SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.09099 · 2020

TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval

arXiv · PDF · Open in the Atlas

Code that ran

19 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; 4 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 7 failures of our instrument; 0 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/2001.09099.json · badge: /api/ran/2001.09099.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
jayleicn/TVCaption canonical (classifier label)
classifier basis: census
15 ran · 0 no recorded run
jayleicn/TVRetrieval canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
caption_collate Ran
ran on a synthesized input
jayleicn/TVCaption/baselines/multimodal_transformer/transformer/tvc_dataset.py
code served (permissive licence) · get_code("ff6297422c0e1b92")
How it ran

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

import torch
import torch.nn as nn
from torch.utils.data.dataloader import default_collate

torch.manual_seed(0)

# Create sample data structures that match what caption_collate expects
# batch is a list of tuples where each tuple is (model_inputs, batch_meta)

# Each model_inputs is a dict with keys that can have either list or tensor values
# Each batch_meta is metadata for that example

sample_model_inputs_1 = {
    'input_ids': torch.randint(0, 100, (2, 4)),
    'attention_mask': torch.ones(2, 4),
    'metadata_list': ['meta1_a', 'meta1_b'],
    'video_features': torch.randn(3, 4),
}

sample_batch_meta_1 = {'id': 'example_1', 'caption': 'a dog runs'}

sample_model_inputs_2 = {
    'input_ids': torch.randint(0, 100, (2, 4)),
    'attention_mask': torch.ones(2, 4),
    'metadata_list': ['meta2_a', 'meta2_b'],
    'video_features': torch.randn(3, 4),
}

sample_batch_meta_2 = {'id': 'example_2', 'caption': 'a cat sleeps'}

sample_model_inputs_3 = {
    'input_ids': torch.randint(0, 100, (2, 4)),
    'attention_mask': torch.ones(2, 4),
    'metadata_list': ['meta3_a', 'meta3_b'],
    'video_features': torch.randn(3, 4),
}

sample_batch_meta_3 = {'id': 'example_3', 'caption': 'a bird flies'}

# Create batch as list of (model_inputs, batch_meta) tuples
batch = [
    (sample_model_inputs_1, sample_batch_meta_1),
    (sample_model_inputs_2, sample_batch_meta_2),
    (sample_model_inputs_3, sample_batch_meta_3),
]

ARGS = {
    'batch': batch,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_temporal_iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jayleicn/TVRetrieval/utils/temporal_nms.py
code served (permissive licence) · get_code("ea2ba2c075c6b18b")
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 torch
import numpy as np

torch.manual_seed(0)

# Based on the function signature and body:
# pred: [st (float), ed (float)] - a list/array with 2 floats representing start and end times
# gt: [st (float), ed (float)] - a list/array with 2 floats representing ground truth start and end times

# The function accesses pred[0], pred[1], gt[0], gt[1] and performs comparisons/arithmetic
# It expects numeric types that support min(), max(), and subtraction

ARGS = {
    "pred": [1.5, 4.2],
    "gt": [2.0, 5.0]
}
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 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
count_parameters Ran
ran, honoured the contract we drafted
jayleicn/TVCaption/baselines/multimodal_transformer/local_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Zhuo-Cao/QV-M2, is pointer only (licence: NONE) · get_code("edb929dece68582e")
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 Zhuo-Cao/QV-M2, 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.

flat_list_of_lists Ran
ran, honoured the contract we drafted
jayleicn/TVCaption/baselines/multimodal_transformer/local_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from nangongningyi/gume, is pointer only (licence: NONE) · get_code("cef10190a6f8f7e9")
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 nangongningyi/gume, 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 Ran
ran, honoured the contract we drafted
jayleicn/TVCaption/baselines/multimodal_transformer/transformer/model.py
code served (permissive licence) · get_code("69e3a274f98c15af")
How it ran

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

import math
import torch

torch.manual_seed(0)

# The gelu function takes a single parameter 'x' which should be a tensor
# The function applies element-wise operations: multiplication, addition, division, erf
# So x should be a torch tensor of any shape

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
length_penalty_builder Ran
ran on a synthesized input
jayleicn/TVCaption/baselines/multimodal_transformer/transformer/decode_strategy.py
code served (permissive licence) · get_code("07940cb25a48bfc4")
How it ran

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

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'length_penalty_name': 'none'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_glove Ran
ran on a synthesized input
jayleicn/TVCaption/baselines/multimodal_transformer/build_vocab.py
code served (permissive licence) · get_code("a81aaf990607f138")
How it ran

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

import tempfile
import os

# Create a temporary GloVe format file
temp_dir = tempfile.mkdtemp()
glove_file = os.path.join(temp_dir, "glove.txt")

# Write sample GloVe format data
with open(glove_file, 'w') as f:
    f.write("hello 0.1 0.2 0.3 0.4\n")
    f.write("world 0.5 0.6 0.7 0.8\n")
    f.write("test 0.9 1.0 1.1 1.2\n")

ARGS = {
    "filename": glove_file
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_json Ran
ran; our contract draft was wrong, not the code
jayleicn/TVCaption/utils/basic_utils.py
code served (permissive licence) · get_code("2d946250dd2f5a4f")
How it ran

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

import json
import tempfile
import os

# Create a temporary JSON file to load
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.json")

# Write a valid JSON file
test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(temp_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "filename": temp_file
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_json Ran
ran; our contract draft was wrong, not the code
jayleicn/TVCaption/baselines/multimodal_transformer/local_utils.py
code served (permissive licence) · get_code("53d425eb1278ddda")
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 dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import json
import tempfile
import os

# Create a temporary JSON file with valid content
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.json")

test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(temp_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "file_path": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_jsonl Ran
ran; our contract draft was wrong, not the code
jayleicn/TVCaption/standalone_eval/evaluate.py
code served (permissive licence) · get_code("f1d1cccccf038785")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family 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 json
import tempfile
import os

# Create a temporary JSONL file with valid data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.jsonl")

# Write sample JSONL data
with open(temp_file, 'w') as f:
    f.write(json.dumps({"key": "value1", "number": 1}) + "\n")
    f.write(json.dumps({"key": "value2", "number": 2}) + "\n")
    f.write(json.dumps({"key": "value3", "number": 3}) + "\n")

ARGS = {
    "filename": temp_file
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_pickle Ran
ran; our contract draft was wrong, not the code
jayleicn/TVCaption/utils/basic_utils.py
code served (permissive licence) · get_code("570ad34bd1af44a8")
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 dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pickle
import tempfile
import os

# Create a temporary file with pickled data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.pkl")

# Create some sample data to pickle
sample_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "dict"}
}

# Write the pickled data to the temporary file
with open(temp_file, 'wb') as f:
    pickle.dump(sample_data, f)

ARGS = {
    "filename": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mask_logits Ran
ran, honoured the contract we drafted
jayleicn/TVRetrieval/baselines/crossmodal_moment_localization/model_xml.py
pointer only (licence: MIT); the stored copy get_code serves, from songpipi/amdnet, is pointer only (licence: NONE) · get_code("1c17153fb5488283")
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 songpipi/amdnet, 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.

pool_across_time Ran
ran on a synthesized input
jayleicn/TVRetrieval/utils/model_utils.py
code served (permissive licence) · get_code("286f821a3988fcbe")
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)

# Create valid arguments for pool_across_time
B = 2  # batch size
T = 5  # time dimension
D = 4  # feature dimension

# outputs: (B, T, D) - RNN outputs
outputs = torch.randn(B, T, D)

# lengths: (B,) - actual lengths for each sequence in batch
lengths = torch.tensor([3, 4], dtype=torch.long)

# pool_type: str - either 'max' or 'mean'
pool_type = 'max'

ARGS = {
    'outputs': outputs,
    'lengths': lengths,
    'pool_type': pool_type
}
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
prepare_batch_inputs Ran
ran on a synthesized input
jayleicn/TVCaption/baselines/multimodal_transformer/transformer/tvc_dataset.py
code served (permissive licence) · get_code("bff9917618d44658")
How it ran

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

import torch

torch.manual_seed(0)

# Create a batch dictionary with mixed tensor and non-tensor values
batch = {
    "input_ids": torch.randint(0, 100, (2, 4)),
    "attention_mask": torch.ones((2, 4)),
    "token_type_ids": torch.zeros((2, 4)),
    "labels": torch.randint(0, 10, (2,)),
    "sample_id": "sample_123",
    "metadata": {"source": "test"}
}

device = "cpu"
non_blocking = False

ARGS = {
    "batch": batch,
    "device": device,
    "non_blocking": non_blocking
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
remove_nonascii Ran
ran; our contract draft was wrong, not the code
jayleicn/TVCaption/standalone_eval/evaluate.py
code served (permissive licence) · get_code("a45f62024eb3d2c5")
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

torch.manual_seed(0)

# The function remove_nonascii takes a text parameter (string)
# and filters out non-ASCII characters, replacing them with spaces
# It iterates through each character and checks if ord(i) < 128

ARGS = {
    "text": "Hello World! Café naïve 你好 Москва"
}
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
sort_res Ran
ran on a synthesized input
jayleicn/TVCaption/baselines/multimodal_transformer/translate.py
code served (permissive licence) · get_code("712ae5d2ea349b4d")
How it ran

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

import torch

# Construct a valid res_dict for the sort_res function
# The function expects:
# - res_dict: a dict where values are lists of items
# - Each item in the lists must have a 'timestamp' key
# - The 'timestamp' value should be indexable (x['timestamp'][0])

res_dict = {
    'category_1': [
        {'timestamp': ['3.5'], 'data': 'item1'},
        {'timestamp': ['1.2'], 'data': 'item2'},
        {'timestamp': ['2.8'], 'data': 'item3'},
    ],
    'category_2': [
        {'timestamp': ['5.1'], 'data': 'item4'},
        {'timestamp': ['4.3'], 'data': 'item5'},
    ],
    'category_3': [
        {'timestamp': ['0.9'], 'data': 'item6'},
    ],
}

ARGS = {
    'res_dict': res_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
step_collate Ran
ran on a synthesized input
jayleicn/TVCaption/baselines/multimodal_transformer/transformer/tvc_dataset.py
code served (permissive licence) · get_code("c1ba877d826f25af")
How it ran

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

import torch
import torch.nn as nn
from torch.utils.data.dataloader import default_collate

torch.manual_seed(0)

# Create a padded_batch_step: a list of dicts
# Each dict represents one example's data for a particular step
# The function iterates over these dicts and collates values

# Create sample data structures
dict1 = {
    "text": "hello world",
    "embedding": torch.randn(4),
    "ids": [1, 2, 3],
    "score": torch.tensor(0.5)
}

dict2 = {
    "text": "foo bar",
    "embedding": torch.randn(4),
    "ids": [4, 5, 6],
    "score": torch.tensor(0.7)
}

dict3 = {
    "text": "test case",
    "embedding": torch.randn(4),
    "ids": [7, 8, 9],
    "score": torch.tensor(0.3)
}

# padded_batch_step is a list of dicts
padded_batch_step = [dict1, dict2, dict3]

ARGS = {
    "padded_batch_step": padded_batch_step
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
temporal_non_maximum_suppression Ran
ran on a synthesized input
jayleicn/TVRetrieval/utils/temporal_nms.py
code served (permissive licence) · get_code("d235ed6d33e43a98")
How it ran

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

# Set random seed for reproducibility
torch.manual_seed(0)

# Define the arguments for temporal_non_maximum_suppression
# predictions: list of sublists, each sublist is [st (float), ed (float), score (float)]
predictions = [
    [1.0, 5.0, 0.9],      # start=1.0, end=5.0, score=0.9
    [2.0, 6.0, 0.8],      # start=2.0, end=6.0, score=0.8
    [10.0, 15.0, 0.85],   # start=10.0, end=15.0, score=0.85
    [11.0, 16.0, 0.7],    # start=11.0, end=16.0, score=0.7
    [20.0, 25.0, 0.75],   # start=20.0, end=25.0, score=0.75
]

nms_threshold = 0.5

max_after_nms = 100

ARGS = {
    "predictions": predictions,
    "nms_threshold": nms_threshold,
    "max_after_nms": max_after_nms,
}
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 list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
tile Ran
ran; our contract draft was wrong, not the code
jayleicn/TVCaption/baselines/multimodal_transformer/translator.py
code served (permissive licence) · get_code("69b8b31e44791260")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 12, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor with distinct dimensions for probing
x = torch.randn(2, 4, 3)  # batch=2, feature_dim=4, spatial_dim=3

# Test with different count and dim values
count = 3
dim = 1

ARGS = {
    "x": x,
    "count": count,
    "dim": dim,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 12, 3) — shape (2, 12, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

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, 13 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 1 the same month, 13 later) and 6 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
gelu 198 other papers
34 dated earlier, 1 the same month, 161 later, 2 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
mask_logits 13 other papers
1 dated earlier, 12 later · 1 only as an assembly brick
1904.11574 (2019-04)
TVQA+: Spatio-Temporal Grounding for Video Question Answering
2005.06409 (2020-05)
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA
2105.06247 (2021-05)
Video Corpus Moment Retrieval with Contrastive Learning
and 10 more not named here
count_parameters 11 other papers
11 later
2105.06247 (2021-05)
Video Corpus Moment Retrieval with Contrastive Learning
2207.00383 (2022-07)
ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022
2301.00746 (2023-01)
NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory
and 8 more not named here
load_json 11 other papers
2 dated earlier, 9 later
1809.01696 (2018-09)
TVQA: Localized, Compositional Video Question Answering
1904.11574 (2019-04)
TVQA+: Spatio-Temporal Grounding for Video Question Answering
2023.findings-emnlp.644 (2023 (year only))
VIP5: Towards Multimodal Foundation Models for Recommendation
and 8 more not named here
load_pickle 10 other papers
10 later
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2023.findings-emnlp.644 (2023 (year only))
VIP5: Towards Multimodal Foundation Models for Recommendation
2305.14302 (2023-05)
VIP5: Towards Multimodal Foundation Models for Recommendation
and 7 more not named here
load_jsonl 8 other papers
8 later
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2022.findings-emnlp.24 (2022 (year only))
AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant
Lin_SwinBERT_End-to-End_Transformers_With_Sparse_Attention_for_Video_Captioning_CVPR_2022_paper (2022 (year only))
SWINBERT: End-to-End Transformers with Sparse Attention for Video Captioning
and 5 more not named here
tile 8 other papers
2 dated earlier, 6 later
1905.13164 (2019-05)
Hierarchical Transformers for Multi-Document Summarization
1906.10508 (2019-06)
Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations
2010.10392 (2020-10)
CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters
and 5 more not named here
load_json 6 other papers
6 later
2010.00515 (2020-10)
Linguistic Structure Guided Context Modeling for Referring Image Segmentation
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2212.03191 (2022-12)
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
and 3 more not named here
compute_temporal_iou 5 other papers
1 dated earlier, 4 later
1904.11574 (2019-04)
TVQA+: Spatio-Temporal Grounding for Video Question Answering
2105.06247 (2021-05)
Video Corpus Moment Retrieval with Contrastive Learning
2306.15255 (2023-06)
GroundNLQ @ Ego4D Natural Language Queries Challenge 2023
and 2 more not named here
remove_nonascii 4 other papers
4 later
2303.06378 (2023-03)
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
2403.17935 (2024-03)
OmniViD: A Generative Framework for Universal Video Understanding
2405.13382 (2024-05)
VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding
and 1 more not named here
flat_list_of_lists 3 other papers
1 dated earlier, 2 later
1904.11574 (2019-04)
TVQA+: Spatio-Temporal Grounding for Video Question Answering
2401.01529 (2024-01)
Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
2407.12338 (2024-07)
GUME: Graphs and User Modalities Enhancement for Long-Tail Multimodal Recommendation
pool_across_time 1 other paper
1 later
2105.06247 (2021-05)
Video Corpus Moment Retrieval with Contrastive Learning
temporal_non_maximum_suppression 1 other paper
1 later
2105.06247 (2021-05)
Video Corpus Moment Retrieval with Contrastive Learning

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

We introduce TV show Retrieval (TVR), a new multimodal retrieval dataset. TVR requires systems to understand both videos and their associated subtitle (dialogue) texts, making it more realistic. The dataset contains 109K queries collected on 21.8K videos from 6 TV shows of diverse genres, where each query is associated with a tight temporal window. The queries are also labeled with query types that indicate whether each of them is more related to video or subtitle or both, allowing for in-depth analysis of the dataset and the methods that built on top of it. Strict qualification and post-annotation verification tests are applied to ensure the quality of the collected data. Further, we present several baselines and a novel Cross-modal Moment Localization (XML ) network for multimodal moment retrieval tasks. The proposed XML model uses a late fusion design with a novel Convolutional Start-End detector (ConvSE), surpassing baselines by a large margin and with better efficiency, providing a strong starting point for future work. We have also collected additional descriptions for each annotated moment in TVR to form a new multimodal captioning dataset with 262K captions, named TV show Caption (TVC). Both datasets are publicly available. TVR: https://tvr.cs.unc.edu, TVC: https://tvr.cs.unc.edu/tvc.html.

For agents

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

get_harvested_code_for_paper("2001.09099")
get_code_for_paper("2001.09099")
have("2001.09099")

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

curl https://syntology.ai/api/ran/2001.09099.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.09099.svg)](https://syntology.ai/paper/2001.09099)

Connect an agent — have() is free.