{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OKJSACW5OZXUOFLQYXURTDF2O5","short_pith_number":"pith:OKJSACW5","schema_version":"1.0","canonical_sha256":"7293200add766f471570c5e9198cba7766b00e88961b1233eb025cdff54ea4f4","source":{"kind":"arxiv","id":"2412.17146","version":1},"attestation_state":"computed","paper":{"title":"LLM Agent for Fire Dynamics Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.AI","authors_text":"Danyal Mohaddes, Leidong Xu, Yi Wang","submitted_at":"2024-12-22T20:03:35Z","abstract_excerpt":"Significant advances have been achieved in leveraging foundation models, such as large language models (LLMs), to accelerate complex scientific workflows. In this work we introduce FoamPilot, a proof-of-concept LLM agent designed to enhance the usability of FireFOAM, a specialized solver for fire dynamics and fire suppression simulations built using OpenFOAM, a popular open-source toolbox for computational fluid dynamics (CFD). FoamPilot provides three core functionalities: code insight, case configuration and simulation evaluation. Code insight is an alternative to traditional keyword searchi"},"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":"2412.17146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-22T20:03:35Z","cross_cats_sorted":["physics.flu-dyn"],"title_canon_sha256":"ca161a38034ceb4903a9f1ebaf972262a0b4c25c125141169710f32a576b6e72","abstract_canon_sha256":"b79f6c4f6ff90e207b9688d347811c5348cea1aed21e1f02ab0fdcbca4c1c84c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:18.183122Z","signature_b64":"wmLpgqcvevckGUweubyy77uOwUn6l9DUEAJUvfca6FqwRmjVxhhtIWcoweLy/YWAvtI2BJyqv/Eo4FOYEuc3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7293200add766f471570c5e9198cba7766b00e88961b1233eb025cdff54ea4f4","last_reissued_at":"2026-07-05T09:53:18.182597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:18.182597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Agent for Fire Dynamics Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.AI","authors_text":"Danyal Mohaddes, Leidong Xu, Yi Wang","submitted_at":"2024-12-22T20:03:35Z","abstract_excerpt":"Significant advances have been achieved in leveraging foundation models, such as large language models (LLMs), to accelerate complex scientific workflows. In this work we introduce FoamPilot, a proof-of-concept LLM agent designed to enhance the usability of FireFOAM, a specialized solver for fire dynamics and fire suppression simulations built using OpenFOAM, a popular open-source toolbox for computational fluid dynamics (CFD). FoamPilot provides three core functionalities: code insight, case configuration and simulation evaluation. Code insight is an alternative to traditional keyword searchi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17146","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/2412.17146/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":"2412.17146","created_at":"2026-07-05T09:53:18.182665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17146v1","created_at":"2026-07-05T09:53:18.182665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17146","created_at":"2026-07-05T09:53:18.182665+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKJSACW5OZXU","created_at":"2026-07-05T09:53:18.182665+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKJSACW5OZXUOFLQ","created_at":"2026-07-05T09:53:18.182665+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKJSACW5","created_at":"2026-07-05T09:53:18.182665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09552","citing_title":"MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrieval","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06607","citing_title":"AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06607","citing_title":"AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06607","citing_title":"AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5","json":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5.json","graph_json":"https://pith.science/api/pith-number/OKJSACW5OZXUOFLQYXURTDF2O5/graph.json","events_json":"https://pith.science/api/pith-number/OKJSACW5OZXUOFLQYXURTDF2O5/events.json","paper":"https://pith.science/paper/OKJSACW5"},"agent_actions":{"view_html":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5","download_json":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5.json","view_paper":"https://pith.science/paper/OKJSACW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17146&json=true","fetch_graph":"https://pith.science/api/pith-number/OKJSACW5OZXUOFLQYXURTDF2O5/graph.json","fetch_events":"https://pith.science/api/pith-number/OKJSACW5OZXUOFLQYXURTDF2O5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5/action/storage_attestation","attest_author":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5/action/author_attestation","sign_citation":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5/action/citation_signature","submit_replication":"https://pith.science/pith/OKJSACW5OZXUOFLQYXURTDF2O5/action/replication_record"}},"created_at":"2026-07-05T09:53:18.182665+00:00","updated_at":"2026-07-05T09:53:18.182665+00:00"}