{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HGKVMVVQLAMRFAL74RPU5CYNSA","short_pith_number":"pith:HGKVMVVQ","schema_version":"1.0","canonical_sha256":"39955656b0581912817fe45f4e8b0d9039c9637de772b79580b0a14c0ee1efdf","source":{"kind":"arxiv","id":"2412.19770","version":2},"attestation_state":"computed","paper":{"title":"Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Jannesari, Bin Lei, Caiwen Ding, Chunhua Liao, Dunzhi Zhou, Le Chen, Pei-Hung Lin","submitted_at":"2024-12-27T18:06:25Z","abstract_excerpt":"Translating legacy Fortran code into C++ is a crucial step in modernizing high-performance computing (HPC) applications. However, the scarcity of high-quality, parallel Fortran-to-C++ datasets and the limited domain-specific expertise in large language models (LLMs) present significant challenges for automated translation. In this paper, we introduce Fortran2CPP, a multi-turn dialogue dataset generated by a novel LLM agent-based approach that integrates a dual-LLM Questioner-Solver module to enhance translation accuracy. Our dataset comprises 11.7k dialogues capturing iterative feedback-decisi"},"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":"2412.19770","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T18:06:25Z","cross_cats_sorted":[],"title_canon_sha256":"9380cd5eaa9d9a10ee2476d3db18101fe06f2f30bd92aac7062a39fce3933498","abstract_canon_sha256":"e12589056e4ffbaa1cf53e6b224ecfe1300d5b247ac0c9955ca169b06308d652"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:26.841407Z","signature_b64":"q1Fhvdhlc9faIzfTydEUmcTWrw0K1ETYJ00gI4AEoclN06A05tkQuSUJZr8ZfbspKK8c+Gg1JwcSVQG+wLwgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39955656b0581912817fe45f4e8b0d9039c9637de772b79580b0a14c0ee1efdf","last_reissued_at":"2026-07-05T10:08:26.840925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:26.840925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Jannesari, Bin Lei, Caiwen Ding, Chunhua Liao, Dunzhi Zhou, Le Chen, Pei-Hung Lin","submitted_at":"2024-12-27T18:06:25Z","abstract_excerpt":"Translating legacy Fortran code into C++ is a crucial step in modernizing high-performance computing (HPC) applications. However, the scarcity of high-quality, parallel Fortran-to-C++ datasets and the limited domain-specific expertise in large language models (LLMs) present significant challenges for automated translation. In this paper, we introduce Fortran2CPP, a multi-turn dialogue dataset generated by a novel LLM agent-based approach that integrates a dual-LLM Questioner-Solver module to enhance translation accuracy. Our dataset comprises 11.7k dialogues capturing iterative feedback-decisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19770","kind":"arxiv","version":2},"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/2412.19770/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":"2412.19770","created_at":"2026-07-05T10:08:26.840982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19770v2","created_at":"2026-07-05T10:08:26.840982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19770","created_at":"2026-07-05T10:08:26.840982+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGKVMVVQLAMR","created_at":"2026-07-05T10:08:26.840982+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGKVMVVQLAMRFAL7","created_at":"2026-07-05T10:08:26.840982+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGKVMVVQ","created_at":"2026-07-05T10:08:26.840982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11356","citing_title":"An Ocean Model Ported by a Large Language Model: Experience and Lessons from FESOM2 (Fortran to C to C++/Kokkos)","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06063","citing_title":"LLM-Based Porting of Optimized C++ to CUDA Through Deoptimization and Reoptimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07681","citing_title":"Systematic LLM Translation of Legacy Scientific Code to Differentiable Frameworks: Application to a Land Surface Model","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA","json":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA.json","graph_json":"https://pith.science/api/pith-number/HGKVMVVQLAMRFAL74RPU5CYNSA/graph.json","events_json":"https://pith.science/api/pith-number/HGKVMVVQLAMRFAL74RPU5CYNSA/events.json","paper":"https://pith.science/paper/HGKVMVVQ"},"agent_actions":{"view_html":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA","download_json":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA.json","view_paper":"https://pith.science/paper/HGKVMVVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19770&json=true","fetch_graph":"https://pith.science/api/pith-number/HGKVMVVQLAMRFAL74RPU5CYNSA/graph.json","fetch_events":"https://pith.science/api/pith-number/HGKVMVVQLAMRFAL74RPU5CYNSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA/action/storage_attestation","attest_author":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA/action/author_attestation","sign_citation":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA/action/citation_signature","submit_replication":"https://pith.science/pith/HGKVMVVQLAMRFAL74RPU5CYNSA/action/replication_record"}},"created_at":"2026-07-05T10:08:26.840982+00:00","updated_at":"2026-07-05T10:08:26.840982+00:00"}