{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZZFTNEXURTIPGPSZ52H2ORQRML","short_pith_number":"pith:ZZFTNEXU","schema_version":"1.0","canonical_sha256":"ce4b3692f48cd0f33e59ee8fa7461162d902aeb92c9d6859f24c0d4452fa8eb8","source":{"kind":"arxiv","id":"2603.19329","version":3},"attestation_state":"computed","paper":{"title":"Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Aarti Gupta, Andrew Zhao, Chi Jin, Deyuan He, Haoyu Zhao, Kaiyu Yang, Shange Tang, Zenan Li, Zhendong Su, Ziran Yang","submitted_at":"2026-03-18T18:42:04Z","abstract_excerpt":"Large language models (LLMs) can generate plausible code but offer limited guarantees of correctness. Formally verifying that implementations satisfy specifications requires constructing machine-checkable proofs, a task that remains beyond current automation. We propose a hierarchical proof search framework for automated code verification in Lean~4 that decomposes complex verification goals into structurally simpler subgoals before attempting tactic-level proving. Central to our approach is a principled decomposition score that combines constructive justification with structural effectiveness."},"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":"2603.19329","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-18T18:42:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ddd3c515622aa6c4bf3f8a3120ca536a7a58a77dbcf496aa0bf9d184991e5dc","abstract_canon_sha256":"50eecac15f1924e85b59bf2b08f5b369e98aca53102b7fa15e819bb639f87be7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:18:56.557106Z","signature_b64":"V3Tjek2RGE8a6x48oqZeVGr90fme7P76qZvHX9sxJHfW0kc2BL8wa9ndKgaPEMfToqP/DoUqYKr69vHsw0SbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce4b3692f48cd0f33e59ee8fa7461162d902aeb92c9d6859f24c0d4452fa8eb8","last_reissued_at":"2026-08-11T02:18:56.555274Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:18:56.555274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Aarti Gupta, Andrew Zhao, Chi Jin, Deyuan He, Haoyu Zhao, Kaiyu Yang, Shange Tang, Zenan Li, Zhendong Su, Ziran Yang","submitted_at":"2026-03-18T18:42:04Z","abstract_excerpt":"Large language models (LLMs) can generate plausible code but offer limited guarantees of correctness. Formally verifying that implementations satisfy specifications requires constructing machine-checkable proofs, a task that remains beyond current automation. We propose a hierarchical proof search framework for automated code verification in Lean~4 that decomposes complex verification goals into structurally simpler subgoals before attempting tactic-level proving. Central to our approach is a principled decomposition score that combines constructive justification with structural effectiveness."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19329","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/2603.19329/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":"2603.19329","created_at":"2026-08-11T02:18:56.555975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.19329v3","created_at":"2026-08-11T02:18:56.555975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19329","created_at":"2026-08-11T02:18:56.555975+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZFTNEXURTIP","created_at":"2026-08-11T02:18:56.555975+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZFTNEXURTIPGPSZ","created_at":"2026-08-11T02:18:56.555975+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZFTNEXU","created_at":"2026-08-11T02:18:56.555975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.17981","citing_title":"Planning to Hammer: Difficulty-Aware Decomposition for Automating Rocq Proofs","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30914","citing_title":"Automating Formal Verification with Reinforcement Learning and Recursive Inference","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23109","citing_title":"Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23772","citing_title":"Agentic Proving for Program Verification","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18747","citing_title":"Code as Agent Harness","ref_index":94,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML","json":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML.json","graph_json":"https://pith.science/api/pith-number/ZZFTNEXURTIPGPSZ52H2ORQRML/graph.json","events_json":"https://pith.science/api/pith-number/ZZFTNEXURTIPGPSZ52H2ORQRML/events.json","paper":"https://pith.science/paper/ZZFTNEXU"},"agent_actions":{"view_html":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML","download_json":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML.json","view_paper":"https://pith.science/paper/ZZFTNEXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.19329&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZFTNEXURTIPGPSZ52H2ORQRML/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZFTNEXURTIPGPSZ52H2ORQRML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML/action/storage_attestation","attest_author":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML/action/author_attestation","sign_citation":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML/action/citation_signature","submit_replication":"https://pith.science/pith/ZZFTNEXURTIPGPSZ52H2ORQRML/action/replication_record"}},"created_at":"2026-08-11T02:18:56.555975+00:00","updated_at":"2026-08-11T02:18:56.555975+00:00"}