SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.09623 · 2026

Adaptive AI Task Partitioning and Safe Offloading in Heterogeneous Edge-Cloud Continuum Akuen Akoi Deng ⋆[0009-0007-6228-3340] , Eimantas Butkus ⋆[0009-0001-5647-0779] , Alfreds Lapkovskis [0009-0003-4424-949X] , and

Praveen Kumar

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2605.09623.json · badge: /api/ran/2605.09623.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
Akuien/DNN-partitioning-and-Oflloading-framework-REAP community
Papers with Code archive
2 ran · 2 no recorded run
FunctionStatusWhere it lives
mean Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Akuien/DNN-partitioning-and-Oflloading-framework-REAP/adaptive-framework/split_infer.py
code served (permissive licence) · get_code("63da45ffd1618ec0")
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)

# The function `mean(xs)` expects:
# - xs: an iterable (list, tuple, etc.) of numeric values
# - It computes sum(xs) / len(xs) if xs is non-empty, else returns 0.0

# Construct a simple list of numbers
xs = [1.0, 2.0, 3.0, 4.0, 5.0]

ARGS = {
    "xs": xs
}
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
score Ran
ran, honoured the contract we drafted
Akuien/DNN-partitioning-and-Oflloading-framework-REAP/adaptive-framework/split_infer.py
code served (permissive licence) · get_code("72847bdb72a3845e")
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

torch.manual_seed(0)

# The function 'score' takes:
# - w: a dict with keys 'pi_e', 'tot_e', 'lat' (accessed as w['pi_e'], etc.)
# - pi_e: a numeric value (scalar or tensor)
# - tot_e: a numeric value (scalar or tensor)
# - lat: a numeric value (scalar or tensor)
# - norms: optional dict with keys 'pi_e', 'tot_e', 'lat' (or None)

w = {
    'pi_e': 0.5,
    'tot_e': 0.3,
    'lat': 0.2
}

pi_e = 10.5
tot_e = 20.3
lat = 5.1

norms = {
    'pi_e': 100.0,
    'tot_e': 50.0,
    'lat': 10.0
}

ARGS = {
    'w': w,
    'pi_e': pi_e,
    'tot_e': tot_e,
    'lat': lat,
    'norms': norms
}
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 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
final_report Not yet run
unverified (harvested, no recorded run)
Akuien/DNN-partitioning-and-Oflloading-framework-REAP/adaptive-framework/split_infer.py
code served (permissive licence) · get_code("9f996cbb50caa812")
How it ran

no invocation recorded.

measure_bandwidths Not yet run
unverified (harvested, no recorded run)
Akuien/DNN-partitioning-and-Oflloading-framework-REAP/adaptive-framework/split_infer.py
code served (permissive licence) · get_code("110c8aee1babefa7")
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

In recent years, the use of artificial intelligence on resourceconstrained IoT devices has grown significantly. However, existing approaches to AI task partitioning and offloading across the edge-cloud continuum typically rely on static methods that ignore runtime dynamics. Furthermore, they are often evaluated in simulated environments rather than on real hardware. To address this gap, we propose a framework that dynamically splits neural network layers across the heterogeneous continuum. The framework profiles the model at startup, measures network link conditions between nodes, and periodically re-evaluates the partition to adapt to environmental changes. We created a physical testbed comprising a Raspberry Pi edge device, a laptop fog, and a highperformance desktop PC as the cloud. We evaluated the framework over three widely adopted convolutional neural networks: VGG16, AlexNet, and MobileNetV2. Our results show that the framework achieves reductions in energy and end-to-end latency of 27.09-35.82% and 6.34-22.92%, respectively, compared to a static partitioning baseline. These findings confirm the superiority of adaptive to static partitioning.

For agents

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

get_harvested_code_for_paper("2605.09623")
get_code_for_paper("2605.09623")
have("2605.09623")

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

curl https://syntology.ai/api/ran/2605.09623.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.09623.svg)](https://syntology.ai/paper/2605.09623)

Connect an agent — have() is free.