{"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/ran/3","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":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,280],"of":280,"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/papers/ran/1","prev":"/task/code-generation/papers/ran/2","next":null,"papers":[{"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/octopack-instruction-tuning-code-large","slug":"octopack-instruction-tuning-code-large","title":"OctoPack: Instruction Tuning Code Large Language Models","date":"2023-08-14","arxiv_id":"2308.07124","repositories_listed":3,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"9 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/octopack-instruction-tuning-code-large#ran","syntology_url":"https://syntology.ai/paper/2308.07124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07124"}},"official":{"repos":["bigcode-project/bigcode-evaluation-harness","bigcode-project/octopack"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/factool-factuality-detection-in-generative-ai","slug":"factool-factuality-detection-in-generative-ai","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","date":"2023-07-25","arxiv_id":"2307.13528","repositories_listed":3,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/factool-factuality-detection-in-generative-ai#ran","syntology_url":"https://syntology.ai/paper/2307.13528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13528"}},"official":{"repos":["gair-nlp/factool"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/how-is-chatgpt-s-behavior-changing-over-time","slug":"how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/how-is-chatgpt-s-behavior-changing-over-time#ran","syntology_url":"https://syntology.ai/paper/2307.09009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09009"}},"official":{"repos":["lchen001/llmdrift"],"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/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","repositories_listed":19,"syntology":{"n":52,"n_ran":33,"n_constructed":7,"n_ran_checked":22,"n_instrument":11,"n_unverified":19,"n_honours":1,"n_violates":1,"n_no_contract":20,"n_pointer_only":20,"phrase":"33 ran (of which 7 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 1 violated, 20 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}},"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"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/intercode-standardizing-and-benchmarking","slug":"intercode-standardizing-and-benchmarking","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","date":"2023-06-26","arxiv_id":"2306.14898","repositories_listed":2,"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/intercode-standardizing-and-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2306.14898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.14898"}},"official":{"repos":["princeton-nlp/intercode"],"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/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/wizardcoder-empowering-code-large-language","slug":"wizardcoder-empowering-code-large-language","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","date":"2023-06-14","arxiv_id":"2306.08568","repositories_listed":4,"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/wizardcoder-empowering-code-large-language#ran","syntology_url":"https://syntology.ai/paper/2306.08568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08568"}},"official":{"repos":["nlpxucan/wizardlm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-static-evaluation-of-code-completion-by","slug":"a-static-evaluation-of-code-completion-by","title":"A Static Evaluation of Code Completion by Large Language Models","date":"2023-06-05","arxiv_id":"2306.03203","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-static-evaluation-of-code-completion-by#ran","syntology_url":"https://syntology.ai/paper/2306.03203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03203"}},"official":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/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/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/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/flexible-grammar-based-constrained-decoding","slug":"flexible-grammar-based-constrained-decoding","title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","date":"2023-05-23","arxiv_id":"2305.13971","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/flexible-grammar-based-constrained-decoding#ran","syntology_url":"https://syntology.ai/paper/2305.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13971"}},"official":{"repos":["epfl-dlab/gcd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"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/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/starcoder-may-the-source-be-with-you","slug":"starcoder-may-the-source-be-with-you","title":"StarCoder: may the source be with you!","date":"2023-05-09","arxiv_id":"2305.06161","repositories_listed":4,"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/starcoder-may-the-source-be-with-you#ran","syntology_url":"https://syntology.ai/paper/2305.06161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06161"}},"official":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/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/large-language-models-are-state-of-the-art-1","slug":"large-language-models-are-state-of-the-art-1","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","date":"2023-04-27","arxiv_id":"2304.14317","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-language-models-are-state-of-the-art-1#ran","syntology_url":"https://syntology.ai/paper/2304.14317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.14317"}},"official":{"repos":["terryyz/llm-code-eval","terryyz/ice-score"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/codegeex-a-pre-trained-model-for-code","slug":"codegeex-a-pre-trained-model-for-code","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","date":"2023-03-30","arxiv_id":"2303.17568","repositories_listed":2,"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/codegeex-a-pre-trained-model-for-code#ran","syntology_url":"https://syntology.ai/paper/2303.17568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17568"}},"official":{"repos":["THUDM/CodeGeeX"],"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":["listed","official"]}}},{"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/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"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/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","repositories_listed":57,"syntology":{"n":58,"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_honours":3,"n_violates":0,"n_no_contract":22,"n_pointer_only":4,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}},"official":{"repos":["facebookresearch/llama"],"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":["listed","unlocated"]}}},{"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/learning-performance-improving-code-edits","slug":"learning-performance-improving-code-edits","title":"Learning Performance-Improving Code Edits","date":"2023-02-15","arxiv_id":"2302.07867","repositories_listed":2,"syntology":{"n":19,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":11,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":19,"phrase":"8 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; 5 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/learning-performance-improving-code-edits#ran","syntology_url":"https://syntology.ai/paper/2302.07867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07867"}},"official":{"repos":["madaan/pie-perf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"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/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/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/santacoder-don-t-reach-for-the-stars","slug":"santacoder-don-t-reach-for-the-stars","title":"SantaCoder: don't reach for the stars!","date":"2023-01-09","arxiv_id":"2301.03988","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/santacoder-don-t-reach-for-the-stars#ran","syntology_url":"https://syntology.ai/paper/2301.03988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.03988"}},"official":{"repos":["bigcode-project/bigcode-evaluation-harness","bigcode-project/starcoder"],"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":["listed","official"]}}},{"url":"/paper/recode-robustness-evaluation-of-code","slug":"recode-robustness-evaluation-of-code","title":"ReCode: Robustness Evaluation of Code Generation Models","date":"2022-12-20","arxiv_id":"2212.10264","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recode-robustness-evaluation-of-code#ran","syntology_url":"https://syntology.ai/paper/2212.10264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10264"}},"official":{"repos":["amazon-science/recode"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"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/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/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/ds-1000-a-natural-and-reliable-benchmark-for","slug":"ds-1000-a-natural-and-reliable-benchmark-for","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","date":"2022-11-18","arxiv_id":"2211.11501","repositories_listed":2,"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":2,"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/ds-1000-a-natural-and-reliable-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2211.11501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11501"}},"official":{"repos":["HKUNLP/DS-1000"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"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/multi-lingual-evaluation-of-code-generation","slug":"multi-lingual-evaluation-of-code-generation","title":"Multi-lingual Evaluation of Code Generation Models","date":"2022-10-26","arxiv_id":"2210.14868","repositories_listed":2,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/multi-lingual-evaluation-of-code-generation#ran","syntology_url":"https://syntology.ai/paper/2210.14868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14868"}},"official":{"repos":["amazon-research/mbxp-exec-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/language-models-of-code-are-few-shot","slug":"language-models-of-code-are-few-shot","title":"Language Models of Code are Few-Shot Commonsense Learners","date":"2022-10-13","arxiv_id":"2210.07128","repositories_listed":2,"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":2,"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/language-models-of-code-are-few-shot#ran","syntology_url":"https://syntology.ai/paper/2210.07128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07128"}},"official":{"repos":["madaan/cocogen"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"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/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/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/doccoder-generating-code-by-retrieving-and","slug":"doccoder-generating-code-by-retrieving-and","title":"DocPrompting: Generating Code by Retrieving the Docs","date":"2022-07-13","arxiv_id":"2207.05987","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_constructed":1,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/doccoder-generating-code-by-retrieving-and#ran","syntology_url":"https://syntology.ai/paper/2207.05987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.05987"}},"official":{"repos":["shuyanzhou/doccoder","shuyanzhou/docprompting"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/coderl-mastering-code-generation-through","slug":"coderl-mastering-code-generation-through","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","date":"2022-07-05","arxiv_id":"2207.01780","repositories_listed":2,"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/coderl-mastering-code-generation-through#ran","syntology_url":"https://syntology.ai/paper/2207.01780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01780"}},"official":{"repos":["salesforce/coderl"],"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/natgen-generative-pre-training-by","slug":"natgen-generative-pre-training-by","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","date":"2022-06-15","arxiv_id":"2206.07585","repositories_listed":2,"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/natgen-generative-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/2206.07585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07585"}},"official":{"repos":["saikat107/natgen"],"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/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/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/training-a-helpful-and-harmless-assistant","slug":"training-a-helpful-and-harmless-assistant","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","date":"2022-04-12","arxiv_id":"2204.05862","repositories_listed":4,"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":2,"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/training-a-helpful-and-harmless-assistant#ran","syntology_url":"https://syntology.ai/paper/2204.05862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05862"}},"official":{"repos":["anthropics/hh-rlhf"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/incoder-a-generative-model-for-code-infilling","slug":"incoder-a-generative-model-for-code-infilling","title":"InCoder: A Generative Model for Code Infilling and Synthesis","date":"2022-04-12","arxiv_id":"2204.05999","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/incoder-a-generative-model-for-code-infilling#ran","syntology_url":"https://syntology.ai/paper/2204.05999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05999"}},"official":{"repos":["dpfried/incoder"],"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":["listed","official"]}}},{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}},"official":null}},{"url":"/paper/a-conversational-paradigm-for-program","slug":"a-conversational-paradigm-for-program","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","date":"2022-03-25","arxiv_id":"2203.13474","repositories_listed":8,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-conversational-paradigm-for-program#ran","syntology_url":"https://syntology.ai/paper/2203.13474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13474"}},"official":{"repos":["salesforce/CodeGen","salesforce/jaxformer"],"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":["listed","official"]}}},{"url":"/paper/synchromesh-reliable-code-generation-from-pre-1","slug":"synchromesh-reliable-code-generation-from-pre-1","title":"Synchromesh: Reliable code generation from pre-trained language models","date":"2022-01-26","arxiv_id":"2201.11227","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"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 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) · 0 unverified","sample_list":"/paper/synchromesh-reliable-code-generation-from-pre-1#ran","syntology_url":"https://syntology.ai/paper/2201.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11227"}},"official":null}},{"url":"/paper/lamda-language-models-for-dialog-applications","slug":"lamda-language-models-for-dialog-applications","title":"LaMDA: Language Models for Dialog Applications","date":"2022-01-20","arxiv_id":"2201.08239","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lamda-language-models-for-dialog-applications#ran","syntology_url":"https://syntology.ai/paper/2201.08239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08239"}},"official":null}},{"url":"/paper/reusing-auto-schedules-for-efficient-dnn","slug":"reusing-auto-schedules-for-efficient-dnn","title":"Transfer-Tuning: Reusing Auto-Schedules for Efficient Tensor Program Code Generation","date":"2022-01-14","arxiv_id":"2201.05587","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reusing-auto-schedules-for-efficient-dnn#ran","syntology_url":"https://syntology.ai/paper/2201.05587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05587"}},"official":{"repos":["giclab/transfer-tuning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/controlling-conditional-language-models-with","slug":"controlling-conditional-language-models-with","title":"Controlling Conditional Language Models without Catastrophic Forgetting","date":"2021-12-01","arxiv_id":"2112.00791","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":1,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/controlling-conditional-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2112.00791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00791"}},"official":{"repos":["naver/gdc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/codet5-identifier-aware-unified-pre-trained","slug":"codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","arxiv_id":"2109.00859","repositories_listed":5,"syntology":{"n":11,"n_ran":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/codet5-identifier-aware-unified-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2109.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00859"}},"official":{"repos":["salesforce/codet5"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/retrieval-augmented-code-generation-and","slug":"retrieval-augmented-code-generation-and","title":"Retrieval Augmented Code Generation and Summarization","date":"2021-08-26","arxiv_id":"2108.11601","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/retrieval-augmented-code-generation-and#ran","syntology_url":"https://syntology.ai/paper/2108.11601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11601"}},"official":{"repos":["rizwan09/redcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","repositories_listed":13,"syntology":{"n":39,"n_ran":26,"n_constructed":0,"n_ran_checked":24,"n_instrument":2,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":23,"n_pointer_only":4,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/evaluating-large-language-models-trained-on#ran","syntology_url":"https://syntology.ai/paper/2107.03374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03374"}},"official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/a-syntax-guided-edit-decoder-for-neural","slug":"a-syntax-guided-edit-decoder-for-neural","title":"A Syntax-Guided Edit Decoder for Neural Program Repair","date":"2021-06-15","arxiv_id":"2106.08253","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":1,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-syntax-guided-edit-decoder-for-neural#ran","syntology_url":"https://syntology.ai/paper/2106.08253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08253"}},"official":null}},{"url":"/paper/improving-tree-structured-decoder-training","slug":"improving-tree-structured-decoder-training","title":"Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning","date":"2021-05-31","arxiv_id":"2105.14796","repositories_listed":0,"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/improving-tree-structured-decoder-training#ran","syntology_url":"https://syntology.ai/paper/2105.14796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14796"}},"official":null}},{"url":"/paper/measuring-coding-challenge-competence-with","slug":"measuring-coding-challenge-competence-with","title":"Measuring Coding Challenge Competence With APPS","date":"2021-05-20","arxiv_id":"2105.09938","repositories_listed":3,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"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) · 4 unverified","sample_list":"/paper/measuring-coding-challenge-competence-with#ran","syntology_url":"https://syntology.ai/paper/2105.09938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.09938"}},"official":{"repos":["hendrycks/apps"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/iot-instance-wise-layer-reordering-for-1","slug":"iot-instance-wise-layer-reordering-for-1","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","date":"2021-03-05","arxiv_id":"2103.03457","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/iot-instance-wise-layer-reordering-for-1#ran","syntology_url":"https://syntology.ai/paper/2103.03457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03457"}},"official":{"repos":["instance-wise-ordered-transformer/IOT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["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/multi-branch-attentive-transformer","slug":"multi-branch-attentive-transformer","title":"Multi-branch Attentive Transformer","date":"2020-06-18","arxiv_id":"2006.10270","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-branch-attentive-transformer#ran","syntology_url":"https://syntology.ai/paper/2006.10270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10270"}},"official":null}},{"url":"/paper/graph-based-self-supervised-program-repair","slug":"graph-based-self-supervised-program-repair","title":"Graph-based, Self-Supervised Program Repair from Diagnostic Feedback","date":"2020-05-20","arxiv_id":"2005.10636","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/graph-based-self-supervised-program-repair#ran","syntology_url":"https://syntology.ai/paper/2005.10636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.10636"}},"official":{"repos":["michiyasunaga/DrRepair","worksheets.codalab.org/worksheets/0x01838644724a433c932bef4cb5c42fbd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/incorporating-external-knowledge-through-pre","slug":"incorporating-external-knowledge-through-pre","title":"Incorporating External Knowledge through Pre-training for Natural Language to Code Generation","date":"2020-04-20","arxiv_id":"2004.09015","repositories_listed":2,"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":0,"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/incorporating-external-knowledge-through-pre#ran","syntology_url":"https://syntology.ai/paper/2004.09015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.09015"}},"official":{"repos":["neulab/external-knowledge-codegen"],"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/treegen-a-tree-based-transformer-architecture","slug":"treegen-a-tree-based-transformer-architecture","title":"TreeGen: A Tree-Based Transformer Architecture for Code Generation","date":"2019-11-22","arxiv_id":"1911.09983","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/treegen-a-tree-based-transformer-architecture#ran","syntology_url":"https://syntology.ai/paper/1911.09983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.09983"}},"official":{"repos":["zysszy/TreeGen"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/code-generation-as-a-dual-task-of-code","slug":"code-generation-as-a-dual-task-of-code","title":"Code Generation as a Dual Task of Code Summarization","date":"2019-10-14","arxiv_id":"1910.05923","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/code-generation-as-a-dual-task-of-code#ran","syntology_url":"https://syntology.ai/paper/1910.05923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05923"}},"official":{"repos":["Bolin0215/CSCGDual"],"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/structural-language-models-for-any-code","slug":"structural-language-models-for-any-code","title":"Structural Language Models of Code","date":"2019-09-30","arxiv_id":"1910.00577","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/structural-language-models-for-any-code#ran","syntology_url":"https://syntology.ai/paper/1910.00577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00577"}},"official":{"repos":["tech-srl/slm-code-generation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/program-synthesis-and-semantic-parsing-with","slug":"program-synthesis-and-semantic-parsing-with","title":"Program Synthesis and Semantic Parsing with Learned Code Idioms","date":"2019-06-26","arxiv_id":"1906.10816","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/program-synthesis-and-semantic-parsing-with#ran","syntology_url":"https://syntology.ai/paper/1906.10816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10816"}},"official":{"repos":["rshin/seq2struct"],"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/tranx-a-transition-based-neural-abstract","slug":"tranx-a-transition-based-neural-abstract","title":"TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation","date":"2018-10-05","arxiv_id":"1810.02720","repositories_listed":4,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tranx-a-transition-based-neural-abstract#ran","syntology_url":"https://syntology.ai/paper/1810.02720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02720"}},"official":{"repos":["pcyin/tranX"],"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":["listed","official"]}}},{"url":"/paper/a-parallel-corpus-of-python-functions-and","slug":"a-parallel-corpus-of-python-functions-and","title":"A parallel corpus of Python functions and documentation strings for automated code documentation and code generation","date":"2017-07-07","arxiv_id":"1707.02275","repositories_listed":6,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/a-parallel-corpus-of-python-functions-and#ran","syntology_url":"https://syntology.ai/paper/1707.02275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.02275"}},"official":{"repos":["Avmb/code-docstring-corpus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-syntactic-neural-model-for-general-purpose","slug":"a-syntactic-neural-model-for-general-purpose","title":"A Syntactic Neural Model for General-Purpose Code Generation","date":"2017-04-06","arxiv_id":"1704.01696","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-syntactic-neural-model-for-general-purpose#ran","syntology_url":"https://syntology.ai/paper/1704.01696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.01696"}},"official":null}},{"url":"/paper/joint-face-detection-and-alignment-using","slug":"joint-face-detection-and-alignment-using","title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","date":"2016-04-11","arxiv_id":"1604.02878","repositories_listed":42,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 5 unverified","sample_list":"/paper/joint-face-detection-and-alignment-using#ran","syntology_url":"https://syntology.ai/paper/1604.02878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.02878"}},"official":null}}],"record_sha256":"170f0d8923173f13a5a5d2939acefb21179131edddaf1d5e56c5877c168b8a2e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}