{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PA4QRK6RK6CNL7T47XWNEOCCLK","short_pith_number":"pith:PA4QRK6R","schema_version":"1.0","canonical_sha256":"783908abd15784d5fe7cfdecd238425ab57e7905eb8b30eb8b6abbcd8fc7ddfa","source":{"kind":"arxiv","id":"2504.21043","version":2},"attestation_state":"computed","paper":{"title":"CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Hainan Zhang, Hongwei Zheng, Jin Dong, Lingxiang Wang, Qinnan Zhang, Zhiming Zheng, Ziwei Wang","submitted_at":"2025-04-28T14:14:16Z","abstract_excerpt":"Large language models (LLMs) excel at generating code from natural language instructions, yet they often lack an understanding of security vulnerabilities. This limitation makes it difficult for LLMs to avoid security risks in generated code, particularly in high-security programming tasks such as smart contract development for blockchain. Researchers have attempted to enhance the vulnerability awareness of these models by training them to differentiate between vulnerable and fixed code snippets. However, this approach relies heavily on manually labeled vulnerability data, which is only availa"},"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":"2504.21043","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-04-28T14:14:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4dcf929874f7ea50dccbd7e87e5e541d6af68b90352b291b69b29595dbd6871a","abstract_canon_sha256":"68dcf36cf905f4e04a538cd60a15c0e2d9b912b724dc8f439c18e005e75513e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:29.343427Z","signature_b64":"vrGJn/dbYJ/mzEG4MPdJB5+/apmBthuiESkQ2oyBLnVY/GhcLudxIuH8dmDhr71+XSyyjksHBHD9nSVLRH/PBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"783908abd15784d5fe7cfdecd238425ab57e7905eb8b30eb8b6abbcd8fc7ddfa","last_reissued_at":"2026-07-05T10:59:29.342746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:29.342746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Hainan Zhang, Hongwei Zheng, Jin Dong, Lingxiang Wang, Qinnan Zhang, Zhiming Zheng, Ziwei Wang","submitted_at":"2025-04-28T14:14:16Z","abstract_excerpt":"Large language models (LLMs) excel at generating code from natural language instructions, yet they often lack an understanding of security vulnerabilities. This limitation makes it difficult for LLMs to avoid security risks in generated code, particularly in high-security programming tasks such as smart contract development for blockchain. Researchers have attempted to enhance the vulnerability awareness of these models by training them to differentiate between vulnerable and fixed code snippets. However, this approach relies heavily on manually labeled vulnerability data, which is only availa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21043","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/2504.21043/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":"2504.21043","created_at":"2026-07-05T10:59:29.342835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21043v2","created_at":"2026-07-05T10:59:29.342835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21043","created_at":"2026-07-05T10:59:29.342835+00:00"},{"alias_kind":"pith_short_12","alias_value":"PA4QRK6RK6CN","created_at":"2026-07-05T10:59:29.342835+00:00"},{"alias_kind":"pith_short_16","alias_value":"PA4QRK6RK6CNL7T4","created_at":"2026-07-05T10:59:29.342835+00:00"},{"alias_kind":"pith_short_8","alias_value":"PA4QRK6R","created_at":"2026-07-05T10:59:29.342835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01129","citing_title":"Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK","json":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK.json","graph_json":"https://pith.science/api/pith-number/PA4QRK6RK6CNL7T47XWNEOCCLK/graph.json","events_json":"https://pith.science/api/pith-number/PA4QRK6RK6CNL7T47XWNEOCCLK/events.json","paper":"https://pith.science/paper/PA4QRK6R"},"agent_actions":{"view_html":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK","download_json":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK.json","view_paper":"https://pith.science/paper/PA4QRK6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21043&json=true","fetch_graph":"https://pith.science/api/pith-number/PA4QRK6RK6CNL7T47XWNEOCCLK/graph.json","fetch_events":"https://pith.science/api/pith-number/PA4QRK6RK6CNL7T47XWNEOCCLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK/action/storage_attestation","attest_author":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK/action/author_attestation","sign_citation":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK/action/citation_signature","submit_replication":"https://pith.science/pith/PA4QRK6RK6CNL7T47XWNEOCCLK/action/replication_record"}},"created_at":"2026-07-05T10:59:29.342835+00:00","updated_at":"2026-07-05T10:59:29.342835+00:00"}