Paper Citation Record · LEDGER

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

As of 8 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2604.03922.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2604.03922 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-14T19:54:08.600196Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

22 of 22 outbound references displayed

verified exact0
verified fuzzy0
unresolved21
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5ccbcc63-fc20-47a4-a144-4845bf20a1f0 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Evaluating Large Language Models Trained on Code

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af18d80c-a96e-49a2-8b39-2db879824143 · outbound

This paper cites DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b67500c-1941-4499-9f6e-e181e8525835 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f18b6b2d-1096-4701-89f5-fddbb4379aa4 · outbound

This paper cites an unresolved cited work.

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

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4dfc75f-3674-4e4f-97d1-157fd84648a9 · outbound

This paper cites an unresolved cited work.

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

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5f174c3-cf4f-41dc-837e-842d525f398f · outbound

This paper cites Program Synthesis with Large Language Models.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Program Synthesis with Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 131fc642-8a86-4e61-be5c-8f23f9cd2b4d · outbound

This paper cites GPT-4 Technical Report.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation GPT-4 Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56d0ef67-af6d-45bd-b001-d1caa998851a · outbound

This paper cites Code Llama: Open Foundation Models for Code.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Code Llama: Open Foundation Models for Code

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 211c770c-d1c8-48c1-8e39-a503354527b6 · outbound

This paper cites StarCoder 2 and The Stack v2: The Next Generation.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation StarCoder 2 and The Stack v2: The Next Generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 901497dc-8554-4741-a659-d5c242093761 · outbound

This paper cites Qwen2.5-Coder Technical Report.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Qwen2.5-Coder Technical Report

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c9c9d34-478b-4258-bc47-1969b596ba22 · outbound

This paper cites Sampling-based approximations to minimum Bayes risk decoding for neural machine translation.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Sampling-based approximations to minimum Bayes risk decoding for neural machine translation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7abc866b-1047-4832-8a6e-0428af205661 · outbound

This paper cites ALGO: Synthesizing algorithmic programs with generated oracle verifiers.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation ALGO: Synthesizing algorithmic programs with generated oracle verifiers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc0e439a-d2d8-4e2f-9234-e633ec6b69e3 · outbound

This paper cites Consistency meets verification: Enhancing test generation quality in large language models without ground-truth solutions.Arxiv Preprint Arxiv:2602.10522,.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Consistency meets verification: Enhancing test generation quality in large language models without ground-truth solutions.Arxiv Preprint Arxiv:2602.10522,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae1fb30-1f0d-401f-93fc-39df798c1181 · outbound

This paper cites DOCE: Finding the Sweet Spot for Execution-Based Code Generation.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation DOCE: Finding the Sweet Spot for Execution-Based Code Generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6753e716-1c19-4582-8b37-a1480cfdc85b · outbound

This paper cites Noise tolerance of learning to rank under class-conditional label noise.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Noise tolerance of learning to rank under class-conditional label noise

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b340f575-376c-445c-aa55-66cc645d5afe · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Training Verifiers to Solve Math Word Problems

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d1c0462-b7d0-4a3f-9062-d1db139bbf3d · outbound

This paper cites LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36b95787-e9f9-49c6-9213-8fa8cc1121c8 · outbound

This paper cites It follows that the true AUC A(w) is the same for every pair (c+ ∈C +, c − ∈C −) and that two codes from the same class have identically distributed scores.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation It follows that the true AUC A(w) is the same for every pair (c+ ∈C +, c − ∈C −) and that two codes from the same class have identically distributed scores

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c73d5b24-1062-43ec-8f6c-fab6d11f1050 · outbound

This paper cites Under uniform initial weights, the leave-one-out scores reduce to unweighted row sums with one column removed; since the AUC is scale-invariant, normalization is unnecessary.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Under uniform initial weights, the leave-one-out scores reduce to unweighted row sums with one column removed; since the AUC is scale-invariant, normalization is unnecessary

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24c2a085-c8df-4e5e-81eb-6fcd2b2111eb · outbound

This paper cites an unresolved cited work.

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

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a75c7d0c-7173-4710-bfd8-62efb9807525 · outbound

This paper cites correct(α j =1)incorrect(α j <1) perf.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation correct(α j =1)incorrect(α j <1) perf

Reference 21

Resolution: malformed identifier; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75890a00-ed46-4d6a-868e-fc8c972131e1 · outbound

This paper cites assert {entry point}(...) ==.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation assert {entry point}(...) ==

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T19:54:08.600196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.