{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZB3GV6CNCMYXGGASRRAKSFUMOT","short_pith_number":"pith:ZB3GV6CN","schema_version":"1.0","canonical_sha256":"c8766af84d13317318128c40a9168c74edf9c1d5a1e3b98c89d03ae19e5974e9","source":{"kind":"arxiv","id":"2406.06835","version":1},"attestation_state":"computed","paper":{"title":"Large language models for generating rules, yay or nay?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mohamed Abdelrazek, Rena Logothetis, Scott Barnett, Shangeetha Sivasothy, Srikanth Thudumu, Zac Brannelly, Zafaryab Rasool","submitted_at":"2024-06-10T22:44:25Z","abstract_excerpt":"Engineering safety-critical systems such as medical devices and digital health intervention systems is complex, where long-term engagement with subject-matter experts (SMEs) is needed to capture the systems' expected behaviour. In this paper, we present a novel approach that leverages Large Language Models (LLMs), such as GPT-3.5 and GPT-4, as a potential world model to accelerate the engineering of software systems. This approach involves using LLMs to generate logic rules, which can then be reviewed and informed by SMEs before deployment. We evaluate our approach using a medical rule set, cr"},"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":"2406.06835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-10T22:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"a33a607c419ded15ec09facf98f6423e72d468c1d51f150b54582f1a0e8df982","abstract_canon_sha256":"d3be86eed25dae9aef37c5af62d0922212be4b1720dbd8942737e96d02dfda71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:51.019377Z","signature_b64":"lSGDhsUyTs4/09pp12b0xS6C30gGwSiYTBv8i9Feks5ytPmDwiUTjJhpHkQTvYnEKspHyJ5oxhutzrDzX4aIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8766af84d13317318128c40a9168c74edf9c1d5a1e3b98c89d03ae19e5974e9","last_reissued_at":"2026-07-05T08:29:51.018891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:51.018891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large language models for generating rules, yay or nay?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mohamed Abdelrazek, Rena Logothetis, Scott Barnett, Shangeetha Sivasothy, Srikanth Thudumu, Zac Brannelly, Zafaryab Rasool","submitted_at":"2024-06-10T22:44:25Z","abstract_excerpt":"Engineering safety-critical systems such as medical devices and digital health intervention systems is complex, where long-term engagement with subject-matter experts (SMEs) is needed to capture the systems' expected behaviour. In this paper, we present a novel approach that leverages Large Language Models (LLMs), such as GPT-3.5 and GPT-4, as a potential world model to accelerate the engineering of software systems. This approach involves using LLMs to generate logic rules, which can then be reviewed and informed by SMEs before deployment. We evaluate our approach using a medical rule set, cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06835","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/2406.06835/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":"2406.06835","created_at":"2026-07-05T08:29:51.018948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06835v1","created_at":"2026-07-05T08:29:51.018948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06835","created_at":"2026-07-05T08:29:51.018948+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZB3GV6CNCMYX","created_at":"2026-07-05T08:29:51.018948+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZB3GV6CNCMYXGGAS","created_at":"2026-07-05T08:29:51.018948+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZB3GV6CN","created_at":"2026-07-05T08:29:51.018948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01293","citing_title":"RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT","json":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT.json","graph_json":"https://pith.science/api/pith-number/ZB3GV6CNCMYXGGASRRAKSFUMOT/graph.json","events_json":"https://pith.science/api/pith-number/ZB3GV6CNCMYXGGASRRAKSFUMOT/events.json","paper":"https://pith.science/paper/ZB3GV6CN"},"agent_actions":{"view_html":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT","download_json":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT.json","view_paper":"https://pith.science/paper/ZB3GV6CN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06835&json=true","fetch_graph":"https://pith.science/api/pith-number/ZB3GV6CNCMYXGGASRRAKSFUMOT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZB3GV6CNCMYXGGASRRAKSFUMOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT/action/storage_attestation","attest_author":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT/action/author_attestation","sign_citation":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT/action/citation_signature","submit_replication":"https://pith.science/pith/ZB3GV6CNCMYXGGASRRAKSFUMOT/action/replication_record"}},"created_at":"2026-07-05T08:29:51.018948+00:00","updated_at":"2026-07-05T08:29:51.018948+00:00"}