SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.06769 · 2022

DEFER: Distributed Edge Inference for Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 2 have no contract verdict; 0 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/2201.06769.json · badge: /api/ran/2201.06769.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
anrgusc/defer canonical (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
get_previous Ran
ran on a synthesized input
anrgusc/defer/src/dag_util.py
code served (permissive licence) · get_code("1f171a07d768d49d")
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 list, 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


class MockLayer(nn.Module):
    def __init__(self, name, inbound_layers=None):
        super().__init__()
        self.name = name
        self.inbound_nodes = []
        if inbound_layers is not None:
            inbound_node = MockInboundNode(inbound_layers)
            self.inbound_nodes.append(inbound_node)
    
    def forward(self, x):
        return x


class MockInboundNode:
    def __init__(self, inbound_layers):
        self.inbound_layers = inbound_layers


class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layers_dict = {}
    
    def add_layer(self, name, layer):
        self.layers_dict[name] = layer
    
    def get_layer(self, name):
        return self.layers_dict[name]


# Create mock model with layers
model = MockModel()

# Create input layers (no inbound nodes)
input_layer = MockLayer("input")
model.add_layer("input", input_layer)

# Create intermediate layer with single inbound layer
intermediate_layer = MockLayer("intermediate", input_layer)
model.add_layer("intermediate", intermediate_layer)

# Create output layer with multiple inbound layers
dense_layer = MockLayer("dense", input_layer)
model.add_layer("dense", dense_layer)

output_layer = MockLayer("output", [intermediate_layer, dense_layer])
model.add_layer("output", output_layer)

ARGS = {
    "model": model,
    "name": "output"
}
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 list, ndim 1, dtype family float — a list 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
socket_recv Ran
ran on a synthesized input
anrgusc/defer/src/node_state.py
code served (permissive licence) · get_code("f1da2cfc4bb9b196")
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 bytearray. 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 socket
import select
import threading
import time

# Create a mock socket pair for testing
server_sock, client_sock = socket.socketpair()

# Set both sockets to non-blocking mode for testing EAGAIN handling
server_sock.setblocking(False)
client_sock.setblocking(False)

def send_data_in_thread():
    """Send test data from server to client in a separate thread"""
    time.sleep(0.1)  # Small delay to ensure client is ready
    
    # Send 8-byte size header
    data_to_send = b"Hello, World!"
    size_bytes = len(data_to_send).to_bytes(8, 'big')
    server_sock.send(size_bytes)
    
    # Send actual data
    server_sock.send(data_to_send)

# Start sender thread
sender_thread = threading.Thread(target=send_data_in_thread, daemon=True)
sender_thread.start()

# Allow time for thread to start
time.sleep(0.05)

ARGS = {
    'sock': client_sock,
    'chunk_size': 1024
}
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 bytearray — a bytearray output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytearray output the recorded ndim 1 and dtype family int 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
construct_model Not yet run
unverified (harvested, no recorded run)
anrgusc/defer/src/dag_util.py
code served (permissive licence) · get_code("74d50cec99584fd7")
How it ran

no invocation recorded.

traverse Not yet run
unverified (harvested, no recorded run)
anrgusc/defer/src/dag_util.py
code served (permissive licence) · get_code("b26c72963654c229")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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

Modern machine learning tools such as deep neural networks (DNNs) are playing a revolutionary role in many fields such as natural language processing, computer vision, and the internet of things. Once they are trained, deep learning models can be deployed on edge computers to perform classification and prediction on real-time data for these applications. Particularly for large models, the limited computational and memory resources on a single edge device can become the throughput bottleneck for an inference pipeline. To increase throughput and decrease per-device compute load, we present DEFER (Distributed Edge inFERence), a framework for distributed edge inference, which partitions deep neural networks into layers that can be spread across multiple compute nodes. The architecture consists of a single "dispatcher" node to distribute DNN partitions and inference data to respective compute nodes. The compute nodes are connected in a series pattern where each node's computed result is relayed to the subsequent node. The result is then returned to the Dispatcher. We quantify the throughput, energy consumption, network payload, and overhead for our framework under realistic network conditions using the CORE network emulator. We find that for the ResNet50 model, the inference throughput of DEFER with 8 compute nodes is 53% higher and per node energy consumption is 63% lower than single device inference. We further reduce network communication demands and energy consumption using the ZFP serialization and LZ4 compression algorithms. We have implemented DEFER in Python using the TensorFlow and Keras ML libraries, and have released DEFER as an open-source framework to benefit the research community.

For agents

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

get_harvested_code_for_paper("2201.06769")
get_code_for_paper("2201.06769")
have("2201.06769")

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

curl https://syntology.ai/api/ran/2201.06769.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.06769.svg)](https://syntology.ai/paper/2201.06769)

Connect an agent — have() is free.