SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.05134 · 2026

SEMPIPES -Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines

Olga Ovcharenko, Sebastian Schelter, Matthias Boehm

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 12 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.05134.json · badge: /api/ran/2602.05134.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
noahho/CAAFE canonical (classifier label)
classifier basis: census
13 ran · 2 no recorded run
FunctionStatusWhere it lives
accuracy_metric Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
noahho/CAAFE/caafe/metrics.py
pointer only (licence: NOASSERTION) · get_code("4b2e97398ff0ffd5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

auc_metric Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
noahho/CAAFE/caafe/metrics.py
pointer only (licence: NOASSERTION) · get_code("08852a7c4075ac4d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_prompt_from_df Ran
ran; our contract draft was wrong, not the code
noahho/CAAFE/caafe/caafe.py
pointer only (licence: NONE); the stored copy get_code serves, from noahho/caafe, is pointer only (licence: NOASSERTION) · get_code("bc4341d2d62b64a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, noahho/CAAFE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_categorical_to_integer_f Ran
ran, honoured the contract we drafted
noahho/CAAFE/caafe/preprocessing.py
pointer only (licence: NOASSERTION) · get_code("426af42ac029f32a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_mappings Ran
ran; our contract draft was wrong, not the code
noahho/CAAFE/caafe/preprocessing.py
pointer only (licence: NOASSERTION) · get_code("2d558b5afaec447b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

draw_stripplot Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
noahho/CAAFE/caafe/plotting.py
pointer only (licence: NOASSERTION) · get_code("5a02b0dae57adafe")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_dataset_helper_extend_df Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
noahho/CAAFE/caafe/evaluate.py
pointer only (licence: NOASSERTION) · get_code("08cb13856884b902")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extend_using_caafe Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
noahho/CAAFE/caafe/feature_extension_baselines.py
pointer only (licence: NOASSERTION) · get_code("22d08057c7865c9f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_prompt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
noahho/CAAFE/caafe/caafe.py
pointer only (licence: NONE); the stored copy get_code serves, from noahho/caafe, is pointer only (licence: NOASSERTION) · get_code("1288c06136735dd7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, noahho/CAAFE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_result Ran
ran; our contract draft was wrong, not the code
noahho/CAAFE/caafe/evaluate.py
pointer only (licence: NOASSERTION) · get_code("29bb04a164941e13")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

refactor_openml_description Ran
ran; our contract draft was wrong, not the code
noahho/CAAFE/caafe/data.py
pointer only (licence: NOASSERTION) · get_code("33256188ee70d2bf")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

run_llm_code Ran
ran; our contract draft was wrong, not the code
noahho/CAAFE/caafe/run_llm_code.py
pointer only (licence: NOASSERTION) · get_code("f3e70dc6d2bcd3a2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

split_target_column Ran
ran; our contract draft was wrong, not the code
noahho/CAAFE/caafe/preprocessing.py
pointer only (licence: NOASSERTION) · get_code("b16a044f07ebfb39")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extend_using_autofeat Not yet run
unverified (harvested, no recorded run)
noahho/CAAFE/caafe/feature_extension_baselines.py
pointer only (licence: NOASSERTION) · get_code("6f55bdc9d585d1a3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

extend_using_dfs Not yet run
unverified (harvested, no recorded run)
noahho/CAAFE/caafe/feature_extension_baselines.py
pointer only (licence: NOASSERTION) · get_code("0545c2bb40d4bc92")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, noahho/CAAFE (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
build_prompt_from_df 1 other paper
1 dated earlier
2305.03403 (2023-05)
Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering
convert_categorical_to_integer_f 1 other paper
1 dated earlier
2503.14434 (2025-03)
LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
create_mappings 1 other paper
1 dated earlier
2503.14434 (2025-03)
LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
get_prompt 1 other paper
1 dated earlier
2305.03403 (2023-05)
Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Real-world machine learning on tabular data relies on complex data preparation pipelines for prediction, data integration, augmentation, and debugging. Designing these pipelines requires substantial domain expertise and engineering effort, motivating the question of how large language models (LLMs) can support tabular ML through code synthesis. We introduce SEMPIPES, a novel declarative programming model that integrates LLM-powered semantic data operators into tabular ML pipelines. Semantic operators specify data transformations in natural language while delegating execution to a runtime system. During training, SEMPIPES synthesizes custom operator implementations based on data characteristics, operator instructions, and pipeline context. This design enables the automatic optimization of data operations in a pipeline via LLM-based code synthesis guided by evolutionary search. We evaluate SEMPIPES across diverse tabular ML tasks and show that semantic operators substantially improve end-to-end predictive performance for both expert-designed and agentgenerated pipelines, while reducing pipeline complexity. We implement SEMPIPES in Python and release it at https://github.com/deem-data/ sempipes/tree/v1.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.05134")
get_code_for_paper("2602.05134")
have("2602.05134")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.05134.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.05134.svg)](https://syntology.ai/paper/2602.05134)

Connect an agent — have() is free.