Paper Citation Record · LEDGER

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation

As of 18 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2509.22768.

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

pith.paper-citation-record.v1
2509.22768 v3

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:52:50.638681Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

45 of 45 outbound references displayed

verified exact1
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e420ec97-8354-432d-a81f-1547a576a8ea · outbound

This paper cites MEGA : Multilingual evaluation of generative AI.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation MEGA : Multilingual evaluation of generative AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:45.456078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4338902-d974-4a93-876b-1961c01736a7 · outbound

This paper cites Don’t push the button! exploring data leakage risks in machine learning and transfer learning.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Don’t push the button! exploring data leakage risks in machine learning and transfer learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:45.542088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda118ab-8731-4786-9027-99de33468a22 · outbound

This paper cites Do, Yan Xu, and Pascale Fung.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Do, Yan Xu, and Pascale Fung

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:45.681840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dca7e741-24e2-4292-9f0e-f13a89578fa3 · outbound

This paper cites MLE -bench: Evaluating machine learning agents on machine learning engineering.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation MLE -bench: Evaluating machine learning agents on machine learning engineering

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:45.852056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10b37b62-bc47-488b-9a0e-fce59ebf2109 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Evaluating Large Language Models Trained on Code

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:45.983121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45a150c-1add-4c85-82db-133695def190 · outbound

This paper cites R o C ode: A dataset for measuring code intelligence from problem definitions in R omanian.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation R o C ode: A dataset for measuring code intelligence from problem definitions in R omanian

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:46.093206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 425917cb-f6cb-41aa-8a6e-6738841ed173 · outbound

This paper cites Abstract Interpretation-Based Data Leakage Static Analysis.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Abstract Interpretation-Based Data Leakage Static Analysis

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:46.250742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39787f77-bd8c-43c9-9bcf-20c0f0673a44 · outbound

This paper cites Code4ml: a large-scale dataset of annotated machine learning code.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Code4ml: a large-scale dataset of annotated machine learning code

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:46.373728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4603158-7b91-40af-9387-07492a75bb3d · outbound

This paper cites Neural architecture search: A survey.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Neural architecture search: A survey

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:46.445465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06e7f6d6-bf49-4634-9cae-cf4c12d5ebb3 · outbound

This paper cites Efficient and robust automated machine learning.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Efficient and robust automated machine learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:46.648892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd74d53-5673-4387-b47e-707c26cb6546 · outbound

This paper cites How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:46.813328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64d76b61-f079-48b1-a95a-190502e4a1bc · outbound

This paper cites DA -code: Agent data science code generation benchmark for large language models.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation DA -code: Agent data science code generation benchmark for large language models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:46.924451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5f330a1-39c7-4150-82bd-85682835644d · outbound

This paper cites CodeSearchNet Challenge: Evaluating the State of Semantic Code Search.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation CodeSearchNet Challenge: Evaluating the State of Semantic Code Search

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:47.012365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d35eff5a-5cfa-4009-bc98-c4dad0339ada · outbound

This paper cites AIDE: AI-Driven Exploration in the Space of Code.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation AIDE: AI-Driven Exploration in the Space of Code

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:47.132960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67fa34a3-6f01-4847-9cac-5ac1b1c4e261 · outbound

This paper cites Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:47.365507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52378ff4-98e4-4e66-95d1-24e301beb581 · outbound

This paper cites Better to ask in english: Cross-lingual evaluation of large language models for healthcare queries.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Better to ask in english: Cross-lingual evaluation of large language models for healthcare queries

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:47.579659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad604c15-4f00-481d-a0ba-c1830dfb1ad1 · outbound

This paper cites Leakage and the reproducibility crisis in machine-learning-based science.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Leakage and the reproducibility crisis in machine-learning-based science

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:47.761260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91e5a2f4-be41-4d93-9f6c-8bad564ac27e · outbound

This paper cites Ds-1000: a natural and reliable benchmark for data science code generation.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Ds-1000: a natural and reliable benchmark for data science code generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:47.897537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4eb0139-5aa9-4a31-b3ab-889cb471791b · outbound

This paper cites H2o automl: Scalable automatic machine learning.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation H2o automl: Scalable automatic machine learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:47.995256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4d37812-aefe-45e9-98a7-5c376415acb8 · outbound

This paper cites Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:48.068875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4a1793e-a95c-4941-a3a7-2bb8a7f54953 · outbound

This paper cites StarCoder: may the source be with you!.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation StarCoder: may the source be with you!

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:48.179470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bfeca5d-667a-4960-8f82-747f5eb2a5a2 · outbound

This paper cites DARTS : Differentiable architecture search.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation DARTS : Differentiable architecture search

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:48.326957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aee95852-047f-4726-848b-90c4e94a2711 · outbound

This paper cites On Leakage of Code Generation Evaluation Datasets.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation On Leakage of Code Generation Evaluation Datasets

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:48.436986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc99bfad-adb8-401d-99c3-edd33fc5aef6 · outbound

This paper cites Evaluating programming language confusion.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Evaluating programming language confusion

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:48.607551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f7c6e13-9f1b-40f0-bdf6-d2d5f498f3a1 · outbound

This paper cites Crosslingual generalization through multitask finetuning.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Crosslingual generalization through multitask finetuning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:48.698716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0c9f926-3437-4da0-a311-d138b1341510 · outbound

This paper cites Olson, Nathan Bartley, Ryan J.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Olson, Nathan Bartley, Ryan J

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:48.870432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 243d93b9-8f3d-4874-9e8c-97848239dccd · outbound

This paper cites Dscodebench: A realistic benchmark for data science code generation.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Dscodebench: A realistic benchmark for data science code generation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.054155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e74f38-68e8-484c-b5ff-0a7d8079fcc3 · outbound

This paper cites Efficient neural architecture search via parameters sharing.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Efficient neural architecture search via parameters sharing

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.202574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 936bb467-1a9a-4eeb-851c-286e5ddfbb1a · outbound

This paper cites Meta kaggle code, 2023.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Meta kaggle code, 2023

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.284097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a33406c-9442-49cb-8bf8-8d48daa9312e · outbound

This paper cites m H uman E val - a multilingual benchmark to evaluate large language models for code generation.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation m H uman E val - a multilingual benchmark to evaluate large language models for code generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.398954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f05b8c5-4f13-46ec-b7c1-fe72e521d0d3 · outbound

This paper cites Do GPTs Produce Less Literal Translations?.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Do GPTs Produce Less Literal Translations?

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.483019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65082097-3b06-4b20-8026-2dbca25f9768 · outbound

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

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Code Llama: Open Foundation Models for Code

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.569202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6db1d1c-91fa-49b1-8832-53d5913799c8 · outbound

This paper cites Sasse, E.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Sasse, E

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.671243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d57d06e2-b08b-40d7-a4fd-2a0050e7339b · outbound

This paper cites Biocoder: a benchmark for bioinformatics code generation with large language models.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Biocoder: a benchmark for bioinformatics code generation with large language models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.760663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c3e951-9187-446f-8974-1a3d1d2f5592 · outbound

This paper cites SciCode: A Research Coding Benchmark Curated by Scientists.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation SciCode: A Research Coding Benchmark Curated by Scientists

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.846361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da2f3360-d57d-4ea2-b2bf-ee6767351e45 · outbound

This paper cites LightAutoML: AutoML Solution for a Large Financial Services Ecosystem.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation LightAutoML: AutoML Solution for a Large Financial Services Ecosystem

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.910664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 326cfc55-677f-4256-a3a3-b34b38dc4559 · outbound

This paper cites OpenHands: An Open Platform for AI Software Developers as Generalist Agents.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:49.994121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0373be4a-3c79-484c-9b03-7ede74aba817 · outbound

This paper cites MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:50.080171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3606950e-8203-4733-bc79-7f5e90003c6f · outbound

This paper cites Data Leakage in Notebooks: Static Detection and Better Processes.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Data Leakage in Notebooks: Static Detection and Better Processes

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:50.160601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 454558da-8267-4e9d-ada2-7797949bcc52 · outbound

This paper cites LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:50.211290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47f62696-d9f4-4954-9b87-f220d173af03 · outbound

This paper cites an unresolved cited work.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Unresolved cited work

Reference 41

Resolution: verified exact; doi, observed 2026-08-04T14:53:21.126268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f4f7e8e6-5ff7-4d32-ba10-0a1256f3afdd · outbound

This paper cites write newline.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation write newline

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:50.383648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcd9988c-2c0a-4aba-9cbc-28b12ce13d36 · outbound

This paper cites @esa (Ref.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation @esa (Ref

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:50.475733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3977f7a0-e450-451e-aab6-3c1c6756bf8f · outbound

This paper cites an unresolved cited work.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:50.558496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1570824f-2e9a-4fab-9e0c-7eb165238048 · outbound

This paper cites 9rD= <8rrr, 5jTXyyy5V ꬦM`0HΞ=[X5Z ꬀[t ߿XܹSԮ];i qsv Ÿu9 >|Xo =z(00PΝ n: UVzǝ]2Z 4 ڸqV 6c4j(] rR g ǎiJHH=--M + P u5k, iӦ . egg+::Z /VLL ] 3Fwy P uӧ-` (WWW+.

ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation 9rD= <8rrr, 5jTXyyy5V ꬦM`0HΞ=[X5Z ꬀[t ߿XܹSԮ];i qsv Ÿu9 >|Xo =z(00PΝ n: UVzǝ]2Z 4 ڸqV 6c4j(] rR g ǎiJHH=--M + P u5k, iӦ . egg+::Z /VLL ] 3Fwy P uӧ-` (WWW+

Reference 45

Resolution: malformed identifier; no resolver link, observed 2026-08-04T14:52:50.638681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.