SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.01951 · 2026

Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network

Hakan Bilen, Yifu Qiu, Shuyang Wu, Ines Nearchou, Sandrine Prost, Jonathan Fallowfield, Timothy Kendall

arXiv · PDF · Open in the Atlas

Code that ran

63 of 76 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 8 honoured the contract we drafted, 4 violated it and 5 have no contract verdict; 46 failures of our instrument; 13 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/2602.01951.json · badge: /api/ran/2602.01951.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
mahmoodlab/HIPT canonical (classifier label)
classifier basis: census
10 ran · 6 no recorded run
mahmoodlab/UNI canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
CraigMyles/SurGen-Dataset canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
BearCleverProud/HAG-MIL canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
szc19990412/TransMIL canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
mahmoodlab/CONCH canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
olgarithmics/ICLR_CAMIL canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
mahmoodlab/CLAM canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
lin-lcx/H2-MIL canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
AMLab-Amsterdam/AttentionDeepMIL community
Papers with Code archive
1 ran · 0 no recorded run
hrlblab/CS-MIL community
Papers with Code archive
1 ran · 0 no recorded run
binli123/dsmil-wsi community
Papers with Code archive
1 ran · 0 no recorded run
franblueee/smmil community
Papers with Code archive
0 ran · 1 no recorded run
mahmoodlab/Patch-GCN community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Attention Ran
ran on a synthesized input
AMLab-Amsterdam/AttentionDeepMIL/model.py
code served (permissive licence) · get_code("d4242c60b1f75593")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) 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 torch
import torch.nn as nn
import torch.nn.functional as F

class Attention(nn.Module):

    def __init__(self):
        super(Attention, self).__init__()
        self.M = 500
        self.L = 128
        self.ATTENTION_BRANCHES = 1
        self.feature_extractor_part1 = nn.Sequential(nn.Conv2d(1, 20, kernel_size=5), nn.ReLU(), nn.MaxPool2d(2, stride=2), nn.Conv2d(20, 50, kernel_size=5), nn.ReLU(), nn.MaxPool2d(2, stride=2))
        self.feature_extractor_part2 = nn.Sequential(nn.Linear(50 * 4 * 4, self.M), nn.ReLU())
        self.attention = nn.Sequential(nn.Linear(self.M, self.L), nn.Tanh(), nn.Linear(self.L, self.ATTENTION_BRANCHES))
        self.classifier = nn.Sequential(nn.Linear(self.M * self.ATTENTION_BRANCHES, 1), nn.Sigmoid())

    def forward(self, x):
        x = x.squeeze(0)
        H = self.feature_extractor_part1(x)
        H = H.view(-1, 50 * 4 * 4)
        H = self.feature_extractor_part2(H)
        A = self.attention(H)
        A = torch.transpose(A, 1, 0)
        A = F.softmax(A, dim=1)
        Z = torch.mm(A, H)
        Y_prob = self.classifier(Z)
        Y_hat = torch.ge(Y_prob, 0.5).float()
        return (Y_prob, Y_hat, A)

    def calculate_classification_error(self, X, Y):
        Y = Y.float()
        _, Y_hat, _ = self.forward(X)
        error = 1.0 - Y_hat.eq(Y).cpu().float().mean().data.item()
        return (error, Y_hat)

    def calculate_objective(self, X, Y):
        Y = Y.float()
        Y_prob, _, A = self.forward(X)
        Y_prob = torch.clamp(Y_prob, min=1e-05, max=1.0 - 1e-05)
        neg_log_likelihood = -1.0 * (Y * torch.log(Y_prob) + (1.0 - Y) * torch.log(1.0 - Y_prob))
        return (neg_log_likelihood, A)


INIT_ARGS = {}

ARGS = {
    'X': torch.randn(1, 1, 28, 28),
    'Y': torch.tensor([[1.0]])
}

METHOD = 'calculate_objective'

if __name__ == '__main__':
    model = Attention(**INIT_ARGS)
    result = getattr(model, METHOD)(**ARGS)
    print("Result:", result)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Attention Ran
ran on a synthesized input · constructed an object; no result was computed
hrlblab/CS-MIL/Train_Test_Code/model3.py
code served (permissive licence) · get_code("54abaec4cabb8d79")
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, Attention: 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)

# The Attention class has no __init__ parameters, so ARGS is empty
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 Attention — 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 Attention 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
MILNet Ran
ran on a synthesized input · constructed an object; no result was computed
binli123/dsmil-wsi/dsmil.py
code served (permissive licence) · get_code("de1b4199048bbf4e")
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, MILNet: 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)

# Build i_classifier: takes x, returns (feats, classes)
class IClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 8)
        self.linear2 = nn.Linear(8, 5)
    
    def forward(self, x):
        # x shape: (batch, 4)
        # Return feats (batch, 8) and classes (batch, 5)
        feats = self.linear1(x)
        classes = self.linear2(feats)
        return feats, classes

# Build b_classifier: takes (feats, classes), returns (prediction_bag, A, B)
class BClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(8, 1)
    
    def forward(self, feats, classes):
        # feats shape: (batch, 8)
        # classes shape: (batch, 5)
        # Return prediction_bag (batch, 1), A (batch, batch), B (batch, batch)
        prediction_bag = self.linear(feats)
        batch_size = feats.shape[0]
        A = torch.randn(batch_size, batch_size)
        B = torch.randn(batch_size, batch_size)
        return prediction_bag, A, B

i_classifier = IClassifier()
b_classifier = BClassifier()

ARGS = {
    'i_classifier': i_classifier,
    'b_classifier': b_classifier
}
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 MILNet — 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 MILNet 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
aggregate_array Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mahmoodlab/CONCH/conch/downstream/utils.py
pointer only (licence: NOASSERTION) · get_code("b76f341d8d32dc9d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/CONCH (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.

bag_dataset Ran
ran; our contract draft was wrong, not the code
olgarithmics/ICLR_CAMIL/feature_extractor/compute_feats.py
pointer only (licence: NONE) · get_code("9676ecbef4203d64")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, olgarithmics/ICLR_CAMIL 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.

collate_MIL Ran
ran; our contract draft was wrong, not the code
BearCleverProud/HAG-MIL/utils.py
pointer only (licence: NONE) · get_code("d046835fc5ae244a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, BearCleverProud/HAG-MIL 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.

collate_features Ran
ran; our contract draft was wrong, not the code
BearCleverProud/HAG-MIL/utils.py
pointer only (licence: NONE) · get_code("ca6cc1908af21a64")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, BearCleverProud/HAG-MIL 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.

compute_edts_forPenalizedLoss Ran
ran, honoured the contract we drafted
szc19990412/TransMIL/MyLoss/ND_Crossentropy.py
pointer only (licence: NONE) · get_code("3827e58ea2156657")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, szc19990412/TransMIL 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.

concat_images Ran
ran, honoured the contract we drafted
mahmoodlab/UNI/uni/downstream/utils.py
pointer only (licence: NOASSERTION) · get_code("920414c82af2eb8b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

concat_scores4k Ran
ran; our contract draft was wrong, not the code
mahmoodlab/HIPT/HIPT_4K/hipt_heatmap_utils.py
pointer only (licence: NOASSERTION) · get_code("e586a895c91f9196")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/HIPT (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.

config_imname Ran
ran; our contract draft was wrong, not the code
mahmoodlab/HIPT/1-Hierarchical-Pretraining/eval_image_retrieval.py
pointer only (licence: NOASSERTION) · get_code("49cf1f4ce52e9613")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/HIPT (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.

config_qimname Ran
ran; our contract draft was wrong, not the code
mahmoodlab/HIPT/1-Hierarchical-Pretraining/eval_image_retrieval.py
pointer only (licence: NOASSERTION) · get_code("91c5ae2396603107")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/HIPT (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.

config_train_step Ran
ran; our contract draft was wrong, not the code
CraigMyles/SurGen-Dataset/reproducibility/transformer_main_multiclass.py
pointer only (licence: GPL-3.0) · get_code("d55b2ef17c915703")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, CraigMyles/SurGen-Dataset, is not in the permissive set Syntology serves inline. 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.

drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mahmoodlab/HIPT/HIPT_4K/vision_transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("55120f2026b56aa2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mahmoodlab/HIPT 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.

euclidean_dist Ran
ran; our contract draft was wrong, not the code
lin-lcx/H2-MIL/code/IHPool.py
pointer only (licence: NONE) · get_code("261a67397af29d5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lin-lcx/H2-MIL 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.

eval_knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mahmoodlab/UNI/uni/downstream/eval_patch_features/fewshot.py
pointer only (licence: NOASSERTION) · get_code("faa2f85b94fa91a5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

eval_metric Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
olgarithmics/ICLR_CAMIL/models/metrics.py
pointer only (licence: NONE) · get_code("6d0f65012732e719")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, olgarithmics/ICLR_CAMIL 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.

eval_transforms Ran
ran; our contract draft was wrong, not the code
CraigMyles/SurGen-Dataset/reproducibility/datasets/dataset_h5.py
pointer only (licence: GPL-3.0) · get_code("cc2cb0baf0de0b6d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, CraigMyles/SurGen-Dataset, is not in the permissive set Syntology serves inline. 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.

extract_patch_features_from_dataloader Ran
ran; our contract draft was wrong, not the code
mahmoodlab/UNI/uni/downstream/extract_patch_features.py
pointer only (licence: NOASSERTION) · get_code("5da51e85b6f85369")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

flatten Ran
ran; our contract draft was wrong, not the code
szc19990412/TransMIL/MyLoss/ND_Crossentropy.py
pointer only (licence: NONE) · get_code("308002c4fb135bbe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, szc19990412/TransMIL 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.

freeze_batch_norm_2d Ran
ran; our contract draft was wrong, not the code
mahmoodlab/CONCH/conch/open_clip_custom/utils.py
pointer only (licence: NOASSERTION) · get_code("9b5765523c6d17fd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/CONCH (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.

generate_surroundings Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
BearCleverProud/HAG-MIL/create_quadtree_wsis.py
pointer only (licence: NONE) · get_code("7614b58635bac91a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, BearCleverProud/HAG-MIL 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.

get_best_level_for_downsample Ran
ran, honoured the contract we drafted
CraigMyles/SurGen-Dataset/reproducibility/wsi_core/WholeSlideImage.py
pointer only (licence: GPL-3.0) · get_code("d15ed64b57312a3c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, CraigMyles/SurGen-Dataset, is not in the permissive set Syntology serves inline. 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.

get_encoder Ran
ran; our contract draft was wrong, not the code
mahmoodlab/UNI/uni/get_encoder/get_encoder.py
pointer only (licence: NOASSERTION) · get_code("a07e1b2d1139417d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

get_eval_metrics Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mahmoodlab/UNI/uni/downstream/eval_patch_features/metrics.py
pointer only (licence: NOASSERTION) · get_code("90b3a2884e9ef8b4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

get_eval_transforms Ran
ran; our contract draft was wrong, not the code
mahmoodlab/UNI/uni/get_encoder/get_encoder.py
pointer only (licence: NOASSERTION) · get_code("8c69a97fedddfc84")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

get_norm_constants Ran
ran, honoured the contract we drafted
mahmoodlab/UNI/uni/get_encoder/get_encoder.py
pointer only (licence: NOASSERTION) · get_code("3167522c249c7c89")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

get_scores256 Ran
ran; our contract draft was wrong, not the code
mahmoodlab/HIPT/HIPT_4K/hipt_heatmap_utils.py
pointer only (licence: NOASSERTION) · get_code("2b68cf8db190bd17")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/HIPT (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.

get_simple_loader Ran
ran on a synthesized input
BearCleverProud/HAG-MIL/utils.py
pointer only (licence: NONE) · get_code("9c335517b3199bc1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, BearCleverProud/HAG-MIL 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.

get_tp_fp_fn Ran
ran; our contract draft was wrong, not the code
szc19990412/TransMIL/MyLoss/boundary_loss.py
pointer only (licence: NONE) · get_code("b9f4ad3e03ad4503")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, szc19990412/TransMIL 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.

get_tp_fp_fn Ran
ran; our contract draft was wrong, not the code
szc19990412/TransMIL/MyLoss/dice_loss.py
pointer only (licence: NONE) · get_code("2457db2dce538ac0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, szc19990412/TransMIL 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.

infer_folder_structure Ran
ran, honoured the contract we drafted
mahmoodlab/CONCH/conch/downstream/wsi_datasets.py
pointer only (licence: NOASSERTION) · get_code("a93fc96526f7c7f7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/CONCH (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.

initialize_df Ran
ran; our contract draft was wrong, not the code
BearCleverProud/HAG-MIL/wsi_core/batch_process_utils.py
pointer only (licence: NONE) · get_code("2294c69b1f977ee2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, BearCleverProud/HAG-MIL 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.

isBlackPatch Ran
ran, violated the contract we drafted
BearCleverProud/HAG-MIL/wsi_core/wsi_utils.py
pointer only (licence: NONE) · get_code("da36c66c0dc9829f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, BearCleverProud/HAG-MIL 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.

isBlackPatch_S Ran
ran; our contract draft was wrong, not the code
BearCleverProud/HAG-MIL/wsi_core/wsi_utils.py
pointer only (licence: NONE) · get_code("9aaa29e4bf4b5c1f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, BearCleverProud/HAG-MIL 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.

isWhitePatch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
BearCleverProud/HAG-MIL/wsi_core/wsi_utils.py
pointer only (licence: NONE) · get_code("f8ae8348aecd8800")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, BearCleverProud/HAG-MIL 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.

is_image_file Ran
ran, violated the contract we drafted
mahmoodlab/HIPT/1-Hierarchical-Pretraining/eval_copy_detection.py
pointer only (licence: NOASSERTION) · get_code("dfebfd56865b6379")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/HIPT (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.

load_params Ran
ran; our contract draft was wrong, not the code
mahmoodlab/CLAM/create_heatmaps.py
pointer only (licence: GPL-3.0) · get_code("0e0d4a1ac74c2632")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mahmoodlab/CLAM, is not in the permissive set Syntology serves inline. 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.

lovasz_grad Ran
ran, violated the contract we drafted
szc19990412/TransMIL/MyLoss/lovasz_loss.py
pointer only (licence: NONE) · get_code("e85b5d21dc5b8382")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, szc19990412/TransMIL 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.

merge_dict Ran
ran; our contract draft was wrong, not the code
mahmoodlab/CONCH/conch/downstream/utils.py
pointer only (licence: NOASSERTION) · get_code("53108a9e6f4eb2c0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/CONCH (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.

nll_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
szc19990412/TransMIL/MyLoss/ND_Crossentropy.py
pointer only (licence: NONE) · get_code("2f6a7a4faec6cb11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, szc19990412/TransMIL 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.

norm_mask Ran
ran; our contract draft was wrong, not the code
mahmoodlab/HIPT/1-Hierarchical-Pretraining/eval_video_segmentation.py
pointer only (licence: NOASSERTION) · get_code("e015f2c93c762aff")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/HIPT (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.

normalise Ran
ran, honoured the contract we drafted
CraigMyles/SurGen-Dataset/reproducibility/wsi_core/WholeSlideImage.py
pointer only (licence: GPL-3.0) · get_code("3a334b495845600c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, CraigMyles/SurGen-Dataset, is not in the permissive set Syntology serves inline. 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.

optimal_thresh Ran
ran, violated the contract we drafted
olgarithmics/ICLR_CAMIL/models/metrics.py
pointer only (licence: NONE) · get_code("125ef8019f9275cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, olgarithmics/ICLR_CAMIL 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.

parse_config_dict Ran
ran; our contract draft was wrong, not the code
mahmoodlab/CLAM/create_heatmaps.py
pointer only (licence: GPL-3.0) · get_code("450847a8f5821550")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mahmoodlab/CLAM, is not in the permissive set Syntology serves inline. 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.

patching Ran
ran; our contract draft was wrong, not the code
CraigMyles/SurGen-Dataset/reproducibility/create_patches.py
pointer only (licence: GPL-3.0) · get_code("6ca1f4cd53ffd7e6")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, CraigMyles/SurGen-Dataset, is not in the permissive set Syntology serves inline. 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.

patching Ran
ran; our contract draft was wrong, not the code
mahmoodlab/CLAM/create_patches.py
pointer only (licence: GPL-3.0) · get_code("1f0265b494709bf9")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mahmoodlab/CLAM, is not in the permissive set Syntology serves inline. 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.

prototype_topk_vote Ran
ran on a synthesized input
mahmoodlab/UNI/uni/downstream/eval_patch_features/protonet.py
pointer only (licence: NOASSERTION) · get_code("04b5b0b3851a614a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

read_state_dict Ran
ran; our contract draft was wrong, not the code
mahmoodlab/CONCH/conch/open_clip_custom/factory.py
pointer only (licence: NOASSERTION) · get_code("18fe2d6550294742")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/CONCH (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.

resnet50_baseline Ran
ran; our contract draft was wrong, not the code
CraigMyles/SurGen-Dataset/reproducibility/models/resnet_custom.py
pointer only (licence: GPL-3.0) · get_code("2fca12b132f7c766")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, CraigMyles/SurGen-Dataset, is not in the permissive set Syntology serves inline. 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.

roc_threshold Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
olgarithmics/ICLR_CAMIL/models/metrics.py
pointer only (licence: NONE) · get_code("0671088a6441acba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, olgarithmics/ICLR_CAMIL 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.

roll_batch2img Ran
ran; our contract draft was wrong, not the code
mahmoodlab/HIPT/HIPT_4K/hipt_model_utils.py
pointer only (licence: NOASSERTION) · get_code("5295ea6e56f2c0a3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/HIPT (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.

save_hdf5 Ran
ran; our contract draft was wrong, not the code
olgarithmics/ICLR_CAMIL/feature_extractor/compute_feats.py
pointer only (licence: NONE) · get_code("c6bbc9c9564d7227")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, olgarithmics/ICLR_CAMIL 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.

scale_img Ran
ran; our contract draft was wrong, not the code
mahmoodlab/UNI/uni/downstream/utils.py
pointer only (licence: NOASSERTION) · get_code("51b8e7e23437e7e1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/UNI (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.

score_ap_from_ranks_1 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mahmoodlab/HIPT/1-Hierarchical-Pretraining/eval_copy_detection.py
pointer only (licence: NOASSERTION) · get_code("5f21619ff716c1ce")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, mahmoodlab/HIPT (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.

segment Ran
ran; our contract draft was wrong, not the code
mahmoodlab/CLAM/create_patches.py
pointer only (licence: GPL-3.0) · get_code("a63b7288bd08c89e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mahmoodlab/CLAM, is not in the permissive set Syntology serves inline. 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.

segment Ran
ran; our contract draft was wrong, not the code
CraigMyles/SurGen-Dataset/reproducibility/create_patches.py
pointer only (licence: GPL-3.0) · get_code("2d44fb6699a9a708")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, CraigMyles/SurGen-Dataset, is not in the permissive set Syntology serves inline. 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.

series Ran
ran, honoured the contract we drafted
CraigMyles/SurGen-Dataset/reproducibility/datasets/dataset_h5.py
pointer only (licence: GPL-3.0) · get_code("9f5f710bfda43d78")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, CraigMyles/SurGen-Dataset, is not in the permissive set Syntology serves inline. 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.

softmax_helper Ran
ran; our contract draft was wrong, not the code
szc19990412/TransMIL/MyLoss/boundary_loss.py
pointer only (licence: NONE) · get_code("c66339fca70da624")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, szc19990412/TransMIL 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.

sum_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
szc19990412/TransMIL/MyLoss/boundary_loss.py
pointer only (licence: NONE) · get_code("9e4e02bee8e90bea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, szc19990412/TransMIL 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.

Showing the first 60. An agent gets every one from get_harvested_code_for_paper("2602.01951").

Also present in other papers' code

Of 76 samples lifted from this paper's linked repositories, 76 carry a function identity and 0 do not. Of the 75 distinct functions with an identity, 30 are also present in other papers whose code we hold (30 with at least one paper dated earlier, 2 the same month, 4 later) and 45 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
drop_path 224 other papers
219 dated earlier, 4 later, 1 undated · 38 only as an assembly brick
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
and 221 more not named here
trunc_normal_ 160 other papers
154 dated earlier, 3 the same month, 3 later · 36 only as an assembly brick
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2007.12911 (2020-07)
Tighter risk certificates for neural networks
and 157 more not named here
lovasz_grad 40 other papers
38 dated earlier, 2 the same month · 1 only as an assembly brick
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
and 37 more not named here
vit_tiny 33 other papers
32 dated earlier, 1 undated
2201.02609 (2022-01)
Generalized Category Discovery
2202.11929 (2022-02)
Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring
2203.08414 (2022-03)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
and 30 more not named here
freeze_batch_norm_2d 16 other papers
14 dated earlier, 2 later · 3 only as an assembly brick
2102.05918 (2021-02)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
2303.07240 (2023-03)
PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
2305.10415 (2023-05)
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
and 13 more not named here
config_imname 4 other papers
4 dated earlier
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
and 1 more not named here
config_qimname 4 other papers
4 dated earlier
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
and 1 more not named here
knn_classifier 4 other papers
4 dated earlier
2104.14294 (2021-04)
Emerging Properties in Self-Supervised Vision Transformers
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
and 1 more not named here
load_pretrained_weights 4 other papers
3 dated earlier, 1 later
2309.07400 (2023-09)
HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis
2407.06508 (2024-07)
A Clinical Benchmark of Public Self-Supervised Pathology Foundation Models
2407.15362 (2024-07)
A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model
and 1 more not named here
norm_mask 3 other papers
3 dated earlier
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
2306.03881 (2023-06)
Emergent Correspondence from Image Diffusion
patching 3 other papers
3 dated earlier
2311.07125 (2023-11)
Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification
2404.13222 (2024-04)
Vim4Path: Self-Supervised Vision Mamba for Histopathology Images
2406.15303 (2024-06)
AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classification
resnet50_baseline 3 other papers
3 dated earlier
2309.07400 (2023-09)
HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis
2407.06508 (2024-07)
A Clinical Benchmark of Public Self-Supervised Pathology Foundation Models
2407.15362 (2024-07)
A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model
restrict_neighborhood 3 other papers
3 dated earlier
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
2306.03881 (2023-06)
Emergent Correspondence from Image Diffusion
score_ap_from_ranks_1 3 other papers
3 dated earlier
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
2202.10261 (2022-02)
A Self-Supervised Descriptor for Image Copy Detection
segment 3 other papers
3 dated earlier
2311.07125 (2023-11)
Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification
2406.15303 (2024-06)
AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classification
2505.17982 (2025-05)
Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling
is_image_file 2 other papers
2 dated earlier
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
label_propagation 2 other papers
2 dated earlier
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
softmax_helper 2 other papers
2 dated earlier
Liu_Perturbed_and_Strict_Mean_Teachers_for_Semi-Supervised_Semantic_Segmentation_CVPR_2022_paper (2022 (year only))
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
2211.09120 (2022-11)
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
sum_tensor 2 other papers
2 dated earlier
aaai_28394 (2024 (year only))
DTMFormer: Dynamic Token Merging for Boosting Transformer-Based Medical Image Segmentation
2410.09299 (2024-10)
Hierarchical uncertainty estimation for learning-based registration in neuroimaging
bag_dataset 1 other paper
1 dated earlier
2205.09671 (2022-05)
A graph-transformer for whole slide image classification

Shown: the 20 functions present in the most other papers. 10 more shared functions are not listed here.

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

Multiple-instance Learning (MIL) is commonly used for computational pathology (CPath), where multi-scale features are essential for capturing both fine cellular details and broad tissue architecture. However, existing multi-scale MIL approaches typically rely on the inflexible multi-magnification inputs or the computationally expensive architectures. As pre-trained foundation models (FMs) become the trend for feature extraction and boost lightweight models, we rethink and explore a more efficient multi-scale MIL method. In this paper, we propose the Multi-scale Pyramidal Network (MSPN), a plug-and-play module for attention-based MIL. MSPN introduces progressive multi-scale whole-slide image analysis using only a single high-magnification input. It consists of (1) grid-based remapping that aggregates high-magnification features to derive spatially-aware coarse feature maps, and (2) the Coarse Guidance Network (CGN) that learns coarse contexts. We benchmark MSPN as an add-on module to 4 attention-based frameworks on 5 clinically relevant tasks with 2 foundation models, and a pre-trained MIL framework. Our results demonstrate that MSPN consistently improves MIL across the compared configurations and tasks, while being lightweight and easy-to-use. Codes are available at: https://anonymous.4open.science/r/MSPN-86D5/.

For agents

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

get_harvested_code_for_paper("2602.01951")
get_code_for_paper("2602.01951")
have("2602.01951")

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

curl https://syntology.ai/api/ran/2602.01951.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.01951.svg)](https://syntology.ai/paper/2602.01951)

Connect an agent — have() is free.