SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.08714 · ECCV · 2022

Selective Query-guided Debiasing for Video Corpus Moment Retrieval

Chang Yoo, Hee Yoon, Eunseop Yoon, Sunjae Yoon, Dahyun Kim, Ji Hong, Junyeong Kim

arXiv · PDF · Open in the Atlas

Code that ran

6 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 18 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2210.08714.json · badge: /api/ran/2210.08714.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
dbstjswo505/SQuiDNet marked official in Papers with Code
Papers with Code archive
6 ran · 18 no recorded run
FunctionStatusWhere it lives
BertIntermediate Ran
ran on a synthesized input · constructed an object; no result was computed
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("b25762789d877739")
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, BertIntermediate: 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 math

torch.manual_seed(0)

# Define activation functions (copied from the function)
def gelu(x):
    return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))

def gelu_new(x):
    return 0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3))))

def swish(x):
    return x * torch.sigmoid(x)

ACT2FN = {'gelu': gelu, 'relu': torch.nn.functional.relu, 'swish': swish, 'gelu_new': gelu_new}

# Define a minimal config class
class Config:
    def __init__(self, hidden_size, intermediate_size, hidden_act):
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.hidden_act = hidden_act

# Create a config instance
config = Config(hidden_size=4, intermediate_size=3, hidden_act='gelu')

ARGS = {
    'config': config
}
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 BertIntermediate — 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 BertIntermediate 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
Conv1D Ran
ran on a synthesized input · constructed an object; no result was computed
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("7d0cf4490a5473d2")
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, Conv1D: 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)

# Create a minimal config class with the required conv_cfg_1 and conv_cfg_2
class Config:
    def __init__(self):
        # Conv1d expects: in_channels, out_channels, kernel_size
        self.conv_cfg_1 = {
            'in_channels': 4,
            'out_channels': 8,
            'kernel_size': 3,
            'padding': 1
        }
        self.conv_cfg_2 = {
            'in_channels': 8,
            'out_channels': 1,
            'kernel_size': 3,
            'padding': 1
        }

config = Config()

ARGS = {
    'config': config
}
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 — 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 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
gelu Ran
ran, honoured the contract we drafted
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("29af270e862dd867")
How it ran

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

import torch
import math

torch.manual_seed(0)

# The gelu function takes a single parameter 'x' which should be a tensor
# The function performs mathematical operations on it: division, erf, addition, multiplication
# So x should be a torch tensor with numeric values

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
gelu_new Ran
ran, honoured the contract we drafted
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("de48fec0ec9764b0")
How it ran

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

import torch
import math

torch.manual_seed(0)

# The function gelu_new takes a single parameter x which is used in:
# - Arithmetic operations (*, +)
# - torch.tanh()
# - torch.pow()
# This means x should be a tensor that supports these operations

# Create a small tensor for x
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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
mask_logits Ran
ran, honoured the contract we drafted
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("e47b0e22eeee3414")
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)

# target: a tensor that will be multiplied element-wise with mask
# mask: a binary tensor (0s and 1s) used to filter logits
target = torch.randn(2, 4)
mask = torch.randint(0, 2, (2, 4)).float()

ARGS = {
    "target": target,
    "mask": mask,
}
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
prune_linear_layer Ran
ran; our contract draft was wrong, not the code
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("409d011257a2b23b")
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 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
import torch.nn as nn

torch.manual_seed(0)

# Create a linear layer to prune
# Input features: 3, Output features: 4
layer = nn.Linear(3, 4, bias=True)

# Create index tensor to select which outputs to keep
# We'll keep indices 0 and 2 (pruning to 2 outputs from 4)
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, 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 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
BertAttention Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("28e6bf1ccec147fb")
How it ran

no invocation recorded.

BertEmbeddings Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("c7064aca92e2f1ef")
How it ran

no invocation recorded.

BertEncoder Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("3c05ca4aa7639bb1")
How it ran

no invocation recorded.

BertLayer Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("120803f3f1246391")
How it ran

no invocation recorded.

BertOutput Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("e1d8bf9abfe29c23")
How it ran

no invocation recorded.

BertSelfAttention Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("57400b456ed52f49")
How it ran

no invocation recorded.

BertSelfOutput Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("cd8f5862f19a2eb6")
How it ran

no invocation recorded.

ConditionalMomentPrediction Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("4e2f1db051fa5268")
How it ran

no invocation recorded.

Encoder Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("0d5e500a3651af20")
How it ran

no invocation recorded.

JointSpaceEmbedding Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("068a9be6451e342a")
How it ran

no invocation recorded.

LinearLayer Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("816eb98da721aba8")
How it ran

no invocation recorded.

MMA Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("acc344e581194643")
How it ran

no invocation recorded.

NVLDModel Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("9fc385888fc431fb")
How it ran

no invocation recorded.

NetVLAD Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("422ff6dfa461b96d")
How it ran

no invocation recorded.

SQuiDNet Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("4bdff0f91d9a99a3")
How it ran

no invocation recorded.

TransformerBaseModel Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("12a6b23359e1c4fe")
How it ran

no invocation recorded.

VQMMApool Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("9ab0d260dbff2e15")
How it ran

no invocation recorded.

VSMMApool Not yet run
unverified (harvested, no recorded run)
dbstjswo505/SQuiDNet/model/squidnet.py
code served (permissive licence) · get_code("2fea40d79306b9d4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 6 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
gelu
brick of this paper's assembly: helper
198 other papers
118 dated earlier, 4 the same month, 72 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
brick of this paper's assembly: helper
29 other papers
22 dated earlier, 7 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
brick of this paper's assembly: helper
23 other papers
18 dated earlier, 5 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
BertOutput
brick of this paper's assembly: helper
12 other papers
4 dated earlier, 1 the same month, 7 later · 8 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2005.05402 (2020-05)
MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning
2110.13309 (2021-10)
History Aware Multimodal Transformer for Vision-and-Language Navigation
and 9 more not named here
BertSelfOutput
brick of this paper's assembly: helper
12 other papers
4 dated earlier, 1 the same month, 7 later · 8 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2005.05402 (2020-05)
MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning
2110.13309 (2021-10)
History Aware Multimodal Transformer for Vision-and-Language Navigation
and 9 more not named here
BertIntermediate
brick of this paper's assembly: helper
8 other papers
2 dated earlier, 6 later · 4 only as an assembly brick
2106.14019 (2021-06)
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
2110.13309 (2021-10)
History Aware Multimodal Transformer for Vision-and-Language Navigation
2303.08409 (2023-03)
LANA: A Language-Capable Navigator for Instruction Following and Generation
and 5 more not named here

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

Video moment retrieval (VMR) aims to localize target moments in untrimmed videos pertinent to a given textual query. Existing retrieval systems tend to rely on retrieval bias as a shortcut and thus, fail to sufficiently learn multi-modal interactions between query and video. This retrieval bias stems from learning frequent co-occurrence patterns between query and moments, which spuriously correlate objects (e.g., a pencil) referred in the query with moments (e.g., scene of writing with a pencil) where the objects frequently appear in the video, such that they converge into biased moment predictions. Although recent debiasing methods have focused on removing this retrieval bias, we argue that these biased predictions sometimes should be preserved because there are many queries where biased predictions are rather helpful. To conjugate this retrieval bias, we propose a Selective Query-guided Debiasing network (SQuiDNet), which incorporates the following two main properties: (1) Biased Moment Retrieval that intentionally uncovers the biased moments inherent in objects of the query and (2) Selective Query-guided Debiasing that performs selective debiasing guided by the meaning of the query. Our experimental results on three moment retrieval benchmarks (i.e., TVR, ActivityNet, DiDeMo) show the effectiveness of SQuiDNet and qualitative analysis shows improved interpretability.

For agents

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

get_harvested_code_for_paper("2210.08714")
get_code_for_paper("2210.08714")
have("2210.08714")

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

curl https://syntology.ai/api/ran/2210.08714.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.08714.svg)](https://syntology.ai/paper/2210.08714)

Connect an agent — have() is free.