Pith Number

pith:HWBWMP5Y

pith:2026:HWBWMP5YXRRWOQTVRXRUMCZTLK

not attested not anchored not stored refs resolved

Query-Conditioned Test-Time Self-Training for Large Language Models

Chaehee Song, Changick Kim, Doyi Kim, Minseok Seo, Yeeun Seong

Large language models can adapt their own parameters during inference by generating training examples directly from the input query.

arxiv:2605.13369 v2 · 2026-05-13 · cs.CL · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{HWBWMP5YXRRWOQTVRXRUMCZTLK}

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

QueST generates such query-conditioned pairs and uses them as supervision for parameter-efficient fine-tuning at test time. The adapted model is then used to produce the final answer, enabling query-specific adaptation without any external data.

C2weakest assumption

the input query itself encodes latent signals sufficient for constructing structurally related problem--solution pairs

C3one line summary

QueST adapts LLMs at test time by generating query-specific problem-solution pairs for self-supervised fine-tuning, improving reasoning performance without external data.

References

42 extracted · 42 resolved · 14 Pith anchors

[1] GPT-4 Technical Report 2023 · arXiv:2303.08774

[2] Training Verifiers to Solve Math Word Problems 2021 · arXiv:2110.14168

[3] In-Place Test-Time Training 2026 · arXiv:2604.06169

[4] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 2025 · arXiv:2501.12948

[5] Test-time training on nearest neighbors for large language models.arXiv preprint arXiv:2305.18466 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:47.996156Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3d83663fb8bc636742758de3460b335a93eb726f3a76521530b9bf4ec57bae6d

Aliases

arxiv: 2605.13369 · arxiv_version: 2605.13369v2 · doi: 10.48550/arxiv.2605.13369 · pith_short_12: HWBWMP5YXRRW · pith_short_16: HWBWMP5YXRRWOQTV · pith_short_8: HWBWMP5Y

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/HWBWMP5YXRRWOQTVRXRUMCZTLK \
  | 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: 3d83663fb8bc636742758de3460b335a93eb726f3a76521530b9bf4ec57bae6d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f8740c8dc59a74afea06d0eb91d97dd84ca9a0c9f9fcf3a24315c6ad7d783b4a",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T11:27:40Z",
    "title_canon_sha256": "129407ebd1cd3bcd2614d4223dc14cb773fdb0c6fff23a384f258abcd960d544"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13369",
    "kind": "arxiv",
    "version": 2
  }
}