SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.00176 · 2020

When2com: Multi-Agent Perception via Communication Graph Grouping

arXiv · PDF · Open in the Atlas

Code that ran

11 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; 0 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 2 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/2006.00176.json · badge: /api/ran/2006.00176.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
GT-RIPL/MultiAgentPerception community (classifier label)
classifier basis not recorded on the link
11 ran · 2 no recorded run
FunctionStatusWhere it lives
alpha_blend Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/process_img.py
code served (permissive licence) · get_code("3a8e7e1d2e1dc425")
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 3, dtype family float, shape (4, 5, 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

# Create small test images with 3 channels
# input_image: RGB image as numpy array
input_image = np.random.rand(4, 5, 3).astype(np.float32)

# segmentation_mask: RGB mask as numpy array with same shape
segmentation_mask = np.random.rand(4, 5, 3).astype(np.float32)

# alpha: blending factor
alpha = 0.5

ARGS = {
    "input_image": input_image,
    "segmentation_mask": segmentation_mask,
    "alpha": alpha,
}
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 3, dtype family float, shape (4, 5, 3) — shape (4, 5, 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
bootstrapped_cross_entropy2d Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/loss/loss.py
code served (permissive licence) · get_code("dfe03b9cbc5639c5")
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 torch.nn as nn

torch.manual_seed(0)

# Create small tensors for the function
# input: (batch_size, channels, height, width) = (2, 4, 3, 3)
# target: (batch_size, height, width) = (2, 3, 3)
batch_size = 2
num_channels = 4
height = 3
width = 3

input_tensor = torch.randn(batch_size, num_channels, height, width)
target_tensor = torch.randint(0, 4, (batch_size, height, width))

# K is the number of top-k losses to keep
K = 5

# weight is optional class weights for cross_entropy
weight = torch.tensor([1.0, 1.0, 1.0, 1.0])

ARGS = {
    "input": input_tensor,
    "target": target_tensor,
    "K": K,
    "weight": weight,
    "size_average": True
}
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 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
convert_state_dict Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/utils.py
code served (permissive licence) · get_code("e71ba6dcf9b2c854")
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 OrderedDict. 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
from collections import OrderedDict

torch.manual_seed(0)

# Create a sample state dict from a DataParallel module
# DataParallel prefixes keys with "module.", so we simulate that
state_dict = OrderedDict()
state_dict["module.layer1.weight"] = torch.randn(4, 3)
state_dict["module.layer1.bias"] = torch.randn(4)
state_dict["module.layer2.weight"] = torch.randn(5, 4)
state_dict["module.layer2.bias"] = torch.randn(5)

ARGS = {
    "state_dict": state_dict
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
cross_entropy2d Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/loss/loss.py
code served (permissive licence) · get_code("187e0bb11e846d2d")
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 torch.nn.functional as F

torch.manual_seed(0)

# input: (n, c, h, w) - batch_size=2, channels=4, height=3, width=5
input_tensor = torch.randn(2, 4, 3, 5)

# target: (nt, ht, wt) - batch_size=2, height=3, width=5
# values should be class indices (0 to c-1), with optional ignore_index=250
target_tensor = torch.randint(0, 4, (2, 3, 5))

# weight: optional class weights, one per class
weight_tensor = torch.ones(4)

ARGS = {
    "input": input_tensor,
    "target": target_tensor,
    "weight": weight_tensor,
    "size_average": True,
}
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 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
generate_noise Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/process_img.py
code served (permissive licence) · get_code("a381497cf6bcb48b")
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 4, dtype family float, shape (2, 3, 4, 5) 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 torch.autograd import Variable

torch.manual_seed(0)

# Create a small RGB image batch
# Shape: (batch_size, channels, height, width)
# Using distinct dimensions: batch=2, channels=3 (RGB), height=4, width=5
img = torch.randn(2, 3, 4, 5)

ARGS = {
    'img': img,
    'noisy_type': 'occlusion'
}
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 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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
get_interp_size Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GT-RIPL/MultiAgentPerception/ptsemseg/models/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from wty-ustc/hairclip, is pointer only (licence: LGPL-2.1) · get_code("80a82d5149279cdf")
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 wty-ustc/hairclip, and LGPL-2.1, 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.

get_vectorize_grad Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/probe.py
code served (permissive licence) · get_code("eb2e6c0fa0a0b86d")
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 1, dtype family float, shape (23,) 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 torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear2(self.linear1(x))

model = SimpleModel()

# Create some dummy input and target
x = torch.randn(2, 4)
y = torch.randn(2, 2)

# Forward pass
output = model(x)

# Compute loss and backward to populate gradients
loss = nn.MSELoss()(output, y)
loss.backward()

# Get model parameters
model_parameter = list(model.parameters())

ARGS = {
    "model_parameter": model_parameter
}
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 Tensor, ndim 1, dtype family float, shape (23,) — shape (23,) 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
interp Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/models/utils.py
code served (permissive licence) · get_code("aed5a907c8821d6d")
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 4, dtype family float, shape (2, 4, 6, 8) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn.functional as F
from torch.autograd import Variable

torch.manual_seed(0)

# Create a small input tensor: (batch=2, channels=4, height=3, width=5)
input_tensor = torch.randn(2, 4, 3, 5)

# Define output size as a tuple (height, width)
output_size = (6, 8)

# Define interpolation mode
mode = 'bilinear'

ARGS = {
    'input': input_tensor,
    'output_size': output_size,
    'mode': mode
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 6, 8) — shape (2, 4, 6, 8) 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
label_region_n_compute_distance Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/loader/airsim_loader.py
code served (permissive licence) · get_code("fba01581708d4ed6")
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 numpy as np

# Analyzing the function:
# - i: an integer index
# - path_tuple: a tuple with at least 2 elements (begin, end), each being a coordinate pair (x, y)
# The function extracts begin and end coordinates, computes Euclidean distance,
# assigns a region based on coordinate thresholds, and returns an extended tuple.

# Setting up arguments
i = 0
begin = (-500, 150)  # x <= -400 triggers 'suburban' region
end = (-450, 200)    # x < -400 also triggers 'suburban' region
path_tuple = (begin, end)

ARGS = {
    'i': i,
    'path_tuple': path_tuple
}
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 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
multi_scale_cross_entropy2d Ran
ran on a synthesized input
GT-RIPL/MultiAgentPerception/ptsemseg/loss/loss.py
code served (permissive licence) · get_code("74ffafeffc94fe17")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn

torch.manual_seed(0)

# Create multi-scale input tuple
# Each input has shape (batch=2, channels=4, height=8, width=6)
input_scale1 = torch.randn(2, 4, 8, 6)
input_scale2 = torch.randn(2, 4, 4, 3)
input_scale3 = torch.randn(2, 4, 2, 1)
input_tuple = (input_scale1, input_scale2, input_scale3)

# Create target with shape (batch=2, height=8, width=6)
# Values should be class indices, avoiding ignore_index=250
target = torch.randint(0, 4, (2, 8, 6))

# Create class weight (4 classes)
weight = torch.tensor([1.0, 1.0, 1.0, 1.0])

ARGS = {
    'input': input_tuple,
    'target': target,
    'weight': weight,
    'size_average': True,
    'scale_weight': None
}
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 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
recursive_glob Ran
ran; our contract draft was wrong, not the code
GT-RIPL/MultiAgentPerception/ptsemseg/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from axi404/pmt, is pointer only (licence: NONE) · get_code("f1e67bfcea91df50")
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 axi404/pmt, 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.

get_upsampling_weight Not yet run
unverified (harvested, no recorded run)
GT-RIPL/MultiAgentPerception/ptsemseg/models/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from jiwei0921/CoNet, is pointer only (licence: NONE) · get_code("68f02849ad3eb678")
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 jiwei0921/CoNet, 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.

recursive_glob Not yet run
unverified (harvested, no recorded run)
GT-RIPL/MultiAgentPerception/ptsemseg/process_img.py
code served (permissive licence) · get_code("aa49d29b2460409a")
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, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 6 later) and 6 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
recursive_glob 10 other papers
4 dated earlier, 6 later
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
1912.13192 (2019-12)
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
2003.09005 (2020-03)
Semi-Supervised Semantic Segmentation with Cross-Consistency Training
and 7 more not named here
get_upsampling_weight 9 other papers
2 dated earlier, 7 later
1807.09856 (2018-07)
Where are the Blobs: Counting by Localization with Point Supervision
1809.00338 (2018-09)
Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition
2007.11782 (2020-07)
Accurate RGB-D Salient Object Detection via Collaborative Learning
and 6 more not named here
get_interp_size 3 other papers
3 later
2106.14917 (2021-06)
Striking the Right Balance: Recall Loss for Semantic Segmentation
2112.05142 (2021-12)
HairCLIP: Design Your Hair by Text and Reference Image
2112.09130 (2021-12)
Ensembling Off-the-shelf Models for GAN Training
alpha_blend 2 other papers
1 dated earlier, 1 later
2004.01800 (2020-04)
Temporally Distributed Networks for Fast Video Semantic Segmentation
2106.14917 (2021-06)
Striking the Right Balance: Recall Loss for Semantic Segmentation
bootstrapped_cross_entropy2d 2 other papers
1 dated earlier, 1 later
1910.13049 (2019-10)
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
2108.08012 (2021-08)
Multi-Anchor Active Domain Adaptation for Semantic Segmentation
interp 1 other paper
1 later
2106.14917 (2021-06)
Striking the Right Balance: Recall Loss for Semantic Segmentation

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

While significant advances have been made for single-agent perception, many applications require multiple sensing agents and cross-agent communication due to benefits such as coverage and robustness. It is therefore critical to develop frameworks which support multi-agent collaborative perception in a distributed and bandwidth-efficient manner. In this paper, we address the collaborative perception problem, where one agent is required to perform a perception task and can communicate and share information with other agents on the same task. Specifically, we propose a communication framework by learning both to construct communication groups and decide when to communicate. We demonstrate the generalizability of our framework on two different perception tasks and show that it significantly reduces communication bandwidth while maintaining superior performance.

For agents

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

get_harvested_code_for_paper("2006.00176")
get_code_for_paper("2006.00176")
have("2006.00176")

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

curl https://syntology.ai/api/ran/2006.00176.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.00176.svg)](https://syntology.ai/paper/2006.00176)

Connect an agent — have() is free.