{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VZHEKXTY7NUZSHGHNN6ZRT35C2","short_pith_number":"pith:VZHEKXTY","schema_version":"1.0","canonical_sha256":"ae4e455e78fb69991cc76b7d98cf7d16b03b7c9f96cc96fd880856939a03ad9c","source":{"kind":"arxiv","id":"2405.02580","version":2},"attestation_state":"computed","paper":{"title":"PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Daoyuan Wu, Miaolei Shi, Yang Liu, Ye Liu, Yi Li, Yue Xue, Yuqiang Sun","submitted_at":"2024-05-04T06:28:27Z","abstract_excerpt":"With recent advances in large language models (LLMs), this paper explores the potential of leveraging state-of-the-art LLMs,such as GPT-4, to transfer existing human-written properties (e.g.,those from Certora auditing reports) and automatically generate customized properties for unknown code. To this end, we embed existing properties into a vector database and retrieve a reference property for LLM-based in-context learning to generate a new property for a given code. While this basic process is relatively straightforward, ensuring that the generated properties are (i) compilable, (ii) appropr"},"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":"2405.02580","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-05-04T06:28:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e6d769f7bdf61dee1af961ff21b1b9e1e89c60870ef4b1bc8ba6afd0a959a16","abstract_canon_sha256":"187d723f64bc047bf6329dbb52b9e3b5bbc9702c9bd488dd7906d66496606e6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:09.818657Z","signature_b64":"PC0oppmM6MLTgfTThq4VacvCnoBxF3vhpqOJKLXvkBR+H8wX68osaBP8A2qGzTp2QLKyZKwJQf3L5j3d6ICYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4e455e78fb69991cc76b7d98cf7d16b03b7c9f96cc96fd880856939a03ad9c","last_reissued_at":"2026-07-05T09:45:09.818115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:09.818115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Daoyuan Wu, Miaolei Shi, Yang Liu, Ye Liu, Yi Li, Yue Xue, Yuqiang Sun","submitted_at":"2024-05-04T06:28:27Z","abstract_excerpt":"With recent advances in large language models (LLMs), this paper explores the potential of leveraging state-of-the-art LLMs,such as GPT-4, to transfer existing human-written properties (e.g.,those from Certora auditing reports) and automatically generate customized properties for unknown code. To this end, we embed existing properties into a vector database and retrieve a reference property for LLM-based in-context learning to generate a new property for a given code. While this basic process is relatively straightforward, ensuring that the generated properties are (i) compilable, (ii) appropr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02580","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/2405.02580/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":"2405.02580","created_at":"2026-07-05T09:45:09.818180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02580v2","created_at":"2026-07-05T09:45:09.818180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02580","created_at":"2026-07-05T09:45:09.818180+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZHEKXTY7NUZ","created_at":"2026-07-05T09:45:09.818180+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZHEKXTY7NUZSHGH","created_at":"2026-07-05T09:45:09.818180+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZHEKXTY","created_at":"2026-07-05T09:45:09.818180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18098","citing_title":"IsabeLLM: Automated Theorem Proving Applied to Formally Verifying Consensus","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02333","citing_title":"Guiding Human Validation of LLM-Generated Code via Verifiable Literate Programming","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21570","citing_title":"SpecSyn: LLM-based Synthesis and Refinement of Formal Specifications for Real-world Program Verification","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13463","citing_title":"From Exploration to Specification: LLM-Based Property Generation for Mobile App Testing","ref_index":30,"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":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2","json":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2.json","graph_json":"https://pith.science/api/pith-number/VZHEKXTY7NUZSHGHNN6ZRT35C2/graph.json","events_json":"https://pith.science/api/pith-number/VZHEKXTY7NUZSHGHNN6ZRT35C2/events.json","paper":"https://pith.science/paper/VZHEKXTY"},"agent_actions":{"view_html":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2","download_json":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2.json","view_paper":"https://pith.science/paper/VZHEKXTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02580&json=true","fetch_graph":"https://pith.science/api/pith-number/VZHEKXTY7NUZSHGHNN6ZRT35C2/graph.json","fetch_events":"https://pith.science/api/pith-number/VZHEKXTY7NUZSHGHNN6ZRT35C2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2/action/storage_attestation","attest_author":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2/action/author_attestation","sign_citation":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2/action/citation_signature","submit_replication":"https://pith.science/pith/VZHEKXTY7NUZSHGHNN6ZRT35C2/action/replication_record"}},"created_at":"2026-07-05T09:45:09.818180+00:00","updated_at":"2026-07-05T09:45:09.818180+00:00"}