Roberto Pietrantuono, Ivano Malavolta, Eziyo Ehsani, Luca Giamattei
5 of 5 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; 4 failures of our instrument; 0 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/2603.26603.json · badge: /api/ran/2603.26603.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.
| Repository | Role | Ran |
|---|---|---|
| eziyoo/LLMs-on-Devices | canonical (classifier label) classifier basis: census |
5 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| battery_parser | Ran ran; our contract draft was wrong, not the code |
eziyoo/LLMs-on-Devices/experiment_runner/parser/battery_parser.py pointer only (licence: NONE) · get_code("c2f11f685c1e9376") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, eziyoo/LLMs-on-Devices 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_head_sizes | Ran ran, honoured the contract we drafted |
eziyoo/LLMs-on-Devices/android-app/ggml/src/ggml-cuda/template-instances/generate_cu_files.py pointer only (licence: NONE) · get_code("074bfdbf2a9c5f3d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, eziyoo/LLMs-on-Devices 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_short_name | Ran ran; our contract draft was wrong, not the code |
eziyoo/LLMs-on-Devices/android-app/ggml/src/ggml-cuda/template-instances/generate_cu_files.py pointer only (licence: NONE) · get_code("a5b8c22a3ac7b238") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, eziyoo/LLMs-on-Devices 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. |
| parse_llama_log | Ran ran; our contract draft was wrong, not the code |
eziyoo/LLMs-on-Devices/experiment_runner/parser/memory_parser.py pointer only (licence: NONE) · get_code("899c714778145d4f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, eziyoo/LLMs-on-Devices 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. |
| parse_llama_log_file | Ran ran; our contract draft was wrong, not the code |
eziyoo/LLMs-on-Devices/experiment_runner/parser/energy_parser.py pointer only (licence: NONE) · get_code("bdb0dd9294d7baa4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, eziyoo/LLMs-on-Devices 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. |
Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| get_short_name | 1 other paper 1 dated earlier |
2212.04356 (2022-12) Robust Speech Recognition via Large-Scale Weak Supervision |
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The migration of Large Language Models (LLMs) from cloud clusters to edge devices promises enhanced privacy and offline accessibility, but this transition encounters a harsh reality: the physical constraints of mobile batteries, thermal limits, and, most importantly, memory constraints. To navigate this landscape, we constructed a replicable and reproducible experimental pipeline to profile the complex interplay between energy consumption, latency, and quality of LLMs on mobile devices. We harness this pipeline to conduct an empirical case study on a flagship Android device, capturing granular metrics across eight LLMs ranging from 0.5B to 9B parameters without requiring root access, ensuring our findings reflect realistic user conditions. The findings highlight the trade-offs between generation quality, performance, power and resource consumption, revealing which LLMs offer the best balance across metrics and under different conditions. Besides, we uncovered a counter-intuitive quantizationenergy paradox: while modern importance-aware quantization successfully reduces memory footprints to fit larger models into RAM, we found it yields negligible energy savings compared to standard mixed-precision methods. This proves that for battery life, the architecture of the model, not its quantization scheme, is the decisive factor. We further identified that Mixture-of-Experts (MoE) architectures defy the standard size-energy trend, offering the storage capacity of a 7B model while maintaining the lower energy profile of a 1B to 2B model. Finally, an analysis of these multi-objective trade-offs reveals a pragmatic sweet spot of mid-sized models, such as Qwen2.5-3B, that effectively balance response quality with sustainable energy consumption.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2603.26603")
get_code_for_paper("2603.26603")
have("2603.26603")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2603.26603.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2603.26603)
Connect an agent — have() is free.