SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.03071 · 2026

Boundary Optimization for Weakly Supervised Video Grounding

Daeho Um, Sunoh Kim, Kimin Yun

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 1 has no contract verdict; 3 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2602.03071.json · badge: /api/ran/2602.03071.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
sunoh-kim/gbo canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
cal_nll_loss Ran
ran on a synthesized input
sunoh-kim/gbo/gbocnm/models/loss.py
code served (permissive licence) · get_code("4e5b6a1ac60347a3")
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

torch.manual_seed(0)

# Small batch size: 2
# Sequence length: 3
# Number of classes: 4

batch_size = 2
seq_length = 3
num_classes = 4

# logit: shape (batch_size, seq_length, num_classes)
# Output of a model before softmax
logit = torch.randn(batch_size, seq_length, num_classes)

# idx: shape (batch_size, seq_length)
# Target class indices
idx = torch.randint(0, num_classes, (batch_size, seq_length))

# mask: shape (batch_size, seq_length)
# Binary mask for valid positions
mask = torch.ones(batch_size, seq_length)
mask[0, 2] = 0  # Mask out one position to test masking

# weights: optional, shape (batch_size, seq_length)
# Per-position weights
weights = torch.ones(batch_size, seq_length) * 0.5

ARGS = {
    "logit": logit,
    "idx": idx,
    "mask": mask,
    "weights": weights,
}
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
iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sunoh-kim/gbo/gbocnm/utils.py
code served (permissive licence) · get_code("fb1b1295bad022cb")
How it ran

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

import numpy as np

# Analyze the function:
# - pred: list of intervals (1D arrays with 2 elements each, or list of such lists)
# - gt: list of intervals (1D arrays with 2 elements each, or list of such lists)
# The function computes IoU (Intersection over Union) between predicted and ground truth intervals

# Test case 1: Single intervals (not wrapped in list)
pred_single = [0.0, 5.0]  # Single interval [start, end]
gt_single = [2.0, 7.0]    # Single interval [start, end]

# Test case 2: Multiple intervals (wrapped in list)
pred_multiple = [[0.0, 5.0], [1.0, 3.0]]  # Two intervals
gt_multiple = [[2.0, 7.0], [0.5, 2.5]]    # Two intervals

ARGS = {
    "pred": pred_multiple,  # List of intervals
    "gt": gt_multiple,      # List of intervals
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_json Ran
ran; our contract draft was wrong, not the code
sunoh-kim/gbo/gbocnm/utils.py
code served (permissive licence) · get_code("0d7ac1b9deeffa50")
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 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', encoding='utf8') as fw:
    json.dump(test_data, fw)

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
rec_loss Ran
ran; our contract draft was wrong, not the code
sunoh-kim/gbo/gbocnm/models/loss.py
code served (permissive licence) · get_code("50f4b905f100c6ea")
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, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Batch size = 2, sequence length = 3, vocabulary size = 4
bsz = 2
seq_len = 3
vocab_size = 4

# Create logits tensor: (batch_size, seq_len, vocab_size)
words_logit = torch.randn(bsz, seq_len, vocab_size)

# Create word indices: (batch_size, seq_len) with values in [0, vocab_size)
words_id = torch.randint(0, vocab_size, (bsz, seq_len))

# Create mask: (batch_size, seq_len) with 0s and 1s
words_mask = torch.ones(bsz, seq_len)
words_mask[0, 2] = 0  # mask out one position

# Create hard negative logits: (batch_size, seq_len, vocab_size)
hard_neg_words_logit = torch.randn(bsz, seq_len, vocab_size)

ARGS = {
    'words_logit': words_logit,
    'words_id': words_id,
    'words_mask': words_mask,
    'hard_neg_words_logit': hard_neg_words_logit,
}
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, ndim 1, dtype family float — a tuple 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
ivc_loss Not yet run
unverified (harvested, no recorded run)
sunoh-kim/gbo/gbocnm/models/loss.py
code served (permissive licence) · get_code("ea051b47b2e7bb3e")
How it ran

no invocation recorded.

main_loss_fn Not yet run
unverified (harvested, no recorded run)
sunoh-kim/gbo/gbopps/model/loss.py
code served (permissive licence) · get_code("ca30cf07c90f45aa")
How it ran

no invocation recorded.

sub_loss_fn Not yet run
unverified (harvested, no recorded run)
sunoh-kim/gbo/gbopps/model/loss.py
code served (permissive licence) · get_code("7ca187567f20bbd0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
cal_nll_loss 1 other paper
1 dated earlier
aaai_28059 (2024 (year only))
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding
main_loss_fn 1 other paper
1 dated earlier
aaai_28059 (2024 (year only))
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding
sub_loss_fn 1 other paper
1 dated earlier
aaai_28059 (2024 (year only))
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding

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

Weakly supervised temporal video grounding aims to localize query-relevant segments in untrimmed videos using only video-sentence pairs, without requiring ground-truth segment annotations that specify exact temporal boundaries. Recent approaches tackle this task by utilizing Gaussian-based temporal proposals to represent query-relevant segments. However, their inference strategies rely on heuristic mappings from Gaussian parameters to segment boundaries, resulting in suboptimal localization performance. To address this issue, we propose Gaussian Boundary Optimization (GBO), a novel inference framework that predicts segment boundaries by solving a principled optimization problem that balances proposal coverage and segment compactness. We derive a closed-form solution for this problem and rigorously analyze the optimality conditions under varying penalty regimes. Beyond its theoretical foundations, GBO offers several practical advantages: it is training-free and compatible with both single-Gaussian and mixture-based proposal architectures. Our experiments show that GBO significantly improves localization, achieving state-of-the-art results across standard benchmarks. Extensive experiments demonstrate the efficiency and generalizability of GBO across various proposal schemes. The code is available at https://github.com/sunoh-kim/gbo.

For agents

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

get_harvested_code_for_paper("2602.03071")
get_code_for_paper("2602.03071")
have("2602.03071")

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

curl https://syntology.ai/api/ran/2602.03071.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.03071.svg)](https://syntology.ai/paper/2602.03071)

Connect an agent — have() is free.