{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MDWOPUFDTLCMB4EX3JGBHU6P2N","short_pith_number":"pith:MDWOPUFD","schema_version":"1.0","canonical_sha256":"60ece7d0a39ac4c0f097da4c13d3cfd36cf207f586b34c3be8ca15f6b195c1de","source":{"kind":"arxiv","id":"2506.00894","version":1},"attestation_state":"computed","paper":{"title":"CODEMENV: Benchmarking Large Language Models on Code Migration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Di Wang, Hanbin Wang, Keyuan Cheng, Lijie Hu, Muhammad Asif Ali, Tengyue Wang, Xudong Shen, Yang Cao, Yihao Yang","submitted_at":"2025-06-01T08:29:59Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities across various software engineering tasks; however, their effectiveness in code migration, adapting code to run in different environments, remains insufficiently studied. In this work, we introduce CODEMENV: Code Migration Across Environment, a new benchmark specifically designed to assess LLMs' abilities in code migration scenarios. CODEMENV consists of 922 examples spanning 19 Python and Java packages, and covers three core tasks: (1) identifying functions incompatible with specific versions, (2) detecting changes in function de"},"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":"2506.00894","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-01T08:29:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"32f8323d4377dc452c1112027d0248a9ac59d7f01bb716d54ff91dd741404601","abstract_canon_sha256":"3fca00515a7ddb813e00f0d549cfd1b67031d3cc0328a24a89338bfedc9c4c75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:42.364605Z","signature_b64":"S+Wh1nRmJZgkvdxajAoitO5lrTY9mCBJKi7jScMVDH69EgZmTkA9kMy3qHsLhbHd9oev/g0vpJJHWgn/rpDOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60ece7d0a39ac4c0f097da4c13d3cfd36cf207f586b34c3be8ca15f6b195c1de","last_reissued_at":"2026-07-05T11:13:42.364116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:42.364116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CODEMENV: Benchmarking Large Language Models on Code Migration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Di Wang, Hanbin Wang, Keyuan Cheng, Lijie Hu, Muhammad Asif Ali, Tengyue Wang, Xudong Shen, Yang Cao, Yihao Yang","submitted_at":"2025-06-01T08:29:59Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities across various software engineering tasks; however, their effectiveness in code migration, adapting code to run in different environments, remains insufficiently studied. In this work, we introduce CODEMENV: Code Migration Across Environment, a new benchmark specifically designed to assess LLMs' abilities in code migration scenarios. CODEMENV consists of 922 examples spanning 19 Python and Java packages, and covers three core tasks: (1) identifying functions incompatible with specific versions, (2) detecting changes in function de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00894","kind":"arxiv","version":1},"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/2506.00894/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":"2506.00894","created_at":"2026-07-05T11:13:42.364174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00894v1","created_at":"2026-07-05T11:13:42.364174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00894","created_at":"2026-07-05T11:13:42.364174+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDWOPUFDTLCM","created_at":"2026-07-05T11:13:42.364174+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDWOPUFDTLCMB4EX","created_at":"2026-07-05T11:13:42.364174+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDWOPUFD","created_at":"2026-07-05T11:13:42.364174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.07180","citing_title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N","json":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N.json","graph_json":"https://pith.science/api/pith-number/MDWOPUFDTLCMB4EX3JGBHU6P2N/graph.json","events_json":"https://pith.science/api/pith-number/MDWOPUFDTLCMB4EX3JGBHU6P2N/events.json","paper":"https://pith.science/paper/MDWOPUFD"},"agent_actions":{"view_html":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N","download_json":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N.json","view_paper":"https://pith.science/paper/MDWOPUFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00894&json=true","fetch_graph":"https://pith.science/api/pith-number/MDWOPUFDTLCMB4EX3JGBHU6P2N/graph.json","fetch_events":"https://pith.science/api/pith-number/MDWOPUFDTLCMB4EX3JGBHU6P2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N/action/storage_attestation","attest_author":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N/action/author_attestation","sign_citation":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N/action/citation_signature","submit_replication":"https://pith.science/pith/MDWOPUFDTLCMB4EX3JGBHU6P2N/action/replication_record"}},"created_at":"2026-07-05T11:13:42.364174+00:00","updated_at":"2026-07-05T11:13:42.364174+00:00"}