{"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-generation/papers/7","list_of":"/task/code-generation","task":"Code Generation","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":17,"rows_per_page":100,"rows":[601,700],"of":1697,"counts":{"archive_papers_tagged":1697,"with_a_code_link":745,"where_syntology_ran_a_sample":280,"not_listed_spam_title":0,"listed":1697,"listed_where_code_ran":280,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":238,"every_run_a_failure_of_syntologys_instrument":42,"listed_with_a_run_with_no_instrument_failure":238,"listed_every_run_a_failure_of_syntologys_instrument":42,"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"},"first_page":"/task/code-generation","prev":"/task/code-generation/papers/6","next":"/task/code-generation/papers/8","papers":[{"url":"/paper/codegen4libs-a-two-stage-approach-for-library","slug":"codegen4libs-a-two-stage-approach-for-library","title":"CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code Generation","date":"2023-09-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/textbooks-are-all-you-need-ii-phi-1-5","slug":"textbooks-are-all-you-need-ii-phi-1-5","title":"Textbooks Are All You Need II: phi-1.5 technical report","date":"2023-09-11","arxiv_id":"2309.05463","repositories_listed":1,"syntology":null},{"url":"/paper/code-style-in-context-learning-for-knowledge","slug":"code-style-in-context-learning-for-knowledge","title":"Code-Style In-Context Learning for Knowledge-Based Question Answering","date":"2023-09-09","arxiv_id":"2309.04695","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":1,"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/code-style-in-context-learning-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2309.04695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.04695"}},"official":{"repos":["arthurizijar/kb-coder"],"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/improving-code-generation-by-dynamic","slug":"improving-code-generation-by-dynamic","title":"Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models","date":"2023-09-06","arxiv_id":"2309.02772","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-code-generation-by-dynamic#ran","syntology_url":"https://syntology.ai/paper/2309.02772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.02772"}},"official":{"repos":["lj2lijia/adapt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/codeapex-a-bilingual-programming-evaluation","slug":"codeapex-a-bilingual-programming-evaluation","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","date":"2023-09-05","arxiv_id":"2309.01940","repositories_listed":1,"syntology":null},{"url":"/paper/copiloting-the-copilots-fusing-large-language","slug":"copiloting-the-copilots-fusing-large-language","title":"Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair","date":"2023-09-01","arxiv_id":"2309.00608","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"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, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/copiloting-the-copilots-fusing-large-language#ran","syntology_url":"https://syntology.ai/paper/2309.00608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00608"}},"official":{"repos":["ise-uiuc/Repilot"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/biocoder-a-benchmark-for-bioinformatics-code","slug":"biocoder-a-benchmark-for-bioinformatics-code","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","date":"2023-08-31","arxiv_id":"2308.16458","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":1,"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/biocoder-a-benchmark-for-bioinformatics-code#ran","syntology_url":"https://syntology.ai/paper/2308.16458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16458"}},"official":{"repos":["gersteinlab/biocoder"],"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/when-do-program-of-thoughts-work-for","slug":"when-do-program-of-thoughts-work-for","title":"When Do Program-of-Thoughts Work for Reasoning?","date":"2023-08-29","arxiv_id":"2308.15452","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-parameter-efficient-fine-tuning","slug":"exploring-parameter-efficient-fine-tuning","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","date":"2023-08-21","arxiv_id":"2308.10462","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"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, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/exploring-parameter-efficient-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2308.10462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10462"}},"official":{"repos":["martin-wey/peft-llm-code"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-study-on-robustness-and-reliability-of","slug":"a-study-on-robustness-and-reliability-of","title":"Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation","date":"2023-08-20","arxiv_id":"2308.10335","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-study-on-robustness-and-reliability-of#ran","syntology_url":"https://syntology.ai/paper/2308.10335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10335"}},"official":{"repos":["floridsleeves/robustapi"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/inductive-bias-learning-generating-code","slug":"inductive-bias-learning-generating-code","title":"Inductive-bias Learning: Generating Code Models with Large Language Model","date":"2023-08-19","arxiv_id":"2308.09890","repositories_listed":1,"syntology":null},{"url":"/paper/case-study-using-ai-assisted-code-generation","slug":"case-study-using-ai-assisted-code-generation","title":"Case Study: Using AI-Assisted Code Generation In Mobile Teams","date":"2023-08-09","arxiv_id":"2308.04736","repositories_listed":1,"syntology":null},{"url":"/paper/vulnerabilities-in-ai-code-generators","slug":"vulnerabilities-in-ai-code-generators","title":"Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks","date":"2023-08-04","arxiv_id":"2308.04451","repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-for-digital-forensic-investigation","slug":"chatgpt-for-digital-forensic-investigation","title":"ChatGPT for Digital Forensic Investigation: The Good, The Bad, and The Unknown","date":"2023-07-10","arxiv_id":"2307.10195","repositories_listed":1,"syntology":null},{"url":"/paper/code-generation-for-machine-learning-using","slug":"code-generation-for-machine-learning-using","title":"Code Generation for Machine Learning using Model-Driven Engineering and SysML","date":"2023-07-10","arxiv_id":"2307.05584","repositories_listed":1,"syntology":null},{"url":"/paper/rltf-reinforcement-learning-from-unit-test","slug":"rltf-reinforcement-learning-from-unit-test","title":"RLTF: Reinforcement Learning from Unit Test Feedback","date":"2023-07-10","arxiv_id":"2307.04349","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rltf-reinforcement-learning-from-unit-test#ran","syntology_url":"https://syntology.ai/paper/2307.04349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04349"}},"official":{"repos":["zyq-scut/rltf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/qigen-generating-efficient-kernels-for","slug":"qigen-generating-efficient-kernels-for","title":"QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Models","date":"2023-07-07","arxiv_id":"2307.03738","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-language-models-of-code-with-global","slug":"guiding-language-models-of-code-with-global","title":"Guiding Language Models of Code with Global Context using Monitors","date":"2023-06-19","arxiv_id":"2306.10763","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/guiding-language-models-of-code-with-global#ran","syntology_url":"https://syntology.ai/paper/2306.10763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.10763"}},"official":{"repos":["microsoft/monitors4codegen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/demystifying-gpt-self-repair-for-code","slug":"demystifying-gpt-self-repair-for-code","title":"Is Self-Repair a Silver Bullet for Code Generation?","date":"2023-06-16","arxiv_id":"2306.09896","repositories_listed":1,"syntology":null},{"url":"/paper/modular-visual-question-answering-via-code","slug":"modular-visual-question-answering-via-code","title":"Modular Visual Question Answering via Code Generation","date":"2023-06-08","arxiv_id":"2306.05392","repositories_listed":1,"syntology":null},{"url":"/paper/is-model-attention-aligned-with-human","slug":"is-model-attention-aligned-with-human","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","date":"2023-06-02","arxiv_id":"2306.01220","repositories_listed":1,"syntology":null},{"url":"/paper/llmatic-neural-architecture-search-via-large","slug":"llmatic-neural-architecture-search-via-large","title":"LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization","date":"2023-06-01","arxiv_id":"2306.01102","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llmatic-neural-architecture-search-via-large#ran","syntology_url":"https://syntology.ai/paper/2306.01102","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01102"}},"official":{"repos":["umair-nasir14/llmatic"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sheetcopilot-bringing-software-productivity","slug":"sheetcopilot-bringing-software-productivity","title":"SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models","date":"2023-05-30","arxiv_id":"2305.19308","repositories_listed":1,"syntology":null},{"url":"/paper/a-systematic-study-and-comprehensive","slug":"a-systematic-study-and-comprehensive","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","date":"2023-05-29","arxiv_id":"2305.18486","repositories_listed":1,"syntology":null},{"url":"/paper/anpl-compiling-natural-programs-with","slug":"anpl-compiling-natural-programs-with","title":"ANPL: Towards Natural Programming with Interactive Decomposition","date":"2023-05-29","arxiv_id":"2305.18498","repositories_listed":1,"syntology":null},{"url":"/paper/algo-synthesizing-algorithmic-programs-with-1","slug":"algo-synthesizing-algorithmic-programs-with-1","title":"ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers","date":"2023-05-24","arxiv_id":"2305.14591","repositories_listed":1,"syntology":null},{"url":"/paper/bytesized32-a-corpus-and-challenge-task-for","slug":"bytesized32-a-corpus-and-challenge-task-for","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","date":"2023-05-24","arxiv_id":"2305.14879","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bytesized32-a-corpus-and-challenge-task-for#ran","syntology_url":"https://syntology.ai/paper/2305.14879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14879"}},"official":{"repos":["cognitiveailab/bytesized32"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/from-words-to-wires-generating-functioning","slug":"from-words-to-wires-generating-functioning","title":"From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions","date":"2023-05-24","arxiv_id":"2305.14874","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/from-words-to-wires-generating-functioning#ran","syntology_url":"https://syntology.ai/paper/2305.14874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14874"}},"official":{"repos":["cognitiveailab/words2wires"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/is-gpt-4-a-good-data-analyst","slug":"is-gpt-4-a-good-data-analyst","title":"Is GPT-4 a Good Data Analyst?","date":"2023-05-24","arxiv_id":"2305.15038","repositories_listed":1,"syntology":null},{"url":"/paper/the-larger-they-are-the-harder-they-fail","slug":"the-larger-they-are-the-harder-they-fail","title":"The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python","date":"2023-05-24","arxiv_id":"2305.15507","repositories_listed":1,"syntology":null},{"url":"/paper/who-wrote-this-code-watermarking-for-code","slug":"who-wrote-this-code-watermarking-for-code","title":"Who Wrote this Code? Watermarking for Code Generation","date":"2023-05-24","arxiv_id":"2305.15060","repositories_listed":1,"syntology":null},{"url":"/paper/generating-data-for-symbolic-language-with","slug":"generating-data-for-symbolic-language-with","title":"Generating Data for Symbolic Language with Large Language Models","date":"2023-05-23","arxiv_id":"2305.13917","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"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, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generating-data-for-symbolic-language-with#ran","syntology_url":"https://syntology.ai/paper/2305.13917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13917"}},"official":{"repos":["hkunlp/symgen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/let-s-sample-step-by-step-adaptive","slug":"let-s-sample-step-by-step-adaptive","title":"Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs","date":"2023-05-19","arxiv_id":"2305.11860","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/let-s-sample-step-by-step-adaptive#ran","syntology_url":"https://syntology.ai/paper/2305.11860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11860"}},"official":{"repos":["Pranjal2041/AdaptiveConsistency"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leti-learning-to-generate-from-textual","slug":"leti-learning-to-generate-from-textual","title":"LeTI: Learning to Generate from Textual Interactions","date":"2023-05-17","arxiv_id":"2305.10314","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/leti-learning-to-generate-from-textual#ran","syntology_url":"https://syntology.ai/paper/2305.10314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10314"}},"official":{"repos":["xingyaoww/leti"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","repositories_listed":1,"syntology":null},{"url":"/paper/autonomous-gis-the-next-generation-ai-powered","slug":"autonomous-gis-the-next-generation-ai-powered","title":"Autonomous GIS: the next-generation AI-powered GIS","date":"2023-05-10","arxiv_id":"2305.06453","repositories_listed":1,"syntology":null},{"url":"/paper/codeie-large-code-generation-models-are","slug":"codeie-large-code-generation-models-are","title":"CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors","date":"2023-05-09","arxiv_id":"2305.05711","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/codeie-large-code-generation-models-are#ran","syntology_url":"https://syntology.ai/paper/2305.05711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05711"}},"official":{"repos":["dasepli/codeie"],"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/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/self-edit-fault-aware-code-editor-for-code","slug":"self-edit-fault-aware-code-editor-for-code","title":"Self-Edit: Fault-Aware Code Editor for Code Generation","date":"2023-05-06","arxiv_id":"2305.04087","repositories_listed":1,"syntology":null},{"url":"/paper/is-your-code-generated-by-chatgpt-really-1","slug":"is-your-code-generated-by-chatgpt-really-1","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","date":"2023-05-02","arxiv_id":"2305.01210","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/is-your-code-generated-by-chatgpt-really-1#ran","syntology_url":"https://syntology.ai/paper/2305.01210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.01210"}},"official":{"repos":["evalplus/evalplus"],"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/exploring-the-effectiveness-of-large-language","slug":"exploring-the-effectiveness-of-large-language","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","date":"2023-04-30","arxiv_id":"2305.00418","repositories_listed":1,"syntology":null},{"url":"/paper/mlcopilot-unleashing-the-power-of-large","slug":"mlcopilot-unleashing-the-power-of-large","title":"MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks","date":"2023-04-28","arxiv_id":"2304.14979","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mlcopilot-unleashing-the-power-of-large#ran","syntology_url":"https://syntology.ai/paper/2304.14979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.14979"}},"official":{"repos":["microsoft/CoML"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/outline-then-details-syntactically-guided","slug":"outline-then-details-syntactically-guided","title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","date":"2023-04-28","arxiv_id":"2305.00909","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":1,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/outline-then-details-syntactically-guided#ran","syntology_url":"https://syntology.ai/paper/2305.00909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00909"}},"official":{"repos":["vita-group/chaincoder"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ai-assisted-coding-experiments-with-gpt-4","slug":"ai-assisted-coding-experiments-with-gpt-4","title":"AI-assisted coding: Experiments with GPT-4","date":"2023-04-25","arxiv_id":"2304.13187","repositories_listed":1,"syntology":null},{"url":"/paper/gnnbuilder-an-automated-framework-for-generic","slug":"gnnbuilder-an-automated-framework-for-generic","title":"GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization","date":"2023-03-29","arxiv_id":"2303.16459","repositories_listed":1,"syntology":null},{"url":"/paper/improving-code-generation-by-training-with","slug":"improving-code-generation-by-training-with","title":"Improving Code Generation by Training with Natural Language Feedback","date":"2023-03-28","arxiv_id":"2303.16749","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/improving-code-generation-by-training-with#ran","syntology_url":"https://syntology.ai/paper/2303.16749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16749"}},"official":{"repos":["nyu-mll/ILF-for-code-generation"],"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/llmseceval-a-dataset-of-natural-language","slug":"llmseceval-a-dataset-of-natural-language","title":"LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations","date":"2023-03-16","arxiv_id":"2303.09384","repositories_listed":1,"syntology":null},{"url":"/paper/vipergpt-visual-inference-via-python","slug":"vipergpt-visual-inference-via-python","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","date":"2023-03-14","arxiv_id":"2303.08128","repositories_listed":1,"syntology":null},{"url":"/paper/amom-adaptive-masking-over-masking-for","slug":"amom-adaptive-masking-over-masking-for","title":"AMOM: Adaptive Masking over Masking for Conditional Masked Language Model","date":"2023-03-13","arxiv_id":"2303.07457","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-evaluation-of-chatgpt-s-zero","slug":"a-comprehensive-evaluation-of-chatgpt-s-zero","title":"A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability","date":"2023-03-12","arxiv_id":"2303.13547","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":3,"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/a-comprehensive-evaluation-of-chatgpt-s-zero#ran","syntology_url":"https://syntology.ai/paper/2303.13547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13547"}},"official":{"repos":["thu-bpm/chatgpt-sql"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/learning-deep-semantics-for-test-completion","slug":"learning-deep-semantics-for-test-completion","title":"Learning Deep Semantics for Test Completion","date":"2023-02-20","arxiv_id":"2302.10166","repositories_listed":1,"syntology":null},{"url":"/paper/pac-prediction-sets-for-large-language-models","slug":"pac-prediction-sets-for-large-language-models","title":"PAC Prediction Sets for Large Language Models of Code","date":"2023-02-17","arxiv_id":"2302.08703","repositories_listed":1,"syntology":null},{"url":"/paper/lever-learning-to-verify-language-to-code","slug":"lever-learning-to-verify-language-to-code","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","date":"2023-02-16","arxiv_id":"2302.08468","repositories_listed":1,"syntology":{"n":22,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":17,"n_pointer_only":1,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/lever-learning-to-verify-language-to-code#ran","syntology_url":"https://syntology.ai/paper/2302.08468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08468"}},"official":{"repos":["niansong1996/lever"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/compositional-exemplars-for-in-context","slug":"compositional-exemplars-for-in-context","title":"Compositional Exemplars for In-context Learning","date":"2023-02-11","arxiv_id":"2302.05698","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/compositional-exemplars-for-in-context#ran","syntology_url":"https://syntology.ai/paper/2302.05698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05698"}},"official":{"repos":["hkunlp/icl-ceil"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/codebertscore-evaluating-code-generation-with","slug":"codebertscore-evaluating-code-generation-with","title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","date":"2023-02-10","arxiv_id":"2302.05527","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-large-language-models-to-generate","slug":"controlling-large-language-models-to-generate","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","date":"2023-02-10","arxiv_id":"2302.05319","repositories_listed":1,"syntology":null},{"url":"/paper/a-multitask-multilingual-multimodal","slug":"a-multitask-multilingual-multimodal","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","date":"2023-02-08","arxiv_id":"2302.04023","repositories_listed":1,"syntology":null},{"url":"/paper/a-vector-quantized-approach-for-text-to","slug":"a-vector-quantized-approach-for-text-to","title":"A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech","date":"2023-02-08","arxiv_id":"2302.04215","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/a-vector-quantized-approach-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2302.04215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04215"}},"official":{"repos":["b04901014/mqtts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-data-augmentation-for-code","slug":"exploring-data-augmentation-for-code","title":"Exploring Data Augmentation for Code Generation Tasks","date":"2023-02-05","arxiv_id":"2302.03499","repositories_listed":1,"syntology":null},{"url":"/paper/execution-based-code-generation-using-deep","slug":"execution-based-code-generation-using-deep","title":"Execution-based Code Generation using Deep Reinforcement Learning","date":"2023-01-31","arxiv_id":"2301.13816","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/execution-based-code-generation-using-deep#ran","syntology_url":"https://syntology.ai/paper/2301.13816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13816"}},"official":{"repos":["reddy-lab-code-research/PPOCoder"],"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/execution-based-evaluation-for-open-domain","slug":"execution-based-evaluation-for-open-domain","title":"Execution-Based Evaluation for Open-Domain Code Generation","date":"2022-12-20","arxiv_id":"2212.10481","repositories_listed":1,"syntology":null},{"url":"/paper/parsel-a-unified-natural-language-framework","slug":"parsel-a-unified-natural-language-framework","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","date":"2022-12-20","arxiv_id":"2212.10561","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":1,"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/parsel-a-unified-natural-language-framework#ran","syntology_url":"https://syntology.ai/paper/2212.10561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10561"}},"official":{"repos":["ezelikman/parsel"],"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/asking-clarification-questions-for-code","slug":"asking-clarification-questions-for-code","title":"Python Code Generation by Asking Clarification Questions","date":"2022-12-19","arxiv_id":"2212.09885","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-large-language-models-for","slug":"benchmarking-large-language-models-for","title":"Benchmarking Large Language Models for Automated Verilog RTL Code Generation","date":"2022-12-13","arxiv_id":"2212.11140","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2212.11140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11140"}},"official":{"repos":["shailja-thakur/vgen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prompting-is-programming-a-query-language-for","slug":"prompting-is-programming-a-query-language-for","title":"Prompting Is Programming: A Query Language for Large Language Models","date":"2022-12-12","arxiv_id":"2212.06094","repositories_listed":1,"syntology":null},{"url":"/paper/programming-is-hard-or-at-least-it-used-to-be","slug":"programming-is-hard-or-at-least-it-used-to-be","title":"Programming Is Hard -- Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation","date":"2022-12-02","arxiv_id":"2212.01020","repositories_listed":1,"syntology":null},{"url":"/paper/coder-reviewer-reranking-for-code-generation","slug":"coder-reviewer-reranking-for-code-generation","title":"Coder Reviewer Reranking for Code Generation","date":"2022-11-29","arxiv_id":"2211.16490","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coder-reviewer-reranking-for-code-generation#ran","syntology_url":"https://syntology.ai/paper/2211.16490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16490"}},"official":{"repos":["facebookresearch/coder_reviewer_reranking"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mariancg-a-code-generation-transformer-model","slug":"mariancg-a-code-generation-transformer-model","title":"MarianCG: a code generation transformer model inspired by machine translation","date":"2022-11-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/clawsat-towards-both-robust-and-accurate-code","slug":"clawsat-towards-both-robust-and-accurate-code","title":"CLAWSAT: Towards Both Robust and Accurate Code Models","date":"2022-11-21","arxiv_id":"2211.11711","repositories_listed":1,"syntology":null},{"url":"/paper/execution-based-evaluation-for-data-science","slug":"execution-based-evaluation-for-data-science","title":"Execution-based Evaluation for Data Science Code Generation Models","date":"2022-11-17","arxiv_id":"2211.09374","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/execution-based-evaluation-for-data-science#ran","syntology_url":"https://syntology.ai/paper/2211.09374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09374"}},"official":{"repos":["jun-jie-huang/exeds"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-how-fine-tuning-on-bimodal-data","slug":"evaluating-how-fine-tuning-on-bimodal-data","title":"Evaluating How Fine-tuning on Bimodal Data Effects Code Generation","date":"2022-11-15","arxiv_id":"2211.07842","repositories_listed":1,"syntology":null},{"url":"/paper/securityeval-dataset-mining-vulnerability","slug":"securityeval-dataset-mining-vulnerability","title":"SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques","date":"2022-11-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/codep-grammatical-seq2seq-model-for-general","slug":"codep-grammatical-seq2seq-model-for-general","title":"CodePAD: Sequence-based Code Generation with Pushdown Automaton","date":"2022-11-02","arxiv_id":"2211.00818","repositories_listed":1,"syntology":null},{"url":"/paper/when-language-model-meets-private-library","slug":"when-language-model-meets-private-library","title":"When Language Model Meets Private Library","date":"2022-10-31","arxiv_id":"2210.17236","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-supervised-salient-object","slug":"synthetic-data-supervised-salient-object","title":"Synthetic Data Supervised Salient Object Detection","date":"2022-10-25","arxiv_id":"2210.13835","repositories_listed":1,"syntology":null},{"url":"/paper/code4struct-code-generation-for-few-shot","slug":"code4struct-code-generation-for-few-shot","title":"Code4Struct: Code Generation for Few-Shot Event Structure Prediction","date":"2022-10-23","arxiv_id":"2210.12810","repositories_listed":1,"syntology":null},{"url":"/paper/pacific-towards-proactive-conversational","slug":"pacific-towards-proactive-conversational","title":"PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance","date":"2022-10-17","arxiv_id":"2210.08817","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/pacific-towards-proactive-conversational#ran","syntology_url":"https://syntology.ai/paper/2210.08817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08817"}},"official":{"repos":["dengyang17/pacific"],"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/extracting-meaningful-attention-on-source","slug":"extracting-meaningful-attention-on-source","title":"Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration","date":"2022-10-11","arxiv_id":"2210.05506","repositories_listed":1,"syntology":null},{"url":"/paper/simscood-systematic-analysis-of-out-of","slug":"simscood-systematic-analysis-of-out-of","title":"SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models","date":"2022-10-10","arxiv_id":"2210.04802","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/selective-annotation-makes-language-models","slug":"selective-annotation-makes-language-models","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","date":"2022-09-05","arxiv_id":"2209.01975","repositories_listed":1,"syntology":null},{"url":"/paper/a-scalable-and-extensible-approach-to","slug":"a-scalable-and-extensible-approach-to","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","date":"2022-08-17","arxiv_id":"2208.08227","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":1,"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/a-scalable-and-extensible-approach-to#ran","syntology_url":"https://syntology.ai/paper/2208.08227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.08227"}},"official":{"repos":["nuprl/multipl-e"],"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/out-of-the-bleu-how-should-we-assess-quality","slug":"out-of-the-bleu-how-should-we-assess-quality","title":"Out of the BLEU: how should we assess quality of the Code Generation models?","date":"2022-08-05","arxiv_id":"2208.03133","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/out-of-the-bleu-how-should-we-assess-quality#ran","syntology_url":"https://syntology.ai/paper/2208.03133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03133"}},"official":{"repos":["JetBrains-Research/codegen-metrics"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/language-models-can-teach-themselves-to","slug":"language-models-can-teach-themselves-to","title":"Language Models Can Teach Themselves to Program Better","date":"2022-07-29","arxiv_id":"2207.14502","repositories_listed":1,"syntology":null},{"url":"/paper/pangu-coder-program-synthesis-with-function","slug":"pangu-coder-program-synthesis-with-function","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","date":"2022-07-22","arxiv_id":"2207.11280","repositories_listed":1,"syntology":null},{"url":"/paper/codet-code-generation-with-generated-tests","slug":"codet-code-generation-with-generated-tests","title":"CodeT: Code Generation with Generated Tests","date":"2022-07-21","arxiv_id":"2207.10397","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codet-code-generation-with-generated-tests#ran","syntology_url":"https://syntology.ai/paper/2207.10397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10397"}},"official":{"repos":["microsoft/codet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/autodice-fully-automated-distributed-cnn","slug":"autodice-fully-automated-distributed-cnn","title":"AutoDiCE: Fully Automated Distributed CNN Inference at the Edge","date":"2022-07-20","arxiv_id":"2207.12113","repositories_listed":1,"syntology":null},{"url":"/paper/ui-layers-merger-merging-ui-layers-via-visual","slug":"ui-layers-merger-merging-ui-layers-via-visual","title":"UI Layers Merger: Merging UI layers via Visual Learning and Boundary Prior","date":"2022-06-18","arxiv_id":"2206.13389","repositories_listed":1,"syntology":null},{"url":"/paper/cert-continual-pre-training-on-sketches-for","slug":"cert-continual-pre-training-on-sketches-for","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","date":"2022-06-14","arxiv_id":"2206.06888","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cert-continual-pre-training-on-sketches-for#ran","syntology_url":"https://syntology.ai/paper/2206.06888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06888"}},"official":{"repos":["microsoft/pycodegpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/structcoder-structure-aware-transformer-for","slug":"structcoder-structure-aware-transformer-for","title":"StructCoder: Structure-Aware Transformer for Code Generation","date":"2022-06-10","arxiv_id":"2206.05239","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/structcoder-structure-aware-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2206.05239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05239"}},"official":{"repos":["reddy-lab-code-research/structcoder"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/fault-aware-neural-code-rankers","slug":"fault-aware-neural-code-rankers","title":"Fault-Aware Neural Code Rankers","date":"2022-06-04","arxiv_id":"2206.03865","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fault-aware-neural-code-rankers#ran","syntology_url":"https://syntology.ai/paper/2206.03865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03865"}},"official":{"repos":["microsoft/coderanker"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/transformer-with-tree-order-encoding-for","slug":"transformer-with-tree-order-encoding-for","title":"Transformer with Tree-order Encoding for Neural Program Generation","date":"2022-05-30","arxiv_id":"2206.13354","repositories_listed":1,"syntology":null},{"url":"/paper/summarize-and-generate-to-back-translate-1","slug":"summarize-and-generate-to-back-translate-1","title":"Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages","date":"2022-05-23","arxiv_id":"2205.11116","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-to-code-translation-with","slug":"natural-language-to-code-translation-with","title":"Natural Language to Code Translation with Execution","date":"2022-04-25","arxiv_id":"2204.11454","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":3,"n_no_contract":5,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 3 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/natural-language-to-code-translation-with#ran","syntology_url":"https://syntology.ai/paper/2204.11454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.11454"}},"official":{"repos":["facebookresearch/mbr-exec"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/symforce-symbolic-computation-and-code","slug":"symforce-symbolic-computation-and-code","title":"SymForce: Symbolic Computation and Code Generation for Robotics","date":"2022-04-17","arxiv_id":"2204.07889","repositories_listed":1,"syntology":null},{"url":"/paper/mconala-a-benchmark-for-code-generation-from","slug":"mconala-a-benchmark-for-code-generation-from","title":"MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages","date":"2022-03-16","arxiv_id":"2203.08388","repositories_listed":1,"syntology":null},{"url":"/paper/open-ended-knowledge-tracing","slug":"open-ended-knowledge-tracing","title":"GPT-based Open-Ended Knowledge Tracing","date":"2022-02-21","arxiv_id":"2203.03716","repositories_listed":1,"syntology":null},{"url":"/paper/can-we-generate-shellcodes-via-natural","slug":"can-we-generate-shellcodes-via-natural","title":"Can We Generate Shellcodes via Natural Language? An Empirical Study","date":"2022-02-08","arxiv_id":"2202.03755","repositories_listed":1,"syntology":null},{"url":"/paper/gap-gen-guided-automatic-python-code","slug":"gap-gen-guided-automatic-python-code","title":"GAP-Gen: Guided Automatic Python Code Generation","date":"2022-01-19","arxiv_id":"2201.08810","repositories_listed":1,"syntology":null}],"record_sha256":"bef8f48ed4c417df7af580c2928e4e7f0fa05ad6c8c8932c192f77774b5da61c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}