{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R4DZSVMTR7FKL7OEBQGRPGSOIS","short_pith_number":"pith:R4DZSVMT","schema_version":"1.0","canonical_sha256":"8f079955938fcaa5fdc40c0d179a4e44b39491233587675deb6192a3be4cfc5c","source":{"kind":"arxiv","id":"2412.08035","version":1},"attestation_state":"computed","paper":{"title":"Scalable, Validated Code Translation of Entire Projects using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.PL","authors_text":"Brandon Paulsen, Cristina David, Daniel Kroening, Hanliang Zhang, Meng Wang","submitted_at":"2024-12-11T02:31:46Z","abstract_excerpt":"Large language models (LLMs) show promise in code translation due to their ability to generate idiomatic code. However, a significant limitation when using LLMs for code translation is scalability: existing works have shown a drop in translation success rates for code exceeding around 100 lines. We overcome this limitation by developing a modular approach to translation, where we partition the code into small code fragments which can be translated independently and semantically validated (that is, checking I/O equivalence). When this approach is applied naively, we discover that LLMs are unrel"},"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":"2412.08035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2024-12-11T02:31:46Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"27e4ffe485a044353f411bc6a9cd1361a873db5ddb4c45db8f808360bc15f615","abstract_canon_sha256":"3904ed76735b379d6cdebeeb1cc3809719cc4618dd3c8b7035ebd72f9e2d507f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:43.441586Z","signature_b64":"VJ45ajSa5s7Cl44dXNwZDjByjnBzOlAwokdtI0pmEHGTRyv3aE3OzZK6yTdo2FrOVqoX7F374tAWhNajvDeECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f079955938fcaa5fdc40c0d179a4e44b39491233587675deb6192a3be4cfc5c","last_reissued_at":"2026-07-05T09:47:43.441187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:43.441187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable, Validated Code Translation of Entire Projects using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.PL","authors_text":"Brandon Paulsen, Cristina David, Daniel Kroening, Hanliang Zhang, Meng Wang","submitted_at":"2024-12-11T02:31:46Z","abstract_excerpt":"Large language models (LLMs) show promise in code translation due to their ability to generate idiomatic code. However, a significant limitation when using LLMs for code translation is scalability: existing works have shown a drop in translation success rates for code exceeding around 100 lines. We overcome this limitation by developing a modular approach to translation, where we partition the code into small code fragments which can be translated independently and semantically validated (that is, checking I/O equivalence). When this approach is applied naively, we discover that LLMs are unrel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08035","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/2412.08035/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":"2412.08035","created_at":"2026-07-05T09:47:43.441243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08035v1","created_at":"2026-07-05T09:47:43.441243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08035","created_at":"2026-07-05T09:47:43.441243+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4DZSVMTR7FK","created_at":"2026-07-05T09:47:43.441243+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4DZSVMTR7FKL7OE","created_at":"2026-07-05T09:47:43.441243+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4DZSVMT","created_at":"2026-07-05T09:47:43.441243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.10708","citing_title":"SafeTrans: LLM-assisted Transpilation from C to Rust","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03535","citing_title":"Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10956","citing_title":"Project-Level C-to-Rust Translation via Pointer Knowledge Graphs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12048","citing_title":"ORBIT: Guided Agentic Orchestration for Autonomous C-to-Rust Transpilation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS","json":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS.json","graph_json":"https://pith.science/api/pith-number/R4DZSVMTR7FKL7OEBQGRPGSOIS/graph.json","events_json":"https://pith.science/api/pith-number/R4DZSVMTR7FKL7OEBQGRPGSOIS/events.json","paper":"https://pith.science/paper/R4DZSVMT"},"agent_actions":{"view_html":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS","download_json":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS.json","view_paper":"https://pith.science/paper/R4DZSVMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08035&json=true","fetch_graph":"https://pith.science/api/pith-number/R4DZSVMTR7FKL7OEBQGRPGSOIS/graph.json","fetch_events":"https://pith.science/api/pith-number/R4DZSVMTR7FKL7OEBQGRPGSOIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS/action/storage_attestation","attest_author":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS/action/author_attestation","sign_citation":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS/action/citation_signature","submit_replication":"https://pith.science/pith/R4DZSVMTR7FKL7OEBQGRPGSOIS/action/replication_record"}},"created_at":"2026-07-05T09:47:43.441243+00:00","updated_at":"2026-07-05T09:47:43.441243+00:00"}