SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.05182 · 2023

CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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 0 have no contract verdict; 8 failures of our instrument; 0 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/2307.05182.json · badge: /api/ran/2307.05182.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
longbai1006/cat-vil canonical (classifier label)
classifier basis: plan_row
8 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; our contract draft was wrong, not the code
longbai1006/cat-vil/utils.py
code served (permissive licence) · get_code("53daad1d7b99fbdf")
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

torch.manual_seed(0)

# Construct small tensors for the function
batch_size = 2
num_classes = 4
k = 2

# scores: model predictions with shape (batch_size, num_classes)
scores = torch.randn(batch_size, num_classes)

# targets: true labels with shape (batch_size,)
targets = torch.randint(0, num_classes, (batch_size,))

ARGS = {
    "scores": scores,
    "targets": targets,
    "k": k,
}
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 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
calc_acc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
longbai1006/cat-vil/utils.py
code served (permissive licence) · get_code("19988d5d6c4a4d7c")
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
from sklearn.metrics import accuracy_score

torch.manual_seed(0)

# The function calc_acc takes y_true and y_pred and computes accuracy_score
# accuracy_score expects array-like inputs of class labels (integers or strings)
# and returns a float between 0 and 1

# Create ground truth labels (small batch of 2 samples with 3 classes: 0, 1, 2)
y_true = np.array([0, 1, 2, 1])

# Create predictions (same shape as y_true)
y_pred = np.array([0, 1, 1, 1])

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, 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
calc_classwise_acc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
longbai1006/cat-vil/utils.py
code served (permissive licence) · get_code("9fd07c1d7cd49c46")
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 1, dtype family float, shape (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 numpy as np
from sklearn.metrics import confusion_matrix

# Create simple ground truth and predictions
# Using 3 classes with 6 samples total
y_true = np.array([0, 1, 2, 0, 1, 2])
y_pred = np.array([0, 1, 2, 0, 1, 1])

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (3,) — shape (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
do_nms Ran
ran; our contract draft was wrong, not the code
longbai1006/cat-vil/dataset/feature_extraction/visual_bert/modeling_frcnn.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("e21bb85b8e1b4836")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

make_mask Ran
ran; our contract draft was wrong, not the code
longbai1006/cat-vil/models/CATViLEmbedding.py
pointer only (licence: MIT); the stored copy get_code serves, from MRUIL/WeakMCN, is pointer only (licence: NONE) · get_code("e766a0a3063c15d0")
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 MRUIL/WeakMCN, 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.

norm_box Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
longbai1006/cat-vil/dataset/feature_extraction/visual_bert/modeling_frcnn.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("cfa4887da544c990")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

pad_list_tensors Ran
ran; our contract draft was wrong, not the code
longbai1006/cat-vil/dataset/feature_extraction/visual_bert/modeling_frcnn.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("54a2fff601881b32")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

tryload Ran
ran; our contract draft was wrong, not the code
longbai1006/cat-vil/dataset/feature_extraction/visual_bert/extracting_data.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("77586e7080d66922")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 3 the same month, 8 later) and 0 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
do_nms 11 other papers
8 dated earlier, 2 later, 1 same year, order not determinable
2112.07566 (2021-12)
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
2203.02013 (2022-03)
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations
2204.03162 (2022-04)
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality
and 8 more not named here
pad_list_tensors 10 other papers
7 dated earlier, 2 later, 1 same year, order not determinable
2203.02013 (2022-03)
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations
2204.03162 (2022-04)
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality
2205.00363 (2022-05)
Visual Spatial Reasoning
and 7 more not named here
accuracy 8 other papers
3 dated earlier, 1 the same month, 4 later
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1606.02960 (2016-06)
Sequence-to-Sequence Learning as Beam-Search Optimization
2305.11692 (2023-05)
Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
and 5 more not named here
make_mask 7 other papers
3 dated earlier, 4 later
2004.06165 (2020-04)
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
2006.15955 (2020-06)
A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis
2305.14836 (2023-05)
NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario
and 4 more not named here
tryload 5 other papers
4 dated earlier, 1 later
2203.02013 (2022-03)
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations
2204.03162 (2022-04)
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality
2205.00363 (2022-05)
Visual Spatial Reasoning
and 2 more not named here
calc_acc 4 other papers
1 dated earlier, 1 the same month, 2 later
2305.11692 (2023-05)
Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
2307.12045 (2023-07)
Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery
2312.10251 (2023-12)
Advancing Surgical VQA with Scene Graph Knowledge
and 1 more not named here
calc_classwise_acc 4 other papers
1 dated earlier, 1 the same month, 2 later
2305.11692 (2023-05)
Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
2307.12045 (2023-07)
Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery
2312.10251 (2023-12)
Advancing Surgical VQA with Scene Graph Knowledge
and 1 more not named here
norm_box 4 other papers
3 dated earlier, 1 later
2112.07566 (2021-12)
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
2206.06522 (2022-06)
LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning
2305.11692 (2023-05)
Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
and 1 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

Medical students and junior surgeons often rely on senior surgeons and specialists to answer their questions when learning surgery. However, experts are often busy with clinical and academic work, and have little time to give guidance. Meanwhile, existing deep learning (DL)-based surgical Visual Question Answering (VQA) systems can only provide simple answers without the location of the answers. In addition, vision-language (ViL) embedding is still a less explored research in these kinds of tasks. Therefore, a surgical Visual Question Localized-Answering (VQLA) system would be helpful for medical students and junior surgeons to learn and understand from recorded surgical videos. We propose an end-to-end Transformer with the Co-Attention gaTed Vision-Language (CAT-ViL) embedding for VQLA in surgical scenarios, which does not require feature extraction through detection models. The CAT-ViL embedding module is designed to fuse multimodal features from visual and textual sources. The fused embedding will feed a standard Data-Efficient Image Transformer (DeiT) module, before the parallel classifier and detector for joint prediction. We conduct the experimental validation on public surgical videos from MICCAI EndoVis Challenge 2017 and 2018. The experimental results highlight the superior performance and robustness of our proposed model compared to the state-of-the-art approaches. Ablation studies further prove the outstanding performance of all the proposed components. The proposed method provides a promising solution for surgical scene understanding, and opens up a primary step in the Artificial Intelligence (AI)-based VQLA system for surgical training. Our code is publicly available.

For agents

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

get_harvested_code_for_paper("2307.05182")
get_code_for_paper("2307.05182")
have("2307.05182")

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

curl https://syntology.ai/api/ran/2307.05182.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.05182.svg)](https://syntology.ai/paper/2307.05182)

Connect an agent — have() is free.