SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.11174 · 2024

Pixel-Wise Recognition for Holistic Surgical Scene Understanding

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 8 failures of our instrument; 3 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/2401.11174.json · badge: /api/ran/2401.11174.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
bcv-uniandes/grasp canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
bcv-uniandes/tapir canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
bcv-uniandes/matis canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
cal_rel_pos_spatial Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bcv-uniandes/grasp/TAPIS/tapis/models/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("156d0bf08e703f3c")
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 rajatmodi62/OccludedActionBenchmark, 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.

compute_weighted_loss Ran
ran, violated the contract we drafted
bcv-uniandes/grasp/TAPIS/tapis/models/losses.py
code served (permissive licence) · get_code("e1053815b1f94169")
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 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

torch.manual_seed(0)

# The function takes:
# 1. losses: an iterable of loss values (likely tensors or floats)
# 2. weight_vector: an indexable collection of weights

# Create small loss tensors
loss1 = torch.tensor(0.5)
loss2 = torch.tensor(0.3)
loss3 = torch.tensor(0.2)
losses = [loss1, loss2, loss3]

# Create weight vector (as a list or tensor)
weight_vector = [0.4, 0.3, 0.3]

ARGS = {
    "losses": losses,
    "weight_vector": weight_vector
}
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 Tensor, 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
construct_optimizer Ran
ran; our contract draft was wrong, not the code
bcv-uniandes/tapir/slowfast/models/optimizer.py
code served (permissive licence) · get_code("d97bc90017599f32")
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 SGD. 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 simple model with batch norm, regular parameters, and bias terms
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 4, kernel_size=3)
        self.bn1 = nn.BatchNorm2d(4)
        self.linear = nn.Linear(4, 2)
        self.bn2 = nn.BatchNorm1d(2)
        
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = x.view(x.size(0), -1)
        x = self.linear(x)
        x = self.bn2(x)
        return x

model = SimpleModel()

# Create a config object with all required attributes
class Config:
    def __init__(self):
        self.NUM_GPUS = 1
        self.BN = BNConfig()
        self.SOLVER = SolverConfig()
        self.MODEL = ModelConfig()

class BNConfig:
    def __init__(self):
        self.WEIGHT_DECAY = 0.0001

class SolverConfig:
    def __init__(self):
        self.OPTIMIZING_METHOD = 'sgd'
        self.BASE_LR = 0.01
        self.MOMENTUM = 0.9
        self.WEIGHT_DECAY = 0.0005
        self.DAMPENING = 0.0
        self.NESTEROV = True
        self.ZERO_WD_1D_PARAM = True

class ModelConfig:
    def __init__(self):
        self.MODEL_NAME = 'ResNet'

cfg = Config()

ARGS = {
    'model': model,
    'cfg': cfg
}
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 SGD — a SGD output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SGD 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
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bcv-uniandes/grasp/TAPIS/tapis/models/common.py
pointer only (licence: MIT); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("bcc1cdae3bb3212c")
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 rajatmodi62/OccludedActionBenchmark, 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.

eval_epoch Ran
ran; our contract draft was wrong, not the code
bcv-uniandes/matis/tools/train_net.py
pointer only (licence: NONE) · get_code("e1aeddec06db2326")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bcv-uniandes/matis 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_loss_func Ran
ran; our contract draft was wrong, not the code
bcv-uniandes/grasp/TAPIS/tapis/models/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from Wenhao-Chi/UNIEGO, is pointer only (licence: NOASSERTION) · get_code("c90b5f606f54d4f7")
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 Wenhao-Chi/UNIEGO, and GitHub could not classify the licence of that repository (NOASSERTION). 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_loss_func Ran
ran; our contract draft was wrong, not the code
bcv-uniandes/tapir/slowfast/models/losses.py
code served (permissive licence) · get_code("aaac7c46cd146e47")
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 type. 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 torch.nn.functional as F

class SoftTargetCrossEntropy(nn.Module):
    """
    Cross entropy loss with soft target.
    """

    def __init__(self, reduction='mean'):
        """
        Args:
            reduction (str): specifies reduction to apply to the output. It can be
                "mean" (default) or "none".
        """
        super(SoftTargetCrossEntropy, self).__init__()
        self.reduction = reduction

    def forward(self, x, y):
        y = F.one_hot(y, num_classes=x.shape[-1])
        loss = torch.sum(-y * F.log_softmax(x, dim=-1), dim=-1)
        if self.reduction == 'mean':
            return loss.mean()
        elif self.reduction == 'none':
            return loss
        else:
            raise NotImplementedError

_LOSSES = {'cross_entropy': nn.CrossEntropyLoss, 'bce': nn.BCELoss, 'bce_logit': nn.BCEWithLogitsLoss, 'soft_cross_entropy': SoftTargetCrossEntropy}

def get_loss_func(loss_name):
    """
    Retrieve the loss given the loss name.
    Args (int):
        loss_name: the name of the loss to use.
    """
    if loss_name not in _LOSSES.keys():
        raise NotImplementedError('Loss {} is not supported'.format(loss_name))
    return _LOSSES[loss_name]

torch.manual_seed(0)

ARGS = {
    'loss_name': 'cross_entropy'
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
get_loss_type Ran
ran; our contract draft was wrong, not the code
bcv-uniandes/grasp/TAPIS/tapis/models/losses.py
code served (permissive licence) · get_code("cdefb159d0ccbc07")
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 dtype. 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

torch.manual_seed(0)

ARGS = {
    'loss_name': 'cross_entropy',
    'presicion': 32
}
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 dtype — a dtype output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dtype 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
get_rel_pos Ran
ran; our contract draft was wrong, not the code
bcv-uniandes/grasp/TAPIS/tapis/models/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("5fc6c9c916e0ebc7")
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 rajatmodi62/OccludedActionBenchmark, 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.

normalize_bbox Ran
ran, honoured the contract we drafted
bcv-uniandes/tapir/slowfast/evaluate/convert_coco_anns_to_our_method.py
code served (permissive licence) · get_code("829565bab809c0f8")
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

torch.manual_seed(0)

# The function normalize_bbox takes 6 parameters:
# x1, y1, w, h: bounding box coordinates and dimensions
# im_w, im_h: image width and height
# All are used in arithmetic operations to normalize bbox coordinates

ARGS = {
    "x1": 10,
    "y1": 20,
    "w": 50,
    "h": 40,
    "im_w": 640,
    "im_h": 480,
}
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
attention_pool Not yet run
unverified (harvested, no recorded run)
bcv-uniandes/tapir/slowfast/models/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("a4723eab8df61dbe")
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 rajatmodi62/OccludedActionBenchmark, 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. No invocation recorded.

attention_pool Not yet run
unverified (harvested, no recorded run)
bcv-uniandes/grasp/TAPIS/tapis/models/attention.py
code served (permissive licence) · get_code("5803e73c1b7f2a96")
How it ran

no invocation recorded.

get_stem_func Not yet run
unverified (harvested, no recorded run)
bcv-uniandes/tapir/slowfast/models/stem_helper.py
code served (permissive licence) · get_code("d296e9fcbb9a1e04")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 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.

FunctionAlso present inEarliest-datedOthers named
get_loss_func 13 other papers
10 dated earlier, 3 later
1812.03982 (2018-12)
SlowFast Networks for Video Recognition
2105.11731 (2021-05)
ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos
2106.09703 (2021-06)
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
and 10 more not named here
drop_path 11 other papers
9 dated earlier, 2 later
2106.09703 (2021-06)
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
2110.06915 (2021-10)
Object-Region Video Transformers
2110.07058 (2021-10)
Ego4D: Around the World in 3,000 Hours of Egocentric Video
and 8 more not named here
attention_pool 8 other papers
7 dated earlier, 1 later
2106.09703 (2021-06)
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
2110.06915 (2021-10)
Object-Region Video Transformers
136950068 (2022 (year only))
Efficient Video Transformers with Spatial-Temporal Token Selection
and 5 more not named here
get_rel_pos 3 other papers
1 dated earlier, 2 later
2302.04869 (2023-02)
Reversible Vision Transformers
2403.05856 (2024-03)
POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World
2410.19553 (2024-10)
On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
cal_rel_pos_spatial 2 other papers
1 dated earlier, 1 later
2302.04869 (2023-02)
Reversible Vision Transformers
2410.19553 (2024-10)
On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
eval_epoch 1 other paper
1 dated earlier
2303.09514 (2023-03)
MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation
get_stem_func 1 other paper
1 later
2403.05856 (2024-03)
POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World

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

This paper presents the Holistic and Multi-Granular Surgical Scene Understanding of Prostatectomies (GraSP) dataset, a curated benchmark that models surgical scene understanding as a hierarchy of complementary tasks with varying levels of granularity. Our approach enables a multi-level comprehension of surgical activities, encompassing long-term tasks such as surgical phases and steps recognition and short-term tasks including surgical instrument segmentation and atomic visual actions detection. To exploit our proposed benchmark, we introduce the Transformers for Actions, Phases, Steps, and Instrument Segmentation (TAPIS) model, a general architecture that combines a global video feature extractor with localized region proposals from an instrument segmentation model to tackle the multi-granularity of our benchmark. Through extensive experimentation, we demonstrate the impact of including segmentation annotations in short-term recognition tasks, highlight the varying granularity requirements of each task, and establish TAPIS's superiority over previously proposed baselines and conventional CNN-based models. Additionally, we validate the robustness of our method across multiple public benchmarks, confirming the reliability and applicability of our dataset. This work represents a significant step forward in Endoscopic Vision, offering a novel and comprehensive framework for future research towards a holistic understanding of surgical procedures.

For agents

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

get_harvested_code_for_paper("2401.11174")
get_code_for_paper("2401.11174")
have("2401.11174")

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

curl https://syntology.ai/api/ran/2401.11174.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.11174.svg)](https://syntology.ai/paper/2401.11174)

Connect an agent — have() is free.