SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.20233 · 2024

Functional Bilevel Optimization for Machine Learning

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2403.20233.json · badge: /api/ran/2403.20233.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
inria-thoth/funcbo canonical (classifier label)
classifier basis: census
9 ran · 3 no recorded run
FunctionStatusWhere it lives
augment_stage1_feature Ran
ran; our contract draft was wrong, not the code
inria-thoth/funcbo/applications/IVRegression/dataset_networks_dsprites/twoSLS.py
pointer only (licence: NONE) · get_code("66ad22617830babb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

augment_stage2_feature Ran
ran; our contract draft was wrong, not the code
inria-thoth/funcbo/applications/IVRegression/dataset_networks_dsprites/twoSLS.py
pointer only (licence: NONE) · get_code("7b2444767629d779")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

image_id Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
inria-thoth/funcbo/applications/IVRegression/dataset_networks_dsprites/generator.py
pointer only (licence: NONE); the stored copy get_code serves, from haotiansun14/SpecIV, is pointer only (licence: NONE) · get_code("f50dc351bfaffcf9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

import_module Ran
ran; our contract draft was wrong, not the code
inria-thoth/funcbo/funcBO/utils.py
pointer only (licence: NONE) · get_code("6e874fefcee59755")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

make_plot_dicts Ran
ran; our contract draft was wrong, not the code
inria-thoth/funcbo/applications/ModelBasedRL/plots.py
pointer only (licence: NONE) · get_code("29f539eb590e0bb0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

mean_std_array Ran
ran; our contract draft was wrong, not the code
inria-thoth/funcbo/applications/ModelBasedRL/plots.py
pointer only (licence: NONE) · get_code("713e1281a06c6a4c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

outer_prod Ran
ran; our contract draft was wrong, not the code
inria-thoth/funcbo/applications/IVRegression/dataset_networks_dsprites/twoSLS.py
pointer only (licence: NONE) · get_code("f987e1b5671dd8d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

rbf_kernel Ran
ran; our contract draft was wrong, not the code
inria-thoth/funcbo/applications/IVRegression/dataset_networks_dsprites/dspriteKernel.py
pointer only (licence: NONE) · get_code("531d3fccbf68a314")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

set_device_and_type Ran
ran; our contract draft was wrong, not the code
inria-thoth/funcbo/funcBO/utils.py
pointer only (licence: NONE) · get_code("6e7e80f833a13690")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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.

config_to_instance Not yet run
unverified (harvested, no recorded run)
inria-thoth/funcbo/funcBO/utils.py
pointer only (licence: NONE) · get_code("f55709ebd4f89c05")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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. No invocation recorded.

generate_test_dsprite Not yet run
unverified (harvested, no recorded run)
inria-thoth/funcbo/applications/IVRegression/dataset_networks_dsprites/generator.py
pointer only (licence: NONE) · get_code("77cfae356e7f0d63")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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. No invocation recorded.

structural_func Not yet run
unverified (harvested, no recorded run)
inria-thoth/funcbo/applications/IVRegression/dataset_networks_dsprites/generator.py
pointer only (licence: NONE); the stored copy get_code serves, from haotiansun14/SpecIV, is pointer only (licence: NONE) · get_code("0143f51530f5fc5c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, inria-thoth/funcbo 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 9 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
image_id 1 other paper
1 later
2407.10448 (2024-07)
Spectral Representation for Causal Estimation with Hidden Confounders
outer_prod 1 other paper
1 dated earlier
2205.09824 (2022-05)
Deep Learning Methods for Proximal Inference via Maximum Moment Restriction
structural_func 1 other paper
1 later
2407.10448 (2024-07)
Spectral Representation for Causal Estimation with Hidden Confounders

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

In this paper, we introduce a new functional point of view on bilevel optimization problems for machine learning, where the inner objective is minimized over a function space. These types of problems are most often solved by using methods developed in the parametric setting, where the inner objective is strongly convex with respect to the parameters of the prediction function. The functional point of view does not rely on this assumption and notably allows using over-parameterized neural networks as the inner prediction function. We propose scalable and efficient algorithms for the functional bilevel optimization problem and illustrate the benefits of our approach on instrumental regression and reinforcement learning tasks.

For agents

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

get_harvested_code_for_paper("2403.20233")
get_code_for_paper("2403.20233")
have("2403.20233")

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

curl https://syntology.ai/api/ran/2403.20233.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.20233.svg)](https://syntology.ai/paper/2403.20233)

Connect an agent — have() is free.