SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.22124 · NeurIPS · 2024

RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier

Yu Tsao, Szu-Wei Fu, Yen Huang

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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 0 have no contract verdict; 7 failures of our instrument; 0 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/2410.22124.json · badge: /api/ran/2410.22124.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
pm25/semi-supervised-regression canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
FunctionStatusWhere it lives
centering_matrix Ran
ran, honoured the contract we drafted
pm25/semi-supervised-regression/semilearn/algorithms/clss/ulb_rank.py
code served (permissive licence) · get_code("167a4dd06cff26c2")
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 2, dtype family float, shape (5, 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

def centering_matrix(n):
    return np.eye(n) - np.ones((n, n)) / n

# The function takes a single parameter 'n' which should be an integer
# representing the size of the matrix to create
ARGS = {
    "n": 5
}
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 2, dtype family float, shape (5, 5) — shape (5, 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
euclidean_dist Ran
ran; our contract draft was wrong, not the code
pm25/semi-supervised-regression/semilearn/algorithms/clss/ordinal_entropy.py
code served (permissive licence) · get_code("0c3edba26968ef75")
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 2, dtype family float, shape (2, 3) 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

torch.manual_seed(0)

# Create two small tensors for testing
# x: (m, d) where m=2, d=4
x = torch.randn(2, 4)

# y: (n, d) where n=3, d=4
y = torch.randn(3, 4)

ARGS = {
    "x": x,
    "y": y,
}
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 2, dtype family float, shape (2, 3) — shape (2, 3) 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
flatten_upper_triangular Ran
ran, honoured the contract we drafted
pm25/semi-supervised-regression/semilearn/algorithms/clss/ordinal_entropy.py
code served (permissive licence) · get_code("070e3cdb56d0acc7")
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 (6,) 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

torch.manual_seed(0)

# Create a small square matrix for testing
x = torch.randn(4, 4)

ARGS = {
    "x": x
}
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 (6,) — shape (6,) 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
load_checkpoint Ran
ran; our contract draft was wrong, not the code
pm25/semi-supervised-regression/semilearn/nets/utils.py
code served (permissive licence) · get_code("3025f4d1699034a5")
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 MinimalViT. 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 torch
import torch.nn as nn
from unittest.mock import MagicMock, patch
import tempfile
import os

torch.manual_seed(0)

# Create a minimal model with pos_embed attribute
class MinimalViT(nn.Module):
    def __init__(self):
        super().__init__()
        # pos_embed shape: (1, num_tokens, embed_dim)
        # num_tokens = 1 (class token) + 16 (4x4 grid) = 17
        self.pos_embed = nn.Parameter(torch.randn(1, 17, 8))
        self.layer1 = nn.Linear(8, 8)
    
    def forward(self, x):
        return self.layer1(x)

# Create a model instance
model = MinimalViT()

# Create a checkpoint dict with pos_embed that needs resizing
# New model will have different grid size, so pos_embed needs interpolation
checkpoint_dict = {
    'model': {
        'pos_embed': torch.randn(1, 10, 8),  # 1 (class token) + 9 (3x3 grid) = 10 tokens
        'layer1.weight': torch.randn(8, 8),
        'layer1.bias': torch.randn(8),
        'fc.weight': torch.randn(5, 8),  # This should be skipped
        'classifier.bias': torch.randn(5),  # This should be skipped
    }
}

# Create a temporary checkpoint file
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pt') as f:
    torch.save(checkpoint_dict, f)
    checkpoint_path = f.name

try:
    ARGS = {
        'model': model,
        'checkpoint_path': checkpoint_path,
    }
finally:
    # Clean up will happen after ARGS is used
    pass
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 MinimalViT — a MinimalViT output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MinimalViT 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
ordinal_entropy Ran
ran; our contract draft was wrong, not the code
pm25/semi-supervised-regression/semilearn/algorithms/clss/ordinal_entropy.py
code served (permissive licence) · get_code("d87487eb1290e628")
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 0, dtype family float, 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.functional as F

torch.manual_seed(0)

# Create sample features and targets
# features: shape (batch_size, feat_dim) = (2, 4)
# targets: shape (batch_size,) = (2,)
features = torch.randn(2, 4)
targets = torch.tensor([0, 1])

ARGS = {
    "features": features,
    "targets": targets,
}
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 0, dtype family float, 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
param_groups_weight_decay Ran
ran; our contract draft was wrong, not the code
pm25/semi-supervised-regression/semilearn/nets/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from yewen1486/emtal, is pointer only (licence: NONE) · get_code("88f4962784e09b88")
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 yewen1486/emtal, 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.

rank Ran
ran; our contract draft was wrong, not the code
pm25/semi-supervised-regression/semilearn/algorithms/clss/ulb_rank.py
pointer only (licence: MIT); the stored copy get_code serves, from BorealisAI/ranksim-imbalanced-regression, is pointer only (licence: NOASSERTION) · get_code("2e1e2e8c543195f7")
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 BorealisAI/ranksim-imbalanced-regression, and GitHub could not classify the licence of that repository (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.

rank_normalised Ran
ran; our contract draft was wrong, not the code
pm25/semi-supervised-regression/semilearn/algorithms/clss/ulb_rank.py
pointer only (licence: MIT); the stored copy get_code serves, from BorealisAI/ranksim-imbalanced-regression, is pointer only (licence: NOASSERTION) · get_code("ed49cae4f66fd45c")
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 BorealisAI/ranksim-imbalanced-regression, and GitHub could not classify the licence of that repository (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.

resize_pos_embed_vit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pm25/semi-supervised-regression/semilearn/nets/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from aah94/JEPAMatch, is pointer only (licence: NOASSERTION) · get_code("4c0668013863ad3f")
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 aah94/JEPAMatch, and GitHub could not classify the licence of that repository (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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 4 later) and 4 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
param_groups_weight_decay 15 other papers
12 dated earlier, 3 later
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
2304.14065 (2023-04)
Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
2305.13002 (2023-05)
Rethinking Semi-supervised Learning with Language Models
and 12 more not named here
resize_pos_embed_vit 6 other papers
5 dated earlier, 1 later
2305.13002 (2023-05)
Rethinking Semi-supervised Learning with Language Models
2306.04621 (2023-06)
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
2310.18910 (2023-10)
InstanT: Semi-supervised Learning with Instance-dependent Thresholds
and 3 more not named here
rank 4 other papers
3 dated earlier, 1 later
2003.11657 (2020-03)
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
2110.01445 (2021-10)
Robust and Decomposable Average Precision for Image Retrieval
2205.15236 (2022-05)
RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression
and 1 more not named here
rank_normalised 4 other papers
3 dated earlier, 1 later
2003.11657 (2020-03)
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
2110.01445 (2021-10)
Robust and Decomposable Average Precision for Image Retrieval
2205.15236 (2022-05)
RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression
and 1 more not named here
euclidean_dist 1 other paper
1 dated earlier
aaai_19970 (2022 (year only))
SECRET: Self-Consistent Pseudo Label Refinement for Unsupervised Domain Adaptive Person Re-identification

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

State-of-the-art (SOTA) semi-supervised learning techniques, such as FixMatch and it's variants, have demonstrated impressive performance in classification tasks. However, these methods are not directly applicable to regression tasks. In this paper, we present RankUp, a simple yet effective approach that adapts existing semisupervised classification techniques to enhance the performance of regression tasks. RankUp achieves this by converting the original regression task into a ranking problem and training it concurrently with the original regression objective. This auxiliary ranking classifier outputs a classification result, thus enabling integration with existing semi-supervised classification methods. Moreover, we introduce regression distribution alignment (RDA), a complementary technique that further enhances RankUp's performance by refining pseudo-labels through distribution alignment. Despite its simplicity, RankUp, with or without RDA, achieves SOTA results in across a range of regression benchmarks, including computer vision, audio, and natural language processing tasks. Our code and log data are opensourced at https://github.com/pm25/semi-supervised-regression. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).

For agents

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

get_harvested_code_for_paper("2410.22124")
get_code_for_paper("2410.22124")
have("2410.22124")

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

curl https://syntology.ai/api/ran/2410.22124.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.22124.svg)](https://syntology.ai/paper/2410.22124)

Connect an agent — have() is free.