Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-05T21:59:42.069033Z
Paper Citation Record · LEDGER
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning
As of 11 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2608.03276.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
30 of 30 outbound references displayed
- verified exact1
- verified fuzzy3
- unresolved26
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation dbe8b821-a598-48a3-a325-b8850c3ab815 · outbound
This paper cites Advances in neural information processing systems , volume=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Advances in neural information processing systems , volume=
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:39.774165Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bdd859cb-8c00-431f-b0b3-dc70ed84abc0 · outbound
This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:39.862174Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1da05a3-d5c9-487f-a586-3aea107f7aff · outbound
This paper cites arXiv e-prints , pages=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning arXiv e-prints , pages=
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:39.949651Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c2ee7334-ce78-4440-80e0-3553412fa3c8 · outbound
This paper cites QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:39.992784Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d3abccd2-8256-4902-a81e-29260a35757a · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Advances in Neural Information Processing Systems , volume=
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.053796Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1ca5b6de-207a-46a4-bc71-e9cb5799be3e · outbound
This paper cites arXiv preprint arXiv:2505.23416 , year=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning arXiv preprint arXiv:2505.23416 , year=
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.150338Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5ef4e41e-96ac-409f-bdc0-d202f9b5b105 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Advances in Neural Information Processing Systems , volume=
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.206983Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d9160a4f-cdd8-456b-b203-e6bfb8f514b4 · outbound
This paper cites Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.312184Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34f0d760-77ab-4334-a0d8-71b227860a66 · outbound
This paper cites 2024 , journal=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning 2024 , journal=
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.377015Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b3f571e3-5f4e-4a0e-bd3b-5dffa2fac473 · outbound
This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.454824Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7ddb599d-f777-4390-9315-b6aa1d9198ca · outbound
This paper cites Aho and Jeffrey D.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Aho and Jeffrey D
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.540575Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 01f19393-51ad-4881-b2a9-75414dfd0c0c · outbound
This paper cites an unresolved cited work.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Unresolved cited work
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.613812Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3b7c5472-42cf-4cf6-854d-6ae2a2f5eb47 · outbound
This paper cites Chandra and Dexter C.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Chandra and Dexter C
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.704848Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff383ca3-9a6f-44e1-a23c-f6d9a5273013 · outbound
This paper cites Scalable training of.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Scalable training of
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.773510Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2c3e9243-dfc0-412e-9079-b4ce804173e8 · outbound
This paper cites Qwen3 Technical Report.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Qwen3 Technical Report
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.837648Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b3e48bfb-cd99-4b1e-a537-10fb8a436515 · outbound
This paper cites YaRN: Efficient Context Window Extension of Large Language Models.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning YaRN: Efficient Context Window Extension of Large Language Models
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.897709Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2a355e80-7671-400c-b963-f70a9aa0df83 · outbound
This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.975548Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ecc679f1-f96a-42cc-b274-f5ae9ed5bf3e · outbound
This paper cites Transactions of the Association for Computational Linguistics , volume=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Transactions of the Association for Computational Linguistics , volume=
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:40.979665Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 57ef335a-7e18-44fb-a6ca-806255c2f040 · outbound
This paper cites Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pages=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pages=
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T21:59:43.840340Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation ebb9345c-c937-44ce-9c33-2ae149964e2c · outbound
This paper cites A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:41.117398Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fe3fd0e6-dd5b-45e0-8251-5881eb78705f · outbound
This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:41.204194Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3d3ea372-f07a-409e-83f4-a56ad2a408e9 · outbound
This paper cites Efficient Streaming Language Models with Attention Sinks.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Efficient Streaming Language Models with Attention Sinks
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:41.276253Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8e7369dd-06b1-4177-8e43-198d788884f2 · outbound
This paper cites an unresolved cited work.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Unresolved cited work
Reference 23
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T21:59:43.672610Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation ffb8fda0-a8f9-4cb8-9bb3-0d37b8c24325 · outbound
This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:41.431019Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b80f8092-b286-4f72-a24a-facc29f085d7 · outbound
This paper cites arXiv preprint arXiv:2510.00636 , year=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning arXiv preprint arXiv:2510.00636 , year=
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:41.520513Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2fb5c9c2-02c6-4dd3-afb1-09f1be56bf53 · outbound
This paper cites SpinQuant: LLM quantization with learned rotations.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning SpinQuant: LLM quantization with learned rotations
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T21:59:41.606605Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a00427ac-07d4-43e3-961f-b1e5cafe5dbb · outbound
This paper cites arXiv preprint arXiv:2509.15038 , year=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning arXiv preprint arXiv:2509.15038 , year=
Reference 27
- Resolution
- verified exact
- raw_fallback, observed 2026-08-05T21:59:42.382640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c9dedf5a-0ced-4481-804d-304b56cb51a9 · outbound
This paper cites an unresolved cited work.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Unresolved cited work
Reference 28
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T21:59:43.436389Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation e5e9855d-2838-4d65-9544-e0f09475d798 · outbound
This paper cites International Conference on Learning Representations , volume=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning International Conference on Learning Representations , volume=
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T21:59:43.116266Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0e718096-f87c-48ed-b599-cef4ed605f5f · outbound
This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T21:59:42.882544Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Pith citing papers
No inbound Pith citation observations are available.