SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.04824 · 2026

SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models

Sergio Escalera, Kamal Nasrollahi, Oriol Rabasseda, Zenjie Li

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2601.04824.json · badge: /api/ran/2601.04824.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
oriol-rabasseda/sovabench canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
collect_video_paths Ran
ran; our contract draft was wrong, not the code
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/datasets/add_distractors.py
pointer only (licence: NONE) · get_code("3f2378caf5d2444f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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.

compute_iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/datasets/correct_overlapping.py
pointer only (licence: NONE) · get_code("98a9cd0eca34704b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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.

compute_iou_timespan Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/datasets/correct_overlapping.py
pointer only (licence: NONE) · get_code("e98c7132294b0e7e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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.

filter_non_overlapping_videos Ran
ran; our contract draft was wrong, not the code
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/datasets/add_distractors.py
pointer only (licence: NONE) · get_code("5e7a31a82cc21fd7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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_augmented_video_path Ran
ran; our contract draft was wrong, not the code
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/datasets/activity_augmentation.py
pointer only (licence: NONE) · get_code("dcbfb23dda297457")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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.

mean_average_precision Ran
ran, honoured the contract we drafted
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/evaluation/utils.py
pointer only (licence: NONE) · get_code("d9ad41829456c560")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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.

video_to_frames Ran
ran, honoured the contract we drafted
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/framework/utils.py
pointer only (licence: NONE) · get_code("5e89e7e0ffea4f62")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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.

filter_overlap Not yet run
unverified (harvested, no recorded run)
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/datasets/add_distractors.py
pointer only (licence: NONE) · get_code("d607e9b00f4c7816")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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. No invocation recorded.

generate_minicpm Not yet run
unverified (harvested, no recorded run)
oriol-rabasseda/sovabench/src/mllm_embeddings_sovabench/framework/mllm_pipeline.py
pointer only (licence: NONE) · get_code("9ef6232513ce7537")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oriol-rabasseda/sovabench 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. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Automatic identification of events and recurrent behavior analysis are critical for video surveillance. However, most existing content-based video retrieval benchmarks focus on scene-level similarity and do not evaluate the action discrimination required in surveillance. To address this gap, we introduce SOVABench (Surveillance Opposite Vehicle Actions Benchmark), a real-world retrieval benchmark built from surveillance footage and centered on vehiclerelated actions. SOVABench defines two evaluation protocols (inter-pair and intra-pair) to assess cross-action discrimination and temporal direction understanding. Although action distinctions are generally intuitive for human observers, our experiments show that they remain challenging for state-of-the-art vision and multimodal models. Leveraging the visual reasoning and instructionfollowing capabilities of Multimodal Large Language Models (MLLMs), we present a training-free framework for producing interpretable embeddings from MLLM-generated descriptions for both images and videos. The framework achieves strong performance on SOVABench as well as on several spatial and counting benchmarks where contrastive Vision-Language Models often fail. The code, annotations, and instructions to construct the benchmark are publicly available 1 .

For agents

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

get_harvested_code_for_paper("2601.04824")
get_code_for_paper("2601.04824")
have("2601.04824")

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

curl https://syntology.ai/api/ran/2601.04824.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.04824.svg)](https://syntology.ai/paper/2601.04824)

Connect an agent — have() is free.