{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SCQIUO33AACYHPQELNTOLXCEBX","short_pith_number":"pith:SCQIUO33","schema_version":"1.0","canonical_sha256":"90a08a3b7b000583be045b66e5dc440dfd4b2d0a1a0f82a0b84d01a6760ee52e","source":{"kind":"arxiv","id":"2402.04380","version":1},"attestation_state":"computed","paper":{"title":"Assured LLM-Based Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alexandru Marginean, Eddy Wang, Inna Harper, Mark Harman, Nadia Alshahwan, Shubho Sengupta","submitted_at":"2024-02-06T20:38:46Z","abstract_excerpt":"In this paper we address the following question: How can we use Large Language Models (LLMs) to improve code independently of a human, while ensuring that the improved code\n  - does not regress the properties of the original code?\n  - improves the original in a verifiable and measurable way?\n  To address this question, we advocate Assured LLM-Based Software Engineering; a generate-and-test approach, inspired by Genetic Improvement. Assured LLMSE applies a series of semantic filters that discard code that fails to meet these twin guarantees. This overcomes the potential problem of LLM's propens"},"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":"2402.04380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-06T20:38:46Z","cross_cats_sorted":[],"title_canon_sha256":"70e0245b530056c71f231445da1f2e1fac0005ea3b10c01c1da22cff032eb8c5","abstract_canon_sha256":"4530c47131b96d3a853f8353cebf2a87b7ba81f3765f65c0073c8a2b93f138b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:25.884906Z","signature_b64":"60M8OfvyzEBQfyiSeiy6rwXCEfPZJML7BNiJFUsg8SKPxvWsMt2YZDQM5DLSpf3T+c0DmVOwXRWAvuiLSloBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90a08a3b7b000583be045b66e5dc440dfd4b2d0a1a0f82a0b84d01a6760ee52e","last_reissued_at":"2026-07-05T07:42:25.884415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:25.884415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assured LLM-Based Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alexandru Marginean, Eddy Wang, Inna Harper, Mark Harman, Nadia Alshahwan, Shubho Sengupta","submitted_at":"2024-02-06T20:38:46Z","abstract_excerpt":"In this paper we address the following question: How can we use Large Language Models (LLMs) to improve code independently of a human, while ensuring that the improved code\n  - does not regress the properties of the original code?\n  - improves the original in a verifiable and measurable way?\n  To address this question, we advocate Assured LLM-Based Software Engineering; a generate-and-test approach, inspired by Genetic Improvement. Assured LLMSE applies a series of semantic filters that discard code that fails to meet these twin guarantees. This overcomes the potential problem of LLM's propens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04380","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/2402.04380/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":"2402.04380","created_at":"2026-07-05T07:42:25.884473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04380v1","created_at":"2026-07-05T07:42:25.884473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04380","created_at":"2026-07-05T07:42:25.884473+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCQIUO33AACY","created_at":"2026-07-05T07:42:25.884473+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCQIUO33AACYHPQE","created_at":"2026-07-05T07:42:25.884473+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCQIUO33","created_at":"2026-07-05T07:42:25.884473+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/SCQIUO33AACYHPQELNTOLXCEBX","json":"https://pith.science/pith/SCQIUO33AACYHPQELNTOLXCEBX.json","graph_json":"https://pith.science/api/pith-number/SCQIUO33AACYHPQELNTOLXCEBX/graph.json","events_json":"https://pith.science/api/pith-number/SCQIUO33AACYHPQELNTOLXCEBX/events.json","paper":"https://pith.science/paper/SCQIUO33"},"agent_actions":{"view_html":"https://pith.science/pith/SCQIUO33AACYHPQELNTOLXCEBX","download_json":"https://pith.science/pith/SCQIUO33AACYHPQELNTOLXCEBX.json","view_paper":"https://pith.science/paper/SCQIUO33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04380&json=true","fetch_graph":"https://pith.science/api/pith-number/SCQIUO33AACYHPQELNTOLXCEBX/graph.json","fetch_events":"https://pith.science/api/pith-number/SCQIUO33AACYHPQELNTOLXCEBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCQIUO33AACYHPQELNTOLXCEBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCQIUO33AACYHPQELNTOLXCEBX/action/storage_attestation","attest_author":"https://pith.science/pith/SCQIUO33AACYHPQELNTOLXCEBX/action/author_attestation","sign_citation":"https://pith.science/pith/SCQIUO33AACYHPQELNTOLXCEBX/action/citation_signature","submit_replication":"https://pith.science/pith/SCQIUO33AACYHPQELNTOLXCEBX/action/replication_record"}},"created_at":"2026-07-05T07:42:25.884473+00:00","updated_at":"2026-07-05T07:42:25.884473+00:00"}