SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.03013 · ICLR · 2024

SemiReward: A General Reward Model for Semi-supervised Learning

Zicheng Liu, Siyuan Li, Stan Li, Cheng Tan, Fang Wu, Zedong Wang, Weiyang Jin

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 1 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/2310.03013.json · badge: /api/ran/2310.03013.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
Westlake-AI/SemiReward canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Rewarder Ran
ran on a synthesized input · constructed an object; no result was computed
Westlake-AI/SemiReward/semilearn/algorithms/semireward/semireward.py
code served (permissive licence) · get_code("f49f78672594e734")
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 an instance of its own class, Rewarder: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# Read the Rewarder.__init__ signature:
# def __init__(self, label_dim, label_embedding_dim, feature_dim=384):

# The forward method expects:
# - features: tensor of shape (batch_size, feature_dim) where feature_dim=384
# - label_indices: tensor of label indices for embedding lookup

# Create small tensors for testing
batch_size = 2
feature_dim = 384
label_embedding_dim = 16
label_dim_value = 10  # number of labels

# Create input tensors
features = torch.randn(batch_size, feature_dim)
label_indices = torch.randint(0, label_dim_value, (batch_size,))

ARGS = {
    "label_dim": label_dim_value,
    "label_embedding_dim": label_embedding_dim,
    "feature_dim": feature_dim,
}
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 Rewarder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Rewarder 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
add_gaussian_noise Ran
ran; our contract draft was wrong, not the code
Westlake-AI/SemiReward/semilearn/algorithms/semireward/semireward.py
code served (permissive licence) · get_code("c416c897b374d349")
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 Tensor, ndim 2, dtype family float, shape (2, 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 a small tensor (batch_size=2, features=4)
tensor = torch.randn(2, 4)

# Define arguments for add_gaussian_noise function
ARGS = {
    "tensor": tensor,
    "mean": 0,
    "std": 1
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
cosine_similarity_n Ran
ran; our contract draft was wrong, not the code
Westlake-AI/SemiReward/semilearn/algorithms/semireward/semireward.py
code served (permissive licence) · get_code("296f0456da95f726")
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 Tensor, ndim 2, dtype family float, shape (2, 1) 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 x and y
# x and y should have the same shape for cosine_similarity
# The function uses dim=-1 and views to (batch_size, 1)
# So we need tensors with shape (batch_size, feature_dim)
x = torch.randn(2, 4)  # batch_size=2, feature_dim=4
y = torch.randn(2, 4)  # batch_size=2, feature_dim=4

ARGS = {
    "x": x,
    "y": y,
}
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 Tensor, ndim 2, dtype family float, shape (2, 1) — shape (2, 1) 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
label_dim Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from Westlake-AI/SemiReward
pointer only · get_code("d7a641a66e8832f8")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

label_dim Not yet run
unverified (harvested, no recorded run)
Westlake-AI/SemiReward/semilearn/algorithms/semireward/semireward.py
code served (permissive licence) · get_code("26c6cc5d552ca423")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
add_gaussian_noise 1 other paper
1 dated earlier
2208.07204 (2022-08)
USB: A Unified Semi-supervised Learning Benchmark for Classification
cosine_similarity_n 1 other paper
1 dated earlier
2208.07204 (2022-08)
USB: A Unified Semi-supervised Learning Benchmark for Classification
label_dim
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2208.07204 (2022-08)
USB: A Unified Semi-supervised Learning Benchmark for Classification

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

Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias. However, existing pseudo-label selection strategies are limited to pre-defined schemes or complex hand-crafted policies specially designed for classification, failing to achieve high-quality labels, fast convergence, and task versatility simultaneously. To these ends, we propose a Semi-supervised Reward framework (SemiReward) that predicts reward scores to evaluate and filter out high-quality pseudo labels, which is pluggable to mainstream SSL methods in wide task types and scenarios. To mitigate confirmation bias, SemiReward is trained online in two stages with a generator model and subsampling strategy. With classification and regression tasks on 13 standard SSL benchmarks across three modalities, extensive experiments verify that SemiReward achieves significant performance gains and faster convergence speeds upon Pseudo Label, FlexMatch, and Free/-SoftMatch. Code and models are available at https://github.com/Westl ake-AI/SemiReward.

For agents

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

get_harvested_code_for_paper("2310.03013")
get_code_for_paper("2310.03013")
have("2310.03013")

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

curl https://syntology.ai/api/ran/2310.03013.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.03013.svg)](https://syntology.ai/paper/2310.03013)

Connect an agent — have() is free.