Paper Citation Record · LEDGER

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering

As of 16 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 1 inbound Pith citation observation for arXiv:2506.04642.

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

pith.paper-citation-record.v1
2506.04642 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:45:09.969345Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T00:47:31.653881Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-10T05:30:23.456663Z

Reference resolution

29 of 29 outbound references displayed

verified exact0
verified fuzzy0
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-10T05:30:23.456663Z

Outbound references

Observation 95ddf0a1-0c66-4313-9ee2-d46877579bad · outbound

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

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.814940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 269b8026-bb4a-49c8-85a8-2ccdac6e1ca7 · outbound

This paper cites an unresolved cited work.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.820633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 484ef146-5291-4782-9dd0-fdc49ba24a4b · outbound

This paper cites Palu: Compressing KV-Cache with Low-Rank Projection.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Palu: Compressing KV-Cache with Low-Rank Projection

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.825323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ff40ad3-f55c-46db-926c-d51afbbd0020 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Training Verifiers to Solve Math Word Problems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.832690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f11cb9aa-bcc5-4735-a342-3b24f0178fc2 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.837526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352a4bf6-f68e-4646-98a1-65937f420473 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.842117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3e9de94-c814-45eb-be2e-14625b18e067 · outbound

This paper cites QAQ: Quality Adaptive Quantization for LLM KV Cache.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering QAQ: Quality Adaptive Quantization for LLM KV Cache

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.847376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bd22f1a-af28-459a-9ec7-6ad28740fc42 · outbound

This paper cites The Llama 3 Herd of Models.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.852555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac17d14e-2ccb-4c22-adc6-cccc746d29ca · outbound

This paper cites FlashDecoding++: Faster Large Language Model Inference on GPUs.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering FlashDecoding++: Faster Large Language Model Inference on GPUs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.857737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dec87567-bce7-4b01-9448-54d41b907068 · outbound

This paper cites KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.862820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d192574-f02b-4608-8b1f-b3895ab9bcc1 · outbound

This paper cites Mistral 7B.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Mistral 7B

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.868431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dac99d7f-cb4a-4bca-8a6d-92b8b0ae33c7 · outbound

This paper cites QCQA: Quality and Capacity-aware grouped Query Attention.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering QCQA: Quality and Capacity-aware grouped Query Attention

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.873091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d693ca11-8206-4880-b0da-41d86b5d3cf7 · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.879572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e40f040f-1e6d-45c2-ab28-b6db27918ed3 · outbound

This paper cites an unresolved cited work.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:45:10.757623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3b2606d6-5df9-419f-af99-9e6c5e097be2 · outbound

This paper cites an unresolved cited work.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:45:10.733674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 74362e38-9bcc-4d39-8626-bfe1b68a55ea · outbound

This paper cites an unresolved cited work.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:45:10.715024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5f34c911-4420-46cd-a5ae-21abb5158006 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Fast Transformer Decoding: One Write-Head is All You Need

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.901527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9696f4f-1dba-44c6-8b5a-95c3d630a868 · outbound

This paper cites FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.907446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59a20d92-ce06-48fe-866a-4610cd1b7b11 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.914455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6cb2726-e83b-48eb-b906-833c6a995ec5 · outbound

This paper cites an unresolved cited work.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.920790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1396b045-3cf4-47a9-a74b-d7326c79c876 · outbound

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

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.926851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a773ade7-6a5e-4d4b-bb47-81844a9ece5c · outbound

This paper cites an unresolved cited work.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:45:10.695637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1a3c3d1d-0243-40c2-ab7c-11379f14c19f · outbound

This paper cites Attention Is All You Need.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Attention Is All You Need

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.938312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd5e42cf-18cb-4fea-9e28-bde12a9c36a8 · outbound

This paper cites Cohen, Ruslan Salakhutdinov, and Christopher D.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Cohen, Ruslan Salakhutdinov, and Christopher D

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.943240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f93231f-9814-4dc5-85c4-ecb43a2b7e43 · outbound

This paper cites Effectively Compress KV Heads for LLM.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Effectively Compress KV Heads for LLM

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.947823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c7daa70-4d90-4fdb-8a50-23d4b97d8245 · outbound

This paper cites Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.952447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee8404e7-937d-4390-a1da-bb201b4e0a22 · outbound

This paper cites an unresolved cited work.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:45:10.649641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8a744468-b86b-4f68-96bc-c8900601386b · outbound

This paper cites online" 'onlinestring :=.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering online" 'onlinestring :=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.964123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c9ebf99-05a5-4efc-9c46-b326a0197ddf · outbound

This paper cites write newline.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering write newline

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.969345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2d0a32dc-d528-42fe-83d6-2749609e6e03 · inbound

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching cites this paper.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T00:47:32.072537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.