SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.17082 · 2023

DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling

arXiv · PDF · Open in the Atlas

Code that ran

16 of 17 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; 5 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 11 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2311.17082.json · badge: /api/ran/2311.17082.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
alexzhou907/dreampropeller canonical (classifier label)
classifier basis: census
16 ran · 1 no recorded run
FunctionStatusWhere it lives
dot Ran
ran, honoured the contract we drafted
alexzhou907/dreampropeller/dreamgaussian/cam_utils.py
code served (permissive licence) · get_code("e35aafbf0069edb6")
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, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

# Test with numpy arrays
x_np = np.random.randn(2, 4).astype(np.float32)
y_np = np.random.randn(2, 4).astype(np.float32)

# Test with torch tensors
x_torch = torch.randn(2, 4)
y_torch = torch.randn(2, 4)

# We'll use torch tensors for the main ARGS
ARGS = {
    "x": x_torch,
    "y": y_torch
}
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 Tensor, ndim 2, dtype family float, shape (2, 1) — shape (2, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
dot Ran
ran; our contract draft was wrong, not the code
alexzhou907/dreampropeller/dreamgaussian/mesh.py
code served (permissive licence) · get_code("456eeade4275ae9d")
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, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create two small tensors for the dot product computation
# x and y should have compatible shapes for element-wise multiplication
# The function sums over the last dimension (-1)
x = torch.randn(2, 4)  # batch_size=2, dim=4
y = torch.randn(2, 4)  # batch_size=2, dim=4

ARGS = {
    "x": x,
    "y": y,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 1) — shape (2, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_expon_lr_func Ran
ran; our contract draft was wrong, not the code
alexzhou907/dreampropeller/dreamgaussian/gs_renderer.py
code served (permissive licence) · get_code("6d2c15014d993b0e")
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 function. 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

ARGS = {
    "lr_init": 0.001,
    "lr_final": 0.0001,
    "lr_delay_steps": 100,
    "lr_delay_mult": 0.1,
    "max_steps": 1000
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
inverse_sigmoid Ran
ran, honoured the contract we drafted
alexzhou907/dreampropeller/dreamgaussian/gs_renderer.py
code served (permissive licence) · get_code("b488da571728b636")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function inverse_sigmoid takes a single parameter x
# It computes log(x / (1 - x)), which is the inverse sigmoid function
# This requires x to be a tensor with values in the range (0, 1)

# Create a small tensor with values in (0, 1)
x = torch.tensor([[0.2, 0.5, 0.7, 0.9],
                   [0.1, 0.3, 0.6, 0.8]])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
length Ran
ran, honoured the contract we drafted
alexzhou907/dreampropeller/dreamgaussian/cam_utils.py
code served (permissive licence) · get_code("43cdc168f88caf9b")
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, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

# Test with a torch tensor
x_torch = torch.randn(2, 4)

# Test with a numpy array
x_numpy = np.random.randn(2, 4)

# The function signature is: def length(x, eps=1e-20)
# It uses x to compute dot products and sqrt
# eps is used as a minimum clamp value

ARGS = {
    "x": x_torch,
    "eps": 1e-20
}
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 Tensor, ndim 2, dtype family float, shape (2, 1) — shape (2, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
r_precision Ran
ran, honoured the contract we drafted
alexzhou907/dreampropeller/dreamgaussian/evaluate.py
code served (permissive licence) · get_code("a15bd2d8e183335b")
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.

import numpy as np

# Set seed for reproducibility
np.random.seed(0)

# Construct candidates list with prediction and gt fields
candidates = [
    {'prediction': 1, 'gt': 1},
    {'prediction': 0, 'gt': 0},
    {'prediction': 1, 'gt': 1},
    {'prediction': 0, 'gt': 1},
    {'prediction': 1, 'gt': 0},
    {'prediction': 1, 'gt': 1},
    {'prediction': 0, 'gt': 0},
    {'prediction': 1, 'gt': 1},
    {'prediction': 1, 'gt': 1},
    {'prediction': 0, 'gt': 0},
    {'prediction': 1, 'gt': 1},
    {'prediction': 0, 'gt': 0},
    {'prediction': 1, 'gt': 1},
    {'prediction': 1, 'gt': 0},
    {'prediction': 0, 'gt': 1},
    {'prediction': 1, 'gt': 1},
    {'prediction': 0, 'gt': 0},
    {'prediction': 1, 'gt': 1},
    {'prediction': 1, 'gt': 1},
    {'prediction': 0, 'gt': 0},
]

ARGS = {
    'candidates': candidates,
    'num_chunks': 10
}
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 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
safe_normalize Ran
ran, honoured the contract we drafted
alexzhou907/dreampropeller/dreamgaussian/cam_utils.py
code served (permissive licence) · get_code("8a8484ccf552d87f")
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 numpy as np

torch.manual_seed(0)

# safe_normalize takes one required parameter: x
# It can be either a numpy array or a torch tensor
# The function uses x in division and passes it to length()
# length() computes x * x and sums over the last dimension

# Create a small torch tensor (batch=2, dim=4)
x_torch = torch.randn(2, 4)

# Also create a numpy equivalent for testing flexibility
x_numpy = np.random.randn(2, 4).astype(np.float32)

# The function can work with either, so we'll use torch
ARGS = {
    "x": x_torch
}
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 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
scale_img_hwc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alexzhou907/dreampropeller/dreamgaussian/mesh_renderer.py
code served (permissive licence) · get_code("1eb01adb2d4db29c")
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 3, dtype family float, shape (4, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small test image tensor in HWC format (Height, Width, Channels)
# Using distinct dimensions: 8 height, 6 width, 3 channels
x = torch.randn(8, 6, 3)

# Target size for scaling
size = (4, 3)

# Magnification mode
mag = 'bilinear'

# Minification mode
min = 'bilinear'

ARGS = {
    'x': x,
    'size': size,
    'mag': mag,
    'min': min
}
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 3, dtype family float, shape (4, 3, 3) — shape (4, 3, 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
scale_img_nhwc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alexzhou907/dreampropeller/dreamgaussian/mesh_renderer.py
code served (permissive licence) · get_code("e3e7b5863ff869ea")
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, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small NHWC tensor (batch=2, height=8, width=6, channels=3)
x = torch.randn(2, 8, 6, 3)

# Target size (height, width)
size = (4, 3)

# Interpolation mode for magnification
mag = 'bilinear'

# Interpolation mode for minification
min_mode = 'bilinear'

ARGS = {
    'x': x,
    'size': size,
    'mag': mag,
    'min': min_mode
}
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, 3) — shape (2, 4, 3, 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
scatter_add_nd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alexzhou907/dreampropeller/dreamgaussian/grid_put.py
code served (permissive licence) · get_code("f677a14137b6170d")
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, 3, 5, 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

torch.manual_seed(0)

# Construct arguments for scatter_add_nd
# The function expects:
# - input: tensor of shape (*size, C) where size is D-dimensional
# - indices: tensor of shape (N, D) with index coordinates
# - values: tensor of shape (N, C) with values to scatter

D = 3  # Number of spatial dimensions
C = 4  # Channel dimension
size = (2, 3, 5)  # 3D spatial size (D=3)
N = 6  # Number of scatter operations

# input: shape (2, 3, 5, 4) - a 3D spatial tensor with 4 channels
input = torch.randn(2, 3, 5, 4)

# indices: shape (6, 3) - 6 index tuples, each with 3 coordinates
# Each coordinate must be within bounds of the corresponding dimension
indices = torch.tensor([
    [0, 0, 0],
    [0, 0, 1],
    [1, 2, 3],
    [1, 1, 4],
    [0, 2, 2],
    [1, 0, 1]
], dtype=torch.long)

# values: shape (6, 4) - 6 values, each with 4 channels
values = torch.randn(6, 4)

ARGS = {
    "input": input,
    "indices": indices,
    "values": values
}
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, 3, 5, 4) — shape (2, 3, 5, 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
scatter_add_nd_with_count Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alexzhou907/dreampropeller/dreamgaussian/grid_put.py
code served (permissive licence) · get_code("0a4a0c5951d1f0bf")
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. 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

torch.manual_seed(0)

# Create small tensors for the function
# D = 2 (spatial dimensions)
# C = 3 (feature channels)
# size = (4, 5) (spatial grid size)

D = 2
C = 3
size = (4, 5)

# input: shape (4, 5, 3) - spatial grid with C features per cell
input = torch.randn(*size, C)

# count: shape (4, 5, 1) - counter for each cell
count = torch.zeros(*size, 1)

# indices: shape (2, 2) - 2 samples, D=2 spatial coordinates each
indices = torch.tensor([
    [1, 2],
    [3, 4]
], dtype=torch.long)

# values: shape (2, 3) - C=3 feature values for each of 2 samples
values = torch.randn(2, C)

# weights: shape (2, 1) - optional weights for each sample
weights = torch.ones(2, 1)

ARGS = {
    "input": input,
    "count": count,
    "indices": indices,
    "values": values,
    "weights": weights
}
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 — 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: none by the harness; any seed is in the setup block
stride_from_shape Ran
ran; our contract draft was wrong, not the code
alexzhou907/dreampropeller/dreamgaussian/grid_put.py
code served (permissive licence) · get_code("be46ebcf4f59432b")
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 list, ndim 1, dtype family int; 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)

# The function stride_from_shape takes a shape (a sequence of integers)
# and computes strides for memory layout based on that shape.
# It iterates through shape[1:] in reverse, building up cumulative products.

shape = (2, 3, 4, 5)

ARGS = {
    "shape": shape
}
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 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
strip_lowerdiag Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alexzhou907/dreampropeller/dreamgaussian/gs_renderer.py
code served (permissive licence) · get_code("77f1ea6fd821edf2")
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, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects L to be a tensor with shape (batch_size, 3, 3)
# representing lower triangular matrices. It extracts 6 elements from each
# 3x3 matrix to form a (batch_size, 6) output.
L = torch.randn(2, 3, 3, dtype=torch.float)

ARGS = {
    "L": L,
}
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, 6) — shape (2, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
take_step Ran
ran; our contract draft was wrong, not the code
alexzhou907/dreampropeller/launch_speedup.py
code served (permissive licence) · get_code("c0bc648c3548dc0c")
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 dict. 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 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
from torch import nn

torch.manual_seed(0)

class DummySystem(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def do_update_step(self, idx, step):
        pass
    
    def training_step(self, batch, step):
        x = batch['input']
        output = self.linear(x)
        loss = output.sum()
        return {'loss': loss}
    
    def do_update_step_end(self, idx, step):
        pass

class DummyDataIter:
    def __init__(self):
        self.batches = [
            {
                'input': torch.randn(2, 4),
                'target': torch.randint(0, 3, (2,))
            }
        ]
        self.batch_idx = 0
    
    def __next__(self):
        batch = self.batches[self.batch_idx % len(self.batches)]
        self.batch_idx += 1
        return batch

class DummyDataIters:
    def __init__(self):
        self.data_iter = DummyDataIter()
    
    def get_current_iter(self, step):
        return self.data_iter

system = DummySystem()
optimizers = {'optimizer': torch.optim.SGD(system.parameters(), lr=0.01)}
dataiters = DummyDataIters()
device = 'cpu'
step = 0
seed_offset = 42

ARGS = {
    'system': system,
    'optimizers': optimizers,
    'dataiters': dataiters,
    'device': device,
    'step': step,
    'seed_offset': seed_offset
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
to_device Ran
ran; our contract draft was wrong, not the code
alexzhou907/dreampropeller/launch_baseline.py
code served (permissive licence) · get_code("2f4294aed3696b58")
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 dict. 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

torch.manual_seed(0)

# Create a sample batch dictionary with various tensor types
batch = {
    "input_ids": torch.randint(0, 100, (2, 4)),
    "attention_mask": torch.ones(2, 4),
    "token_type_ids": torch.zeros(2, 4),
    "logits": torch.randn(2, 3),
    "non_tensor_field": "this should not be moved"
}

device = "cpu"

ARGS = {
    "batch": batch,
    "device": device
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
to_device Ran
ran; our contract draft was wrong, not the code
alexzhou907/dreampropeller/launch_baseline.py
code served (permissive licence) · get_code("c6999bab7905428e")
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 dict. 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

torch.manual_seed(0)

# Create a batch dictionary with tensors and nested dicts
batch = {
    "input_ids": torch.randn(2, 4),
    "attention_mask": torch.randn(2, 4),
    "nested": {
        "embeddings": torch.randn(2, 3),
        "scores": torch.randn(2, 5)
    },
    "metadata": "some_string"
}

device = "cpu"

ARGS = {
    "batch": batch,
    "device": device
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
scale_img_nhw Not yet run
unverified (harvested, no recorded run)
alexzhou907/dreampropeller/dreamgaussian/mesh_renderer.py
code served (permissive licence) · get_code("7d11ee5002c743ed")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 12 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 5 the same month, 12 later) and 5 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
inverse_sigmoid 21 other papers
2 the same month, 19 later
2311.11284 (2023-11)
LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching
2311.17061 (2023-11)
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
and 18 more not named here
dot 9 other papers
2 dated earlier, 7 later
2302.14859 (2023-02)
BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis
2308.07391 (2023-08)
PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects
2312.09527 (2023-12)
TIFace: Improving Facial Reconstruction through Tensorial Radiance Fields and Implicit Surfaces
and 6 more not named here
dot 8 other papers
1 the same month, 7 later
2311.17061 (2023-11)
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2312.14937 (2023-12)
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
and 5 more not named here
length 8 other papers
1 the same month, 7 later
2311.17061 (2023-11)
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2312.14937 (2023-12)
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
and 5 more not named here
safe_normalize 8 other papers
1 the same month, 7 later
2311.17061 (2023-11)
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2312.14937 (2023-12)
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
and 5 more not named here
get_expon_lr_func 5 other papers
1 the same month, 4 later
2311.17061 (2023-11)
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2404.03736 (2024-04)
SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer
and 2 more not named here
scale_img_hwc 3 other papers
3 later
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2404.06091 (2024-04)
Hash3D: Training-free Acceleration for 3D Generation
2412.06785 (2024-12)
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
scale_img_nhw 3 other papers
3 later
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2404.06091 (2024-04)
Hash3D: Training-free Acceleration for 3D Generation
2412.06785 (2024-12)
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
scale_img_nhwc 3 other papers
3 later
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2404.06091 (2024-04)
Hash3D: Training-free Acceleration for 3D Generation
2412.06785 (2024-12)
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
scatter_add_nd 3 other papers
3 later
2404.06091 (2024-04)
Hash3D: Training-free Acceleration for 3D Generation
2405.02280 (2024-05)
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
2405.20669 (2024-05)
Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation
scatter_add_nd_with_count 3 other papers
3 later
2404.06091 (2024-04)
Hash3D: Training-free Acceleration for 3D Generation
2405.02280 (2024-05)
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
2405.20669 (2024-05)
Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation
stride_from_shape 3 other papers
3 later
2404.06091 (2024-04)
Hash3D: Training-free Acceleration for 3D Generation
2405.02280 (2024-05)
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
2405.20669 (2024-05)
Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation

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

Recent methods such as Score Distillation Sampling (SDS) and Variational Score Distillation (VSD) using 2D diffusion models for text-to-3D generation have demonstrated impressive generation quality. However, the long generation time of such algorithms significantly degrades the user experience. To tackle this problem, we propose DreamPropeller, a drop-in acceleration algorithm that can be wrapped around any existing text-to-3D generation pipeline based on score distillation. Our framework generalizes Picard iterations, a classical algorithm for parallel sampling an ODE path, and can account for non-ODE paths such as momentum-based gradient updates and changes in dimensions during the optimization process as in many cases of 3D generation. We show that our algorithm trades parallel compute for wallclock time and empirically achieves up to 4.7x speedup with a negligible drop in generation quality for all tested frameworks.

For agents

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

get_harvested_code_for_paper("2311.17082")
get_code_for_paper("2311.17082")
have("2311.17082")

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

curl https://syntology.ai/api/ran/2311.17082.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.17082.svg)](https://syntology.ai/paper/2311.17082)

Connect an agent — have() is free.