SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.06499 · AAAI · 2020

Temporal Interlacing Network

Shengju Qian, Hao Shao, Yu Liu

arXiv · PDF · Open in the Atlas

Code that ran

17 of 25 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (9 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 12 have no contract verdict; 5 failures of our instrument; 8 no recorded run), measured 2026-11-21; 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/2001.06499.json · badge: /api/ran/2001.06499.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
eynaij/X-Temporal_catdim community (classifier label)
classifier basis not recorded on the link
8 ran · 4 no recorded run
Sense-X/X-Temporal community
Papers with Code archive
6 ran · 3 no recorded run
open-mmlab/mmaction2 community
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
BiasConvFc2Net Ran
ran on a synthesized input · constructed an object; no result was computed
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("b0d4348ec5d54e62")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, BiasConvFc2Net: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define parameters for BiasConvFc2Net
in_channels = 4
groups = 3
n_segment = 5
kernel_size = 3
padding = 1

ARGS = {
    'in_channels': in_channels,
    'groups': groups,
    'n_segment': n_segment,
    'kernel_size': kernel_size,
    'padding': padding,
}
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 BiasConvFc2Net — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a BiasConvFc2Net 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
BiasNet Ran
ran on a synthesized input · constructed an object; no result was computed
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("af9eef72e039d34a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, BiasNet: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Parameters for BiasNet
in_channels = 4
groups = 3
n_segment = 5

ARGS = {
    "in_channels": in_channels,
    "groups": groups,
    "n_segment": n_segment,
}
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 BiasNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a BiasNet 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
CombinNet Ran
ran on a synthesized input · constructed an object; no result was computed
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("c7f2d4eeb9a8f2c5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, CombinNet: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define a simple first network that takes input and transforms it
class SimpleNet1(nn.Module):
    def __init__(self):
        super(SimpleNet1, self).__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Define a simple second network that takes the output of net1 and transforms it
class SimpleNet2(nn.Module):
    def __init__(self):
        super(SimpleNet2, self).__init__()
        self.linear = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear(x)

# Instantiate the two networks
net1 = SimpleNet1()
net2 = SimpleNet2()

# Create the ARGS dictionary with all parameters
ARGS = {
    'net1': net1,
    'net2': net2
}
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 CombinNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CombinNet 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
OffsetNet Ran
ran on a synthesized input · constructed an object; no result was computed
open-mmlab/mmaction2/mmaction/models/backbones/resnet_tin.py
code served (permissive licence) · get_code("e2d69011327a8587")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, OffsetNet: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define parameters for OffsetNet
in_channels = 4
groups = 3
num_segments = 5

ARGS = {
    "in_channels": in_channels,
    "groups": groups,
    "num_segments": num_segments,
}
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 OffsetNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a OffsetNet 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
TemporalDeform Ran
ran on a synthesized input · constructed an object; no result was computed
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("56142e0364e50045")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, TemporalDeform: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

class TemporalDeform(nn.Module):

    def __init__(self, in_channels, n_segment=3, shift_div=1):
        super(TemporalDeform, self).__init__()
        self.n_segment = n_segment
        self.shift_div = shift_div
        self.in_channels = in_channels

    @staticmethod
    def _init_weights(weights, std):
        fan_out = weights.size(0)
        fan_in = weights.size(1) * weights.size(2)
        w = np.random.normal(0.0, std, (fan_out, fan_in))
        return torch.from_numpy(w.reshape(weights.size()))

    def forward(self, x):
        pass

ARGS = {
    'in_channels': 8,
    'n_segment': 3,
    'shift_div': 2
}
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 TemporalDeform — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TemporalDeform 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
TemporalInterlace Ran
ran on a synthesized input · constructed an object; no result was computed
open-mmlab/mmaction2/mmaction/models/backbones/resnet_tin.py
code served (permissive licence) · get_code("ea215c4e9afdcbaa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, TemporalInterlace: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_channels': 64,
    'num_segments': 8,
    'shift_div': 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
mmcv, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TemporalInterlace — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TemporalInterlace 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
WeightConvNet Ran
ran on a synthesized input · constructed an object; no result was computed
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("ac3b269e2d2ea9f1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, WeightConvNet: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_channels": 4,
    "groups": 3,
    "n_segment": 8
}
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 WeightConvNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a WeightConvNet 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
WeightNet Ran
ran on a synthesized input · constructed an object; no result was computed
open-mmlab/mmaction2/mmaction/models/backbones/resnet_tin.py
code served (permissive licence) · get_code("a31c3a0942051e85")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, WeightNet: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_channels": 4,
    "groups": 3,
}
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 WeightNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a WeightNet 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
WeightNet Ran
ran on a synthesized input · constructed an object; no result was computed
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("be409544d0de19db")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, WeightNet: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_channels': 4,
    'groups': 2,
    'n_segment': 3
}
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 WeightNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a WeightNet 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
calculate_mAP Ran
ran on a synthesized input
eynaij/X-Temporal_catdim/x_temporal/core/calculate_map.py
code served (permissive licence) · get_code("abad6636feaa1854")
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 float64, ndim 0, 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 numpy as np

torch.manual_seed(0)

# The function expects:
# - y_pred: a tensor with .detach(), .cpu(), .numpy() methods
# - y_true: a tensor with .detach(), .cpu(), .numpy() methods
# Both should be 2D arrays where each row can be passed to average_precision_score

# Create small 2D tensors (batch_size=2, num_classes=4)
y_pred = torch.tensor([
    [0.1, 0.9, 0.3, 0.7],
    [0.8, 0.2, 0.6, 0.4]
], dtype=torch.float32)

y_true = torch.tensor([
    [0, 1, 0, 1],
    [1, 0, 1, 0]
], dtype=torch.float32)

ARGS = {
    'y_pred': y_pred,
    'y_true': y_true
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
conv3x3 Ran
ran; our contract draft was wrong, not the code
eynaij/X-Temporal_catdim/x_temporal/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, 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.

conv3x3x3 Ran
ran; our contract draft was wrong, not the code
eynaij/X-Temporal_catdim/x_temporal/models/resnet3D.py
code served (permissive licence) · get_code("c3b215555357b9d1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Conv3d. 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 conv3x3x3 creates a 3D convolution layer
# Parameters:
# - in_planes: number of input channels
# - out_planes: number of output channels  
# - stride: stride for the convolution (default=1)

# We need to provide distinct values for in_planes and out_planes
in_planes = 3
out_planes = 5
stride = 2

ARGS = {
    'in_planes': in_planes,
    'out_planes': out_planes,
    'stride': stride
}
Setup block drafted by
a language model, Claude Sonnet 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 Conv3d — a Conv3d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv3d 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
downsample_basic_block Ran
ran; our contract draft was wrong, not the code
eynaij/X-Temporal_catdim/x_temporal/models/resnet3D.py
code served (permissive licence) · get_code("43c0211ff8dbca5f")
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 5, dtype family float, shape (2, 8, 2, 2, 2) as a later run recorded it. 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, 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create a small 5D tensor (batch_size=2, channels=4, depth=3, height=3, width=3)
# This matches the expected input for a 3D convolution operation
x = torch.randn(2, 4, 3, 3, 3)

# planes should be greater than the number of input channels (4)
# so that zero padding can be added
planes = 8

# stride for the pooling operation
stride = 2

ARGS = {
    "x": x,
    "planes": planes,
    "stride": stride
}
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 5, dtype family float, shape (2, 8, 2, 2, 2) — shape (2, 8, 2, 2, 2) 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
resnet18 Ran
ran; our contract draft was wrong, not the code
eynaij/X-Temporal_catdim/x_temporal/models/resnet.py
code served (permissive licence) · get_code("3133a91c5f65faf6")
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 ResNet. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet34 Ran
ran; our contract draft was wrong, not the code
eynaij/X-Temporal_catdim/x_temporal/models/resnet.py
code served (permissive licence) · get_code("55e1a04ae56f65ff")
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 ResNet. 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)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
softmax Ran
ran on a synthesized input
eynaij/X-Temporal_catdim/x_temporal/core/utils.py
code served (permissive licence) · get_code("2fc0c71db48a9af8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family 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 numpy as np

# Create a small scores array for the softmax function
# Shape: (2, 4) - batch size 2, 4 classes
scores = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [2.0, 1.0, 4.0, 3.0]
], dtype=np.float32)

ARGS = {
    'scores': scores
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family 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
solve_sigmoid Ran
ran on a synthesized input
eynaij/X-Temporal_catdim/x_temporal/core/tin.py
code served (permissive licence) · get_code("54338eeed53ef717")
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 float, 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 math

def solve_sigmoid(x):
    return -math.log(1.0 / x - 1)

# The function takes a single parameter 'x' which should be a value between 0 and 1
# (valid sigmoid output range) so that 1.0/x - 1 is positive and log is defined.
# We'll use a value in the valid range.

x = 0.73

ARGS = {
    "x": x
}
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 float, 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
ShiftFeatureFunc Not yet run
unverified (harvested, no recorded run)
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("782157bcd8af4111")
How it ran

no invocation recorded.

accuracy Not yet run
unverified (harvested, no recorded run)
eynaij/X-Temporal_catdim/x_temporal/core/utils.py
code served (permissive licence) · get_code("f0c9a29156911331")
How it ran

no invocation recorded.

get_augmentation Not yet run
unverified (harvested, no recorded run)
eynaij/X-Temporal_catdim/x_temporal/core/models_entry.py
code served (permissive licence) · get_code("a69a49fb8e893188")
How it ran

no invocation recorded.

get_optim_policies Not yet run
unverified (harvested, no recorded run)
eynaij/X-Temporal_catdim/x_temporal/core/models_entry.py
code served (permissive licence) · get_code("853dc3e095a9a4d3")
How it ran

no invocation recorded.

linear_sampler Not yet run
unverified (harvested, no recorded run)
open-mmlab/mmaction2/mmaction/models/backbones/resnet_tin.py
code served (permissive licence) · get_code("1697f830d024d096")
How it ran

no invocation recorded.

linear_sampler Not yet run
unverified (harvested, no recorded run)
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("3f29fda7782b535b")
How it ran

no invocation recorded.

make_temporal_interlace Not yet run
unverified (harvested, no recorded run)
Sense-X/X-Temporal/x_temporal/core/tin.py
code served (permissive licence) · get_code("0c82a4c90fd7bea8")
How it ran

no invocation recorded.

make_temporal_shift Not yet run
unverified (harvested, no recorded run)
eynaij/X-Temporal_catdim/x_temporal/core/tsm.py
code served (permissive licence) · get_code("3672320d68533e51")
How it ran

no invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 7 later) and 18 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
conv3x3 686 other papers
182 dated earlier, 4 the same month, 499 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
resnet18 89 other papers
24 dated earlier, 64 later, 1 same year, order not determinable
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 86 more not named here
accuracy 71 other papers
22 dated earlier, 1 the same month, 48 later · 2 only as an assembly brick
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1705.07204 (2017-05)
Ensemble Adversarial Training: Attacks and Defenses
1802.10399 (2018-02)
Compressing Neural Networks using the Variational Information Bottleneck
and 68 more not named here
resnet34 53 other papers
22 dated earlier, 31 later
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 50 more not named here
conv3x3x3 19 other papers
6 dated earlier, 13 later
1711.08580 (2017-11)
3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes
1711.09577 (2017-11)
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
1908.01373 (2019-08)
Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network
and 16 more not named here
downsample_basic_block 15 other papers
6 dated earlier, 9 later
1705.07750 (2017-05)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
1711.09577 (2017-11)
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
1908.01373 (2019-08)
Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network
and 12 more not named here
softmax 2 other papers
2 later
2005.06803 (2020-05)
TAM: Temporal Adaptive Module for Video Recognition
2007.09933 (2020-07)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

For a long time, the vision community tries to learn the spatio-temporal representation by combining convolutional neural network together with various temporal models, such as the families of Markov chain, optical flow, RNN and temporal convolution. However, these pipelines consume enormous computing resources due to the alternately learning process for spatial and temporal information. One natural question is whether we can embed the temporal information into the spatial one so the information in the two domains can be jointly learned once-only. In this work, we answer this question by presenting a simple yet powerful operator -temporal interlacing network (TIN). Instead of learning the temporal features, TIN fuses the two kinds of information by interlacing spatial representations from the past to the future, and vice versa. A differentiable interlacing target can be learned to control the interlacing process. In this way, a heavy temporal model is replaced by a simple interlacing operator. We theoretically prove that with a learnable interlacing target, TIN performs equivalently to the regularized temporal convolution network (r-TCN), but gains 4% more accuracy with 6x less latency on 6 challenging benchmarks. These results push the state-of-the-art performances of video understanding by a considerable margin. Not surprising, the ensemble model of the proposed TIN won the 1 st place in the ICCV19 -Multi Moments in Time challenge. Code is made available to facilitate further research. 1

For agents

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

get_harvested_code_for_paper("2001.06499")
get_code_for_paper("2001.06499")
have("2001.06499")

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

curl https://syntology.ai/api/ran/2001.06499.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.06499.svg)](https://syntology.ai/paper/2001.06499)

Connect an agent — have() is free.