SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.09219 · 2020

Stochastic Latent Residual Video Prediction

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 2 violated it and 5 have no contract verdict; 3 failures of our instrument; 2 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/2002.09219.json · badge: /api/ran/2002.09219.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
edouardelasalles/srvp canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
activation_factory Ran
ran on a synthesized input
edouardelasalles/srvp/module/utils.py
code served (permissive licence) · get_code("75673c3489a5111c")
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 ReLU. 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 function takes a single parameter: name (str)
# It returns an activation layer based on the name
# Valid names are: 'relu', 'leaky_relu', 'elu', 'sigmoid', 'tanh'

ARGS = {
    'name': 'relu'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
l2 Ran
ran, violated the contract we drafted
edouardelasalles/srvp/metrics/lpips/loss.py
code served (permissive licence) · get_code("cebd4a767f96722b")
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 float32, ndim 0, dtype family float, shape () 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

# Set seed for reproducibility
torch.manual_seed(0)

# Create two small numpy arrays as inputs
# The function computes L2 distance between normalized versions of p0 and p1
p0 = np.random.rand(2, 4).astype(np.float32) * 255.0
p1 = np.random.rand(2, 4).astype(np.float32) * 255.0

# range parameter with default value
range_val = 255.0

# Construct the ARGS dict with all function parameters
ARGS = {
    "p0": p0,
    "p1": p1,
    "range": range_val
}
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 float32, ndim 0, dtype family float, shape () — shape () 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
load_json Ran
ran on a synthesized input
edouardelasalles/srvp/helper.py
code served (permissive licence) · get_code("1525ee5c735dc09b")
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 DotDict. 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 json
import tempfile
import os

class DotDict(dict):
    """
    Dot notation access to dictionary attributes.
    """
    __getattr__ = dict.get
    __setattr__ = dict.__setitem__
    __delattr__ = dict.__delitem__

def load_json(path):
    """
    Loads a json input file.
    """
    with open(path, 'r') as f:
        opt = json.load(f)
    return DotDict(opt)

# Create a temporary JSON file with sample configuration data
temp_dir = tempfile.mkdtemp()
json_path = os.path.join(temp_dir, "config.json")

sample_config = {
    "model": "resnet50",
    "batch_size": 32,
    "learning_rate": 0.001,
    "epochs": 100,
    "optimizer": "adam",
    "nested": {
        "param1": "value1",
        "param2": 42
    }
}

with open(json_path, 'w') as f:
    json.dump(sample_config, f)

ARGS = {
    "path": json_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DotDict — a DotDict 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
load_yaml Ran
ran on a synthesized input
edouardelasalles/srvp/helper.py
code served (permissive licence) · get_code("2e294d738f6cc876")
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 DotDict. 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 os
import tempfile
import yaml

class DotDict(dict):
    """
    Dot notation access to dictionary attributes.
    """
    __getattr__ = dict.get
    __setattr__ = dict.__setitem__
    __delattr__ = dict.__delitem__

def load_yaml(path):
    """
    Loads a yaml input file.
    """
    with open(path, 'r') as f:
        opt = yaml.safe_load(f)
    return DotDict(opt)

# Create a temporary YAML file
temp_dir = tempfile.mkdtemp()
yaml_path = os.path.join(temp_dir, "config.yaml")

yaml_content = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "nested": {
        "key": "value"
    }
}

with open(yaml_path, 'w') as f:
    yaml.dump(yaml_content, f)

ARGS = {
    "path": yaml_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DotDict — a DotDict 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
make_normal_from_raw_params Ran
ran on a synthesized input
edouardelasalles/srvp/module/utils.py
code served (permissive licence) · get_code("df7836d4e167b95e")
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 Normal. 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.distributions as distrib
import torch.nn.functional as F

torch.manual_seed(0)

# Create raw_params tensor
# The function chunks this tensor in half on the specified dimension
# First half becomes loc (mean), second half becomes raw_scale
# Shape: (batch=2, features=4, params=8) where last dim has mean + raw_scale
raw_params = torch.randn(2, 4, 8)

# scale_stddev: a float multiplier for the scale parameter
scale_stddev = 1.5

# dim: the dimension along which to chunk (split into mean and scale)
# We're chunking the last dimension here
dim = -1

# eps: minimum value added to the scale for numerical stability
eps = 1e-8

ARGS = {
    "raw_params": raw_params,
    "scale_stddev": scale_stddev,
    "dim": dim,
    "eps": eps,
}
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 Normal — a Normal output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Normal output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalize_tensor Ran
ran; our contract draft was wrong, not the code
edouardelasalles/srvp/metrics/lpips/loss.py
code served (permissive licence) · get_code("15df2c2c65353c11")
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

torch.manual_seed(0)

# Construct a small input tensor with shape (batch=2, dim=4)
in_feat = torch.randn(2, 4)

ARGS = {
    "in_feat": in_feat,
    "eps": 1e-10
}
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
psnr Ran
ran, violated the contract we drafted
edouardelasalles/srvp/metrics/lpips/loss.py
code served (permissive licence) · get_code("e844cf206c6621e3")
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 float32, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create two small image arrays with the same shape
# p0 and p1 should be numeric arrays (images or image-like data)
p0 = np.random.rand(2, 4).astype(np.float32) * 255.0
p1 = np.random.rand(2, 4).astype(np.float32) * 255.0

# peak is the maximum possible pixel value (typically 255 for 8-bit images)
peak = 255.0

ARGS = {
    "p0": p0,
    "p1": p1,
    "peak": peak
}
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 float32, ndim 0, dtype family float, shape () — shape () 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
rsample_normal Ran
ran on a synthesized input
edouardelasalles/srvp/module/utils.py
code served (permissive licence) · get_code("f202199f0213bab0")
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.distributions as distrib
import torch.nn.functional as F

torch.manual_seed(0)

# raw_params should be a tensor where the last dimension (or specified dim)
# contains both mean and raw scale parameters concatenated.
# Since dim=-1 by default and we chunk on that dimension,
# we need a tensor where the last dimension has even size.
# Let's create a tensor of shape (2, 8) where last dim=8 will be chunked into (2, 4) and (2, 4)
raw_params = torch.randn(2, 8)

# scale_stddev is a float multiplier for the scale parameter
scale_stddev = 1.0

ARGS = {
    "raw_params": raw_params,
    "scale_stddev": scale_stddev,
}
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
spatial_average Ran
ran; our contract draft was wrong, not the code
edouardelasalles/srvp/metrics/lpips/networks_basic.py
code served (permissive licence) · get_code("29e5e72bcd006dcd")
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 4, dtype family float, shape (2, 4, 1, 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)

# The function performs spatial averaging on a 4D tensor (batch, channels, height, width)
# by taking the mean over dimensions 2 and 3 (height and width)
in_tens = torch.randn(2, 4, 3, 5)  # batch=2, channels=4, height=3, width=5

ARGS = {
    "in_tens": in_tens,
    "keepdim": True,
}
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 4, dtype family float, shape (2, 4, 1, 1) — shape (2, 4, 1, 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
upsample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
edouardelasalles/srvp/metrics/lpips/networks_basic.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cychungg/hairfusion, is pointer only (licence: NONE) · get_code("351677a36e1961df")
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 cychungg/hairfusion, 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.

score_2afc_dataset Not yet run
unverified (harvested, no recorded run)
edouardelasalles/srvp/metrics/lpips/dist_model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cychungg/hairfusion, is pointer only (licence: NONE) · get_code("dfd2379e29a03aef")
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 cychungg/hairfusion, 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. No invocation recorded.

score_jnd_dataset Not yet run
unverified (harvested, no recorded run)
edouardelasalles/srvp/metrics/lpips/dist_model.py
code served (permissive licence) · get_code("2cdf9c19c6aff6a0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 9 later) and 3 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
spatial_average 19 other papers
2 dated earlier, 17 later
1801.03924 (2018-01)
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2005.05999 (2020-05)
Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
and 16 more not named here
score_2afc_dataset 15 other papers
1 dated earlier, 14 later
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2005.00953 (2020-05)
Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution
2005.05999 (2020-05)
Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
and 12 more not named here
normalize_tensor 11 other papers
11 later
2103.16194 (2021-03)
Differentiable Drawing and Sketching
2111.14292 (2021-11)
Deblur-NeRF: Neural Radiance Fields from Blurry Images
2203.09301 (2022-03)
One-Shot Adaptation of GAN in Just One CLIP
and 8 more not named here
upsample 10 other papers
1 dated earlier, 9 later
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2005.05999 (2020-05)
Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
2006.09461 (2020-06)
Robust Compressed Sensing using Generative Models
and 7 more not named here
l2 6 other papers
6 later
2111.14292 (2021-11)
Deblur-NeRF: Neural Radiance Fields from Blurry Images
2211.12046 (2022-11)
DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors
2211.12853 (2022-11)
BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields
and 3 more not named here
psnr 6 other papers
6 later
2111.14292 (2021-11)
Deblur-NeRF: Neural Radiance Fields from Blurry Images
2211.12046 (2022-11)
DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors
2211.12853 (2022-11)
BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields
and 3 more not named here
score_jnd_dataset 6 other papers
1 dated earlier, 5 later
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2006.09461 (2020-06)
Robust Compressed Sensing using Generative Models
2007.06600 (2020-07)
Closed-Form Factorization of Latent Semantics in GANs
and 3 more not named here
load_json 1 other paper
1 later
2008.01352 (2020-08)
PDE-Driven Spatiotemporal Disentanglement
load_yaml 1 other paper
1 later
2008.01352 (2020-08)
PDE-Driven Spatiotemporal Disentanglement

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

Designing video prediction models that account for the inherent uncertainty of the future is challenging. Most works in the literature are based on stochastic image-autoregressive recurrent networks, which raises several performance and applicability issues. An alternative is to use fully latent temporal models which untie frame synthesis and temporal dynamics. However, no such model for stochastic video prediction has been proposed in the literature yet, due to design and training difficulties. In this paper, we overcome these difficulties by introducing a novel stochastic temporal model whose dynamics are governed in a latent space by a residual update rule. This first-order scheme is motivated by discretization schemes of differential equations. It naturally models video dynamics as it allows our simpler, more interpretable, latent model to outperform prior state-of-the-art methods on challenging datasets.

For agents

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

get_harvested_code_for_paper("2002.09219")
get_code_for_paper("2002.09219")
have("2002.09219")

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

curl https://syntology.ai/api/ran/2002.09219.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.09219.svg)](https://syntology.ai/paper/2002.09219)

Connect an agent — have() is free.