Pith Number

pith:QD35AOPB

pith:2026:QD35AOPB5NUKK4XV3LYGQS4KWT

not attested not anchored not stored refs pending

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation

Hui Sun, Ming Li, Ren-Biao Liu, Xin-Ye Li, Yali Du, Yun-Ji Zhang, Zheng Xie

You can weight LLM-generated tests by leave-one-out ranking agreement, recovering each test’s power to separate correct from incorrect code without knowing which codes are right.

arxiv:2604.03922 v2 · 2026-04-05 · 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{QD35AOPB5NUKK4XV3LYGQS4KWT}

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

Expected leave-one-out AUC of test j equals 1/2 plus a positive coefficient times the test's discriminative power δ_j = α_j − β_j (Theorem 3); consequently the closed-form ACES-C weights recover the sign of δ_j in expectation under Assumption 4 and approximate the oracle signal-to-noise ratio (Theorem 6, Corollary 8), while both ACES variants achieve state-of-the-art Pass@k among execution-only methods on HumanEval, HumanEval+ and MBPP.

C2weakest assumption

Assumption 4: the average discriminative power of the generated test pool is positive and large enough that leaving any single test out still leaves the remaining ranking better than random (¯δ > 2√(ln 2 / m)). The closed-form guarantees of ACES-C and the positivity of the LOO-AUC coefficients rest on this average-quality condition; when it fails, only the iterative ACES-O variant is claimed to remain effective.

C3one line summary

Leave-one-out AUC of each test against the ranking induced by the remaining tests is proportional to that test's latent discriminative power, yielding closed-form and optimized weights that raise Pass@k.

Receipt and verification

First computed	2026-07-14T01:20:58.243140Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

80f7d039e1eb68a572f5daf0684b8ab4cfadfeabe19789c719f8e1319867a9ec

Aliases

arxiv: 2604.03922 · arxiv_version: 2604.03922v2 · doi: 10.48550/arxiv.2604.03922 · pith_short_12: QD35AOPB5NUK · pith_short_16: QD35AOPB5NUKK4XV · pith_short_8: QD35AOPB

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/QD35AOPB5NUKK4XV3LYGQS4KWT \
  | 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: 80f7d039e1eb68a572f5daf0684b8ab4cfadfeabe19789c719f8e1319867a9ec

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2078fc0156308494a9f1d6959e2ee50ae782be1829cc5ae74c6197da9bcd0210",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-05T01:15:57Z",
    "title_canon_sha256": "1933a0131b8773a4f2fda92822fbd59f27c840ed9cbd55f9c42c32fe9d3ff427"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.03922",
    "kind": "arxiv",
    "version": 2
  }
}