{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WRVJGJA5SZOG4UZRGYDWK4U3RT","short_pith_number":"pith:WRVJGJA5","schema_version":"1.0","canonical_sha256":"b46a93241d965c6e5331360765729b8cd85bc467c6cd6ed512caa669a2349cda","source":{"kind":"arxiv","id":"2606.22413","version":1},"attestation_state":"computed","paper":{"title":"Formal-Method-Guided Vibe Coding: Closing the Verification Loop on AI-Generated Safety-Critical Software Through Model-Driven Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.SE","authors_text":"Fang Yan, Haochi Wang, Jim Woodcock, Le Zhu, Ran Wei, Simon Foster, Xiangyang Ji","submitted_at":"2026-06-21T10:01:45Z","abstract_excerpt":"Vibe coding -- accepting LLM-generated source from natural-language intent with minimal review -- is fast and may be adequate for low-criticality consumer software. But for safety-critical systems governed by DO-178C, IEC 61508, or ISO 26262, it offers no path to certification: large language models (LLMs) provide no formal correctness guarantees, and existing remedies target verification-aware languages (Dafny, Verus, Lean) that are scarce in pretraining data and absent from industrial toolchains.\n  This paper closes the gap. We present Forge (Formal method Oriented Refinement loop for GEnera"},"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":"2606.22413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-21T10:01:45Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"b6d707d369792fdcfef62105aa4da3ddc788ae6d9b02d1e29bcb03f70848a093","abstract_canon_sha256":"fa11dd01855bf11f5726046619ed153cb98edcbec122f011cd28f97c2e2711f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:37.724059Z","signature_b64":"2jw9wwBePyCS6RzudU6TGPKjhcDQaq+IgMqwqenxD9ZTqemB91zBN45XrJ7uYyJY+YbnL21rLoZcRh7z6PDfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b46a93241d965c6e5331360765729b8cd85bc467c6cd6ed512caa669a2349cda","last_reissued_at":"2026-06-23T02:13:37.723637Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:37.723637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Formal-Method-Guided Vibe Coding: Closing the Verification Loop on AI-Generated Safety-Critical Software Through Model-Driven Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.SE","authors_text":"Fang Yan, Haochi Wang, Jim Woodcock, Le Zhu, Ran Wei, Simon Foster, Xiangyang Ji","submitted_at":"2026-06-21T10:01:45Z","abstract_excerpt":"Vibe coding -- accepting LLM-generated source from natural-language intent with minimal review -- is fast and may be adequate for low-criticality consumer software. But for safety-critical systems governed by DO-178C, IEC 61508, or ISO 26262, it offers no path to certification: large language models (LLMs) provide no formal correctness guarantees, and existing remedies target verification-aware languages (Dafny, Verus, Lean) that are scarce in pretraining data and absent from industrial toolchains.\n  This paper closes the gap. We present Forge (Formal method Oriented Refinement loop for GEnera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22413","kind":"arxiv","version":1},"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/2606.22413/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":"2606.22413","created_at":"2026-06-23T02:13:37.723716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22413v1","created_at":"2026-06-23T02:13:37.723716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22413","created_at":"2026-06-23T02:13:37.723716+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRVJGJA5SZOG","created_at":"2026-06-23T02:13:37.723716+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRVJGJA5SZOG4UZR","created_at":"2026-06-23T02:13:37.723716+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRVJGJA5","created_at":"2026-06-23T02:13:37.723716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT","json":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT.json","graph_json":"https://pith.science/api/pith-number/WRVJGJA5SZOG4UZRGYDWK4U3RT/graph.json","events_json":"https://pith.science/api/pith-number/WRVJGJA5SZOG4UZRGYDWK4U3RT/events.json","paper":"https://pith.science/paper/WRVJGJA5"},"agent_actions":{"view_html":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT","download_json":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT.json","view_paper":"https://pith.science/paper/WRVJGJA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22413&json=true","fetch_graph":"https://pith.science/api/pith-number/WRVJGJA5SZOG4UZRGYDWK4U3RT/graph.json","fetch_events":"https://pith.science/api/pith-number/WRVJGJA5SZOG4UZRGYDWK4U3RT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT/action/storage_attestation","attest_author":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT/action/author_attestation","sign_citation":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT/action/citation_signature","submit_replication":"https://pith.science/pith/WRVJGJA5SZOG4UZRGYDWK4U3RT/action/replication_record"}},"created_at":"2026-06-23T02:13:37.723716+00:00","updated_at":"2026-06-23T02:13:37.723716+00:00"}