MASTOR is a multi-agent system that generates semantic test oracles from REST API source code via source extraction and dual oracle-generation paths with challenger review, achieving 75.4% average mutation score on 13 projects.
Traces of memorisation in large language models for code
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
Plainbook makes data-science notebooks natural-language-first by preserving cell descriptions, generating code via AI, enforcing linear execution via a checkpointing kernel, and adding value-centered cell and global tests.
Kani is a model checker that compiles Rust proof harnesses from MIR to CBMC for bounded verification of safety properties and supports contracts to extend checks to unbounded correctness.
AdaTrans uses strategy-driven RAG, error-stratified transformation, and multi-stage validation to reach 95.51% mean compilation pass rate and 81.09% solve rate on 104 algorithmic problems with only 1.19% unsafe files.
A large open crowdsourced effort verifies substantial parts of the Rust standard library for memory safety properties by integrating complementary verification tools into CI on a forked repository.
ATTAIN is a three-module trace-driven framework that combines exploit execution, LLM-guided diff search, and evidence-based judgment to identify affected library versions for CVEs, reporting 93.24% F1 on 224 CVEs across 25,943 versions.
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
RL Developer Memory is a feedback-normalized, safety-gated memory architecture for RL coding agents that logs contextual decisions and applies conservative off-policy gates to maintain 80% decision accuracy and full hard-negative suppression on a 200-case benchmark.
EditFlow reconstructs temporal developer editing flows from code changes to benchmark and optimize AI code edit recommenders so they align with natural incremental reasoning rather than static snapshots.
LLM approaches ExArch and ArTEMiS reach F1 scores of 0.86 and 0.81 for architecture entity recognition and traceability, matching or approaching baselines that require manual models.
MR-Adopt deduces input transformations from hard-coded MR test cases using LLMs, data-flow refinement, and output-relation selection to enable reuse with new source inputs.
Describes a tool landscape (REST API, TraceView, TraceViz) that makes ARDoCo's four TLR pipelines publicly accessible with a preliminary study showing TraceViz improves developer comprehension.
SBridge uses cross-domain control block matching to find source-to-binary function similarity, reporting 75.13% recall@1 and 80.98% recall@5 on 3,904 real-world binaries despite ~40% inlining.
citing papers explorer
-
MASTOR: A Multi-Agent Approach to Semantic Test Oracle Generation for RESTful APIs
MASTOR is a multi-agent system that generates semantic test oracles from REST API source code via source extraction and dual oracle-generation paths with challenger review, achieving 75.4% average mutation score on 13 projects.
-
Plainbook: Data Science, in Plain Language
Plainbook makes data-science notebooks natural-language-first by preserving cell descriptions, generating code via AI, enforcing linear execution via a checkpointing kernel, and adding value-centered cell and global tests.
-
Kani: A Model Checker for Rust
Kani is a model checker that compiles Rust proof harnesses from MIR to CBMC for bounded verification of safety properties and supports contracts to extend checks to unbounded correctness.
-
AdaTrans: Automated C to Rust Transformation via Error-Adaptive Repair
AdaTrans uses strategy-driven RAG, error-stratified transformation, and multi-stage validation to reach 95.51% mean compilation pass rate and 81.09% solve rate on 104 algorithmic problems with only 1.19% unsafe files.
-
Verifying the Rust Standard Library
A large open crowdsourced effort verifies substantial parts of the Rust standard library for memory safety properties by integrating complementary verification tools into CI on a forked repository.
-
ATTAIN: Automated Exploit Failure Analysis through Trace-Driven Diff Analysis
ATTAIN is a three-module trace-driven framework that combines exploit execution, LLM-guided diff search, and evidence-based judgment to identify affected library versions for CVEs, reporting 93.24% F1 on 224 CVEs across 25,943 versions.
-
Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
-
Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture
RL Developer Memory is a feedback-normalized, safety-gated memory architecture for RL coding agents that logs contextual decisions and applies conservative off-policy gates to maintain 80% decision accuracy and full hard-negative suppression on a 200-case benchmark.
-
EditFlow: Benchmarking and Optimizing Code Edit Recommendation Systems via Reconstruction of Developer Flows
EditFlow reconstructs temporal developer editing flows from code changes to benchmark and optimize AI code edit recommenders so they align with natural incremental reasoning rather than static snapshots.
-
Who's Who? LLM-assisted Software Traceability with Architecture Entity Recognition
LLM approaches ExArch and ArTEMiS reach F1 scores of 0.86 and 0.81 for architecture entity recognition and traceability, matching or approaching baselines that require manual models.
-
MR-Adopt: Automatic Deduction of Input Transformation Function for Metamorphic Testing
MR-Adopt deduces input transformations from hard-coded MR test cases using LLMs, data-flow refinement, and output-relation selection to enable reuse with new source inputs.
-
The ARDoCo Tool Landscape: REST API, TraceView, and TraceViz for Architecture Traceability
Describes a tool landscape (REST API, TraceView, TraceViz) that makes ARDoCo's four TLR pipelines publicly accessible with a preliminary study showing TraceViz improves developer comprehension.
-
SBridge: Identifying Source-to-Binary Function Similarity via Cross-Domain Control Block Matching
SBridge uses cross-domain control block matching to find source-to-binary function similarity, reporting 75.13% recall@1 and 80.98% recall@5 on 3,904 real-world binaries despite ~40% inlining.