Paper Citation Record · LEDGER

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 13 inbound Pith citation observations for arXiv:2410.13835.

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

pith.paper-citation-record.v1
2410.13835 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:36:04.105142Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 262c214b-3e81-412f-81c8-1d78c7c0890b · inbound

When Attention Sink Emerges in Language Models: An Empirical View cites this paper.

When Attention Sink Emerges in Language Models: An Empirical View Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:41:03.853766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 410a4356-0453-4abd-824f-fd832f509777 · inbound

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training cites this paper.

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T16:30:21.134085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca337ddb-00d4-49cc-a2a2-caf5602bebf9 · inbound

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations cites this paper.

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-10T14:54:22.643035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aefffdbe-a479-4736-b1c2-ef40f138775f · inbound

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models cites this paper.

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T18:36:04.105142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 567a46fb-426a-49f0-86f3-762340c2edb4 · inbound

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse cites this paper.

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:47:37.184210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 003e22ec-6a54-4df1-87fe-80dfe421c7c1 · inbound

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse cites this paper.

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T05:50:23.598961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eff0441d-5568-494d-851a-bcb9b289c353 · inbound

A Structural Theory of Position Bias in Transformers cites this paper.

A Structural Theory of Position Bias in Transformers Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-02T22:32:01.495636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a71185b-c6a3-4de8-ab81-2353bb781396 · inbound

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation cites this paper.

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 163

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:05:58.291708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3cf4f915-e0c0-4841-b2c1-d644b29341ab · inbound

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning cites this paper.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.524206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5bcaaeb4-84f8-49a7-a303-44f426b2c0d2 · inbound

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond cites this paper.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.507093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a72ce87c-b991-4e11-994c-9c6b4559bf25 · inbound

Transformers Provably Learn to Internalize Chain-of-Thought cites this paper.

Transformers Provably Learn to Internalize Chain-of-Thought Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:33:30.533348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 699ccffe-1720-44be-b526-6b78a08d266b · inbound

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 87

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T23:32:46.644793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cb0bc544-4789-4ac4-b9c9-c1dda6bd2890 · inbound

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 160

Resolution: verified exact; arxiv_id, observed 2026-06-28T23:32:47.274391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.