Time-Division Online Speculative Inference for Cost-Effective Intelligent Internet of Things
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Intelligent Internet of Things (IIoT), a network paradigm, is an interconnection of intelligent edge devices, empowered by machine learning models. The recent emergence of large language models (LLMs) opens a new path towards IIoT. Although device models are generally lightweight and suitable for edge devices with limited processing power, their performance is less impressive compared to LLMs running on large servers. Server models offer superior performance with the cost of significant computational resources for model inference. To realize cost-effective IIoT, we introduce a novel collaborative inference framework: the online speculative inference enabled by device collaboration and time divisions. We aim to find the minimum number of servers required for the immediate processing of arrived inference requests. To solve the problem, we propose an evolving directed acyclic graph along with a Proof-of-Deletion mechanism for cost reduction and privacy protection. Based on computer simulations using heterogeneous LLMs, it is found that time-division online speculative inference is a promising approach towards cost-effective IIoT.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it