SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.09424 · 2023

SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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 9 have no contract verdict; 1 failure 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/2306.09424.json · badge: /api/ran/2306.09424.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
zhu-xlab/ssl4eo-s12 canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhu-xlab/ssl4eo-s12/src/benchmark/pretrain_ssl/pretrain_moco_v2_s2c.py
code served (permissive licence) · get_code("131a82fd65128218")
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 list, ndim 2, dtype family float; 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 torch

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
num_classes = 4

# output: logits/scores tensor of shape (batch_size, num_classes)
output = torch.randn(batch_size, num_classes)

# target: class indices tensor of shape (batch_size,)
target = torch.tensor([1, 3])

# topk: tuple of k values to compute accuracy for
topk = (1, 2)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk,
}
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 list, ndim 2, dtype family float — a list 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
date2str Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/download_data/ssl4eo_s12_downloader.py
code served (permissive licence) · get_code("b3bd317a63c0e5a9")
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 str. 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.

from datetime import datetime, timedelta, date

ARGS = {
    "date": date(2024, 1, 15)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
date2str Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/download_data/ssl4eo_downloader.py
code served (permissive licence) · get_code("6956cf22c99cfa9d")
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 str. 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.

from datetime import datetime

ARGS = {
    "date": datetime(2024, 1, 15)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_period Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/download_data/ssl4eo_s12_downloader.py
code served (permissive licence) · get_code("98e89406336bcd07")
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 1, dtype family float; 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.

from datetime import datetime, timedelta, date

# Construct a valid date object
test_date = date(2024, 1, 15)

# Define ARGS dict mapping all parameters of get_period
ARGS = {
    'date': test_date,
    'days': 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — 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
get_period Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/download_data/ssl4eo_downloader.py
code served (permissive licence) · get_code("b9a9229f92b6dedb")
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 1, dtype family float; 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.

from datetime import datetime, timedelta

ARGS = {
    "date": datetime(2024, 6, 15, 12, 30, 45),
    "days": 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — 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
maskS2clouds Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/download_data/ssl4eo_s12_downloader.py
code served (permissive licence) · get_code("08537317d4bdd531")
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 MockEEImage. 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 numpy as np

# Mock the Earth Engine ee module since this function uses EE methods
class MockEEImage:
    def __init__(self):
        self.bands = {
            'QA60': MockEEImage.MockBand()
        }
    
    def select(self, band_name):
        """Returns a band selected from the image"""
        return self.bands[band_name]
    
    def updateMask(self, mask):
        """Updates the image with a mask"""
        return self
    
    class MockBand:
        def bitwiseAnd(self, bitmask):
            """Performs bitwise AND operation"""
            return MockEEImage.MockMaskedBand(bitmask)
        
    class MockMaskedBand:
        def __init__(self, bitmask):
            self.bitmask = bitmask
        
        def eq(self, value):
            """Checks equality"""
            return MockEEImage.MockMask(self.bitmask, value)
        
    class MockMask:
        def __init__(self, bitmask, value):
            self.bitmask = bitmask
            self.value = value
        
        def bitwiseAnd(self, other_bitmask):
            """Performs bitwise AND with another mask"""
            return MockEEImage.MockMaskedBand(other_bitmask)
        
        def eq(self, value):
            """Checks equality"""
            return self

# Create a mock image object that has the required methods
image = MockEEImage()

ARGS = {
    'image': image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockEEImage — a MockEEImage output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockEEImage 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
normalize Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/benchmark/pretrain_ssl/datasets/SSL4EO/ssl4eo_dataset.py
code served (permissive licence) · get_code("15c4c0f9b256fee4")
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 int, shape (4, 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 numpy as np

# Create sample image data as a numpy array
img = np.random.rand(4, 3) * 100  # Small 4x3 image with values in range [0, 100]

# Define normalization parameters
mean = 50.0
std = 10.0

ARGS = {
    "img": img,
    "mean": mean,
    "std": std,
}
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 int, shape (4, 3) — shape (4, 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
random_subset Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/benchmark/pretrain_ssl/datasets/SSL4EO/ssl4eo_dataset.py
code served (permissive licence) · get_code("d88646daaeb020ef")
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 Subset. 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
import torch
from torch.utils.data import Dataset, DataLoader

torch.manual_seed(0)

# Create a minimal dataset class that implements __len__ and __getitem__
class MinimalDataset(Dataset):
    def __init__(self, size=10):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return torch.randn(4)

# Create instances for the arguments
dataset = MinimalDataset(size=10)
frac = 0.5
seed = 42

ARGS = {
    "dataset": dataset,
    "frac": frac,
    "seed": seed
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Subset — a Subset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Subset output the recorded ndim 2 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
train Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/benchmark/pretrain_ssl/pretrain_moco_v2_s2c.py
code served (permissive licence) · get_code("22e63e9ba09c6b88")
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 1, dtype family float; no output shape is stated. 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 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 torch
import torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Create a minimal model that matches the expected interface
class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 10)
    
    def forward(self, im_q, im_k):
        # im_q and im_k are the two image inputs
        # Return output (logits) and target (labels)
        output = self.linear(im_q)
        target = torch.randint(0, 10, (im_q.size(0),))
        return output, target

# Create a minimal criterion (loss function)
criterion = nn.CrossEntropyLoss()

# Create a mock args object with required attributes
class Args:
    def __init__(self):
        self.gpu = None  # CPU only
        self.print_freq = 2
        self.rank = 0

args = Args()

# Create train_loader - list of batches where each batch is [images_q, images_k]
# Batch size 2, feature dim 4
train_loader = [
    [torch.randn(2, 4), torch.randn(2, 4)] for _ in range(4)
]

# Create model and optimizer
model = MockModel()
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Create epoch number
epoch = 0

ARGS = {
    'train_loader': train_loader,
    'model': model,
    'criterion': criterion,
    'optimizer': optimizer,
    'epoch': epoch,
    'args': args
}
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 tuple, ndim 1, dtype family float — 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
train Ran
ran on a synthesized input
zhu-xlab/ssl4eo-s12/src/benchmark/pretrain_ssl/pretrain_moco_v2_seco_ms.py
code served (permissive licence) · get_code("d65aefdf2f95c196")
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 1, dtype family float; no output shape is stated. 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 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 torch
import torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Build a minimal model that accepts im_q and im_k and returns output, target
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 8)
    
    def forward(self, im_q, im_k):
        # im_q and im_k are both [batch_size, 4]
        # Return logits and target labels
        output = self.fc(im_q)  # [batch_size, 8]
        target = torch.randint(0, 8, (im_q.size(0),))  # [batch_size]
        return output, target

# Build a minimal criterion (cross entropy loss)
criterion = nn.CrossEntropyLoss()

# Build model and optimizer
model = SimpleModel()
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Build train_loader: list of batches, each batch is [images_q, images_k]
# where images_q and images_k are tensors of shape [batch_size, 4]
train_loader = [
    [torch.randn(2, 4), torch.randn(2, 4)] for _ in range(3)
]

# Build args object with required attributes
class Args:
    def __init__(self):
        self.gpu = None  # CPU only
        self.print_freq = 1
        self.rank = 0

args = Args()

# Define ARGS dict
ARGS = {
    'train_loader': train_loader,
    'model': model,
    'criterion': criterion,
    'optimizer': optimizer,
    'epoch': 1,
    'args': args
}
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 tuple, ndim 1, dtype family float — 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
get_model Not yet run
unverified (harvested, no recorded run)
zhu-xlab/ssl4eo-s12/src/benchmark/pretrain_ssl/pretrain_data2vec.py
code served (permissive licence) · get_code("42c054802a568e6b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 1 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
accuracy 116 other papers
75 dated earlier, 2 the same month, 37 later, 2 same year, order not determinable · 8 only as an assembly brick
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1610.05820 (2016-10)
Membership Inference Attacks Against Machine Learning Models
1905.03696 (2019-05)
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
and 113 more not named here
normalize 1 other paper
1 dated earlier
2103.16607 (2021-03)
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data

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

The Landsat program is the longest-running Earth observation program in history, with 50+ years of data acquisition by 8 satellites. The multispectral imagery captured by sensors onboard these satellites is critical for a wide range of scientific fields. Despite the increasing popularity of deep learning and remote sensing, the majority of researchers still use decision trees and random forests for Landsat image analysis due to the prevalence of small labeled datasets and lack of foundation models. In this paper, we introduce SSL4EO-L, the first ever dataset designed for Self-Supervised Learning for Earth Observation for the Landsat family of satellites (including 3 sensors and 2 product levels) and the largest Landsat dataset in history (5M image patches). Additionally, we modernize and re-release the L7 Irish and L8 Biome cloud detection datasets, and introduce the first ML benchmark datasets for Landsats 4-5 TM and Landsat 7 ETM+ SR. Finally, we pre-train the first foundation models for Landsat imagery using SSL4EO-L and evaluate their performance on multiple semantic segmentation tasks. All datasets and model weights are available via the TorchGeo (https://github.com/microsoft/torchgeo) library, making reproducibility and experimentation easy, and enabling scientific advancements in the burgeoning field of remote sensing for a multitude of downstream applications.

For agents

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

get_harvested_code_for_paper("2306.09424")
get_code_for_paper("2306.09424")
have("2306.09424")

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

curl https://syntology.ai/api/ran/2306.09424.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.09424.svg)](https://syntology.ai/paper/2306.09424)

Connect an agent — have() is free.