{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WCGXQRRUQMOC7VW3MQDASUASBO","short_pith_number":"pith:WCGXQRRU","schema_version":"1.0","canonical_sha256":"b08d784634831c2fd6db64060950120bb593926c0d985a077bc231b0181e885e","source":{"kind":"arxiv","id":"2403.16073","version":3},"attestation_state":"computed","paper":{"title":"Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Daoyuan Wu, Jian Zhang, Shangqing Liu, Tianwen Wang, Wei Ma, Yang Liu, Yue Xue, Yuqiang Sun","submitted_at":"2024-03-24T09:26:53Z","abstract_excerpt":"Smart contracts are decentralized applications built atop blockchains like Ethereum. Recent research has shown that large language models (LLMs) have potential in auditing smart contracts, but the state-of-the-art indicates that even GPT-4 can achieve only 30% precision (when both decision and justification are correct). This is likely because off-the-shelf LLMs were primarily pre-trained on a general text/code corpus and not fine-tuned on the specific domain of Solidity smart contract auditing.\n  In this paper, we propose iAudit, a general framework that combines fine-tuning and LLM-based age"},"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":"2403.16073","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-03-24T09:26:53Z","cross_cats_sorted":[],"title_canon_sha256":"591c793a1f70191d9fb286db6d21910a267ac3a6b812efc472a0675aecd5a7b9","abstract_canon_sha256":"3016a62257172659f9d97e972d0037efbe20044a7c98c89cdcd3284c6e0acec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:58.467076Z","signature_b64":"iNCmgDoVu1WnOWi1oEI78UqOYGi82MkI0ASRQTY97i9VJGL0Zx5pS5R2ijq+JdKyLroMJDqPc8h8hGXDbLUbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b08d784634831c2fd6db64060950120bb593926c0d985a077bc231b0181e885e","last_reissued_at":"2026-07-05T09:06:58.466561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:58.466561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Daoyuan Wu, Jian Zhang, Shangqing Liu, Tianwen Wang, Wei Ma, Yang Liu, Yue Xue, Yuqiang Sun","submitted_at":"2024-03-24T09:26:53Z","abstract_excerpt":"Smart contracts are decentralized applications built atop blockchains like Ethereum. Recent research has shown that large language models (LLMs) have potential in auditing smart contracts, but the state-of-the-art indicates that even GPT-4 can achieve only 30% precision (when both decision and justification are correct). This is likely because off-the-shelf LLMs were primarily pre-trained on a general text/code corpus and not fine-tuned on the specific domain of Solidity smart contract auditing.\n  In this paper, we propose iAudit, a general framework that combines fine-tuning and LLM-based age"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16073","kind":"arxiv","version":3},"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/2403.16073/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":"2403.16073","created_at":"2026-07-05T09:06:58.466629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16073v3","created_at":"2026-07-05T09:06:58.466629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16073","created_at":"2026-07-05T09:06:58.466629+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCGXQRRUQMOC","created_at":"2026-07-05T09:06:58.466629+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCGXQRRUQMOC7VW3","created_at":"2026-07-05T09:06:58.466629+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCGXQRRU","created_at":"2026-07-05T09:06:58.466629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03128","citing_title":"Decoupled Smart Contract Audits: Lightweight LLM Framework via Distillation and Aggregation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22655","citing_title":"Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21272","citing_title":"LLM-Powered Detection of Price Manipulation in DeFi","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21058","citing_title":"Zero-Shot Vulnerability Detection in Low-Resource Smart Contracts Through Solidity-Only Training","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18395","citing_title":"Capturing Monetarily Exploitable Vulnerability in Smart Contracts via Auditor Knowledge-Learning Fuzzing","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13611","citing_title":"V2E: Validating Smart Contract Vulnerabilities through Profit-driven Exploit Generation and Execution","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO","json":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO.json","graph_json":"https://pith.science/api/pith-number/WCGXQRRUQMOC7VW3MQDASUASBO/graph.json","events_json":"https://pith.science/api/pith-number/WCGXQRRUQMOC7VW3MQDASUASBO/events.json","paper":"https://pith.science/paper/WCGXQRRU"},"agent_actions":{"view_html":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO","download_json":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO.json","view_paper":"https://pith.science/paper/WCGXQRRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16073&json=true","fetch_graph":"https://pith.science/api/pith-number/WCGXQRRUQMOC7VW3MQDASUASBO/graph.json","fetch_events":"https://pith.science/api/pith-number/WCGXQRRUQMOC7VW3MQDASUASBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO/action/storage_attestation","attest_author":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO/action/author_attestation","sign_citation":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO/action/citation_signature","submit_replication":"https://pith.science/pith/WCGXQRRUQMOC7VW3MQDASUASBO/action/replication_record"}},"created_at":"2026-07-05T09:06:58.466629+00:00","updated_at":"2026-07-05T09:06:58.466629+00:00"}