SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.00325 · 2020

Uncovering Hidden Challenges in Query-Based Video Moment Retrieval

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2009.00325.json · badge: /api/ran/2009.00325.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
mayu-ot/hidden-challenges-MR community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
ActivityNetCap2Instances Ran
ran on a synthesized input
mayu-ot/hidden-challenges-MR/src/toolbox/data_converters.py
code served (permissive licence) · get_code("d38491f87e0ce7a9")
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. 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
from typing import Tuple, List, Dict

Query = Tuple[str, str]
Location = Tuple[float, float, float]
Instance = Tuple[Query, Location]

# Construct raw_data dictionary matching the function's expected structure
raw_data = {
    "video_001": {
        "sentences": ["A person is walking down the street", "The person stops at a corner"],
        "timestamps": [[0.5, 2.3], [2.3, 5.1]],
        "duration": 10.5
    },
    "video_002": {
        "sentences": ["A car drives by", "The car turns left"],
        "timestamps": [[1.2, 3.4], [3.4, 6.7]],
        "duration": 8.9
    }
}

ARGS = {
    "raw_data": raw_data
}
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 — a list 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
CharadesSTA2Instances Ran
ran on a synthesized input
mayu-ot/hidden-challenges-MR/src/toolbox/data_converters.py
code served (permissive licence) · get_code("45c768f3cb355e85")
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. 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 pandas as pd
from typing import Tuple, List

Query = Tuple[str, str]
Location = Tuple[float, float, float]
Instance = Tuple[Query, Location]

# Create a small valid DataFrame with the required columns
raw_data = pd.DataFrame({
    'id': ['video_001', 'video_002'],
    'description': ['person walking in the park', 'dog running on beach'],
    'start (sec)': [1.5, 3.2],
    'end (sec)': [5.7, 8.1],
    'length': [4.2, 4.9]
})

ARGS = {
    'raw_data': raw_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
plot_performance_per_class Ran
ran on a synthesized input
mayu-ot/hidden-challenges-MR/src/toolbox/visualization.py
code served (permissive licence) · get_code("772d8fa3a2566b57")
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 Figure. 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 numpy as np
import matplotlib.pyplot as plt
from typing import List, Tuple, Dict

Query = Tuple[str, str]
Location = Tuple[float, float, float]
Rating = List[float]
Metrics = Dict[str, float]
Result = Tuple[Query, List[Location], Rating, Metrics]

# Build sample data for metrics_per_cls
# The function expects a dict where keys are class names (strings)
# and values are dicts with 'rate_success', 'n_success', and 'n_instance' keys

metrics_per_cls = {
    "class_a": {
        "rate_success": 0.85,
        "n_success": 17,
        "n_instance": 20
    },
    "class_b": {
        "rate_success": 0.70,
        "n_success": 14,
        "n_instance": 20
    },
    "class_c": {
        "rate_success": 0.95,
        "n_success": 19,
        "n_instance": 20
    },
    "class_d": {
        "rate_success": 0.60,
        "n_success": 12,
        "n_instance": 20
    }
}

ARGS = {
    "metrics_per_cls": metrics_per_cls
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, seaborn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
predict Not yet run
unverified (harvested, no recorded run)
mayu-ot/hidden-challenges-MR/src/toolbox/baseline.py
code served (permissive licence) · get_code("6c74cb414063c07d")
How it ran

no invocation recorded.

predict_job Not yet run
unverified (harvested, no recorded run)
mayu-ot/hidden-challenges-MR/src/toolbox/baseline.py
code served (permissive licence) · get_code("41036504a8a51d5b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

The query-based moment retrieval is a problem of localising a specific clip from an untrimmed video according a query sentence. This is a challenging task that requires interpretation of both the natural language query and the video content. Like in many other areas in computer vision and machine learning, the progress in query-based moment retrieval is heavily driven by the benchmark datasets and, therefore, their quality has significant impact on the field. In this paper, we present a series of experiments assessing how well the benchmark results reflect the true progress in solving the moment retrieval task. Our results indicate substantial biases in the popular datasets and unexpected behaviour of the state-of-the-art models. Moreover, we present new sanity check experiments and approaches for visualising the results. Finally, we suggest possible directions to improve the temporal sentence grounding in the future. Our code for this paper is available at https://mayu-ot.github.io/hidden-challenges-MR .

For agents

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

get_harvested_code_for_paper("2009.00325")
get_code_for_paper("2009.00325")
have("2009.00325")

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

curl https://syntology.ai/api/ran/2009.00325.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.00325.svg)](https://syntology.ai/paper/2009.00325)

Connect an agent — have() is free.