Detection and Analysis of Ethereum Energy Smart Contracts
Bibliographic record
Abstract
As blockchain technology advances, so has the deployment of smart contracts on blockchain platforms, making it exceedingly challenging for users to explicitly identify application services. Unlike traditional contracts, smart contracts are not written in a natural language, making it difficult to determine their provenance. Automatic classification of smart contracts offers blockchain users keyword-based contract queries and a streamlined effective management of smart contracts. In addition, the advancement in smart contracts is accompanied by security challenges, which are generally caused by domain-specific security breaches in smart contract implementation. The development of secure and reliable smart contracts can be extremely challenging due to domain-specific vulnerabilities and constraints associated with various business logics. Accordingly, contract classification based on the application domain and the transaction context offers greater insight into the syntactic and semantic properties of that class. However, despite initial attempts at classifying Ethereum smart contracts, there has been no research on the identification of smart contracts deployed in transactive energy systems for energy exchange purposes. In this article, in response to the widely recognized prospects of blockchain-enabled smart contracts towards an economical and transparent energy sector, we propose a methodology for the detection and analysis of energy smart contracts. First, smart contracts are parsed by transforming code elements into vectors that encapsulate the semantic and syntactic characteristics of each term. This generates a corpus of annotated text as a balanced, representative collection of terms in energy contracts. The use of a domain corpus builder as an embedding layer to annotate energy smart contracts in conjunction with machine learning models results in a classification accuracy of 98.34%. Subsequently, a source code analysis scheme is applied to identified energy contracts to uncover patterns in code segment distribution, predominant adoption of certain functions, and recurring contracts across the Ethereum network.
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.
How this classification was reachedexpand
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".