Paper Citation Record · LEDGER

Classifier Context Rot: Monitor Performance Degrades with Context Length

As of 1 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 3 inbound Pith citation observations for arXiv:2605.12366.

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

pith.paper-citation-record.v1
2605.12366 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T06:15:49.105846Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-01T06:32:01.292127+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T04:48:27.161442Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-30T08:14:25.806164Z

Reference resolution

23 of 23 outbound references displayed

verified exact1
verified fuzzy18
unresolved1
parse uncertain1
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a96b687d-e1be-44b4-8b66-ae5167c412c6 · outbound

This paper cites Measuring AI Ability to Complete Long Software Tasks.

Classifier Context Rot: Monitor Performance Degrades with Context Length Measuring AI Ability to Complete Long Software Tasks

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-14T01:19:52.953392Z

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 4abd936f-86dc-4e6b-8d87-b2c64aaaad16 · outbound

This paper cites an unresolved cited work.

Classifier Context Rot: Monitor Performance Degrades with Context Length Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-05-13T06:17:23.674414Z

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 a1af0ac2-9397-4a1f-8a92-1c2d0b05beb3 · outbound

This paper cites Sabotage Evaluations for Frontier Models.

Classifier Context Rot: Monitor Performance Degrades with Context Length Sabotage Evaluations for Frontier Models

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:17:22.933707Z

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 783a7270-c997-46f5-8dc7-b6fc68e43d4a · outbound

This paper cites 2026 , howpublished=.

Classifier Context Rot: Monitor Performance Degrades with Context Length 2026 , howpublished=

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.666335Z

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 118f2f69-3807-4a48-b50c-b2d8a5cf8b08 · outbound

This paper cites A Sketch of an.

Classifier Context Rot: Monitor Performance Degrades with Context Length A Sketch of an

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.670359Z

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 1238607b-6686-42e0-a373-5baf7681f07c · outbound

This paper cites 2025 , howpublished=.

Classifier Context Rot: Monitor Performance Degrades with Context Length 2025 , howpublished=

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.655979Z

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 778d7095-5a76-4659-83f1-453abde4c788 · outbound

This paper cites Constitutional Black-Box Monitoring for Scheming in.

Classifier Context Rot: Monitor Performance Degrades with Context Length Constitutional Black-Box Monitoring for Scheming in

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.672331Z

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 8f4c202f-fbba-4759-9c8a-0323df55a7e0 · outbound

This paper cites Needle In A Haystack -- Pressure Testing.

Classifier Context Rot: Monitor Performance Degrades with Context Length Needle In A Haystack -- Pressure Testing

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.660189Z

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 528f13e2-58b1-4e08-9b0d-875ced0c8831 · outbound

This paper cites 2025 , howpublished=.

Classifier Context Rot: Monitor Performance Degrades with Context Length 2025 , howpublished=

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.652199Z

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 7cc6626e-a4b2-4c40-8a0a-f0daf3603e22 · outbound

This paper cites OpenAI GPT-5 System Card.

Classifier Context Rot: Monitor Performance Degrades with Context Length OpenAI GPT-5 System Card

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:17:22.936729Z

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 9448748c-4bf4-43c9-831c-1ab4a0284f60 · outbound

This paper cites 2026 , howpublished=.

Classifier Context Rot: Monitor Performance Degrades with Context Length 2026 , howpublished=

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.654061Z

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 4a2bece0-5525-4bdd-827a-160622e2aeed · outbound

This paper cites Context Rot: How Increasing Input Tokens Impacts.

Classifier Context Rot: Monitor Performance Degrades with Context Length Context Rot: How Increasing Input Tokens Impacts

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.658061Z

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 8757b43e-3504-41a7-8dfa-d6d218168dda · outbound

This paper cites Can't Remember Details in Long Documents?.

Classifier Context Rot: Monitor Performance Degrades with Context Length Can't Remember Details in Long Documents?

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.662350Z

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 d38042eb-f5b4-41a7-8d1d-5e8d6c2a76cc · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Classifier Context Rot: Monitor Performance Degrades with Context Length Advances in Neural Information Processing Systems , volume=

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.668402Z

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 7333cc26-6b6b-4297-8504-5a9d28109279 · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

Classifier Context Rot: Monitor Performance Degrades with Context Length Transactions of the Association for Computational Linguistics , volume=

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.650019Z

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 dc2a35d3-252a-4fe5-8833-5eac92435128 · outbound

This paper cites and Irving, Geoffrey and Farquhar, Sebastian and Cooney, Alan , journal=.

Classifier Context Rot: Monitor Performance Degrades with Context Length and Irving, Geoffrey and Farquhar, Sebastian and Cooney, Alan , journal=

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.646386Z

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 75df15b9-a8e0-4043-957c-a670c0788c86 · outbound

This paper cites 2024 , howpublished=.

Classifier Context Rot: Monitor Performance Degrades with Context Length 2024 , howpublished=

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.648081Z

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 f72808d1-8895-481b-b521-54d52afe71fd · outbound

This paper cites 2025 , howpublished=.

Classifier Context Rot: Monitor Performance Degrades with Context Length 2025 , howpublished=

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.637502Z

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 78d81376-2895-490c-93c5-2b6f45f8507c · outbound

This paper cites an unresolved cited work.

Classifier Context Rot: Monitor Performance Degrades with Context Length Unresolved cited work

Reference 19

Resolution: parse uncertain; raw_fallback, observed 2026-05-13T06:17:23.635792Z

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 12484ba1-e9e4-4ddb-b95d-7419df6c5f90 · outbound

This paper cites ICLR 2026 Workshop on Agents in the Wild (AIWILD) , year=.

Classifier Context Rot: Monitor Performance Degrades with Context Length ICLR 2026 Workshop on Agents in the Wild (AIWILD) , year=

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.642783Z

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 6ec0a25f-a0f8-404f-91dc-14b1a06d8013 · outbound

This paper cites 2025 , url=.

Classifier Context Rot: Monitor Performance Degrades with Context Length 2025 , url=

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.641143Z

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 73a6447d-ac3b-4c83-9e05-a19cf41665dd · outbound

This paper cites Adaptive Attacks on Trusted Monitors Subvert.

Classifier Context Rot: Monitor Performance Degrades with Context Length Adaptive Attacks on Trusted Monitors Subvert

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.644447Z

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 ac250c1d-17da-466a-9b7b-a079c5d31efb · outbound

This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , year=.

Classifier Context Rot: Monitor Performance Degrades with Context Length Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , year=

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:17:23.639556Z

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 16006c3b-a165-40fd-94dc-47500e0e3eb5 · inbound

Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning cites this paper.

Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning Classifier Context Rot: Monitor Performance Degrades with Context Length

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-30T08:14:25.808089Z

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 2f158e50-ffe5-4e11-9869-ea52a8359199 · inbound

Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages cites this paper.

Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages Classifier Context Rot: Monitor Performance Degrades with Context Length

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T04:00:44.072640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25e91874-cdb6-4784-a869-841968aa6bdb · inbound

Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines cites this paper.

Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines Classifier Context Rot: Monitor Performance Degrades with Context Length

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T04:48:27.161442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.