{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/code-search","name":"Code Search","slug":"code-search","description_markdown":"The goal of **Code Search** is to retrieve code fragments from a large code corpus that most closely match a developer’s intent, which is expressed in natural language.\r\n\r\n\r\n<span class=\"description-source\">Source: [When Deep Learning Met Code Search ](https://arxiv.org/abs/1905.03813)</span>","categories":[{"name":"Computer Code","url":"/area/computer-code"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":125,"papers_with_code":60,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":14,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/code-search-on-codesearchnet","slug":"code-search-on-codesearchnet","dataset":"CodeSearchNet","dataset_url":"/dataset/codesearchnet","rows_in_archive":6,"metrics":["Overall","Go","Ruby","Python","Java","JS","PHP"],"first_row_in_archive_order":{"model":"cpt-code M","paper_title":"Text and Code Embeddings by Contrastive Pre-Training","paper_url":"/paper/text-and-code-embeddings-by-contrastive-pre","paper_date":"2022-01-24","arxiv_id":"2201.10005","code_links":[{"title":"openmatch/coco-dr","url":"https://github.com/openmatch/coco-dr"}],"syntology":null}},{"leaderboard":"/sota/code-search-on-codesc","slug":"code-search-on-codesc","dataset":"CoDesc","dataset_url":"/dataset/codesc","rows_in_archive":3,"metrics":["Test MRR"],"first_row_in_archive_order":{"model":"Self-attention","paper_title":"CoDesc: A Large Code-Description Parallel Dataset","paper_url":"/paper/codesc-a-large-code-description-parallel","paper_date":"2021-05-29","arxiv_id":"2105.14220","code_links":[{"title":"csebuetnlp/CoDesc","url":"https://github.com/csebuetnlp/CoDesc"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/codesc-a-large-code-description-parallel#ran","syntology_url":"https://syntology.ai/paper/2105.14220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14220"}},"official":{"repos":["csebuetnlp/CoDesc"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/code-search-on-codexglue-advtest","slug":"code-search-on-codexglue-advtest","dataset":"CodeXGLUE - AdvTest","dataset_url":"/dataset/codexglue","rows_in_archive":3,"metrics":["MRR"],"first_row_in_archive_order":{"model":"CodeT5+ 770M","paper_title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","paper_url":"/paper/codet5-open-code-large-language-models-for","paper_date":"2023-05-13","arxiv_id":"2305.07922","code_links":[{"title":"salesforce/codet5","url":"https://github.com/salesforce/codet5"},{"title":"leiluk1/codesearcher","url":"https://github.com/leiluk1/codesearcher"}],"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/codet5-open-code-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2305.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07922"}},"official":{"repos":["salesforce/codet5"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/code-search-on","slug":"code-search-on","dataset":null,"dataset_url":null,"rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Voyage-code-002","paper_title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","paper_url":"/paper/coir-a-comprehensive-benchmark-for-code","paper_date":"2024-07-03","arxiv_id":"2407.02883","code_links":[{"title":"coir-team/coir","url":"https://github.com/coir-team/coir"}],"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/coir-a-comprehensive-benchmark-for-code#ran","syntology_url":"https://syntology.ai/paper/2407.02883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02883"}},"official":{"repos":["coir-team/coir"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/code-search-on-codesearchnet-ruby","slug":"code-search-on-codesearchnet-ruby","dataset":"CodeSearchNet - Ruby","dataset_url":"/dataset/codesearchnet","rows_in_archive":1,"metrics":["MRR"],"first_row_in_archive_order":{"model":"Uni-SBT","paper_title":"Multimodal Representation for Neural Code Search","paper_url":"/paper/multimodal-representation-for-neural-code","paper_date":"2021-07-02","arxiv_id":"2107.00992","code_links":[{"title":"jianguda/mrncs","url":"https://github.com/jianguda/mrncs"}],"syntology":null}},{"leaderboard":"/sota/code-search-on-codexglue-webquerytest","slug":"code-search-on-codexglue-webquerytest","dataset":"CodeXGLUE - WebQueryTest","dataset_url":"/dataset/codexglue","rows_in_archive":1,"metrics":["Accuracy","F1"],"first_row_in_archive_order":{"model":"CodeBERT","paper_title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","paper_url":"/paper/codexglue-a-machine-learning-benchmark","paper_date":"2021-02-09","arxiv_id":"2102.04664","code_links":[{"title":"microsoft/CodeXGLUE","url":"https://github.com/microsoft/CodeXGLUE"},{"title":"facebookresearch/CodeGen","url":"https://github.com/facebookresearch/CodeGen"},{"title":"sberbank-ai/fusion_brain_aij2021","url":"https://github.com/sberbank-ai/fusion_brain_aij2021"},{"title":"kilimanj4r0/code-summarization-beyond-function-level","url":"https://github.com/kilimanj4r0/code-summarization-beyond-function-level"},{"title":"yueyuel/programgen-lms-reliability","url":"https://github.com/yueyuel/programgen-lms-reliability"},{"title":"Avmb/semantic_neq_game","url":"https://github.com/Avmb/semantic_neq_game"},{"title":"deeplearnxmu/unigencoder","url":"https://github.com/deeplearnxmu/unigencoder"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codexglue-a-machine-learning-benchmark#ran","syntology_url":"https://syntology.ai/paper/2102.04664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04664"}},"official":{"repos":["microsoft/CodeXGLUE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/code-search-on-coir","slug":"code-search-on-coir","dataset":"CoIR","dataset_url":"/dataset/coir","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Voyage-code-002","paper_title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","paper_url":"/paper/coir-a-comprehensive-benchmark-for-code","paper_date":"2024-07-03","arxiv_id":"2407.02883","code_links":[{"title":"coir-team/coir","url":"https://github.com/coir-team/coir"}],"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/coir-a-comprehensive-benchmark-for-code#ran","syntology_url":"https://syntology.ai/paper/2407.02883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02883"}},"official":{"repos":["coir-team/coir"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/codesearchnet","name":"CodeSearchNet","full_name":"","num_papers_in_archive":308},{"url":"/dataset/codexglue","name":"CodeXGLUE","full_name":"","num_papers_in_archive":205},{"url":"/dataset/conala","name":"CoNaLa","full_name":"CMU CoNaLa, the Code/Natural Language Challenge","num_papers_in_archive":77},{"url":"/dataset/xlcost","name":"XLCoST","full_name":"Cross-Lingual Code Snippet","num_papers_in_archive":22},{"url":"/dataset/staqc","name":"StaQC","full_name":"","num_papers_in_archive":19},{"url":"/dataset/coir","name":"CoIR","full_name":"Code Information Retrieval Benchmark","num_papers_in_archive":18},{"url":"/dataset/pytorrent","name":"PyTorrent","full_name":"PyTorrent","num_papers_in_archive":5},{"url":"/dataset/codesc","name":"CoDesc","full_name":"","num_papers_in_archive":4},{"url":"/dataset/cosqa-1","name":"CoSQA+","full_name":"CoSQA_Plus","num_papers_in_archive":1},{"url":"/dataset/isadetect-dataset","name":"ISAdetect dataset","full_name":"ISAdetect binary file and object code dataset","num_papers_in_archive":1},{"url":"/dataset/res-q","name":"RES-Q","full_name":"RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository Scale","num_papers_in_archive":1},{"url":"/dataset/search4code","name":"Search4Code","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/washed-contract","name":"washed_contract","full_name":"","num_papers_in_archive":1},{"url":"/dataset/codescan","name":"CodeSCAN","full_name":"ScreenCast ANalysis for Video Programming Tutorials","num_papers_in_archive":0}],"subtasks":[{"url":"/task/annotated-code-search","name":"Annotated Code Search"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":125,"of_with_code":60,"tagged_in_all":125,"counts":{"archive_papers_tagged":125,"with_a_code_link":60,"where_syntology_ran_a_sample":16,"not_listed_spam_title":0,"listed":125,"listed_where_code_ran":16,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":14,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":14,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/codesearchnet-challenge-evaluating-the-state","slug":"codesearchnet-challenge-evaluating-the-state","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","date":"2019-09-20","arxiv_id":"1909.09436","repositories_listed":14,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/codesearchnet-challenge-evaluating-the-state#ran","syntology_url":"https://syntology.ai/paper/1909.09436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.09436"}},"official":{"repos":["github/CodeSearchNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/codexglue-a-machine-learning-benchmark","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codexglue-a-machine-learning-benchmark#ran","syntology_url":"https://syntology.ai/paper/2102.04664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04664"}},"official":{"repos":["microsoft/CodeXGLUE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/autocoderover-autonomous-program-improvement","slug":"autocoderover-autonomous-program-improvement","title":"AutoCodeRover: Autonomous Program Improvement","date":"2024-04-08","arxiv_id":"2404.05427","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autocoderover-autonomous-program-improvement#ran","syntology_url":"https://syntology.ai/paper/2404.05427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05427"}},"official":{"repos":["nus-apr/auto-code-rover"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/melt-mining-effective-lightweight","slug":"melt-mining-effective-lightweight","title":"MELT: Mining Effective Lightweight Transformations from Pull Requests","date":"2023-08-28","arxiv_id":"2308.14687","repositories_listed":2,"syntology":null},{"url":"/paper/structure-aware-language-model-pretraining","slug":"structure-aware-language-model-pretraining","title":"Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data","date":"2023-05-31","arxiv_id":"2305.19912","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/structure-aware-language-model-pretraining#ran","syntology_url":"https://syntology.ai/paper/2305.19912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19912"}},"official":{"repos":["openmatch/openmatch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/codet5-open-code-large-language-models-for","slug":"codet5-open-code-large-language-models-for","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","date":"2023-05-13","arxiv_id":"2305.07922","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/codet5-open-code-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2305.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07922"}},"official":{"repos":["salesforce/codet5"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unixcoder-unified-cross-modal-pre-training","slug":"unixcoder-unified-cross-modal-pre-training","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","date":"2022-03-08","arxiv_id":"2203.03850","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unixcoder-unified-cross-modal-pre-training#ran","syntology_url":"https://syntology.ai/paper/2203.03850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03850"}},"official":{"repos":["microsoft/CodeBERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/memorization-and-generalization-in-neural","slug":"memorization-and-generalization-in-neural","title":"Memorization and Generalization in Neural Code Intelligence Models","date":"2021-06-16","arxiv_id":"2106.08704","repositories_listed":2,"syntology":null},{"url":"/paper/dobf-a-deobfuscation-pre-training-objective","slug":"dobf-a-deobfuscation-pre-training-objective","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","date":"2021-02-15","arxiv_id":"2102.07492","repositories_listed":2,"syntology":null},{"url":"/paper/concra-a-convolutional-neural-network-code","slug":"concra-a-convolutional-neural-network-code","title":"CoNCRA: A Convolutional Neural Network Code Retrieval Approach","date":"2020-09-03","arxiv_id":"2009.01959","repositories_listed":2,"syntology":null},{"url":"/paper/when-deep-learning-met-code-search","slug":"when-deep-learning-met-code-search","title":"When Deep Learning Met Code Search","date":"2019-05-09","arxiv_id":"1905.03813","repositories_listed":2,"syntology":null},{"url":"/paper/zero-shot-cross-domain-code-search-without","slug":"zero-shot-cross-domain-code-search-without","title":"Zero-Shot Cross-Domain Code Search without Fine-Tuning","date":"2025-04-10","arxiv_id":"2504.07740","repositories_listed":1,"syntology":null},{"url":"/paper/repository-level-code-search-with-neural","slug":"repository-level-code-search-with-neural","title":"Repository-level Code Search with Neural Retrieval Methods","date":"2025-02-10","arxiv_id":"2502.07067","repositories_listed":1,"syntology":null},{"url":"/paper/isotropy-matters-soft-zca-whitening-of","slug":"isotropy-matters-soft-zca-whitening-of","title":"Isotropy Matters: Soft-ZCA Whitening of Embeddings for Semantic Code Search","date":"2024-11-26","arxiv_id":"2411.17538","repositories_listed":1,"syntology":null},{"url":"/paper/codesam-source-code-representation-learning","slug":"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/vic-virtual-compiler-is-all-you-need-for","slug":"vic-virtual-compiler-is-all-you-need-for","title":"ViC: Virtual Compiler Is All You Need For Assembly Code Search","date":"2024-08-10","arxiv_id":"2408.06385","repositories_listed":1,"syntology":null},{"url":"/paper/coir-a-comprehensive-benchmark-for-code","slug":"coir-a-comprehensive-benchmark-for-code","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","date":"2024-07-03","arxiv_id":"2407.02883","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/coir-a-comprehensive-benchmark-for-code#ran","syntology_url":"https://syntology.ai/paper/2407.02883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02883"}},"official":{"repos":["coir-team/coir"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cosqa-enhancing-code-search-dataset-with","slug":"cosqa-enhancing-code-search-dataset-with","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","date":"2024-06-17","arxiv_id":"2406.11589","repositories_listed":1,"syntology":null},{"url":"/paper/repoqa-evaluating-long-context-code","slug":"repoqa-evaluating-long-context-code","title":"RepoQA: Evaluating Long Context Code Understanding","date":"2024-06-10","arxiv_id":"2406.06025","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/repoqa-evaluating-long-context-code#ran","syntology_url":"https://syntology.ai/paper/2406.06025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06025"}},"official":{"repos":["evalplus/repoqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/advanced-detection-of-source-code-clones-via","slug":"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/procqa-a-large-scale-community-based","slug":"procqa-a-large-scale-community-based","title":"ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search","date":"2024-03-25","arxiv_id":"2403.16702","repositories_listed":1,"syntology":null},{"url":"/paper/source-code-clone-detection-using","slug":"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/rewriting-the-code-a-simple-method-for-large","slug":"rewriting-the-code-a-simple-method-for-large","title":"Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search","date":"2024-01-09","arxiv_id":"2401.04514","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rewriting-the-code-a-simple-method-for-large#ran","syntology_url":"https://syntology.ai/paper/2401.04514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04514"}},"official":{"repos":["alex-haochenli/reco"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/gencodesearchnet-a-benchmark-test-suite-for","slug":"gencodesearchnet-a-benchmark-test-suite-for","title":"GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding","date":"2023-11-16","arxiv_id":"2311.09707","repositories_listed":1,"syntology":null},{"url":"/paper/transformcode-a-contrastive-learning","slug":"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/language-models-are-universal-embedders","slug":"language-models-are-universal-embedders","title":"Language Models are Universal Embedders","date":"2023-10-12","arxiv_id":"2310.08232","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-negative-pairs-in-code-search","slug":"rethinking-negative-pairs-in-code-search","title":"Rethinking Negative Pairs in Code Search","date":"2023-10-12","arxiv_id":"2310.08069","repositories_listed":1,"syntology":null},{"url":"/paper/constructing-multilingual-code-search-dataset","slug":"constructing-multilingual-code-search-dataset","title":"Constructing Multilingual Code Search Dataset Using Neural Machine Translation","date":"2023-06-27","arxiv_id":"2306.15604","repositories_listed":1,"syntology":null},{"url":"/paper/backdooring-neural-code-search","slug":"backdooring-neural-code-search","title":"Backdooring Neural Code Search","date":"2023-05-27","arxiv_id":"2305.17506","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/backdooring-neural-code-search#ran","syntology_url":"https://syntology.ai/paper/2305.17506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17506"}},"official":{"repos":["wssun/badcode"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/the-vault-a-comprehensive-multilingual","slug":"the-vault-a-comprehensive-multilingual","title":"The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation","date":"2023-05-09","arxiv_id":"2305.06156","repositories_listed":1,"syntology":null},{"url":"/paper/code-execution-with-pre-trained-language","slug":"code-execution-with-pre-trained-language","title":"Code Execution with Pre-trained Language Models","date":"2023-05-08","arxiv_id":"2305.05383","repositories_listed":1,"syntology":null},{"url":"/paper/on-contrastive-learning-of-semantic","slug":"on-contrastive-learning-of-semantic","title":"REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search Models","date":"2023-05-05","arxiv_id":"2305.03843","repositories_listed":1,"syntology":null},{"url":"/paper/one-adapter-for-all-programming-languages","slug":"one-adapter-for-all-programming-languages","title":"One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization","date":"2023-03-28","arxiv_id":"2303.15822","repositories_listed":1,"syntology":null},{"url":"/paper/tail-batch-sampling-approximating-global","slug":"tail-batch-sampling-approximating-global","title":"Global Contrastive Batch Sampling via Optimization on Sample Permutations","date":"2022-10-23","arxiv_id":"2210.12874","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tail-batch-sampling-approximating-global#ran","syntology_url":"https://syntology.ai/paper/2210.12874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12874"}},"official":{"repos":["vinayak1/gcbs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-representation-level-augmentation","slug":"exploring-representation-level-augmentation","title":"Exploring Representation-Level Augmentation for Code Search","date":"2022-10-21","arxiv_id":"2210.12285","repositories_listed":1,"syntology":null},{"url":"/paper/contragen-effective-contrastive-learning-for","slug":"contragen-effective-contrastive-learning-for","title":"ContraCLM: Contrastive Learning For Causal Language Model","date":"2022-10-03","arxiv_id":"2210.01185","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/contragen-effective-contrastive-learning-for#ran","syntology_url":"https://syntology.ai/paper/2210.01185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01185"}},"official":null}},{"url":"/paper/xlcost-a-benchmark-dataset-for-cross-lingual","slug":"xlcost-a-benchmark-dataset-for-cross-lingual","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","date":"2022-06-16","arxiv_id":"2206.08474","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/xlcost-a-benchmark-dataset-for-cross-lingual#ran","syntology_url":"https://syntology.ai/paper/2206.08474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08474"}},"official":{"repos":["reddy-lab-code-research/xlcost"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ns3-neuro-symbolic-semantic-code-search","slug":"ns3-neuro-symbolic-semantic-code-search","title":"NS3: Neuro-Symbolic Semantic Code Search","date":"2022-05-21","arxiv_id":"2205.10674","repositories_listed":1,"syntology":null},{"url":"/paper/code-search-based-on-context-aware-code","slug":"code-search-based-on-context-aware-code","title":"Code Search based on Context-aware Code Translation","date":"2022-02-16","arxiv_id":"2202.08029","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-importance-of-building-high-quality","slug":"on-the-importance-of-building-high-quality","title":"On the Importance of Building High-quality Training Datasets for Neural Code Search","date":"2022-02-14","arxiv_id":"2202.06649","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-importance-of-building-high-quality#ran","syntology_url":"https://syntology.ai/paper/2202.06649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06649"}},"official":{"repos":["v587su/nlqf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/what-do-they-capture-a-structural-analysis-of","slug":"what-do-they-capture-a-structural-analysis-of","title":"What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code","date":"2022-02-14","arxiv_id":"2202.06840","repositories_listed":1,"syntology":null},{"url":"/paper/learning-deep-semantic-model-for-code-search","slug":"learning-deep-semantic-model-for-code-search","title":"Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus","date":"2022-01-27","arxiv_id":"2201.11313","repositories_listed":1,"syntology":null},{"url":"/paper/coderetriever-unimodal-and-bimodal-1","slug":"coderetriever-unimodal-and-bimodal-1","title":"CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search","date":"2022-01-26","arxiv_id":"2201.10866","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/coderetriever-unimodal-and-bimodal-1#ran","syntology_url":"https://syntology.ai/paper/2201.10866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10866"}},"official":{"repos":["microsoft/ar2"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/generating-clarifying-questions-for-query","slug":"generating-clarifying-questions-for-query","title":"Generating Clarifying Questions for Query Refinement in Source Code Search","date":"2022-01-24","arxiv_id":"2201.09974","repositories_listed":1,"syntology":null},{"url":"/paper/text-and-code-embeddings-by-contrastive-pre","slug":"text-and-code-embeddings-by-contrastive-pre","title":"Text and Code Embeddings by Contrastive Pre-Training","date":"2022-01-24","arxiv_id":"2201.10005","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-pre-trained-models-and-downstream","slug":"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":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-pre-trained-models-and-downstream#ran","syntology_url":"https://syntology.ai/paper/2112.02268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02268"}},"official":{"repos":["wangdeze18/DACL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/graphsearchnet-enhancing-gnns-via-capturing","slug":"graphsearchnet-enhancing-gnns-via-capturing","title":"GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search","date":"2021-11-04","arxiv_id":"2111.02671","repositories_listed":1,"syntology":null},{"url":"/paper/is-a-single-model-enough-mucos-a-multi-model","slug":"is-a-single-model-enough-mucos-a-multi-model","title":"Is a Single Model Enough? MuCoS: A Multi-Model Ensemble Learning for Semantic Code Search","date":"2021-07-10","arxiv_id":"2107.04773","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-representation-for-neural-code","slug":"multimodal-representation-for-neural-code","title":"Multimodal Representation for Neural Code Search","date":"2021-07-02","arxiv_id":"2107.00992","repositories_listed":1,"syntology":null},{"url":"/paper/codesc-a-large-code-description-parallel","slug":"codesc-a-large-code-description-parallel","title":"CoDesc: A Large Code-Description Parallel Dataset","date":"2021-05-29","arxiv_id":"2105.14220","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/codesc-a-large-code-description-parallel#ran","syntology_url":"https://syntology.ai/paper/2105.14220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14220"}},"official":{"repos":["csebuetnlp/CoDesc"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cosqa-20000-web-queries-for-code-search-and","slug":"cosqa-20000-web-queries-for-code-search-and","title":"CoSQA: 20,000+ Web Queries for Code Search and Question Answering","date":"2021-05-27","arxiv_id":"2105.13239","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/cosqa-20000-web-queries-for-code-search-and#ran","syntology_url":"https://syntology.ai/paper/2105.13239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13239"}},"official":{"repos":["Jun-jie-Huang/CoCLR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/degraphcs-embedding-variable-based-flow-graph","slug":"degraphcs-embedding-variable-based-flow-graph","title":"deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search","date":"2021-03-24","arxiv_id":"2103.13020","repositories_listed":1,"syntology":null},{"url":"/paper/palmtree-learning-an-assembly-language-model","slug":"palmtree-learning-an-assembly-language-model","title":"PalmTree: Learning an Assembly Language Model for Instruction Embedding","date":"2021-01-21","arxiv_id":"2103.03809","repositories_listed":1,"syntology":null},{"url":"/paper/code-search-intent-classification-using-weak","slug":"code-search-intent-classification-using-weak","title":"Search4Code: Code Search Intent Classification Using Weak Supervision","date":"2020-11-24","arxiv_id":"2011.11950","repositories_listed":1,"syntology":null},{"url":"/paper/graphcodebert-pre-training-code","slug":"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/neural-code-search-revisited-enhancing-code","slug":"neural-code-search-revisited-enhancing-code","title":"Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent","date":"2020-08-27","arxiv_id":"2008.12193","repositories_listed":1,"syntology":null},{"url":"/paper/faster-person-re-identification","slug":"faster-person-re-identification","title":"Faster Person Re-Identification","date":"2020-08-16","arxiv_id":"2008.06826","repositories_listed":1,"syntology":null},{"url":"/paper/funcgnn-a-graph-neural-network-approach-to","slug":"funcgnn-a-graph-neural-network-approach-to","title":"funcGNN: A Graph Neural Network Approach to Program Similarity","date":"2020-07-26","arxiv_id":"2007.13239","repositories_listed":1,"syntology":null},{"url":"/paper/graph4code-a-machine-interpretable-knowledge","slug":"graph4code-a-machine-interpretable-knowledge","title":"A Toolkit for Generating Code Knowledge Graphs","date":"2020-02-21","arxiv_id":"2002.09440","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-how-developers-use-general-purpose","slug":"evaluating-how-developers-use-general-purpose","title":"Evaluating How Developers Use General-Purpose Web-Search for Code Retrieval","date":"2018-03-22","arxiv_id":"1803.08612","repositories_listed":1,"syntology":null},{"url":null,"slug":"mgs3-a-multi-granularity-self-supervised-code","title":"MGS3: A Multi-Granularity Self-Supervised Code Search Framework","date":"2025-05-30","arxiv_id":"2505.24274","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeprtl2-a-versatile-model-for-rtl-related","title":"DeepRTL2: A Versatile Model for RTL-Related Tasks","date":"2025-05-28","arxiv_id":"2506.15697","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-graph-based-repository-level-code","title":"Knowledge Graph Based Repository-Level Code Generation","date":"2025-05-20","arxiv_id":"2505.14394","repositories_listed":0,"syntology":null},{"url":null,"slug":"leancode-understanding-models-better-for-code","title":"LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models","date":"2025-05-20","arxiv_id":"2505.14759","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-are-qualified-benchmark","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","date":"2025-04-28","arxiv_id":"2504.19444","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-leveraging-large-language-model","title":"Towards Leveraging Large Language Model Summaries for Topic Modeling in Source Code","date":"2025-04-24","arxiv_id":"2504.17426","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-mixup-inspired-augmentation","title":"A Study on Mixup-Inspired Augmentation Methods for Software Vulnerability Detection","date":"2025-04-22","arxiv_id":"2504.15632","repositories_listed":0,"syntology":null},{"url":"/paper/oasis-order-augmented-strategy-for-improved","slug":"oasis-order-augmented-strategy-for-improved","title":"OASIS: Order-Augmented Strategy for Improved Code Search","date":"2025-03-11","arxiv_id":"2503.08161","repositories_listed":0,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/oasis-order-augmented-strategy-for-improved#ran","syntology_url":"https://syntology.ai/paper/2503.08161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08161"}},"official":null}},{"url":null,"slug":"loracode-lora-adapters-for-code-embeddings","title":"LoRACode: LoRA Adapters for Code Embeddings","date":"2025-03-07","arxiv_id":"2503.05315","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-model-to-train-them-all-hierarchical-self","title":"MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings","date":"2025-03-04","arxiv_id":"2503.03008","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-natural-language-perplexity-detecting","title":"Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets","date":"2025-02-27","arxiv_id":"2502.20246","repositories_listed":0,"syntology":null},{"url":null,"slug":"ureca-the-chain-of-two-minimum-set-cover","title":"URECA: The Chain of Two Minimum Set Cover Problems exists behind Adaptation to Shifts in Semantic Code Search","date":"2025-02-11","arxiv_id":"2502.07494","repositories_listed":0,"syntology":null},{"url":null,"slug":"orcaloca-an-llm-agent-framework-for-software","title":"OrcaLoca: An LLM Agent Framework for Software Issue Localization","date":"2025-02-01","arxiv_id":"2502.00350","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-compression-of-language-models-for","title":"On the Compression of Language Models for Code: An Empirical Study on CodeBERT","date":"2024-12-18","arxiv_id":"2412.13737","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-the-loop-hyper-parameter-optimization-for","title":"In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics","date":"2024-10-07","arxiv_id":"2410.16309","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-code-search-with-naming-agnostic","title":"Deep Code Search with Naming-Agnostic Contrastive Multi-View Learning","date":"2024-08-18","arxiv_id":"2408.09345","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-outlines-for-code-literate","title":"Natural Language Outlines for Code: Literate Programming in the LLM Era","date":"2024-08-09","arxiv_id":"2408.04820","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02232","title":"SpecRover: Code Intent Extraction via LLMs","date":"2024-08-05","arxiv_id":"2408.02232","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-agents-improve-semantic-code-search","title":"LLM Agents Improve Semantic Code Search","date":"2024-08-05","arxiv_id":"2408.11058","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-exploring-the-code-understanding","title":"Toward Exploring the Code Understanding Capabilities of Pre-trained Code Generation Models","date":"2024-06-18","arxiv_id":"2406.12326","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-search-debiasing-improve-search-results","title":"Code Search Debiasing:Improve Search Results beyond Overall Ranking Performance","date":"2023-11-25","arxiv_id":"2311.14901","repositories_listed":0,"syntology":null},{"url":null,"slug":"noisy-pair-corrector-for-dense-retrieval","title":"Noisy Pair Corrector for Dense Retrieval","date":"2023-11-07","arxiv_id":"2311.03798","repositories_listed":0,"syntology":null},{"url":null,"slug":"aces-generating-diverse-programming-puzzles","title":"ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models","date":"2023-10-15","arxiv_id":"2310.10692","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-prompt-learning-based-code-search","title":"Contrastive Prompt Learning-based Code Search based on Interaction Matrix","date":"2023-10-10","arxiv_id":"2310.06342","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-representation-pre-training-with","title":"Code Representation Pre-training with Complements from Program Executions","date":"2023-09-04","arxiv_id":"2309.09980","repositories_listed":0,"syntology":null},{"url":null,"slug":"laminar-a-new-serverless-stream-based","title":"Laminar: A New Serverless Stream-based Framework with Semantic Code Search and Code Completion","date":"2023-09-01","arxiv_id":"2309.00584","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-and-optimizing-the-effectiveness","title":"Evaluating and Optimizing the Effectiveness of Neural Machine Translation in Supporting Code Retrieval Models: A Study on the CAT Benchmark","date":"2023-08-09","arxiv_id":"2308.04693","repositories_listed":0,"syntology":null},{"url":null,"slug":"cct-code-cross-consistency-training-for","title":"CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search","date":"2023-05-19","arxiv_id":"2305.11626","repositories_listed":0,"syntology":null},{"url":null,"slug":"searching-by-code-a-new-searchbysnippet","title":"Searching by Code: a New SearchBySnippet Dataset and SnippeR Retrieval Model for Searching by Code Snippets","date":"2023-05-19","arxiv_id":"2305.11625","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-zero-shot-code-cloning-with","title":"Neuro-symbolic Zero-Shot Code Cloning with Cross-Language Intermediate Representation","date":"2023-04-26","arxiv_id":"2304.13350","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-self-attention-powerful-to-learn-code","title":"Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities","date":"2022-12-20","arxiv_id":"2212.10017","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-don-t-know-search-helping-users-find-code","title":"You Don't Know Search: Helping Users Find Code by Automatically Evaluating Alternative Queries","date":"2022-12-07","arxiv_id":"2212.03459","repositories_listed":0,"syntology":null},{"url":null,"slug":"codedsi-differentiable-code-search","title":"CodeDSI: Differentiable Code Search","date":"2022-10-01","arxiv_id":"2210.00328","repositories_listed":0,"syntology":null},{"url":null,"slug":"cssam-code-search-via-attention-matching-of","title":"CSSAM:Code Search via Attention Matching of Code Semantics and Structures","date":"2022-08-08","arxiv_id":"2208.03922","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-semantic-code-search-with","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","date":"2022-04-07","arxiv_id":"2204.03293","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-transferability-of-pre-trained-1","title":"On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages","date":"2022-04-05","arxiv_id":"2204.09653","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-code-search-with-deep-hashing","title":"Accelerating Code Search with Deep Hashing and Code Classification","date":"2022-03-29","arxiv_id":"2203.15287","repositories_listed":0,"syntology":null},{"url":null,"slug":"astbert-enabling-language-model-for-code","title":"AstBERT: Enabling Language Model for Financial Code Understanding with Abstract Syntax Trees","date":"2022-01-20","arxiv_id":"2201.07984","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-codebert-s-performance-on-natural","title":"Analyzing CodeBERT's Performance on Natural Language Code Search","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"better-modeling-the-programming-world-with","title":"Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning","date":"2022-01-10","arxiv_id":"2201.03346","repositories_listed":0,"syntology":null}],"syntology_records":19,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":16,"papers_where_code_ran_first_page":"/task/code-search/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/code-search/papers/2","json":"/task/code-search/papers/2.json","rows":25},{"order":"ran","page":1,"of":1,"url":"/task/code-search/papers/ran/1","json":"/task/code-search/papers/ran/1.json","rows":16}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"6351e24f5e2a21c20a53d6fb4da08d98ff2d29d144f42c175801646222e3b96b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}