{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L5UTBG66GS2KXUO2RKWU5ZDSCA","short_pith_number":"pith:L5UTBG66","schema_version":"1.0","canonical_sha256":"5f69309bde34b4abd1da8aad4ee472100c7394716b8e24f25a2195897ae386c2","source":{"kind":"arxiv","id":"2302.01973","version":3},"attestation_state":"computed","paper":{"title":"Measuring The Impact Of Programming Language Distribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.PL"],"primary_cat":"cs.LG","authors_text":"Gabriel Orlanski, Jacob Austin, Jeffrey Hui, Jonathan Malmaud, Joshua Howland, Kefan Xiao, Michele Catasta, Rishabh Singh, Xavier Garcia","submitted_at":"2023-02-03T19:47:22Z","abstract_excerpt":"Current benchmarks for evaluating neural code models focus on only a small subset of programming languages, excluding many popular languages such as Go or Rust. To ameliorate this issue, we present the BabelCode framework for execution-based evaluation of any benchmark in any language. BabelCode enables new investigations into the qualitative performance of models' memory, runtime, and individual test case results. Additionally, we present a new code translation dataset called Translating Python Programming Puzzles (TP3) from the Python Programming Puzzles (Schuster et al. 2021) benchmark that"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.01973","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-03T19:47:22Z","cross_cats_sorted":["cs.CL","cs.PL"],"title_canon_sha256":"15bc0b81e9cdcaae3341c4d72db76c31e603f8c3df13ff2999f5c14a3cd8760e","abstract_canon_sha256":"befde9a7dca4caf32b252c9f7ff874c7204f1016ef90e521d4059a86c6c5e808"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:19.312186Z","signature_b64":"28vXFKLxYz+ek5lFCdDtmz7Flccd8Byre2RMHIzfJLBpORV0q7fCIOjn28pnR4DtnRqkYTlLeX4wfOdqIrIeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f69309bde34b4abd1da8aad4ee472100c7394716b8e24f25a2195897ae386c2","last_reissued_at":"2026-07-05T06:13:19.311603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:19.311603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring The Impact Of Programming Language Distribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.PL"],"primary_cat":"cs.LG","authors_text":"Gabriel Orlanski, Jacob Austin, Jeffrey Hui, Jonathan Malmaud, Joshua Howland, Kefan Xiao, Michele Catasta, Rishabh Singh, Xavier Garcia","submitted_at":"2023-02-03T19:47:22Z","abstract_excerpt":"Current benchmarks for evaluating neural code models focus on only a small subset of programming languages, excluding many popular languages such as Go or Rust. To ameliorate this issue, we present the BabelCode framework for execution-based evaluation of any benchmark in any language. BabelCode enables new investigations into the qualitative performance of models' memory, runtime, and individual test case results. Additionally, we present a new code translation dataset called Translating Python Programming Puzzles (TP3) from the Python Programming Puzzles (Schuster et al. 2021) benchmark that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01973","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.01973/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.01973","created_at":"2026-07-05T06:13:19.311672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01973v3","created_at":"2026-07-05T06:13:19.311672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01973","created_at":"2026-07-05T06:13:19.311672+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5UTBG66GS2K","created_at":"2026-07-05T06:13:19.311672+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5UTBG66GS2KXUO2","created_at":"2026-07-05T06:13:19.311672+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5UTBG66","created_at":"2026-07-05T06:13:19.311672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2304.05128","citing_title":"Teaching Large Language Models to Self-Debug","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09894","citing_title":"Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Modernization","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA","json":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA.json","graph_json":"https://pith.science/api/pith-number/L5UTBG66GS2KXUO2RKWU5ZDSCA/graph.json","events_json":"https://pith.science/api/pith-number/L5UTBG66GS2KXUO2RKWU5ZDSCA/events.json","paper":"https://pith.science/paper/L5UTBG66"},"agent_actions":{"view_html":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA","download_json":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA.json","view_paper":"https://pith.science/paper/L5UTBG66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01973&json=true","fetch_graph":"https://pith.science/api/pith-number/L5UTBG66GS2KXUO2RKWU5ZDSCA/graph.json","fetch_events":"https://pith.science/api/pith-number/L5UTBG66GS2KXUO2RKWU5ZDSCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA/action/storage_attestation","attest_author":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA/action/author_attestation","sign_citation":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA/action/citation_signature","submit_replication":"https://pith.science/pith/L5UTBG66GS2KXUO2RKWU5ZDSCA/action/replication_record"}},"created_at":"2026-07-05T06:13:19.311672+00:00","updated_at":"2026-07-05T06:13:19.311672+00:00"}