SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.11310 · CVPR · 2021

Towards Long-Form Video Understanding

Chao-Yuan Wu, Philipp Krähenbühl

arXiv · PDF · Open in the Atlas

Code that ran

18 of 19 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; 2 honoured the contract we drafted, 1 violated it and 7 have no contract verdict; 8 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2106.11310.json · badge: /api/ran/2106.11310.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
chaoyuaw/lvu canonical (classifier label)
classifier basis: census
18 ran · 1 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
chaoyuaw/lvu/src/models/modeling_bert.py
code served (permissive licence) · get_code("0f786c407fb1ee4c")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:33:52Z). 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 swish takes a single parameter 'x' which is used with:
# - torch.sigmoid(x) - requires a tensor
# - x * ... - requires a tensor that supports multiplication
# So x should be a tensor

x = torch.randn(2, 4)

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
MaskedBCEWithLogitsLoss Ran
ran on a synthesized input
chaoyuaw/lvu/src/models/modeling_roberta.py
code served (permissive licence) · get_code("a788ae380900c50e")
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 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 torch
import torch.nn as nn
from torch.nn import BCEWithLogitsLoss

torch.manual_seed(0)

# Create predictions and labels tensors
# preds: logits for binary classification (batch_size=2, num_classes=4)
preds = torch.randn(2, 4, dtype=torch.float32)

# labels: contains values -100 (ignore), 0, or 1
# Create a valid label tensor with a mix of -100, 0, and 1
labels = torch.tensor([
    [-100, 0, 1, 0],
    [1, -100, 0, 1]
], dtype=torch.float32)

ARGS = {
    "preds": preds,
    "labels": labels
}
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 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
gelu Ran
ran, honoured the contract we drafted
chaoyuaw/lvu/src/models/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from lonePatient/BERT-SDA, is pointer only (licence: NONE) · get_code("211753ba29188d4e")
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 lonePatient/BERT-SDA, 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.

gelu_new Ran
ran, honoured the contract we drafted
chaoyuaw/lvu/src/models/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from lonePatient/BERT-SDA, is pointer only (licence: NONE) · get_code("77601724cad03f95")
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 lonePatient/BERT-SDA, 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.

get_constant_schedule Ran
ran on a synthesized input
chaoyuaw/lvu/src/models/optimization.py
code served (permissive licence) · get_code("4575f85aa7122560")
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 LambdaLR. 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
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 2)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define arguments for get_constant_schedule
ARGS = {
    "optimizer": optimizer,
    "last_epoch": -1
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
get_constant_schedule_with_warmup Ran
ran on a synthesized input
chaoyuaw/lvu/src/models/optimization.py
code served (permissive licence) · get_code("a2003a42a1bf5632")
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 LambdaLR. 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
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define arguments
ARGS = {
    "optimizer": optimizer,
    "num_warmup_steps": 100,
    "last_epoch": -1
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
get_linear_schedule_with_warmup Ran
ran; our contract draft was wrong, not the code
chaoyuaw/lvu/src/models/optimization.py
code served (permissive licence) · get_code("a3c458ae06a14711")
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 LambdaLR. 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
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define arguments for get_linear_schedule_with_warmup
ARGS = {
    "optimizer": optimizer,
    "num_warmup_steps": 100,
    "num_training_steps": 1000,
    "last_epoch": -1
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
get_pairs Ran
ran; our contract draft was wrong, not the code
chaoyuaw/lvu/src/models/tokenization_gpt2.py
code served (permissive licence) · get_code("4f76173dfe4b0c11")
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 set. 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 numpy as np

# The function get_pairs takes a word parameter
# Looking at the function body:
# - word is indexed with [0] to get the first element
# - word is iterated over with word[1:] 
# - Elements are added to a set as tuples (prev_char, char)
# So word should be a sequence/tuple of symbols (strings or any hashable objects)

# Create a simple word as a tuple of symbols
word = ("h", "e", "l", "l", "o")

ARGS = {
    "word": word
}
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 set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
hf_bucket_url Ran
ran; our contract draft was wrong, not the code
chaoyuaw/lvu/src/models/file_utils.py
code served (permissive licence) · get_code("b2be6c932ce41084")
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 str. 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

ARGS = {
    'identifier': 'bert-base-uncased',
    'postfix': 'pytorch_model.bin',
    'cdn': 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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
is_remote_url Ran
ran, violated the contract we drafted
chaoyuaw/lvu/src/models/file_utils.py
code served (permissive licence) · get_code("4381d1f588a7f42a")
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 bool, 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 torch
from urllib.parse import urlparse

ARGS = {
    'url_or_filename': 'https://example.com/model.pth'
}
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 bool, 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
make_image_key Ran
ran on a synthesized input
chaoyuaw/lvu/src/utils/ava_eval_helper.py
code served (permissive licence) · get_code("15e577f3614f1586")
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 str. 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 numpy as np

def make_image_key(video_id, timestamp):
    """Returns a unique identifier for a video id & timestamp."""
    return '%s,%04d' % (video_id, int(timestamp))

ARGS = {
    "video_id": "video_001",
    "timestamp": 42.7
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
prune_conv1d_layer Ran
ran; our contract draft was wrong, not the code
chaoyuaw/lvu/src/models/modeling_utils.py
code served (permissive licence) · get_code("8cc492d40c50497b")
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 Conv1D. 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
from torch import nn

torch.manual_seed(0)

class Conv1D(nn.Module):
    def __init__(self, nf, nx):
        super().__init__()
        self.nf = nf
        w = torch.empty(nx, nf)
        nn.init.normal_(w, std=0.02)
        self.weight = nn.Parameter(w)
        self.bias = nn.Parameter(torch.zeros(nf))

    def forward(self, x):
        size_out = x.size()[:-1] + (self.nf,)
        x = torch.addmm(self.bias, x.view(-1, x.size(-1)), self.weight)
        x = x.view(*size_out)
        return x

# Create a Conv1D layer to prune
# nf=5 (output features), nx=4 (input features)
layer = Conv1D(nf=5, nx=4)

# Create an index tensor to select which dimensions to keep
# dim=1 means we're selecting output features, so index should have length <= 5
index = torch.tensor([0, 2, 4], dtype=torch.long)

ARGS = {
    "layer": layer,
    "index": index,
    "dim": 1
}
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 Conv1D — a Conv1D output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv1D 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
prune_linear_layer Ran
ran; our contract draft was wrong, not the code
chaoyuaw/lvu/src/models/modeling_utils.py
code served (permissive licence) · get_code("d30d6c3098df2c42")
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 Linear. 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
from torch import nn

torch.manual_seed(0)

# Create a linear layer to prune
# Using distinct sizes: input_features=3, output_features=4
layer = nn.Linear(in_features=3, out_features=4, bias=True)

# Create an index tensor to select which output features to keep
# Selecting 2 out of 4 output features
index = torch.tensor([0, 2], dtype=torch.long)

# dim=0 means we're pruning along the output dimension (rows of weight matrix)
dim = 0

ARGS = {
    "layer": layer,
    "index": index,
    "dim": dim,
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
read_exclusions Ran
ran on a synthesized input
chaoyuaw/lvu/src/utils/ava_eval_helper.py
code served (permissive licence) · get_code("66b0d97a822e992a")
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 set. 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 csv
import tempfile
import os

def make_image_key(video_id, timestamp):
    """Returns a unique identifier for a video id & timestamp."""
    return '%s,%04d' % (video_id, int(timestamp))

# Create a temporary CSV file with exclusion data
temp_dir = tempfile.mkdtemp()
exclusions_file_path = os.path.join(temp_dir, "exclusions.csv")

with open(exclusions_file_path, 'w', newline='') as f:
    writer = csv.writer(f)
    writer.writerow(['video_123', '0042'])
    writer.writerow(['video_456', '0100'])

ARGS = {
    'exclusions_file': exclusions_file_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 set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
soft_label_loss_sigmoid Ran
ran on a synthesized input
chaoyuaw/lvu/src/models/modeling_roberta.py
code served (permissive licence) · get_code("9547eabe3165408d")
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 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function expects:
# - preds: tensor with shape (..., dim) where dim in [80, 365, 8]
# - soft_labels: tensor with same shape as preds, containing values or -100 (ignore)
# - temperature: float scalar

# Create small tensors with dim=8 (one of the valid dimensions)
batch_size = 2
dim = 8

preds = torch.randn(batch_size, dim)
soft_labels = torch.randn(batch_size, dim)

# Set some values to -100 to test the ignore mask
soft_labels[0, 0] = -100

temperature = 0.5

ARGS = {
    "preds": preds,
    "soft_labels": soft_labels,
    "temperature": temperature,
}
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 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
soft_label_loss_softmax Ran
ran on a synthesized input
chaoyuaw/lvu/src/models/modeling_roberta.py
code served (permissive licence) · get_code("f8a333d6a2819774")
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 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# The function expects:
# - preds: a tensor that will be indexed and log_softmax'd along dim=1
# - soft_labels: a tensor with shape[0] == preds.shape[0], shape[-1] in [80, 365, 8, 81, 600]
# - temperature: a scalar (float or tensor)

# Create batch_size=2, with soft_labels having dim=80 (valid dimension)
batch_size = 2
num_classes = 80

# preds: shape (2, 80) - logits
preds = torch.randn(batch_size, num_classes)

# soft_labels: shape (2, 80) - soft probability targets
# Include some -100 values in the first column to test the ignore mask
soft_labels = torch.randn(batch_size, num_classes)
soft_labels[0, 0] = -100  # This will trigger the ignore mask for row 0

# temperature: scalar temperature for distillation
temperature = 3.0

ARGS = {
    'preds': preds,
    'soft_labels': soft_labels,
    'temperature': temperature
}
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 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
top_k_top_p_filtering Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chaoyuaw/lvu/src/models/modeling_utils.py
code served (permissive licence) · get_code("8e873fc150477bd1")
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; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:14:48Z. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small logits tensor: (batch_size=2, vocab_size=4)
logits = torch.randn(2, 4)

# Define ARGS dictionary with all parameters
ARGS = {
    "logits": logits,
    "top_k": 2,
    "top_p": 0.9,
    "filter_value": -float('Inf'),
    "min_tokens_to_keep": 1
}
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 — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
url_to_filename Ran
ran; our contract draft was wrong, not the code
chaoyuaw/lvu/src/models/file_utils.py
code served (permissive licence) · get_code("e827d94caab33f59")
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 str. 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.

from hashlib import sha256

ARGS = {
    "url": "https://example.com/model.weights",
    "etag": "abc123def456"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
read_csv Not yet run
unverified (harvested, no recorded run)
chaoyuaw/lvu/src/utils/ava_eval_helper.py
code served (permissive licence) · get_code("a49fc9f33754fd90")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 14 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 6 the same month, 13 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
get_pairs 258 other papers
11 dated earlier, 246 later, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
swish 206 other papers
69 dated earlier, 5 the same month, 129 later, 3 same year, order not determinable · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
gelu 198 other papers
77 dated earlier, 4 the same month, 113 later, 4 same year, order not determinable · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
prune_linear_layer 29 other papers
18 dated earlier, 1 the same month, 10 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.08230 (2019-06)
Evaluating Protein Transfer Learning with TAPE
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
and 26 more not named here
gelu_new 23 other papers
14 dated earlier, 1 the same month, 8 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
1911.03631 (2019-11)
Hierarchical Graph Network for Multi-hop Question Answering
and 20 more not named here
top_k_top_p_filtering 21 other papers
4 dated earlier, 1 the same month, 16 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
2009.06367 (2020-09)
GeDi: Generative Discriminator Guided Sequence Generation
and 18 more not named here
prune_conv1d_layer 16 other papers
10 dated earlier, 6 later
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1909.05311 (2019-09)
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
and 13 more not named here
url_to_filename 12 other papers
6 dated earlier, 6 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
and 9 more not named here
hf_bucket_url 8 other papers
5 dated earlier, 3 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
and 5 more not named here
is_remote_url 7 other papers
5 dated earlier, 2 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
and 4 more not named here
get_linear_schedule_with_warmup 6 other papers
1 dated earlier, 1 the same month, 4 later
2005.13837 (2020-05)
Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs
2106.13353 (2021-06)
Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models
2204.07275 (2022-04)
Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection
and 3 more not named here
get_constant_schedule_with_warmup 3 other papers
1 dated earlier, 2 later
2104.14757 (2021-04)
An Adversarial Transfer Network for Knowledge Representation Learning
2107.03444 (2021-07)
Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text
2204.07275 (2022-04)
Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection
get_constant_schedule 2 other papers
2 later
2107.03444 (2021-07)
Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text
2204.07275 (2022-04)
Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection
make_image_key 1 other paper
1 dated earlier
2006.07976 (2020-06)
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

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

Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In this paper, we study long-form video understanding. We introduce a framework for modeling long-form videos and develop evaluation protocols on large-scale datasets. We show that existing state-of-the-art short-term models are limited for long-form tasks. A novel object-centric transformer-based video recognition architecture performs significantly better on 7 diverse tasks. It also outperforms comparable state-of-the-art on the AVA dataset.

For agents

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

get_harvested_code_for_paper("2106.11310")
get_code_for_paper("2106.11310")
have("2106.11310")

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

curl https://syntology.ai/api/ran/2106.11310.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.11310.svg)](https://syntology.ai/paper/2106.11310)

Connect an agent — have() is free.