{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GPNSX27K5JGYGRWQ5O7CZXPWIZ","short_pith_number":"pith:GPNSX27K","schema_version":"1.0","canonical_sha256":"33db2bebeaea4d8346d0ebbe2cddf64670da41ad5c0e5356d63f2bac36cc72b0","source":{"kind":"arxiv","id":"2310.17807","version":4},"attestation_state":"computed","paper":{"title":"Clover: Closed-Loop Verifiable Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Chuyue Sun, Clark Barrett, Oded Padon, Ying Sheng","submitted_at":"2023-10-26T22:58:19Z","abstract_excerpt":"The use of large language models for code generation is a rapidly growing trend in software development. However, without effective methods for ensuring the correctness of generated code, this trend could lead to undesirable outcomes. In this paper, we introduce a new approach for addressing this challenge: the Clover paradigm, short for Closed-Loop Verifiable Code Generation, which uses consistency checking to provide a strong filter for incorrect code. Clover performs consistency checks among code, docstrings, and formal annotations. The checker is implemented using a novel integration of fo"},"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":"2310.17807","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T22:58:19Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"195c4cddf5cddd8505d8b1c8e92a6ce78d8771df9714908871e4b3fb7e63cd42","abstract_canon_sha256":"8142959d2609cb72053a14191e8fb9ee99b6286e9e2b2ae56f6c5a647eb948b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:08.107740Z","signature_b64":"v20lKNkxfEBh9G9V/cFIJLj/OoD/37onovd9LN1fvb3xUWqFzTZbaD8a7nPTTDsCHpOoI2B1NEOLbfXsACEaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33db2bebeaea4d8346d0ebbe2cddf64670da41ad5c0e5356d63f2bac36cc72b0","last_reissued_at":"2026-07-05T09:36:08.107233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:08.107233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clover: Closed-Loop Verifiable Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Chuyue Sun, Clark Barrett, Oded Padon, Ying Sheng","submitted_at":"2023-10-26T22:58:19Z","abstract_excerpt":"The use of large language models for code generation is a rapidly growing trend in software development. However, without effective methods for ensuring the correctness of generated code, this trend could lead to undesirable outcomes. In this paper, we introduce a new approach for addressing this challenge: the Clover paradigm, short for Closed-Loop Verifiable Code Generation, which uses consistency checking to provide a strong filter for incorrect code. Clover performs consistency checks among code, docstrings, and formal annotations. The checker is implemented using a novel integration of fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17807","kind":"arxiv","version":4},"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/2310.17807/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":"2310.17807","created_at":"2026-07-05T09:36:08.107296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17807v4","created_at":"2026-07-05T09:36:08.107296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17807","created_at":"2026-07-05T09:36:08.107296+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPNSX27K5JGY","created_at":"2026-07-05T09:36:08.107296+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPNSX27K5JGYGRWQ","created_at":"2026-07-05T09:36:08.107296+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPNSX27K","created_at":"2026-07-05T09:36:08.107296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30914","citing_title":"Automating Formal Verification with Reinforcement Learning and Recursive Inference","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23109","citing_title":"Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21104","citing_title":"BRIDGE: Building Representations In Domain Guided Program Synthesis","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07935","citing_title":"TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16584","citing_title":"Certified Program Synthesis with a Multi-Modal Verifier","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ","json":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ.json","graph_json":"https://pith.science/api/pith-number/GPNSX27K5JGYGRWQ5O7CZXPWIZ/graph.json","events_json":"https://pith.science/api/pith-number/GPNSX27K5JGYGRWQ5O7CZXPWIZ/events.json","paper":"https://pith.science/paper/GPNSX27K"},"agent_actions":{"view_html":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ","download_json":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ.json","view_paper":"https://pith.science/paper/GPNSX27K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17807&json=true","fetch_graph":"https://pith.science/api/pith-number/GPNSX27K5JGYGRWQ5O7CZXPWIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GPNSX27K5JGYGRWQ5O7CZXPWIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ/action/storage_attestation","attest_author":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ/action/author_attestation","sign_citation":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ/action/citation_signature","submit_replication":"https://pith.science/pith/GPNSX27K5JGYGRWQ5O7CZXPWIZ/action/replication_record"}},"created_at":"2026-07-05T09:36:08.107296+00:00","updated_at":"2026-07-05T09:36:08.107296+00:00"}