{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FLZ623OKHWRBK7JBUAISVUVF5U","short_pith_number":"pith:FLZ623OK","schema_version":"1.0","canonical_sha256":"2af3ed6dca3da2157d21a0112ad2a5ed0372047fb57a20e3e0e518a1699f500f","source":{"kind":"arxiv","id":"2503.18460","version":1},"attestation_state":"computed","paper":{"title":"ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jiahui Xiang, Peiyu Liu, Tong Ye, Wenhai Wang, Yinan Zhang","submitted_at":"2025-03-24T09:04:49Z","abstract_excerpt":"Modelica is a widely adopted language for simulating complex physical systems, yet effective model creation and optimization require substantial domain expertise. Although large language models (LLMs) have demonstrated promising capabilities in code generation, their application to modeling remains largely unexplored. To address this gap, we have developed benchmark datasets specifically designed to evaluate the performance of LLMs in generating Modelica component models and test cases. Our evaluation reveals substantial limitations in current LLMs, as the generated code often fails to simulat"},"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":"2503.18460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-24T09:04:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b4de81c3d3d034f33714f6c830ea9298865b893d2632f7e4e46e1d632c32568","abstract_canon_sha256":"e3b3e5cf58ed3ac67d68e71453d3b273fc4c9503f8775089cf050f6d3d2d33e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:11.160852Z","signature_b64":"2zzAfOeCdqkL2G47PAMnrZSWrFL37Ez8t0L8IREaMDbZtubK1UjDNOgCOuVNY6gDJhlI9NynJE+/n5I3PJe1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2af3ed6dca3da2157d21a0112ad2a5ed0372047fb57a20e3e0e518a1699f500f","last_reissued_at":"2026-07-05T10:38:11.160354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:11.160354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jiahui Xiang, Peiyu Liu, Tong Ye, Wenhai Wang, Yinan Zhang","submitted_at":"2025-03-24T09:04:49Z","abstract_excerpt":"Modelica is a widely adopted language for simulating complex physical systems, yet effective model creation and optimization require substantial domain expertise. Although large language models (LLMs) have demonstrated promising capabilities in code generation, their application to modeling remains largely unexplored. To address this gap, we have developed benchmark datasets specifically designed to evaluate the performance of LLMs in generating Modelica component models and test cases. Our evaluation reveals substantial limitations in current LLMs, as the generated code often fails to simulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18460","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/2503.18460/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":"2503.18460","created_at":"2026-07-05T10:38:11.160423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18460v1","created_at":"2026-07-05T10:38:11.160423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18460","created_at":"2026-07-05T10:38:11.160423+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLZ623OKHWRB","created_at":"2026-07-05T10:38:11.160423+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLZ623OKHWRBK7JB","created_at":"2026-07-05T10:38:11.160423+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLZ623OK","created_at":"2026-07-05T10:38:11.160423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.29389","citing_title":"Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U","json":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U.json","graph_json":"https://pith.science/api/pith-number/FLZ623OKHWRBK7JBUAISVUVF5U/graph.json","events_json":"https://pith.science/api/pith-number/FLZ623OKHWRBK7JBUAISVUVF5U/events.json","paper":"https://pith.science/paper/FLZ623OK"},"agent_actions":{"view_html":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U","download_json":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U.json","view_paper":"https://pith.science/paper/FLZ623OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18460&json=true","fetch_graph":"https://pith.science/api/pith-number/FLZ623OKHWRBK7JBUAISVUVF5U/graph.json","fetch_events":"https://pith.science/api/pith-number/FLZ623OKHWRBK7JBUAISVUVF5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U/action/storage_attestation","attest_author":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U/action/author_attestation","sign_citation":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U/action/citation_signature","submit_replication":"https://pith.science/pith/FLZ623OKHWRBK7JBUAISVUVF5U/action/replication_record"}},"created_at":"2026-07-05T10:38:11.160423+00:00","updated_at":"2026-07-05T10:38:11.160423+00:00"}