Paper Citation Record · LEDGER

SinkTrack: Attention Sink based Context Anchoring for Large Language Models

As of 7 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2604.10027.

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

pith.paper-citation-record.v1
2604.10027 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T01:37:33.760985Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

20 of 20 outbound references displayed

verified exact13
verified fuzzy4
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f1c161c6-de5a-49bc-8b1f-1a36fb3b5d3a · outbound

This paper cites Qwen2.5-VL Technical Report.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Qwen2.5-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:39:22.605100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0c11eee7-bf6d-434b-b005-e5e55f5c01d8 · outbound

This paper cites Graph of thoughts: Solving elaborate problems with large language models.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Graph of thoughts: Solving elaborate problems with large language models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T01:39:23.344392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1dd49a5b-8381-4fad-97c8-96a56df28826 · outbound

This paper cites Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T01:39:22.636753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 79866a24-79af-42f1-bace-aca02dfdc792 · outbound

This paper cites The Llama 3 Herd of Models.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models The Llama 3 Herd of Models

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:39:22.611754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a026da1f-7c41-4712-a64d-fcf2c42f77b9 · outbound

This paper cites Zerotuning: Unlocking the initial to- ken’s power to enhance large language models without training.arXiv preprint arXiv:2505.11739.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Zerotuning: Unlocking the initial to- ken’s power to enhance large language models without training.arXiv preprint arXiv:2505.11739

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:39:22.644104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7707c984-aa25-41fd-8351-3eca6283c05e · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:39:22.670454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4720b6ce-2385-4b4a-bcb6-d91f9f25b9b8 · outbound

This paper cites Llm agents for smart city management: Enhancing decision support through multi-agent ai sys- tems.Smart Cities (2624-6511), 8(1).

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Llm agents for smart city management: Enhancing decision support through multi-agent ai sys- tems.Smart Cities (2624-6511), 8(1)

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T01:39:23.348361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8b6e2a00-3baf-486b-8939-2843537ecb44 · outbound

This paper cites Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:39:22.650614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0de1dc43-2832-4448-ae20-42dfdc9fc68b · outbound

This paper cites Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T01:39:22.676699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 197824ca-fbb1-4569-b467-120afb0b3932 · outbound

This paper cites Attention Sorting Combats Recency Bias In Long Context Language Models.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Attention Sorting Combats Recency Bias In Long Context Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:39:22.657396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 05912b6f-9f0f-4f25-96a6-69b943efe0b9 · outbound

This paper cites Qwen2.5 Technical Report.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Qwen2.5 Technical Report

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:39:22.598067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41e4d16e-dd7e-4db1-a225-f658ee2d61cf · outbound

This paper cites A Survey of Hallucination in Large Foundation Models.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models A Survey of Hallucination in Large Foundation Models

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:39:22.663095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a199941f-9665-4718-9f86-0167199ca53e · outbound

This paper cites What are you sinking? A geometric approach on attention sink.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models What are you sinking? A geometric approach on attention sink

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:39:22.630672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0d4dc6d5-4f5e-4e8e-9a9a-8a1abfd04d3a · outbound

This paper cites Gemma 3 Technical Report.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Gemma 3 Technical Report

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:39:22.584536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41c94adc-4fe6-46cf-bff0-fd677d3c1725 · outbound

This paper cites Steering Language Models With Activation Engineering.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Steering Language Models With Activation Engineering

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:39:22.617731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f377d4da-48ab-499b-bdc8-b560e90ac653 · outbound

This paper cites RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:39:22.624227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d2a9c266-8b47-432a-b333-ad88de2c34aa · outbound

This paper cites Chain-of-note: Enhancing robustness in retrieval-augmented language models.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Chain-of-note: Enhancing robustness in retrieval-augmented language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T01:39:23.336498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6e8cb558-0dd3-4bf0-9b84-887acdb27540 · outbound

This paper cites Mitigating object hallucinations in large vision-language models via attention calibration.arXiv preprint arXiv:2502.01969.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Mitigating object hallucinations in large vision-language models via attention calibration.arXiv preprint arXiv:2502.01969

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:39:22.591730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fa4b5282-8ac4-4755-b849-48774024a623 · outbound

This paper cites "" h_ori: hidden states of the original sequence (Lori ×D h)) h_info: hidden states of the external information (L inf o ×D h)) cfg: configuration for injection rules.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models "" h_ori: hidden states of the original sequence (Lori ×D h)) h_info: hidden states of the external information (L inf o ×D h)) cfg: configuration for injection rules

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T01:39:23.340484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2f71aaba-a0f5-4b94-83b0-db2adf401d37 · outbound

This paper cites Drift Test.

SinkTrack: Attention Sink based Context Anchoring for Large Language Models Drift Test

Reference 20

Resolution: malformed identifier; raw_fallback, observed 2026-05-21T01:39:23.351710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.