Erik Husom, Arda Goknil, Khin Lwin, Sagar Shar, Sen, L Shar
6 of 9 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 0 have no contract verdict; 6 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/2407.16893.json · badge: /api/ran/2407.16893.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 |
|---|---|---|
| ejhusom/melodi | canonical (classifier label) classifier basis: census |
6 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| flatten_data | Ran ran; our contract draft was wrong, not the code |
ejhusom/melodi/src/LLMEC.py pointer only (licence: NONE) · get_code("b855d50ad67ed2a8") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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. |
| generate_hardware_hatches | Ran ran; our contract draft was wrong, not the code |
ejhusom/melodi/src/analyze.py pointer only (licence: NONE) · get_code("3d98ad5ce3d0e60e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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. |
| generate_promptset_colors | Ran ran; our contract draft was wrong, not the code |
ejhusom/melodi/src/analyze.py pointer only (licence: NONE) · get_code("0e68515ae93f052c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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. |
| neural_network | Ran ran; our contract draft was wrong, not the code |
ejhusom/melodi/src/train_forecasting_model.py pointer only (licence: NONE) · get_code("2258fbc436acfc06") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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_json_objects | Ran ran; our contract draft was wrong, not the code |
ejhusom/melodi/src/LLMEC.py pointer only (licence: NONE) · get_code("95938f8b43e3aaf2") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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. |
| select_model | Ran ran; our contract draft was wrong, not the code |
ejhusom/melodi/src/train_forecasting_model.py pointer only (licence: NONE) · get_code("fe26277272cef0d4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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_json_objects_from_file | Not yet run unverified (harvested, no recorded run) |
ejhusom/melodi/src/LLMEC.py pointer only (licence: NONE) · get_code("013cb5afc8a6f519") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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. |
| plot_single_correlations | Not yet run unverified (harvested, no recorded run) |
ejhusom/melodi/src/plot_data_collection_results.py pointer only (licence: NONE) · get_code("5d74d3771d01c1cb") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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. |
| preprocess_data | Not yet run unverified (harvested, no recorded run) |
ejhusom/melodi/src/train_forecasting_model.py pointer only (licence: NONE) · get_code("dceaa34a68276fe1") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, ejhusom/melodi 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. |
Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In the realm of Artificial Intelligence (AI), the deployment of Large Language Models (LLMs) has become fundamental to advancing technology and enriching user experiences across various applications. However, as these models grow in complexity and size, they pose significant computational and environmental challenges due to their substantial energy consumption. The increasing deployment of LLMs accentuates the need for sustainable practices to manage their energy demands effectively, especially in resource-constrained environments. In this paper, we introduce MELODI -Monitoring Energy Levels and Optimization for Data-driven Inference -a multifaceted framework crafted to monitor and analyze the energy consumed during LLM inference processes. Unlike existing tools that measure energy at the system level, MELODI uniquely combines process-level CPU monitoring via Scaphandre with GPU tracking via nvidia-smi, employing configurable temporal buffers to capture complete inference cycles with high precision. MELODI enables detailed observations of power consumption dynamics and facilitates the creation of datasets reflective of energy efficiency across various deployment scenarios. We apply MELODI to profile inference-time energy consumption under a diverse set of scenarios. Our findings reveal pronounced energy efficiency disparities: large models (≥70B parameters) consume roughly two orders of magnitude more energy per token than smaller models, while response token length is a strong predictor of energy use (R 2 > 0.95 in most settings). We further derive a predictive model with an R 2 value of 0.9962, utilizing response length, model type, and hardware. Prompt characteristics exhibit minimal correlation with energy consumption. In contrast, hardware choice has a substantial impact-laptop deployments consistently consume more energy than workstations for comparable models-highlighting significant opportunities for optimization and more sustainable LLM deployment.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.16893")
get_code_for_paper("2407.16893")
have("2407.16893")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2407.16893.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2407.16893)
Connect an agent — have() is free.