Pith Number

pith:A2CQIYS2

pith:2026:A2CQIYS2XN45L2QU7VB6BF4IDK

not attested not anchored not stored refs resolved

Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

Dit-Yan Yeung, Lemao Liu, Mo Yu, Tsz Ting Chung

Many-shot chain-of-thought in-context learning behaves as test-time learning when demonstrations are ordered for smooth conceptual progression.

arxiv:2605.13511 v1 · 2026-05-13 · cs.CL · 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{A2CQIYS2XN45L2QU7VB6BF4IDK}

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

We interpret these behaviors by viewing many-shot CoT-ICL as in-context test-time learning rather than scaled pattern matching, and suggests two principles: (i) demonstrations should be easy for the target model to understand, and (ii) they should be ordered to support a smooth conceptual progression. Guided by the principle, we propose Curvilinear Demonstration Selection (CDS), a simple ordering method that yields up to a 5.42 percentage-point gain on geometry with 64 demonstrations.

C2weakest assumption

That the observed scaling effects and performance gains stem from the model performing test-time learning enabled by ordered demonstrations, rather than from other factors such as prompt length or specific model architectures, and that the two principles generalize beyond the tested models and tasks.

C3one line summary

Many-shot CoT-ICL functions as test-time learning when demonstrations are ordered for smooth conceptual progression rather than similarity, enabling a new selection method that improves reasoning performance.

References

58 extracted · 58 resolved · 2 Pith anchors

[1] Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability 2024 · doi:10.18653/v1/2024.findings-emnlp.646

[2] Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning 2025 · doi:10.18653/v1/2025.findings-naacl.283

[3] In-context Learning and Induction Heads , author=. 2022 , eprint= 2022

[4] The Stochastic Parrot on LLM ' s Shoulder: A Summative Assessment of Physical Concept Understanding 2025 · doi:10.18653/v1/2025.naacl-long.569

[5] D iv L ogic E val: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models 2025 · doi:10.18653/v1/2025.findings-emnlp.47

Receipt and verification

First computed	2026-05-18T02:44:24.563722Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

068504625abb79d5ea14fd43e097881aa71107d568124dc8bd4b852ab359651e

Aliases

arxiv: 2605.13511 · arxiv_version: 2605.13511v1 · doi: 10.48550/arxiv.2605.13511 · pith_short_12: A2CQIYS2XN45 · pith_short_16: A2CQIYS2XN45L2QU · pith_short_8: A2CQIYS2

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/A2CQIYS2XN45L2QU7VB6BF4IDK \
  | 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: 068504625abb79d5ea14fd43e097881aa71107d568124dc8bd4b852ab359651e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7828fb637367750ebde2ded28567528f32c3e172fbc430ffd398bd3311476826",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T13:30:12Z",
    "title_canon_sha256": "2283beec5815ca27fdd347c93e6e5ed8ee9085a0c0c5643a150bc5da89cebf07"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13511",
    "kind": "arxiv",
    "version": 1
  }
}