介绍了高温蠕变工况下运行的压力容器可能出现的失效模式,结合工程设计现状,指出了我国当前压力容器标准体系在确定高温蠕变工况许用压应力时存在的技术瓶颈,在此基础之上引出ASME Code Case 3029,对其适用范围、发展历程、产生背景及...介绍了高温蠕变工况下运行的压力容器可能出现的失效模式,结合工程设计现状,指出了我国当前压力容器标准体系在确定高温蠕变工况许用压应力时存在的技术瓶颈,在此基础之上引出ASME Code Case 3029,对其适用范围、发展历程、产生背景及工程意义进行了简单的介绍,以某工程设计项目中的实际结构为例,介绍了该方法的使用过程及注意事项,并结合压力容器工程设计领域的实际需求,对我国标准体系下一步的制定或修订方向提出了展望。展开更多
Mobile communications are reaching out to every aspect of our daily life,necessitating highefficiency data transmission and support for diverse data types and communication scenarios.Polar codes have emerged as a prom...Mobile communications are reaching out to every aspect of our daily life,necessitating highefficiency data transmission and support for diverse data types and communication scenarios.Polar codes have emerged as a promising solution due to their outstanding error-correction performance and low complexity.Unequal error protection(UEP)involves nonuniform error safeguarding for distinct data segments,achieving a fine balance between error resilience and resource allocation,which ultimately enhancing system performance and efficiency.In this paper,we propose a novel class of UEP rateless polar codes.The codes are designed based on matrix extension of polar codes,and elegant mapping and duplication operations are designed to achieve UEP property while preserving the overall performance of conventional polar codes.Superior UEP performance is attained without significant modifications to conventional polar codes,making it straightforward for compatibility with existing polar codes.A theoretical analysis is conducted on the block error rate and throughput efficiency performance.To the best of our knowledge,this work provides the first theoretical performance analysis of UEP rateless polar codes.Simulation results show that the proposed codes significantly outperform existing polar coding schemes in both block error rate and throughput efficiency.展开更多
Differential pulse-position modulation(DP PM)can achieve a good compromise between power and bandwidth requirements.However,the output sequence has undetectable insertions and deletions.This paper proposes a successiv...Differential pulse-position modulation(DP PM)can achieve a good compromise between power and bandwidth requirements.However,the output sequence has undetectable insertions and deletions.This paper proposes a successive cancellation(SC)decoding scheme based on the weighted levenshtein distance(WLD)of polar codes for correcting insertions/deletions in DPPM systems.In this method,the WLD is used to calculate the transfer probabilities recursively to obtain likelihood ratios,and the low-complexity SC decoding method is built according to the error characteristics to match the DPPM system.Additionally,the proposed SC decoding scheme is extended to list decoding,which can further improve error correction performance.Simulation results show that the proposed scheme can effectively correct insertions/deletions in the DPPM system,which enhances its reliability and performance.展开更多
As artificial Intelligence(AI)continues to expand exponentially,particularly with the emergence of generative pre-trained transformers(GPT)based on a transformer’s architecture,which has revolutionized data processin...As artificial Intelligence(AI)continues to expand exponentially,particularly with the emergence of generative pre-trained transformers(GPT)based on a transformer’s architecture,which has revolutionized data processing and enabled significant improvements in various applications.This document seeks to investigate the security vulnerabilities detection in the source code using a range of large language models(LLM).Our primary objective is to evaluate the effectiveness of Static Application Security Testing(SAST)by applying various techniques such as prompt persona,structure outputs and zero-shot.To the selection of the LLMs(CodeLlama 7B,DeepSeek coder 7B,Gemini 1.5 Flash,Gemini 2.0 Flash,Mistral 7b Instruct,Phi 38b Mini 128K instruct,Qwen 2.5 coder,StartCoder 27B)with comparison and combination with Find Security Bugs.The evaluation method will involve using a selected dataset containing vulnerabilities,and the results to provide insights for different scenarios according to the software criticality(Business critical,non-critical,minimum effort,best effort)In detail,the main objectives of this study are to investigate if large language models outperform or exceed the capabilities of traditional static analysis tools,if the combining LLMs with Static Application Security Testing(SAST)tools lead to an improvement and the possibility that local machine learning models on a normal computer produce reliable results.Summarizing the most important conclusions of the research,it can be said that while it is true that the results have improved depending on the size of the LLM for business-critical software,the best results have been obtained by SAST analysis.This differs in“NonCritical,”“Best Effort,”and“Minimum Effort”scenarios,where the combination of LLM(Gemini)+SAST has obtained better results.展开更多
Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Althoug...Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Although adversarial examples can strategically undermine the accuracy of BCSD models and protect critical code,existing techniques predominantly depend on inserting artificial instructions,which incur high computational costs and offer limited diversity of perturbations.To address these limitations,we propose AIMA,a novel gradient-guided assembly instruction relocation method.Our method decouples the detection model into tokenization,embedding,and encoding layers to enable efficient gradient computation.Since token IDs of instructions are discrete and nondifferentiable,we compute gradients in the continuous embedding space to evaluate the influence of each token.The most critical tokens are identified by calculating the L2 norm of their embedding gradients.We then establish a mapping between instructions and their corresponding tokens to aggregate token-level importance into instructionlevel significance.To maximize adversarial impact,a sliding window algorithm selects the most influential contiguous segments for relocation,ensuring optimal perturbation with minimal length.This approach efficiently locates critical code regions without expensive search operations.The selected segments are relocated outside their original function boundaries via a jump mechanism,which preserves runtime control flow and functionality while introducing“deletion”effects in the static instruction sequence.Extensive experiments show that AIMA reduces similarity scores by up to 35.8%in state-of-the-art BCSD models.When incorporated into training data,it also enhances model robustness,achieving a 5.9%improvement in AUROC.展开更多
The ultracold neutron(UCN)transport code,MCUCN,designed initially for simulating UCN transportation from a solid deuterium(SD_2)source and neutron electric dipole moment experiments,could not simulate UCN storage and ...The ultracold neutron(UCN)transport code,MCUCN,designed initially for simulating UCN transportation from a solid deuterium(SD_2)source and neutron electric dipole moment experiments,could not simulate UCN storage and transportation in a superfluid^(4)He(SFHe,He-Ⅱ)source accurately.This limitation arose from the absence of an^(4)He upscattering mechanism and the absorption of^(3)He.And the provided source energy distribution in MCUCN is different from that in SFHe source.This study introduced enhancements to MCUCN to address these constraints,explicitly incorporating the^(4)He upscattering effect,the absorption of^(3)He,the loss caused by impurities on converter wall,UCN source energy distribution in SFHe,and the transmission through negative optical potential.Additionally,a Python-based visualization code for intermediate states and results was developed.To validate these enhancements,we systematically compared the simulation results of the Lujan Center Mark3 UCN system by MCUCN and the improved MCUCN code(iMCUCN)with UCNtransport simulations.Additionally,we compared the results of the SUN1 system simulated by MCUCN and iMCUCN with measurement results.The study demonstrates that iMCUCN effectively simulates the storage and transportation of ultracold neutrons in He-Ⅱ.展开更多
Blind recognition of low-density paritycheck(LDPC)codes has gradually attracted more attention with the development of military and civil communications.However,in the case of the paritycheck matrices with relatively ...Blind recognition of low-density paritycheck(LDPC)codes has gradually attracted more attention with the development of military and civil communications.However,in the case of the paritycheck matrices with relatively high row weights,the existing blind recognition algorithms based on a candidate set generally perform worse.In this paper,we propose a blind recognition method for LDPC codes,called as tangent function assisted least square(TLS)method,which improves recognition performances by constructing a new cost function.To characterize the constraint degree among received vectors and paritycheck vectors,a feature function based on tangent function is constructed in the proposed algorithm.A cost function based on least square method is also established according to the feature function values satisfying the parity-check relationship.Moreover,the minimum average value in TLS is obtained on the candidate set.Numerical analysis and simulation results show that recognition performances of TLS algorithm are consistent with theoretical results.Compared with existing algorithms,the proposed method possesses better recognition performances.展开更多
LargeLanguageModels(LLMs)are increasingly appliedinthe fieldof code translation.However,existing evaluation methodologies suffer from two major limitations:(1)the high overlap between test data and pretraining corpora...LargeLanguageModels(LLMs)are increasingly appliedinthe fieldof code translation.However,existing evaluation methodologies suffer from two major limitations:(1)the high overlap between test data and pretraining corpora,which introduces significant bias in performance evaluation;and(2)mainstream metrics focus primarily on surface-level accuracy,failing to uncover the underlying factors that constrain model capabilities.To address these issues,this paper presents TCode(Translation-Oriented Code Evaluation benchmark)—a complexity-controllable,contamination-free benchmark dataset for code translation—alongside a dedicated static feature sensitivity evaluation framework.The dataset is carefully designed to control complexity along multiple dimensions—including syntactic nesting and expression intricacy—enabling both broad coverage and fine-grained differentiation of sample difficulty.This design supports precise evaluation of model capabilities across a wide spectrum of translation challenges.The proposed evaluation framework introduces a correlation-driven analysis mechanism based on static program features,enabling predictive modeling of translation success from two perspectives:Code Form Complexity(e.g.,code length and character density)and Semantic Modeling Complexity(e.g.,syntactic depth,control-flow nesting,and type system complexity).Empirical evaluations across representative LLMs—including Qwen2.5-72B and Llama3.3-70B—demonstrate that even state-of-the-art models achieve over 80% compilation success on simple samples,but their accuracy drops sharply below 40% on complex cases.Further correlation analysis indicates that Semantic Modeling Complexity alone is correlated with up to 60% of the variance in translation success,with static program features exhibiting nonlinear threshold effects that highlight clear capability boundaries.This study departs fromthe traditional accuracy-centric evaluation paradigm and,for the first time,systematically characterizes the capabilities of large languagemodels in translation tasks through the lens of programstatic features.The findings provide actionable insights for model refinement and training strategy development.展开更多
Automated Program Repair(APR)techniques have shown significant potential in mitigating the cost and complexity associated with debugging by automatically generating corrective patches for software defects.Despite cons...Automated Program Repair(APR)techniques have shown significant potential in mitigating the cost and complexity associated with debugging by automatically generating corrective patches for software defects.Despite considerable progress in APR methodologies,existing approaches frequently lack contextual awareness of runtime behaviors and structural intricacies inherent in buggy source code.In this paper,we propose a novel APR approach that integrates attention mechanisms within an autoencoder-based framework,explicitly utilizing structural code affinity and execution context correlation derived from stack trace analysis.Our approach begins with an innovative preprocessing pipeline,where code segments and stack traces are transformed into tokenized representations.Subsequently,the BM25 ranking algorithm is employed to quantitatively measure structural code affinity and execution context correlation,identifying syntactically and semantically analogous buggy code snippets and relevant runtime error contexts from extensive repositories.These extracted features are then encoded via an attention-enhanced autoencoder model,specifically designed to capture significant patterns and correlations essential for effective patch generation.To assess the efficacy and generalizability of our proposed method,we conducted rigorous experimental comparisons against DeepFix,a state-of-the-art APR system,using a substantial dataset comprising 53,478 studentdeveloped C programs.Experimental outcomes indicate that our model achieves a notable bug repair success rate of approximately 62.36%,representing a statistically significant performance improvement of over 6%compared to the baseline.Furthermore,a thorough K-fold cross-validation reinforced the consistency,robustness,and reliability of our method across diverse subsets of the dataset.Our findings present the critical advantage of integrating attentionbased learning with code structural and execution context features in APR tasks,leading to improved accuracy and practical applicability.Future work aims to extend the model’s applicability across different programming languages,systematically optimize hyperparameters,and explore alternative feature representation methods to further enhance debugging efficiency and effectiveness.展开更多
In erasure-coded storage systems,updating data requires parity maintenance,which often leads to significant I/O amplification due to“write-after-read”operations.Furthermore,scattered parity placement increases disk ...In erasure-coded storage systems,updating data requires parity maintenance,which often leads to significant I/O amplification due to“write-after-read”operations.Furthermore,scattered parity placement increases disk seek overhead during repair,resulting in degraded system performance.To address these challenges,this paper proposes a Cognitive Update and Repair Method(CURM)that leverages machine learning to classify files into writeonly,read-only,and read-write categories,enabling tailored update and repair strategies.For write-only and read-write files,CURM employs a data-differencemechanism combined with fine-grained I/O scheduling to minimize redundant read operations and mitigate I/O amplification.For read-write files,CURM further reserves adjacent disk space near parity blocks,supporting parallel reads and reducing disk seek overhead during repair.We implement CURM in a prototype system,Cognitive Update and Repair File System(CURFS),and conduct extensive experiments using realworld Network File System(NFS)and Microsoft Research(MSR)workloads on a 25-node cluster.Experimental results demonstrate that CURMimproves data update throughput by up to 82.52%,reduces recovery time by up to 47.47%,and decreases long-term storage overhead by more than 15% compared to state-of-the-art methods including Full Logging(FL),ParityLogging(PL),ParityLoggingwithReservedspace(PLR),andPARIX.These results validate the effectiveness of CURM in enhancing both update and repair performance,providing a scalable and efficient solution for large-scale erasure-coded storage systems.展开更多
In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shippi...In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.展开更多
文摘介绍了高温蠕变工况下运行的压力容器可能出现的失效模式,结合工程设计现状,指出了我国当前压力容器标准体系在确定高温蠕变工况许用压应力时存在的技术瓶颈,在此基础之上引出ASME Code Case 3029,对其适用范围、发展历程、产生背景及工程意义进行了简单的介绍,以某工程设计项目中的实际结构为例,介绍了该方法的使用过程及注意事项,并结合压力容器工程设计领域的实际需求,对我国标准体系下一步的制定或修订方向提出了展望。
基金supported by National Natural Science Foundation of China(No.62301008)China Postdoctoral Science Foundation(No.2022M720272)New Cornerstone Science Foundation through the XPLORER PRIZE。
文摘Mobile communications are reaching out to every aspect of our daily life,necessitating highefficiency data transmission and support for diverse data types and communication scenarios.Polar codes have emerged as a promising solution due to their outstanding error-correction performance and low complexity.Unequal error protection(UEP)involves nonuniform error safeguarding for distinct data segments,achieving a fine balance between error resilience and resource allocation,which ultimately enhancing system performance and efficiency.In this paper,we propose a novel class of UEP rateless polar codes.The codes are designed based on matrix extension of polar codes,and elegant mapping and duplication operations are designed to achieve UEP property while preserving the overall performance of conventional polar codes.Superior UEP performance is attained without significant modifications to conventional polar codes,making it straightforward for compatibility with existing polar codes.A theoretical analysis is conducted on the block error rate and throughput efficiency performance.To the best of our knowledge,this work provides the first theoretical performance analysis of UEP rateless polar codes.Simulation results show that the proposed codes significantly outperform existing polar coding schemes in both block error rate and throughput efficiency.
基金supported by National Natural Science Foundation of China(No.61801327).
文摘Differential pulse-position modulation(DP PM)can achieve a good compromise between power and bandwidth requirements.However,the output sequence has undetectable insertions and deletions.This paper proposes a successive cancellation(SC)decoding scheme based on the weighted levenshtein distance(WLD)of polar codes for correcting insertions/deletions in DPPM systems.In this method,the WLD is used to calculate the transfer probabilities recursively to obtain likelihood ratios,and the low-complexity SC decoding method is built according to the error characteristics to match the DPPM system.Additionally,the proposed SC decoding scheme is extended to list decoding,which can further improve error correction performance.Simulation results show that the proposed scheme can effectively correct insertions/deletions in the DPPM system,which enhances its reliability and performance.
文摘As artificial Intelligence(AI)continues to expand exponentially,particularly with the emergence of generative pre-trained transformers(GPT)based on a transformer’s architecture,which has revolutionized data processing and enabled significant improvements in various applications.This document seeks to investigate the security vulnerabilities detection in the source code using a range of large language models(LLM).Our primary objective is to evaluate the effectiveness of Static Application Security Testing(SAST)by applying various techniques such as prompt persona,structure outputs and zero-shot.To the selection of the LLMs(CodeLlama 7B,DeepSeek coder 7B,Gemini 1.5 Flash,Gemini 2.0 Flash,Mistral 7b Instruct,Phi 38b Mini 128K instruct,Qwen 2.5 coder,StartCoder 27B)with comparison and combination with Find Security Bugs.The evaluation method will involve using a selected dataset containing vulnerabilities,and the results to provide insights for different scenarios according to the software criticality(Business critical,non-critical,minimum effort,best effort)In detail,the main objectives of this study are to investigate if large language models outperform or exceed the capabilities of traditional static analysis tools,if the combining LLMs with Static Application Security Testing(SAST)tools lead to an improvement and the possibility that local machine learning models on a normal computer produce reliable results.Summarizing the most important conclusions of the research,it can be said that while it is true that the results have improved depending on the size of the LLM for business-critical software,the best results have been obtained by SAST analysis.This differs in“NonCritical,”“Best Effort,”and“Minimum Effort”scenarios,where the combination of LLM(Gemini)+SAST has obtained better results.
基金supported by Key Laboratory of Cyberspace Security,Ministry of Education,China。
文摘Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Although adversarial examples can strategically undermine the accuracy of BCSD models and protect critical code,existing techniques predominantly depend on inserting artificial instructions,which incur high computational costs and offer limited diversity of perturbations.To address these limitations,we propose AIMA,a novel gradient-guided assembly instruction relocation method.Our method decouples the detection model into tokenization,embedding,and encoding layers to enable efficient gradient computation.Since token IDs of instructions are discrete and nondifferentiable,we compute gradients in the continuous embedding space to evaluate the influence of each token.The most critical tokens are identified by calculating the L2 norm of their embedding gradients.We then establish a mapping between instructions and their corresponding tokens to aggregate token-level importance into instructionlevel significance.To maximize adversarial impact,a sliding window algorithm selects the most influential contiguous segments for relocation,ensuring optimal perturbation with minimal length.This approach efficiently locates critical code regions without expensive search operations.The selected segments are relocated outside their original function boundaries via a jump mechanism,which preserves runtime control flow and functionality while introducing“deletion”effects in the static instruction sequence.Extensive experiments show that AIMA reduces similarity scores by up to 35.8%in state-of-the-art BCSD models.When incorporated into training data,it also enhances model robustness,achieving a 5.9%improvement in AUROC.
基金the National Key R&D Program of China(No.2024YFE0110001)the National Natural Science Foundation of China(U1932219)the Mobility Programme endorsed by the Joint Committee of the Sino-German Center(M0728)。
文摘The ultracold neutron(UCN)transport code,MCUCN,designed initially for simulating UCN transportation from a solid deuterium(SD_2)source and neutron electric dipole moment experiments,could not simulate UCN storage and transportation in a superfluid^(4)He(SFHe,He-Ⅱ)source accurately.This limitation arose from the absence of an^(4)He upscattering mechanism and the absorption of^(3)He.And the provided source energy distribution in MCUCN is different from that in SFHe source.This study introduced enhancements to MCUCN to address these constraints,explicitly incorporating the^(4)He upscattering effect,the absorption of^(3)He,the loss caused by impurities on converter wall,UCN source energy distribution in SFHe,and the transmission through negative optical potential.Additionally,a Python-based visualization code for intermediate states and results was developed.To validate these enhancements,we systematically compared the simulation results of the Lujan Center Mark3 UCN system by MCUCN and the improved MCUCN code(iMCUCN)with UCNtransport simulations.Additionally,we compared the results of the SUN1 system simulated by MCUCN and iMCUCN with measurement results.The study demonstrates that iMCUCN effectively simulates the storage and transportation of ultracold neutrons in He-Ⅱ.
基金Fundamental Research Funds for the Central Universities under Grant 3072025YC0802the National Natural Science Foundation of China under Grant 62001138Heilongjiang Provincial Natural Science Foundation of China under Grant LH2021F009。
文摘Blind recognition of low-density paritycheck(LDPC)codes has gradually attracted more attention with the development of military and civil communications.However,in the case of the paritycheck matrices with relatively high row weights,the existing blind recognition algorithms based on a candidate set generally perform worse.In this paper,we propose a blind recognition method for LDPC codes,called as tangent function assisted least square(TLS)method,which improves recognition performances by constructing a new cost function.To characterize the constraint degree among received vectors and paritycheck vectors,a feature function based on tangent function is constructed in the proposed algorithm.A cost function based on least square method is also established according to the feature function values satisfying the parity-check relationship.Moreover,the minimum average value in TLS is obtained on the candidate set.Numerical analysis and simulation results show that recognition performances of TLS algorithm are consistent with theoretical results.Compared with existing algorithms,the proposed method possesses better recognition performances.
文摘LargeLanguageModels(LLMs)are increasingly appliedinthe fieldof code translation.However,existing evaluation methodologies suffer from two major limitations:(1)the high overlap between test data and pretraining corpora,which introduces significant bias in performance evaluation;and(2)mainstream metrics focus primarily on surface-level accuracy,failing to uncover the underlying factors that constrain model capabilities.To address these issues,this paper presents TCode(Translation-Oriented Code Evaluation benchmark)—a complexity-controllable,contamination-free benchmark dataset for code translation—alongside a dedicated static feature sensitivity evaluation framework.The dataset is carefully designed to control complexity along multiple dimensions—including syntactic nesting and expression intricacy—enabling both broad coverage and fine-grained differentiation of sample difficulty.This design supports precise evaluation of model capabilities across a wide spectrum of translation challenges.The proposed evaluation framework introduces a correlation-driven analysis mechanism based on static program features,enabling predictive modeling of translation success from two perspectives:Code Form Complexity(e.g.,code length and character density)and Semantic Modeling Complexity(e.g.,syntactic depth,control-flow nesting,and type system complexity).Empirical evaluations across representative LLMs—including Qwen2.5-72B and Llama3.3-70B—demonstrate that even state-of-the-art models achieve over 80% compilation success on simple samples,but their accuracy drops sharply below 40% on complex cases.Further correlation analysis indicates that Semantic Modeling Complexity alone is correlated with up to 60% of the variance in translation success,with static program features exhibiting nonlinear threshold effects that highlight clear capability boundaries.This study departs fromthe traditional accuracy-centric evaluation paradigm and,for the first time,systematically characterizes the capabilities of large languagemodels in translation tasks through the lens of programstatic features.The findings provide actionable insights for model refinement and training strategy development.
文摘Automated Program Repair(APR)techniques have shown significant potential in mitigating the cost and complexity associated with debugging by automatically generating corrective patches for software defects.Despite considerable progress in APR methodologies,existing approaches frequently lack contextual awareness of runtime behaviors and structural intricacies inherent in buggy source code.In this paper,we propose a novel APR approach that integrates attention mechanisms within an autoencoder-based framework,explicitly utilizing structural code affinity and execution context correlation derived from stack trace analysis.Our approach begins with an innovative preprocessing pipeline,where code segments and stack traces are transformed into tokenized representations.Subsequently,the BM25 ranking algorithm is employed to quantitatively measure structural code affinity and execution context correlation,identifying syntactically and semantically analogous buggy code snippets and relevant runtime error contexts from extensive repositories.These extracted features are then encoded via an attention-enhanced autoencoder model,specifically designed to capture significant patterns and correlations essential for effective patch generation.To assess the efficacy and generalizability of our proposed method,we conducted rigorous experimental comparisons against DeepFix,a state-of-the-art APR system,using a substantial dataset comprising 53,478 studentdeveloped C programs.Experimental outcomes indicate that our model achieves a notable bug repair success rate of approximately 62.36%,representing a statistically significant performance improvement of over 6%compared to the baseline.Furthermore,a thorough K-fold cross-validation reinforced the consistency,robustness,and reliability of our method across diverse subsets of the dataset.Our findings present the critical advantage of integrating attentionbased learning with code structural and execution context features in APR tasks,leading to improved accuracy and practical applicability.Future work aims to extend the model’s applicability across different programming languages,systematically optimize hyperparameters,and explore alternative feature representation methods to further enhance debugging efficiency and effectiveness.
基金supported by the National Natural Science Foundation of China(Grant No.62362019)the Natural Science Foundation of Hainan Province(Grant No.624RC482)the Hainan Provincial Higher Education Teaching Reform Research Project(Grant Hnjg2024-27).
文摘In erasure-coded storage systems,updating data requires parity maintenance,which often leads to significant I/O amplification due to“write-after-read”operations.Furthermore,scattered parity placement increases disk seek overhead during repair,resulting in degraded system performance.To address these challenges,this paper proposes a Cognitive Update and Repair Method(CURM)that leverages machine learning to classify files into writeonly,read-only,and read-write categories,enabling tailored update and repair strategies.For write-only and read-write files,CURM employs a data-differencemechanism combined with fine-grained I/O scheduling to minimize redundant read operations and mitigate I/O amplification.For read-write files,CURM further reserves adjacent disk space near parity blocks,supporting parallel reads and reducing disk seek overhead during repair.We implement CURM in a prototype system,Cognitive Update and Repair File System(CURFS),and conduct extensive experiments using realworld Network File System(NFS)and Microsoft Research(MSR)workloads on a 25-node cluster.Experimental results demonstrate that CURMimproves data update throughput by up to 82.52%,reduces recovery time by up to 47.47%,and decreases long-term storage overhead by more than 15% compared to state-of-the-art methods including Full Logging(FL),ParityLogging(PL),ParityLoggingwithReservedspace(PLR),andPARIX.These results validate the effectiveness of CURM in enhancing both update and repair performance,providing a scalable and efficient solution for large-scale erasure-coded storage systems.
文摘In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.
