{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J5BO4DNY37BROIAVXALJ5IGWBC","short_pith_number":"pith:J5BO4DNY","schema_version":"1.0","canonical_sha256":"4f42ee0db8dfc3172015b8169ea0d608a99903b809cb3544da5fa43c9c7bae94","source":{"kind":"arxiv","id":"2411.13269","version":1},"attestation_state":"computed","paper":{"title":"Towards Specification-Driven LLM-Based Generation of Embedded Automotive Software","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Gustav Ung, Mattias Nyberg, Minal Suresh Patil","submitted_at":"2024-11-20T12:38:17Z","abstract_excerpt":"The paper studies how code generation by LLMs can be combined with formal verification to produce critical embedded software. The first contribution is a general framework, spec2code, in which LLMs are combined with different types of critics that produce feedback for iterative backprompting and fine-tuning. The second contribution presents a first feasibility study, where a minimalistic instantiation of spec2code, without iterative backprompting and fine-tuning, is empirically evaluated using three industrial case studies from the heavy vehicle manufacturer Scania. The goal is to automaticall"},"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":"2411.13269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-20T12:38:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a1eb3c711034eb1e2ca5dd536e0724fc2417d4f16bd31a0c4f8c49e772dd49c","abstract_canon_sha256":"75dfac107b61f4329dbbc061bc67caa8c7ae0f44dbced3d7ef03efb760a3ec92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:07.763034Z","signature_b64":"K02X2FmubvJAtodMzcXecoARfKsA7eGGaT9U5I4bryG5ENSFFEdsYSNh26v0JD+awxCVjVMd6CxQEZcNeDt+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f42ee0db8dfc3172015b8169ea0d608a99903b809cb3544da5fa43c9c7bae94","last_reissued_at":"2026-07-05T09:38:07.762460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:07.762460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Specification-Driven LLM-Based Generation of Embedded Automotive Software","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Gustav Ung, Mattias Nyberg, Minal Suresh Patil","submitted_at":"2024-11-20T12:38:17Z","abstract_excerpt":"The paper studies how code generation by LLMs can be combined with formal verification to produce critical embedded software. The first contribution is a general framework, spec2code, in which LLMs are combined with different types of critics that produce feedback for iterative backprompting and fine-tuning. The second contribution presents a first feasibility study, where a minimalistic instantiation of spec2code, without iterative backprompting and fine-tuning, is empirically evaluated using three industrial case studies from the heavy vehicle manufacturer Scania. The goal is to automaticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13269","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/2411.13269/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":"2411.13269","created_at":"2026-07-05T09:38:07.762526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13269v1","created_at":"2026-07-05T09:38:07.762526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13269","created_at":"2026-07-05T09:38:07.762526+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5BO4DNY37BR","created_at":"2026-07-05T09:38:07.762526+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5BO4DNY37BROIAV","created_at":"2026-07-05T09:38:07.762526+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5BO4DNY","created_at":"2026-07-05T09:38:07.762526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15025","citing_title":"Survey of GenAI for Automotive Software Development: From Requirements to Executable Code","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC","json":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC.json","graph_json":"https://pith.science/api/pith-number/J5BO4DNY37BROIAVXALJ5IGWBC/graph.json","events_json":"https://pith.science/api/pith-number/J5BO4DNY37BROIAVXALJ5IGWBC/events.json","paper":"https://pith.science/paper/J5BO4DNY"},"agent_actions":{"view_html":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC","download_json":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC.json","view_paper":"https://pith.science/paper/J5BO4DNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13269&json=true","fetch_graph":"https://pith.science/api/pith-number/J5BO4DNY37BROIAVXALJ5IGWBC/graph.json","fetch_events":"https://pith.science/api/pith-number/J5BO4DNY37BROIAVXALJ5IGWBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC/action/storage_attestation","attest_author":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC/action/author_attestation","sign_citation":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC/action/citation_signature","submit_replication":"https://pith.science/pith/J5BO4DNY37BROIAVXALJ5IGWBC/action/replication_record"}},"created_at":"2026-07-05T09:38:07.762526+00:00","updated_at":"2026-07-05T09:38:07.762526+00:00"}