pith. sign in
Pith Number

pith:XARKISWT

pith:2026:XARKISWTWL77GOF3REB7SEHZXM
not attested not anchored not stored refs resolved

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

Beomseok Kang, Dongwon Jo, Jae-Joon Kim, Jiwon Song

Block-union KV selection builds minimal tables so chunked prefill attention runs up to 2.72 times faster while staying close to dense accuracy.

arxiv:2605.16839 v1 · 2026-05-16 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{XARKISWTWL77GOF3REB7SEHZXM}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On LLaMA-3.1-8B-Instruct, CompactAttention maintains accuracy close to dense attention on the RULER benchmark while delivering up to 2.72× attention speedup at 128K context length under chunked prefill.

C2weakest assumption

The construction of GQA-aware per-group KV block tables via Q-block union and intra-group union produces the minimal tables that preserve all KV blocks selected by the input masks under paged execution constraints without missing query-specific entries.

C3one line summary

CompactAttention accelerates chunked-prefill attention via Block-Union KV Selection, delivering up to 2.72x speedup at 128K context on LLaMA-3.1-8B while matching dense accuracy on RULER.

References

28 extracted · 28 resolved · 9 Pith anchors

[1] OpenAI GPT-5 System Card 2025 · arXiv:2601.03267
[2] System card: Claude Opus 4.6 2026
[3] Gemini 3 Pro model card 2025
[4] Kimi K2.5: Visual Agentic Intelligence 2026 · arXiv:2602.02276
[5] Deepseek-v4: Towards highly efficient million-token context intelligence 2026

Formal links

1 machine-checked theorem link

Receipt and verification
First computed 2026-05-20T00:03:25.502780Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

b822a44ad3b2fff338bb8903f910f9bb14f361a79e1e056d6778f43b63fabd8f

Aliases

arxiv: 2605.16839 · arxiv_version: 2605.16839v1 · doi: 10.48550/arxiv.2605.16839 · pith_short_12: XARKISWTWL77 · pith_short_16: XARKISWTWL77GOF3 · pith_short_8: XARKISWT
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: b822a44ad3b2fff338bb8903f910f9bb14f361a79e1e056d6778f43b63fabd8f
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "7ae9a3ee0b125d2213d63e83abef7aacf5a01522096f9c596bd9658a473937a5",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-16T06:47:41Z",
    "title_canon_sha256": "737bfbe36fe943f6268813677dd619f9410ed42f63c6c0a7ea40ef1f71ee028d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16839",
    "kind": "arxiv",
    "version": 1
  }
}