{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H6F3GTQGK4EYNZPYHDCPG4436J","short_pith_number":"pith:H6F3GTQG","schema_version":"1.0","canonical_sha256":"3f8bb34e06570986e5f838c4f3739bf261dc4a677833ac14713a9d90d8b7d168","source":{"kind":"arxiv","id":"2512.03086","version":2},"attestation_state":"computed","paper":{"title":"Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.PL","authors_text":"Ali Jannesari, Bin Lei, Caiwen Ding, Chunhua Liao, Dunzhi Zhou, Le Chen, Nuo Xu, Pei-Hung Lin, Rajeev Thakur, Winson Chen","submitted_at":"2025-11-29T05:26:53Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA, where high-quality parallel data are scarce. We present an automated dataset generation pipeline featuring a dual-LLM Questioner-Solver design that incorporates external knowledge from compilers and runtime feedback. Beyond traditional source-target code pair datasets, our approach additionally generates (1) verified translations with unit tests for assessing functional consistency and (2) "},"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":"2512.03086","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-11-29T05:26:53Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"664a3a63e7c4f7b7f40d8c43a3b2ae728535d0ddb81ac13cf90c10a6e5629772","abstract_canon_sha256":"93ddd66aee533efad97d34d9df9e0d86328519a8db77293f90d55555afc82dc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:44.572230Z","signature_b64":"EV85erv8VL9dQU/uFWt+h3+DjaiMy9W6WZOmn1Ty2EOGc0aFFtCDCMLADIgNNki9QbzRMng63jgGi/4GqmO7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8bb34e06570986e5f838c4f3739bf261dc4a677833ac14713a9d90d8b7d168","last_reissued_at":"2026-06-05T00:13:44.571718Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:44.571718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.PL","authors_text":"Ali Jannesari, Bin Lei, Caiwen Ding, Chunhua Liao, Dunzhi Zhou, Le Chen, Nuo Xu, Pei-Hung Lin, Rajeev Thakur, Winson Chen","submitted_at":"2025-11-29T05:26:53Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA, where high-quality parallel data are scarce. We present an automated dataset generation pipeline featuring a dual-LLM Questioner-Solver design that incorporates external knowledge from compilers and runtime feedback. Beyond traditional source-target code pair datasets, our approach additionally generates (1) verified translations with unit tests for assessing functional consistency and (2) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.03086","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/2512.03086/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":"2512.03086","created_at":"2026-06-05T00:13:44.571779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.03086v2","created_at":"2026-06-05T00:13:44.571779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.03086","created_at":"2026-06-05T00:13:44.571779+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6F3GTQGK4EY","created_at":"2026-06-05T00:13:44.571779+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6F3GTQGK4EYNZPY","created_at":"2026-06-05T00:13:44.571779+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6F3GTQG","created_at":"2026-06-05T00:13:44.571779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J","json":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J.json","graph_json":"https://pith.science/api/pith-number/H6F3GTQGK4EYNZPYHDCPG4436J/graph.json","events_json":"https://pith.science/api/pith-number/H6F3GTQGK4EYNZPYHDCPG4436J/events.json","paper":"https://pith.science/paper/H6F3GTQG"},"agent_actions":{"view_html":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J","download_json":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J.json","view_paper":"https://pith.science/paper/H6F3GTQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.03086&json=true","fetch_graph":"https://pith.science/api/pith-number/H6F3GTQGK4EYNZPYHDCPG4436J/graph.json","fetch_events":"https://pith.science/api/pith-number/H6F3GTQGK4EYNZPYHDCPG4436J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/action/storage_attestation","attest_author":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/action/author_attestation","sign_citation":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/action/citation_signature","submit_replication":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/action/replication_record"}},"created_at":"2026-06-05T00:13:44.571779+00:00","updated_at":"2026-06-05T00:13:44.571779+00:00"}