arXiv subjects

Gang Fan

Publications and source records attributed to Gang Fan.

13 recordsLinked to original sources

arXiv2026

OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development

We present OPENHARMONY BENCH, an app-level coding benchmark for evaluating LLM-based coding agents on OpenHarmony ArkTS applications. Unlike function-level benchmarks, it evaluates complete app-level changes: each task requires an agent to modify a buildable ArkTS project so that a requested behavior works end to end, involving UI state, data persistence, build configuration, and platform APIs. The benchmark installs and drives the delivered application on a device to check whether the behavior is observable. It covers three input sources: natural-language feature requests (new-feature), structured scenario specifications (spec-driven), and bug descriptions (bug-fix). The benchmark contains 153 top-level tasks and 242 Feature points (F-points), where an F-point is one executable behavior check. The snapshot includes 32 new-feature tasks, 50 spec-driven tasks with 139 F-points, and 71 bug-fix tasks. The main leaderboard is scored over top-level tasks rather than independently weighted F-points. We describe the benchmark construction, statistics, and build-and-test evaluation pipeline, and evaluate DevEco Code with eight LLMs across three independent full-suite runs per configuration. Three findings emerge. First, newer generations complete more tasks than their predecessors within evaluated model-family pairs. Second, buildability is close to saturated while behavioral correctness is not: mean Final Build Success Rate is 94.77% to 100.00%, whereas mean Task Completion is 48.36% to 58.39%. Third, spec-driven tasks have the lowest Task Completion under all-checks task scoring, with no configuration exceeding 35%. The code, data, tasks, reference solutions, tests, evaluation scripts, and leaderboard are released through the official OPENHARMONY BENCH website at https://bench.matrix.openharmony.cn/.

cs.SE↗

arXiv2026

Source-Free Detection and Impact Analysis of Compiler Optimization Problems in Mobile Applications

Mobile apps frequently suffer from frame drops, overheating, and excessive power consumption. While developers optimize algorithms and debug code, a critical bottleneck often goes unnoticed: native libraries compiled with low optimization levels (O0/O1 instead of O2/O3). Because these libraries execute without functional errors, the resulting performance degradation remains hidden in production apps. We present \textsc{OptDetect}, a source-free framework that detects compiler optimization problems directly from app binaries. \textsc{OptDetect} handles mixed optimization levels through binary disassembly, chunk-level classification, and weighted score aggregation, achieving 93.0\% accuracy on controlled datasets and 81.9\% on real-world datasets. Applying \textsc{OptDetect} to 21,972 native libraries from 830 top-ranked Google Play apps, we find that 30.5\% of libraries use low optimization levels, affecting 91.7\% of apps. Through case studies on 12 production apps, fixing detected issues reduces CPU instructions by 10-63\% (median: 20.5\%) for commercial apps and 15-58\% (median: 32\%) for open-source apps. Performance complaints decrease in 5 of 6 commercial apps, and ratings increase in 5 of 6. Further investigation reveals that widely-used third-party libraries are themselves distributed at low optimization levels, with 49.7\% of 1,073 libraries in a major repository exhibiting this problem. These findings show that compiler optimization problems are common, source-free detectable, and practically consequential in mobile app ecosystems.

cs.SE↗

arXiv2024

A Computation-Enhanced High-Dimensional Quantum Gate for Silicon-Vacancy Spins

Qudit-based quantum gates in high-dimensional Hilbert space can provide a viable route towards effectively accelerating the speed of quantum computing and performing complex quantum logic operations. In the paper, we propose a 2-qudit $4\times4$-dimensional controlled-not (CNOT) gate for four silicon-vacancy spins, in which the first two electron-spin states in silicon-vacancy centers are encoded as the control qudits, and the other ones as the target qudits. The proposed protocol is implemented with assistance of an ancillary photon that serves as a common-data bus linking four motionless silicon-vacancy spins placed in four independent single-sided optical nanocavities. Moreover, the CNOT gate works in a deterministic manner by performing the relational feed-forward operations corresponding to the diverse outcomes of the single-photon detectors to be directed against the ancillary photon. Further, it can be potentially generalized to other solid-state quantum system. Under current technological conditions, both the efficiency and fidelity of the 2-qudit CNOT gate are high.

quant-ph↗

arXiv2024

REPOFUSE: Repository-Level Code Completion with Fused Dual Context

The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can inadvertently increase inference latency, potentially undermining the developer experience and deterring tool adoption - a challenge we termed the Context-Latency Conundrum. This paper introduces REPOFUSE, a pioneering solution designed to enhance repository-level code completion without the latency trade-off. REPOFUSE uniquely fuses two types of context: the analogy context, rooted in code analogies, and the rationale context, which encompasses in-depth semantic relationships. We propose a novel rank truncated generation (RTG) technique that efficiently condenses these contexts into prompts with restricted size. This enables REPOFUSE to deliver precise code completions while maintaining inference efficiency. Through testing with the CrossCodeEval suite, REPOFUSE has demonstrated a significant leap over existing models, achieving a 40.90% to 59.75% increase in exact match (EM) accuracy for code completions and a 26.8% enhancement in inference speed. Beyond experimental validation, REPOFUSE has been integrated into the workflow of a large enterprise, where it actively supports various coding tasks.

cs.SE↗

arXiv2024

Principles and Practices of Large-Scale Code Analysis at Ant Group: A Data- and Logic-Oriented Approach

Large-scale software development requires dynamic and multifaceted static code analysis that extends beyond the capabilities of traditional tools. Existing tools like CodeQL lack cross-language analysis capabilities and can be time-consuming and resource-intensive. We present CodeFuse-Query, a data system tailored for large-scale code analysis. First, CodeFuse-Query adopts a Logic-Oriented Computation Design, employing Datalog with a two-tiered schema, COREF, to convert source code into data facts, and Godel to express complex analysis tasks in logical terms. Furthermore, CodeFuse-Query adopts a Domain-Optimized System Design. This approach optimizes resource utilization, prioritizes data reusability, applies incremental code extraction, and introduces task-type characteristics specifically for code changes, underscoring its domain-optimized design. We present empirical results demonstrating CodeFuse-Query's robustness, scalability, and efficiency in large-scale real-world scenarios at Ant Group, where it serves as a core static analysis infrastructure. Deployed in production environments, CodeFuse-Query processes up to 10 billion lines of code daily across more than 300,000 distinct analysis tasks. CodeFuse-Query has been open-sourced.

cs.SE↗

arXiv2023

Static Code Analysis in the AI Era: An In-depth Exploration of the Concept, Function, and Potential of Intelligent Code Analysis Agents

The escalating complexity of software systems and accelerating development cycles pose a significant challenge in managing code errors and implementing business logic. Traditional techniques, while cornerstone for software quality assurance, exhibit limitations in handling intricate business logic and extensive codebases. To address these challenges, we introduce the Intelligent Code Analysis Agent (ICAA), a novel concept combining AI models, engineering process designs, and traditional non-AI components. The ICAA employs the capabilities of large language models (LLMs) such as GPT-3 or GPT-4 to automatically detect and diagnose code errors and business logic inconsistencies. In our exploration of this concept, we observed a substantial improvement in bug detection accuracy, reducing the false-positive rate to 66\% from the baseline's 85\%, and a promising recall rate of 60.8\%. However, the token consumption cost associated with LLMs, particularly the average cost for analyzing each line of code, remains a significant consideration for widespread adoption. Despite this challenge, our findings suggest that the ICAA holds considerable potential to revolutionize software quality assurance, significantly enhancing the efficiency and accuracy of bug detection in the software development process. We hope this pioneering work will inspire further research and innovation in this field, focusing on refining the ICAA concept and exploring ways to mitigate the associated costs.

cs.SE↗

arXiv2023

CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model

Code Large Language Models (Code LLMs) have gained significant attention in the industry due to their wide applications in the full lifecycle of software engineering. However, the effectiveness of existing models in understanding non-English inputs for multi-lingual code-related tasks is still far from well studied. This paper introduces CodeFuse-13B, an open-sourced pre-trained code LLM. It is specifically designed for code-related tasks with both English and Chinese prompts and supports over 40 programming languages. CodeFuse achieves its effectiveness by utilizing a high quality pre-training dataset that is carefully filtered by program analyzers and optimized during the training process. Extensive experiments are conducted using real-world usage scenarios, the industry-standard benchmark HumanEval-x, and the specially designed CodeFuseEval for Chinese prompts. To assess the effectiveness of CodeFuse, we actively collected valuable human feedback from the AntGroup's software development process where CodeFuse has been successfully deployed. The results demonstrate that CodeFuse-13B achieves a HumanEval pass@1 score of 37.10%, positioning it as one of the top multi-lingual code LLMs with similar parameter sizes. In practical scenarios, such as code generation, code translation, code comments, and testcase generation, CodeFuse performs better than other models when confronted with Chinese prompts.

cs.SE↗

arXiv2023

Kerr-effect-based quantum logical gates in decoherence-free subspace

The decoherence effect caused by the coupling between the system and the environment undoubtedly leads to the errors in efficient implementations of two (or three) qubit logical gates in quantum information processing. Fortunately, decoherence-free subspace (DFS) introduced can effectively decrease the influence of decoherence effect. In this paper, we propose some schemes for setting up a family of quantum control gates, including controlled-NOT (CNOT), Toffoli, and Fredkin gates for two or three logical qubits by means of cross-Kerr nonlinearities in DFS. These three logical gates require neither complicated quantum computational circuits nor auxiliary photons (or entangled states). The success probabilities of three logical gates are approximate 1 by performing the corresponding classical feed-forward operations based on the different measuring results of the X-homodyne detectors, and their fidelities are robust against the photon loss with the current technology. The proposed logical gates rely on only simple linear-optics elements, available single-qubit operations, and mature measurement methods, making our proposed gates be feasible and efficient in practical applications.

quant-ph↗

arXiv2023

Synthesizing Conjunctive Queries for Code Search

This paper presents Squid, a new conjunctive query synthesis algorithm for searching code with target patterns. Given positive and negative examples along with a natural language description, Squid analyzes the relations derived from the examples by a Datalog-based program analyzer and synthesizes a conjunctive query expressing the search intent. The synthesized query can be further used to search for desired grammatical constructs in the editor. To achieve high efficiency, we prune the huge search space by removing unnecessary relations and enumerating query candidates via refinement. We also introduce two quantitative metrics for query prioritization to select the queries from multiple candidates, yielding desired queries for code search. We have evaluated Squid on over thirty code search tasks. It is shown that Squid successfully synthesizes the conjunctive queries for all the tasks, taking only 2.56 seconds on average.

cs.PL↗

arXiv2023

Verifying Data Constraint Equivalence in FinTech Systems

Data constraints are widely used in FinTech systems for monitoring data consistency and diagnosing anomalous data manipulations. However, many equivalent data constraints are created redundantly during the development cycle, slowing down the FinTech systems and causing unnecessary alerts. We present EqDAC, an efficient decision procedure to determine the data constraint equivalence. We first propose the symbolic representation for semantic encoding and then introduce two light-weighted analyses to refute and prove the equivalence, respectively, which are proved to achieve in polynomial time. We evaluate EqDAC upon 30,801 data constraints in a FinTech system. It is shown that EqDAC detects 11,538 equivalent data constraints in three hours. It also supports efficient equivalence searching with an average time cost of 1.22 seconds, enabling the system to check new data constraints upon submission.

cs.PL↗

arXiv2022

Refined quantum gates for $\Lambda$-type atom-photon hybrid systems

High-efficiency quantum information processing is equivalent to the fewest quantum resources and the simplest operations by means of logic qubit gates. Based on the reflection geometry of a single photon interacting with a three-level $\Lambda$-typle atom-cavity system, we present some refined protocols for realizing controlled-not (CNOT), Fredkin, and Toffoli gates on hybrid systems. The first control qubit of our gates is encoded on a flying photon, and the rest qubits are encoded on the atoms in optical cavity. Moreover, these quantum gates can be extended to the optimal synthesis of multi-qubit CNOT, Fredkin and Toffoli gates with O(n) optical elements without auxiliary photons or atoms. Further, the simplest single-qubit operations are applied to the photon only, which make these logic gates experimentally feasible with current technology.

quant-ph↗

arXiv2022

TokenPatronus: A Decentralized NFT Anti-theft Mechanism

The emergence of metaverse brings tremendous evolution to Non-Fungible Tokens (NFTs), which could certify the ownership the unique digital asset in the cyber world. The NFT market has garnered unprecedented attention from investors and created billions of dollars in transaction volume. Meanwhile, securing NFT is still a challenging issue. Recently, numerous incidents of NFT theft have been reported, leading to incalculable losses for holders. We propose a decentralized NFT anti-theft mechanism called TokenPatronus, which supports the general ERC-721 standard and provide the holders with strong property protection. TokenPatronus contains pre-event protection, in-event interruption, and post-event replevin enhancements for the complete NFTs transactions stages. Four modules are designed to make up the decentralized anti-theft mechanism, including the decentralized access control (DAC), the decentralized risk management (DRM), the decentralized arbitration system (DAS) and the ERC-721G standard smart contract. TokenPatronus is performing on the Turtlecase NFT project of Ethereum and will support more blockchains in the future.

cs.CR↗

arXiv2019

Conquering the Extensional Scalability Problem for Value-Flow Analysis Frameworks

With an increasing number of value-flow properties to check, existing static program analysis still tends to have scalability issues when high precision is required. We observe that the key design flaw behind the scalability problem is that the core static analysis engine is oblivious of the mutual synergies among different properties being checked and, thus, inevitably loses many optimization opportunities. Our approach is inter-property-aware and able to capture possible overlaps and inconsistencies among different properties. Thus, before analyzing a program, we can make optimization plans which decide how to reuse the specific analysis results of a property to speed up checking other properties. Such a synergistic interaction among the properties significantly improves the analysis performance. We have evaluated our approach by checking twenty value-flow properties in standard benchmark programs and ten real-world software systems. The results demonstrate that our approach is more than 8x faster than existing ones but consumes only 1/7 memory. Such a substantial improvement in analysis efficiency is not achieved by sacrificing the effectiveness: at the time of writing, 39 bugs found by our approach have been fixed by developers and four of them have been assigned CVE IDs due to their security impact.

cs.SE↗