{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U7OHMXYPFIW6LRLOOA74Z5WFRP","short_pith_number":"pith:U7OHMXYP","schema_version":"1.0","canonical_sha256":"a7dc765f0f2a2de5c56e703fccf6c58bd1abbc2e5de74d90014806386d051b70","source":{"kind":"arxiv","id":"2504.10178","version":2},"attestation_state":"computed","paper":{"title":"MSCoT: Structured Chain-of-Thought Generation for Multiple Programming Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Naizhu Jin, Qingkai Zeng, Tian Zhang, Zhong Li","submitted_at":"2025-04-14T12:30:47Z","abstract_excerpt":"With the rapid development of code intelligence, the application of multiple programming languages is becoming increasingly widespread. However, most existing code generation models mainly focus on a single or a few programming languages, resulting in unsatisfactory performance in a multilingual environment. Chain-of-Thought (CoT) reasoning can significantly improve the performance of the model without the need for retraining or fine-tuning the code generation model by reasonably decomposing complex code generation tasks into multiple subtasks and gradually deriving solutions for each subtask."},"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":"2504.10178","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-14T12:30:47Z","cross_cats_sorted":[],"title_canon_sha256":"97b4a6103aad2849d589b55f56082453e94f2583b80af8fcecdcb68805854b94","abstract_canon_sha256":"c282e281bd1838042e5aa786b69d7870c6d4e5be259be0d6bf1eca5eeb1f52f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:54.104814Z","signature_b64":"rZQD2uxXrEpM8Va+L5p/UJitJBdHIL0VefcZHrO2YClFYZNBDc9HeF538ZaifQGTO9y5JUdOmFVSQL+hjECuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7dc765f0f2a2de5c56e703fccf6c58bd1abbc2e5de74d90014806386d051b70","last_reissued_at":"2026-07-05T10:53:54.104208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:54.104208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSCoT: Structured Chain-of-Thought Generation for Multiple Programming Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Naizhu Jin, Qingkai Zeng, Tian Zhang, Zhong Li","submitted_at":"2025-04-14T12:30:47Z","abstract_excerpt":"With the rapid development of code intelligence, the application of multiple programming languages is becoming increasingly widespread. However, most existing code generation models mainly focus on a single or a few programming languages, resulting in unsatisfactory performance in a multilingual environment. Chain-of-Thought (CoT) reasoning can significantly improve the performance of the model without the need for retraining or fine-tuning the code generation model by reasonably decomposing complex code generation tasks into multiple subtasks and gradually deriving solutions for each subtask."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10178","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/2504.10178/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":"2504.10178","created_at":"2026-07-05T10:53:54.104276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10178v2","created_at":"2026-07-05T10:53:54.104276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10178","created_at":"2026-07-05T10:53:54.104276+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7OHMXYPFIW6","created_at":"2026-07-05T10:53:54.104276+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7OHMXYPFIW6LRLO","created_at":"2026-07-05T10:53:54.104276+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7OHMXYP","created_at":"2026-07-05T10:53:54.104276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21425","citing_title":"GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP","json":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP.json","graph_json":"https://pith.science/api/pith-number/U7OHMXYPFIW6LRLOOA74Z5WFRP/graph.json","events_json":"https://pith.science/api/pith-number/U7OHMXYPFIW6LRLOOA74Z5WFRP/events.json","paper":"https://pith.science/paper/U7OHMXYP"},"agent_actions":{"view_html":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP","download_json":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP.json","view_paper":"https://pith.science/paper/U7OHMXYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10178&json=true","fetch_graph":"https://pith.science/api/pith-number/U7OHMXYPFIW6LRLOOA74Z5WFRP/graph.json","fetch_events":"https://pith.science/api/pith-number/U7OHMXYPFIW6LRLOOA74Z5WFRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP/action/storage_attestation","attest_author":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP/action/author_attestation","sign_citation":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP/action/citation_signature","submit_replication":"https://pith.science/pith/U7OHMXYPFIW6LRLOOA74Z5WFRP/action/replication_record"}},"created_at":"2026-07-05T10:53:54.104276+00:00","updated_at":"2026-07-05T10:53:54.104276+00:00"}