SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.01130 · 2022

Improving Pareto Front Learning via Multi-Sample Hypernetworks

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 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; 2 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 1 failure of our instrument; 0 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/2212.01130.json · badge: /api/ran/2212.01130.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
longhoangphi225/MultiSample-Hypernetworks canonical (classifier label)
classifier basis not recorded on the link
10 ran · 0 no recorded run
FunctionStatusWhere it lives
checkDomination Ran
ran on a synthesized input
longhoangphi225/MultiSample-Hypernetworks/Jura/functions_evaluation.py
code served (permissive licence) · get_code("42d7425cbbe80c4f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create small test arrays for multi-objective optimization domination checking
# objValA: shape (num_objectives,) - objective values for solution A
# objValArray: shape (num_objectives, num_solutions) - objective values for multiple solutions

objValA = np.array([1.0, 2.0, 3.0, 4.0])

objValArray = np.array([
    [1.5, 2.0, 0.5, 3.0],  # objective 1 for 4 solutions
    [2.5, 1.5, 4.0, 2.0],  # objective 2 for 4 solutions
    [3.5, 2.5, 3.0, 5.0],  # objective 3 for 4 solutions
    [4.5, 3.5, 2.0, 4.0]   # objective 4 for 4 solutions
])

ARGS = {
    'objValA': objValA,
    'objValArray': objValArray
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
circle_points Ran
ran, honoured the contract we drafted
longhoangphi225/MultiSample-Hypernetworks/Jura/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from tuantran23012000/cpfl_hyper_transformer, is pointer only (licence: NONE) · get_code("f76ba0f4cbb3d733")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tuantran23012000/cpfl_hyper_transformer, and GitHub detected no licence in that repository 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.

count_parameters Ran
ran, honoured the contract we drafted
longhoangphi225/MultiSample-Hypernetworks/Jura/utils.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
determine_mo_sol_in_exterior Ran
ran on a synthesized input
longhoangphi225/MultiSample-Hypernetworks/Jura/functions_hv_grad_3d.py
code served (permissive licence) · get_code("323b62405a8df3d5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Analyzing the function:
# - mo_obj_val: used with shape indexing, needs to be 2D array (n_objectives x n_solutions)
# - ref_point: used with [:, None] slicing, needs to be 1D array (n_objectives,)
# - The function compares mo_obj_val > ref_point_temp element-wise
# - Uses np.any and np.where

# Create small test data
# ref_point: 1D array with 3 objectives
ref_point = np.array([1.0, 2.0, 3.0])

# mo_obj_val: 2D array with shape (3 objectives, 5 solutions)
# Some solutions should be exterior (have at least one objective value > corresponding ref_point)
mo_obj_val = np.array([
    [0.5, 1.5, 2.0, 3.5, 0.8],  # objective 1
    [1.0, 3.0, 1.5, 2.5, 2.2],  # objective 2
    [2.5, 2.8, 4.0, 3.2, 3.1]   # objective 3
])

ARGS = {
    "mo_obj_val": mo_obj_val,
    "ref_point": ref_point
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
determine_mo_sol_in_interior Ran
ran on a synthesized input
longhoangphi225/MultiSample-Hypernetworks/Jura/functions_hv_grad_3d.py
code served (permissive licence) · get_code("4c8ef15f99bfbd06")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct valid arguments for determine_mo_sol_in_interior
# The function expects:
# - mo_obj_val: a 2D array where each column represents objective values for a solution
# - ref_point: a 1D array representing the reference point

# Create a reference point (1D array with 4 objectives)
ref_point = np.array([5.0, 6.0, 7.0, 8.0])

# Create multi-objective values (4 objectives x 2 solutions)
# Some solutions should be interior (all values < ref_point)
# Some solutions should be exterior (at least one value >= ref_point)
mo_obj_val = np.array([
    [3.0, 5.5],   # objective 1: first solution interior, second exterior
    [4.0, 5.5],   # objective 2: first solution interior, second interior
    [5.5, 6.5],   # objective 3: first solution interior, second exterior
    [6.0, 7.5]    # objective 4: first solution interior, second exterior
])

ARGS = {
    "mo_obj_val": mo_obj_val,
    "ref_point": ref_point
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
determine_mo_sol_on_ref_boundary Ran
ran on a synthesized input
longhoangphi225/MultiSample-Hypernetworks/Jura/functions_hv_grad_3d.py
code served (permissive licence) · get_code("b14d93e8c7be509c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create setup for determine_mo_sol_on_ref_boundary
# This function takes multi-objective values and a reference point
# and determines which solutions are on the reference boundary

# mo_obj_val: 2D array of objective values (objectives x solutions)
# ref_point: 1D array of reference point values (one per objective)

# Create multi-objective values: 3 objectives, 5 solutions
mo_obj_val = np.array([
    [1.0, 2.0, 1.5, 3.0, 2.5],
    [2.0, 1.0, 2.5, 1.5, 1.0],
    [3.0, 3.0, 2.0, 2.0, 3.5]
])

# Create reference point: one value per objective
ref_point = np.array([3.0, 3.0, 4.0])

ARGS = {
    "mo_obj_val": mo_obj_val,
    "ref_point": ref_point
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
determine_non_dom_mo_sol Ran
ran on a synthesized input
longhoangphi225/MultiSample-Hypernetworks/Jura/functions_evaluation.py
code served (permissive licence) · get_code("51349084c756d3a1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small multi-objective optimization problem
# 2 objectives, 5 solutions
N_OBJECTIVES = 2
N_SOLUTIONS = 5

# Create objective values where some solutions are non-dominated
# Solution 0: [1.0, 2.0]
# Solution 1: [2.0, 1.0]
# Solution 2: [1.5, 1.5] (dominated by 0 and 1)
# Solution 3: [0.5, 3.0] (non-dominated)
# Solution 4: [3.0, 0.5] (non-dominated)
mo_obj_val = np.array([
    [1.0, 2.0, 1.5, 0.5, 3.0],
    [2.0, 1.0, 1.5, 3.0, 0.5]
], dtype=float)

ARGS = {
    "mo_obj_val": mo_obj_val
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
fastNonDominatedSort Ran
ran on a synthesized input
longhoangphi225/MultiSample-Hypernetworks/Jura/functions_evaluation.py
code served (permissive licence) · get_code("7a212c0b10ec2e95")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family int, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct a small multi-objective optimization problem
# The function expects objVal to be shape (N_OBJECTIVES, N_SOLUTIONS)
# where each column represents a solution and each row represents an objective value

# Create a simple 2D Pareto front problem with 5 solutions
N_OBJECTIVES = 2
N_SOLUTIONS = 5

# Objective values: 2 objectives, 5 solutions
# These represent different points in objective space
objVal = np.array([
    [1.0, 2.0, 1.5, 3.0, 2.5],  # Objective 1
    [5.0, 3.0, 4.0, 2.0, 3.5]   # Objective 2
], dtype=float)

# Verify shape is correct
assert objVal.shape == (N_OBJECTIVES, N_SOLUTIONS)

ARGS = {
    'objVal': objVal
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (5,) — shape (5,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_device Ran
ran; our contract draft was wrong, not the code
longhoangphi225/MultiSample-Hypernetworks/Jura/utils.py
code served (permissive licence) · get_code("398ef1efd0ea4048")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned device. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    'no_cuda': False,
    'gpus': '0'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_losses Ran
ran on a synthesized input
longhoangphi225/MultiSample-Hypernetworks/Jura/trainer.py
code served (permissive licence) · get_code("f745c0a67e824256")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors for pred and label
# pred: model predictions, shape (batch=2, dim=4)
# label: ground truth labels, shape (batch=2, dim=4)
pred = torch.randn(2, 4)
label = torch.randn(2, 4)

ARGS = {
    'pred': pred,
    'label': label,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 3 later) and 7 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
count_parameters 180 other papers
75 dated earlier, 1 the same month, 103 later, 1 same year, order not determinable · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
circle_points 1 other paper
1 later
2402.05955 (2024-02)
A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints
get_device 1 other paper
1 later
2609.01558 (2026-09)
Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks

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

Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to the inherent trade-off between conflicting objectives, PFL offers a flexible approach in many scenarios in which the decision makers can not specify the preference of one Pareto solution over another, and must switch between them depending on the situation. However, existing PFL methods ignore the relationship between the solutions during the optimization process, which hinders the quality of the obtained front. To overcome this issue, we propose a novel PFL framework namely PHN-HVI, which employs a hypernetwork to generate multiple solutions from a set of diverse trade-off preferences and enhance the quality of the Pareto front by maximizing the Hypervolume indicator defined by these solutions. The experimental results on several MOO machine learning tasks show that the proposed framework significantly outperforms the baselines in producing the trade-off Pareto front.

For agents

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

get_harvested_code_for_paper("2212.01130")
get_code_for_paper("2212.01130")
have("2212.01130")

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

curl https://syntology.ai/api/ran/2212.01130.json

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

[![Syntology run record](https://syntology.ai/api/ran/2212.01130.svg)](https://syntology.ai/paper/2212.01130)

Connect an agent — have() is free.