This paper cites F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., and Liang, P.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., and Liang, P

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:23:10.949341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5e72af-c88d-4045-8fb3-5c8b8f35a363 · outbound

This paper cites and Vockenberg, K.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length and Vockenberg, K

Reference 9

Resolution: verified exact; doi, observed 2026-08-07T05:23:11.049968Z

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 850e001f-e26d-4744-bdef-12b3fa66c0d2 · outbound

This paper cites Introducing GPT -4.1 in the API , April 2025 a.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length Introducing GPT -4.1 in the API , April 2025 a

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:23:11.294317Z

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 db67d7a2-d00a-4ec7-bbf3-18b1bc8a186b · outbound

This paper cites multiple-needle-in-a-haystack.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length multiple-needle-in-a-haystack

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:23:11.272630Z

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 d93ff9f9-c6df-4ec1-8109-a271f3d6a320 · outbound

This paper cites Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries.

Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:23:10.981613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation de624e59-82b3-4351-9330-7217cd4c491f · inbound

WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking cites this paper.

WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:03:03.132889Z

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.