{"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":"/paper/natural-language-to-code-translation-with","title":"Natural Language to Code Translation with Execution","arxiv_id":"2204.11454","date":"2022-04-25","proceeding":null,"authors":["Freda Shi","Daniel Fried","Marjan Ghazvininejad","Luke Zettlemoyer","Sida I. Wang"],"abstract":"Generative models of code, pretrained on large corpora of programs, have shown great success in translating natural language to code (Chen et al., 2021; Austin et al., 2021; Li et al., 2022, inter alia). While these models do not explicitly incorporate program semantics (i.e., execution results) during training, they are able to generate correct solutions for many problems. However, choosing a single correct program from a generated set for each problem remains challenging. In this work, we introduce execution result--based minimum Bayes risk decoding (MBR-EXEC) for program selection and show that it improves the few-shot performance of pretrained code models on natural-language-to-code tasks. We select output programs from a generated candidate set by marginalizing over program implementations that share the same semantics. Because exact equivalence is intractable, we execute each program on a small number of test inputs to approximate semantic equivalence. Across datasets, execution or simulated execution significantly outperforms the methods that do not involve program semantics. We find that MBR-EXEC consistently improves over all execution-unaware selection methods, suggesting it as an effective approach for natural language to code translation. We open-source our code at github.com/facebookresearch/mbr-exec and data at dl.fbaipublicfiles.com/mbr-exec/mbr-exec-release.zip","url_abs":"https://arxiv.org/abs/2204.11454v2","url_pdf":"https://arxiv.org/pdf/2204.11454v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"natural-language-to-code-translation-with","repo_url":"https://github.com/facebookresearch/mbr-exec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"code-translation","task_name":"Code Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"code-davinci-001 175B + MBR-Exec","rank_in_archive_order":50,"of":99,"metrics":{"Accuracy":"58.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.11454","atlas_url":"https://app.syntology.ai/?focus=2204.11454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.11454"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.11454"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.11454"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.11454\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2204.11454"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2204.11454\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2204.11454"},"call":"get_concepts_for_paper(arxiv_id=\"2204.11454\")"}],"by_repo":[{"repo":"facebookresearch/mbr-exec","kind":"official","samples":12,"ran":9,"instrument":2,"unverified":3}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2204.11454.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2204.11454.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/mbr-exec","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":3,"ran":3,"ran_draft_wrong":2,"ran_honours":1,"unverified":3},"n_samples":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"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)"},"by_repo_kind":{"official":{"samples":12,"ran":9,"n_ran_checked":7,"n_instrument":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":2,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":9,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"8231e3fdffa9c8ee","code_sha256_prefix":"8231e3fdffa9c8ee","entry":"condition_has_like","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"utils_sql.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/utils_sql.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"conds:list/1/tuple","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/condition-has-like","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8231e3fdffa9c8ee"}},{"code_sha256":"f2d76234528d3b57","code_sha256_prefix":"f2d76234528d3b57","entry":"condition_has_or","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"utils_sql.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/utils_sql.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"conds:list/1/str","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f2d76234528d3b57"},"code_page":"/code/condition-has-or","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f2d76234528d3b57"}},{"code_sha256":"954c76e256cc7220","code_sha256_prefix":"954c76e256cc7220","entry":"condition_has_sql","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"utils_sql.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/utils_sql.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"conds:list/1/list","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/condition-has-sql","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"954c76e256cc7220"}},{"code_sha256":"684a636f41be9e03","code_sha256_prefix":"684a636f41be9e03","entry":"evaluate_spider","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"dataset:list/1/dict, gold_path:str/0/str, eval_mode:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"684a636f41be9e03"}},{"code_sha256":"6a5cb99badd4bfea","code_sha256_prefix":"6a5cb99badd4bfea","entry":"executability_selection_function","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"sample_selectors.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/sample_selectors.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:dict/0/?, good_execution_result:int/0/int","fixture_out_type":"bool","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6a5cb99badd4bfea"}},{"code_sha256":"de850df14e9ba78e","code_sha256_prefix":"de850df14e9ba78e","entry":"execution_selection_function","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"sample_selectors.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/sample_selectors.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:dict/0/?, y:dict/0/?, good_execution_result:int/0/int","fixture_out_type":"int","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"de850df14e9ba78e"}},{"code_sha256":"0992d2a47ae733fa","code_sha256_prefix":"0992d2a47ae733fa","entry":"get_schema","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"process_sql.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/process_sql.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"db:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"0992d2a47ae733fa"},"code_page":"/code/get-schema","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0992d2a47ae733fa"}},{"code_sha256":"c4dcaf29b663a364","code_sha256_prefix":"c4dcaf29b663a364","entry":"get_schema_from_json","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"process_sql.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/process_sql.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"fpath:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-schema-from-json","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ygan/NatSQL, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"c4dcaf29b663a364"}},{"code_sha256":"e0d0a3c69f5ae939","code_sha256_prefix":"e0d0a3c69f5ae939","entry":"single_exec_result_matching","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"sample_selectors.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/sample_selectors.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"exec_x:tuple/1/str, exec_y:tuple/1/str, good_execution_result:str/0/str","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"e0d0a3c69f5ae939"},"code_page":null,"census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from facebookresearch/coder_reviewer_reranking, and GitHub could not classify the licence of that repository (NOASSERTION)","mcp_get_code":{"code_sha256":"e0d0a3c69f5ae939"}},{"code_sha256":"92903e4e5086d7ec","code_sha256_prefix":"92903e4e5086d7ec","entry":"codex","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"collectors.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/collectors.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"92903e4e5086d7ec"}},{"code_sha256":"573e53ead6564561","code_sha256_prefix":"573e53ead6564561","entry":"codex_with_info","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"collectors.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/collectors.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"573e53ead6564561"}},{"code_sha256":"a906f5de1f5971b0","code_sha256_prefix":"a906f5de1f5971b0","entry":"tokenize","repo":"facebookresearch/mbr-exec","repo_kind":"official","path":"process_sql.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/process_sql.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/tokenize","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ad27f61a25e0990e49e8d4afe33187e5173d1eec62e27e22602a501c07c5115a","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}