SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.03017 · 2024

Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach

arXiv · PDF · Open in the Atlas

Code that ran

22 of 24 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; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 17 failures of our instrument; 2 no recorded run); 3 of them were also run on the host, not in the jail, by the peer-agreement lane that set their level, 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/2412.03017.json · badge: /api/ran/2412.03017.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
cswry/osediff canonical (classifier label)
classifier basis: census
13 ran · 0 no recorded run
csslc/pisa-sr canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
FunctionStatusWhere it lives
parse_float_list Ran
ran, honoured the contract we drafted
cswry/osediff/train_osediff.py
code served (permissive licence) · get_code("8bc0bbc72282d3f8")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:52:19Z). 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 argparse

def parse_float_list(arg):
    try:
        return [float(x) for x in arg.split(',')]
    except ValueError:
        raise argparse.ArgumentTypeError('List elements should be floats')

ARGS = {
    'arg': '1.5,2.3,3.7,4.2'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 list, ndim 1, 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
parse_int_list Ran
ran, honoured the contract we drafted
cswry/osediff/train_osediff.py
code served (permissive licence) · get_code("b2d5ad9f0fef3e14")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T01:33:15Z). 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 argparse

def parse_int_list(arg):
    try:
        return [int(x) for x in arg.split(',')]
    except ValueError:
        raise argparse.ArgumentTypeError('List elements should be integers')

# Setup code
ARGS = {
    'arg': '1,2,3,4,5'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 list, ndim 1, dtype family int — 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
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
csslc/pisa-sr/ram/models/swin_transformer.py
pointer only (licence: NONE) · get_code("144d10b49baeb8a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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.

adain_color_fix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cswry/osediff/my_utils/wavelet_color_fix.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Joyies/TVT, is pointer only (licence: NONE) · get_code("d9c806cdedc044ef")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Joyies/TVT, 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.

attn_forward Ran
ran; our contract draft was wrong, not the code
cswry/osediff/my_utils/vaehook.py
code served (permissive licence) · get_code("174fab602409ffc2")
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 4, dtype family float, shape (2, 4, 3, 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 torch
import torch.nn as nn

torch.manual_seed(0)

class AttentionModule(nn.Module):
    def __init__(self, channels):
        super().__init__()
        self.q = nn.Conv2d(channels, channels, kernel_size=1)
        self.k = nn.Conv2d(channels, channels, kernel_size=1)
        self.v = nn.Conv2d(channels, channels, kernel_size=1)
        self.proj_out = nn.Conv2d(channels, channels, kernel_size=1)
    
    def forward(self, h_):
        q = self.q(h_)
        k = self.k(h_)
        v = self.v(h_)
        b, c, h, w = q.shape
        q = q.reshape(b, c, h * w)
        q = q.permute(0, 2, 1)
        k = k.reshape(b, c, h * w)
        w_ = torch.bmm(q, k)
        w_ = w_ * int(c) ** (-0.5)
        w_ = torch.nn.functional.softmax(w_, dim=2)
        v = v.reshape(b, c, h * w)
        w_ = w_.permute(0, 2, 1)
        h_ = torch.bmm(v, w_)
        h_ = h_.reshape(b, c, h, w)
        h_ = self.proj_out(h_)
        return h_

# Create attention module with 4 channels
channels = 4
attn_module = AttentionModule(channels)

# Create input tensor: (batch=2, channels=4, height=3, width=5)
h_input = torch.randn(2, 4, 3, 5)

ARGS = {
    "self": attn_module,
    "h_": h_input,
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 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
attn_forward_new Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cswry/osediff/my_utils/vaehook.py
code served (permissive licence) · get_code("08822a10826682a0")
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 4, dtype family float, shape (2, 8, 3, 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)

class AttentionLayer(nn.Module):
    def __init__(self, hidden_dim, num_heads):
        super().__init__()
        self.hidden_dim = hidden_dim
        self.num_heads = num_heads
        self.head_dim = hidden_dim // num_heads
        
        self.to_q = nn.Linear(hidden_dim, hidden_dim)
        self.to_k = nn.Linear(hidden_dim, hidden_dim)
        self.to_v = nn.Linear(hidden_dim, hidden_dim)
        
        self.norm_cross = False
        self.norm_encoder_hidden_states = nn.LayerNorm(hidden_dim)
        
        self.to_out = nn.ModuleList([
            nn.Linear(hidden_dim, hidden_dim),
            nn.Identity()
        ])
    
    def prepare_attention_mask(self, attention_mask, sequence_length, batch_size):
        return None
    
    def head_to_batch_dim(self, tensor):
        batch_size, sequence_length, channels = tensor.shape
        tensor = tensor.reshape(batch_size, sequence_length, self.num_heads, self.head_dim)
        tensor = tensor.permute(0, 2, 1, 3).reshape(batch_size * self.num_heads, sequence_length, self.head_dim)
        return tensor
    
    def batch_to_head_dim(self, tensor):
        batch_size_times_heads, sequence_length, head_dim = tensor.shape
        batch_size = batch_size_times_heads // self.num_heads
        tensor = tensor.reshape(batch_size, self.num_heads, sequence_length, head_dim)
        tensor = tensor.permute(0, 2, 1, 3).reshape(batch_size, sequence_length, self.hidden_dim)
        return tensor
    
    def get_attention_scores(self, query, key, attention_mask):
        scores = torch.bmm(query, key.transpose(1, 2))
        scores = scores / (self.head_dim ** 0.5)
        attention_probs = torch.softmax(scores, dim=-1)
        return attention_probs
    
    def forward(self, h_):
        batch_size, channel, height, width = h_.shape
        hidden_states = h_.view(batch_size, channel, height * width).transpose(1, 2)
        attention_mask = None
        encoder_hidden_states = None
        batch_size, sequence_length, _ = hidden_states.shape
        attention_mask = self.prepare_attention_mask(attention_mask, sequence_length, batch_size)
        query = self.to_q(hidden_states)
        if encoder_hidden_states is None:
            encoder_hidden_states = hidden_states
        elif self.norm_cross:
            encoder_hidden_states = self.norm_encoder_hidden_states(encoder_hidden_states)
        key = self.to_k(encoder_hidden_states)
        value = self.to_v(encoder_hidden_states)
        query = self.head_to_batch_dim(query)
        key = self.head_to_batch_dim(key)
        value = self.head_to_batch_dim(value)
        attention_probs = self.get_attention_scores(query, key, attention_mask)
        hidden_states = torch.bmm(attention_probs, value)
        hidden_states = self.batch_to_head_dim(hidden_states)
        hidden_states = self.to_out[0](hidden_states)
        hidden_states = self.to_out[1](hidden_states)
        hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
        return hidden_states

attention_module = AttentionLayer(hidden_dim=8, num_heads=2)
h_input = torch.randn(2, 8, 3, 4)

ARGS = {
    "self": attention_module,
    "h_": h_input
}
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 4, dtype family float, shape (2, 8, 3, 4) — shape (2, 8, 3, 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
calc_mean_std Ran
ran; our contract draft was wrong, not the code
cswry/osediff/my_utils/wavelet_color_fix.py
code served (permissive licence) · get_code("4c8c3d07d7aa35cb")
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 tuple, ndim 5, 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
import torch.nn as nn

torch.manual_seed(0)

# Create a 4D tensor with shape (batch=2, channels=4, height=3, width=5)
# This satisfies the requirement that feat is a 4D tensor
feat = torch.randn(2, 4, 3, 5)

ARGS = {
    'feat': feat,
    'eps': 1e-05
}
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 tuple, ndim 5, 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
cond_cast_float Ran
ran, honoured the contract we drafted
cswry/osediff/my_utils/devices.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SHH-Han/DNF-SR, is pointer only (licence: NOASSERTION) · get_code("a1316b96fc0dc988")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SHH-Han/DNF-SR, 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.

cond_cast_unet Ran
ran, honoured the contract we drafted
cswry/osediff/my_utils/devices.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SHH-Han/DNF-SR, is pointer only (licence: NOASSERTION) · get_code("6e1abd17fa1ce3b2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SHH-Han/DNF-SR, 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.

find_filepath Ran
ran; our contract draft was wrong, not the code
csslc/pisa-sr/pisasr.py
pointer only (licence: NONE); the stored copy get_code serves, from Joyies/TVT, is pointer only (licence: NONE) · get_code("6145c0b4a5012336")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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_device_for Ran
ran; our contract draft was wrong, not the code
cswry/osediff/my_utils/devices.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SHH-Han/DNF-SR, is pointer only (licence: NOASSERTION) · get_code("a861df384ac42eeb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SHH-Han/DNF-SR, 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.

inference_ram Ran
ran; our contract draft was wrong, not the code
csslc/pisa-sr/ram/inference.py
pointer only (licence: NONE) · get_code("7ea931fd6b54f5cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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.

inference_ram_openset Ran
ran; our contract draft was wrong, not the code
csslc/pisa-sr/ram/inference.py
pointer only (licence: NONE); the stored copy get_code serves, from Joyies/TVT, is pointer only (licence: NONE) · get_code("cc4cd40ee7f7cce8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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.

inference_tag2text Ran
ran; our contract draft was wrong, not the code
csslc/pisa-sr/ram/inference.py
pointer only (licence: NONE); the stored copy get_code serves, from Joyies/TVT, is pointer only (licence: NONE) · get_code("3d89c9c107a089ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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.

inplace_nonlinearity Ran
ran; our contract draft was wrong, not the code
cswry/osediff/my_utils/vaehook.py
code served (permissive licence) · get_code("76a017e88938061d")
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, 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.functional as F

torch.manual_seed(0)

# inplace_nonlinearity takes a single parameter 'x' which should be a tensor
# The function applies F.silu with inplace=True to it
x = torch.randn(2, 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 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
is_url Ran
ran, violated the contract we drafted
csslc/pisa-sr/ram/models/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from jylins/videoxum, is pointer only (licence: NONE) · get_code("4d1d9c47619920ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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.

opt_parse Ran
ran; our contract draft was wrong, not the code
cswry/osediff/dataloaders/codeformer.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SHH-Han/DNF-SR, is pointer only (licence: NOASSERTION) · get_code("fce64ea4638101fc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SHH-Han/DNF-SR, 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.

parse_str_list Ran
ran; our contract draft was wrong, not the code
cswry/osediff/train_osediff.py
code served (permissive licence) · get_code("fa3b3cc4f07c4a0f")
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 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.

import torch

torch.manual_seed(0)

ARGS = {
    "arg": "hello,world,test"
}
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 1, 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
read_json Ran
ran; our contract draft was wrong, not the code
csslc/pisa-sr/ram/models/utils.py
pointer only (licence: NONE) · get_code("e1cf6464da33ec0c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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.

read_yaml Ran
ran; our contract draft was wrong, not the code
csslc/pisa-sr/pisasr.py
pointer only (licence: NONE); the stored copy get_code serves, from Joyies/TVT, is pointer only (licence: NONE) · get_code("4fb85a5d5907d6dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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.

wavelet_color_fix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cswry/osediff/my_utils/wavelet_color_fix.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Joyies/TVT, is pointer only (licence: NONE) · get_code("2353cdd05b03300f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Joyies/TVT, 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.

window_reverse Ran
ran; our contract draft was wrong, not the code
csslc/pisa-sr/ram/models/swin_transformer.py
pointer only (licence: NONE) · get_code("61bf152e6a42a184")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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.

create_vit Not yet run
unverified (harvested, no recorded run)
csslc/pisa-sr/ram/models/utils.py
pointer only (licence: NONE) · get_code("f837c334ddfa8af4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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. No invocation recorded.

interpolate_relative_pos_embed Not yet run
unverified (harvested, no recorded run)
csslc/pisa-sr/ram/models/swin_transformer.py
pointer only (licence: NONE) · get_code("199b2766250bd139")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csslc/pisa-sr 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. No invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 23 are also present in other papers whose code we hold (21 with at least one paper dated earlier, 2 the same month, 21 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
window_reverse 227 other papers
196 dated earlier, 3 the same month, 19 later, 9 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
window_partition 223 other papers
192 dated earlier, 3 the same month, 19 later, 9 same year, order not determinable · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 220 more not named here
is_url 11 other papers
10 dated earlier, 1 same year, order not determinable
2211.09790 (2022-11)
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
2303.12060 (2023-03)
VideoXum: Cross-modal Visual and Textural Summarization of Videos
2304.05977 (2023-04)
ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
and 8 more not named here
interpolate_relative_pos_embed 6 other papers
5 dated earlier, 1 later
2306.02898 (2023-06)
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
2404.18253 (2024-04)
Workshop for Machine Learning for Remote Sensing (ML4RS) EFFICIENT REMOTE SENSING WITH HARMONIZED TRANSFER LEARNING AND MODALITY ALIGNMENT
2409.19961 (2024-09)
Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval
and 3 more not named here
create_vit 5 other papers
5 dated earlier
2210.01936 (2022-10)
When and why vision-language models behave like bags-of-words, and what to do about it?
2304.05977 (2023-04)
ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
2305.16304 (2023-05)
Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
and 2 more not named here
attn_forward_new 4 other papers
2 dated earlier, 2 later
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2505.18600 (2025-05)
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
and 1 more not named here
inplace_nonlinearity 4 other papers
2 dated earlier, 2 later
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2505.18600 (2025-05)
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
and 1 more not named here
opt_parse 4 other papers
1 dated earlier, 2 later, 1 same year, order not determinable
01705 (2024 (year only))
Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
2507.20291 (2025-07)
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
and 1 more not named here
attn_forward 3 other papers
1 dated earlier, 2 later
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2505.18600 (2025-05)
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
2609.15120 (2026-09)
DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
calc_mean_std 3 other papers
2 dated earlier, 1 later
2409.17778 (2024-09)
Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2507.20291 (2025-07)
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
cond_cast_float 3 other papers
2 dated earlier, 1 later
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2609.15120 (2026-09)
DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
cond_cast_unet 3 other papers
2 dated earlier, 1 later
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2609.15120 (2026-09)
DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
get_device_for 3 other papers
2 dated earlier, 1 later
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2609.15120 (2026-09)
DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
parse_float_list 3 other papers
2 dated earlier, 1 later
2401.00877 (2024-01)
Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
2406.08177 (2024-06)
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
2502.09873 (2025-02)
Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
parse_int_list 3 other papers
2 dated earlier, 1 later
2401.00877 (2024-01)
Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
2406.08177 (2024-06)
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
2502.09873 (2025-02)
Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
parse_str_list 3 other papers
2 dated earlier, 1 later
2401.00877 (2024-01)
Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
2406.08177 (2024-06)
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
2502.09873 (2025-02)
Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
adain_color_fix 2 other papers
1 dated earlier, 1 later
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2507.20291 (2025-07)
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
inference_ram_openset 2 other papers
1 dated earlier, 1 later
2310.15200 (2023-10)
Open-Set Image Tagging with Multi-Grained Text Supervision
2507.20291 (2025-07)
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
inference_tag2text 2 other papers
1 dated earlier, 1 later
2310.15200 (2023-10)
Open-Set Image Tagging with Multi-Grained Text Supervision
2507.20291 (2025-07)
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
read_json 2 other papers
1 dated earlier, 1 later
2404.18253 (2024-04)
Workshop for Machine Learning for Remote Sensing (ML4RS) EFFICIENT REMOTE SENSING WITH HARMONIZED TRANSFER LEARNING AND MODALITY ALIGNMENT
Yang_Beyond_Walking_A_Large-Scale_Image-Text_Benchmark_for_Text-based_Person_Anomaly_ICCV_2025_paper (2025 (year only))
Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search

Shown: the 20 functions present in the most other papers. 3 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

Diffusion prior-based methods have shown impressive results in real-world image super-resolution (SR). However, most existing methods entangle pixel-level and semantic-level SR objectives in the training process, struggling to balance pixel-wise fidelity and perceptual quality. Meanwhile, users have varying preferences on SR results, thus it is demanded to develop an adjustable SR model that can be tailored to different fidelity-perception preferences during inference without re-training. We present Pixel-level and Semantic-level Adjustable SR (PiSA-SR), which learns two LoRA modules upon the pre-trained stable-diffusion (SD) model to achieve improved and adjustable SR results. We first formulate the SD-based SR problem as learning the residual between the low-quality input and the high-quality output, then show that the learning objective can be decoupled into two distinct LoRA weight spaces: one is characterized by the $\ell_2$-loss for pixel-level regression, and another is characterized by the LPIPS and classifier score distillation losses to extract semantic information from pre-trained classification and SD models. In its default setting, PiSA-SR can be performed in a single diffusion step, achieving leading real-world SR results in both quality and efficiency. By introducing two adjustable guidance scales on the two LoRA modules to control the strengths of pixel-wise fidelity and semantic-level details during inference, PiSASR can offer flexible SR results according to user preference without re-training. Codes and models can be found at https://github.com/csslc/PiSA-SR.

For agents

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

get_harvested_code_for_paper("2412.03017")
get_code_for_paper("2412.03017")
have("2412.03017")

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

curl https://syntology.ai/api/ran/2412.03017.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.03017.svg)](https://syntology.ai/paper/2412.03017)

Connect an agent — have() is free.