{"url":"/task/clone-detection","name":"Clone Detection","slug":"clone-detection","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":68,"papers_with_code":27,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/codexglue","name":"CodeXGLUE","full_name":"","num_papers_in_archive":205}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":27,"of":27,"tagged_in_all":68,"items":[{"url":"/paper/codexglue-a-machine-learning-benchmark","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","date":"2021-02-09","arxiv_id":"2102.04664","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","arxiv_id":"2109.00859","repositories_listed":5,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/trained-without-my-consent-detecting-code","title":"Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code","date":"2024-02-14","arxiv_id":"2402.09299","repositories_listed":2,"syntology":null},{"url":"/paper/unified-pre-training-for-program","title":"Unified Pre-training for Program Understanding and Generation","date":"2021-03-10","arxiv_id":"2103.06333","repositories_listed":2,"syntology":null},{"url":"/paper/ast-enhanced-or-ast-overloaded-the-surprising","title":"AST-Enhanced or AST-Overloaded? The Surprising Impact of Hybrid Graph Representations on Code Clone Detection","date":"2025-06-17","arxiv_id":"2506.14470","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-use-of-deep-learning-models-for","title":"On the Use of Deep Learning Models for Semantic Clone Detection","date":"2024-12-19","arxiv_id":"2412.14739","repositories_listed":1,"syntology":null},{"url":"/paper/codesam-source-code-representation-learning","title":"CodeSAM: Source Code Representation Learning by Infusing Self-Attention with Multi-Code-View Graphs","date":"2024-11-21","arxiv_id":"2411.14611","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-the-interpretability-of","title":"Augmenting the Interpretability of GraphCodeBERT for Code Similarity Tasks","date":"2024-09-20","arxiv_id":"2410.05275","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-cross-language-code","title":"The Struggles of LLMs in Cross-lingual Code Clone Detection","date":"2024-08-08","arxiv_id":"2408.04430","repositories_listed":1,"syntology":null},{"url":"/paper/advanced-detection-of-source-code-clones-via","title":"Advanced Detection of Source Code Clones via an Ensemble of Unsupervised Similarity Measures","date":"2024-05-03","arxiv_id":"2405.02095","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-efficacy-of-large-language-1","title":"Investigating the Efficacy of Large Language Models for Code Clone Detection","date":"2024-01-24","arxiv_id":"2401.13802","repositories_listed":1,"syntology":null},{"url":"/paper/source-code-clone-detection-using","title":"Source Code Clone Detection Using Unsupervised Similarity Measures","date":"2024-01-18","arxiv_id":"2401.09885","repositories_listed":1,"syntology":null},{"url":"/paper/graph-convolutions-enrich-the-self-attention","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","date":"2023-12-07","arxiv_id":"2312.04234","repositories_listed":1,"syntology":{"n":29,"n_ran":19,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/transformcode-a-contrastive-learning","title":"TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation","date":"2023-11-10","arxiv_id":"2311.08157","repositories_listed":1,"syntology":null},{"url":"/paper/cloning-and-beyond-a-quantum-solution-to","title":"Cloning and Beyond: A Quantum Solution to Duplicate Code","date":"2023-10-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zc3-zero-shot-cross-language-code-clone","title":"ZC3: Zero-Shot Cross-Language Code Clone Detection","date":"2023-08-26","arxiv_id":"2308.13754","repositories_listed":1,"syntology":null},{"url":"/paper/graph-neural-networks-for-mapping-variables","title":"Graph Neural Networks For Mapping Variables Between Programs -- Extended Version","date":"2023-07-24","arxiv_id":"2307.13014","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-programs-by-exploiting-fuzzing","title":"Understanding Programs by Exploiting (Fuzzing) Test Cases","date":"2023-05-23","arxiv_id":"2305.13592","repositories_listed":1,"syntology":null},{"url":"/paper/transcoder-towards-unified-transferable-code","title":"TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills","date":"2023-05-23","arxiv_id":"2306.07285","repositories_listed":1,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/uniasm-binary-code-similarity-detection","title":"UniASM: Binary Code Similarity Detection without Fine-tuning","date":"2022-10-28","arxiv_id":"2211.01144","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/a-neural-network-architecture-for-program-1","title":"A Neural Network Architecture for Program Understanding Inspired by Human Behaviors","date":"2022-05-10","arxiv_id":"2206.04730","repositories_listed":1,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/on-the-cross-modal-transfer-from-natural","title":"On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules","date":"2022-04-19","arxiv_id":"2204.08653","repositories_listed":1,"syntology":null},{"url":"/paper/learning-program-semantics-with-code","title":"Learning Program Semantics with Code Representations: An Empirical Study","date":"2022-03-22","arxiv_id":"2203.11790","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-pre-trained-models-and-downstream","title":"Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding","date":"2021-12-04","arxiv_id":"2112.02268","repositories_listed":1,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/graphcodebert-pre-training-code","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","date":"2020-09-17","arxiv_id":"2009.08366","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-code-representation-learning","title":"Contrastive Code Representation Learning","date":"2020-07-09","arxiv_id":"2007.04973","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-code-clones-with-graph-neural","title":"Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree","date":"2020-02-20","arxiv_id":"2002.08653","repositories_listed":1,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}