Pith Number

pith:A4NJWH45

pith:2026:A4NJWH45ZFZNHD7F546JB5HE5E

not attested not anchored not stored refs pending

AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse

Jie Ou, Jinyu Guo, Ruiqi Wu, Shiyao Guo, Wenhong Tian, Wenyi Li, Yuang Li, Zhaokun Wang

AdapShot selects the optimal number of in-context examples for each query by measuring output entropy in a probe run and reuses KV cache with reordering to enable efficient many-shot learning.

arxiv:2605.03644 v2 · 2026-05-05 · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{A4NJWH45ZFZNHD7F546JB5HE5E}

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

Extensive experiments demonstrate that AdapShot achieves an average performance gain of around 10% and a 4.64x speedup compared to state-of-the-art DBSA.

C2weakest assumption

That output entropy from a short probe run is a sufficient and unbiased signal for selecting the globally optimal shot count, and that the decoupling-plus-re-encoding step for KV cache reordering introduces no accuracy degradation.

C3one line summary

AdapShot adaptively tunes shot count via entropy probes and reuses semantically-matched KV caches with position decoupling to deliver ~10% accuracy gains and 4.64x speedup over fixed-shot baselines.

Receipt and verification

First computed	2026-06-03T01:05:50.890531Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

071a9b1f9dc972d38fe5ef3c90f4e4e91381fb4ec0d4ac2285235ff8f99e2fc1

Aliases

arxiv: 2605.03644 · arxiv_version: 2605.03644v2 · doi: 10.48550/arxiv.2605.03644 · pith_short_12: A4NJWH45ZFZN · pith_short_16: A4NJWH45ZFZNHD7F · pith_short_8: A4NJWH45

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/A4NJWH45ZFZNHD7F546JB5HE5E \
  | 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: 071a9b1f9dc972d38fe5ef3c90f4e4e91381fb4ec0d4ac2285235ff8f99e2fc1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0d81d3e09cbef1c2e8703e8927e07d85d2761b8ac951a86d81ae3d72fece01b1",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-05T11:16:52Z",
    "title_canon_sha256": "88d4d948f000aa1dc98aa7aa50b7aadc83d436905600b399c06e67ce4bc2151c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.03644",
    "kind": "arxiv",
    "version": 2
  }
}