Paper Citation Record · LEDGER

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge

As of 21 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2608.12218.

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

pith.paper-citation-record.v1
2608.12218 v2

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:19:14.601846Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

21 of 21 outbound references displayed

verified exact0
verified fuzzy7
unresolved10
parse uncertain0
malformed identifier4
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bdf7361d-85fe-4867-8c25-cff95beb666d · outbound

This paper cites Each task applies a unary bitwise operation to the input string, such as NOT, which maps each bit to its complement.5 The valid output tokens are0and1.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Each task applies a unary bitwise operation to the input string, such as NOT, which maps each bit to its complement.5 The valid output tokens are0and1

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:19:15.143312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a051f91a-2bc3-454b-9f40-ead1f2e791cc · outbound

This paper cites Each task applies a deterministic string transformation, such as REVERSE.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Each task applies a deterministic string transformation, such as REVERSE

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:19:15.122625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0096ffbf-3a85-4ca6-98fc-420247e4346a · outbound

This paper cites Each task applies a digit-wise arithmetic operation modulo 10.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Each task applies a digit-wise arithmetic operation modulo 10

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:19:15.102748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c1ce9677-fd93-4cd0-80a8-2cc53a951226 · outbound

This paper cites Each task shifts every digit by a global offset modulo.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Each task shifts every digit by a global offset modulo

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:19:15.084674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dad96c4b-2b3b-4027-ade1-e2ce5da0a84e · outbound

This paper cites Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.526462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c6a9532-3c50-4a66-b2d8-a098049d3a4b · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.531730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2fedd67-f17a-4a45-804d-0fb2d63fe79d · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.537111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81f1e740-3244-431f-add7-e29cecc3ebf8 · outbound

This paper cites LLMZip: Lossless Text Compression using Large Language Models.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge LLMZip: Lossless Text Compression using Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.542038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67e2ceff-6028-41b8-bd4f-3e47bfd6271a · outbound

This paper cites Memorizing Transformers.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Memorizing Transformers

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.547102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79af68f6-f363-49b4-829b-d53b82194a8d · outbound

This paper cites ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.551979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 122cd1ac-e3fa-409c-ab99-ec6adfc05f81 · outbound

This paper cites LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models

Reference 13

Resolution: malformed identifier; no resolver link, observed 2026-08-16T00:19:14.557284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23734d3e-3f21-49d5-8efc-91106e23ffd2 · outbound

This paper cites We train each model for 10 epochs.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge We train each model for 10 epochs

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:19:15.066870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 308ae936-b600-4c4d-ab5a-16e5f565befa · outbound

This paper cites This condition measures performance when the model can rely on useful in-context evidence.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge This condition measures performance when the model can rely on useful in-context evidence

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:19:15.050139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 228c9cb0-dc75-4a7e-9882-247fce2b1bbf · outbound

This paper cites This condition measures whether the model follows the supplied context even when it conflicts with the parametrically correct rule.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge This condition measures whether the model follows the supplied context even when it conflicts with the parametrically correct rule

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:19:15.032427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c78d98ac-edf1-4067-a78e-51a9774b7303 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.520177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 892f52c3-8a2c-4a52-b0a3-5765f95d31a2 · outbound

This paper cites Longformer: The Long-Document Transformer.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Longformer: The Long-Document Transformer

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.504369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6f9e748-e2fe-413a-a370-58239cfe1272 · outbound

This paper cites Transformers generalize differently from information stored in context vs in weights.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Transformers generalize differently from information stored in context vs in weights

Reference 2022

Resolution: malformed identifier; no resolver link, observed 2026-08-16T00:19:14.514893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3db998a-bf25-4439-b7b6-c12de98bcfec · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.493028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04dc6d74-d55d-4e0d-a757-e2410cf8dc95 · outbound

This paper cites Implicit Gradient Regularization.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Implicit Gradient Regularization

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T00:19:14.499066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f828942-c7a5-442e-82d0-fa9bb2eeceea · outbound

This paper cites ISBN 979-8-89176-189-6.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge ISBN 979-8-89176-189-6

Reference 2025

Resolution: malformed identifier; no resolver link, observed 2026-08-16T00:19:14.509319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce557b1-30b1-4745-867c-e77d59d6dd79 · outbound

This paper cites furthermore.

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge furthermore

Reference 8192

Resolution: malformed identifier; raw_fallback, observed 2026-08-16T00:19:14.730177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

No inbound Pith citation observations are available.