{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J5LSNFADPLXMGNQCSPSIN3ILNB","short_pith_number":"pith:J5LSNFAD","schema_version":"1.0","canonical_sha256":"4f572694037aeec3360293e486ed0b6841960b7f5cc15720e8badd364bcd46fe","source":{"kind":"arxiv","id":"2603.20253","version":2},"attestation_state":"computed","paper":{"title":"SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.LG"],"primary_cat":"physics.comp-ph","authors_text":"Alessandro Marinoni, Alexey Arefiev, Chung-Hao Tsai, Hao Liu, Izzy F. Thomas, Jiahe Huang, Mingyun Cao, Rohan Bhakta, Rose Yu, Sicheng Lai, Yadi Cao, Yang Zhang, Yidong Zhao, Zach Lawrence, Zihao Zhou","submitted_at":"2026-03-11T05:00:48Z","abstract_excerpt":"Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental resources. As a result, metrics like pass@k become impractical under realistic budget constraints. To address this gap, we introduce SimulCost, the first benchmark targeting cost-sensitive parameter tuning in physics simulations. SimulCost compares LLM tuning cost-sensitive parameters against traditional scanning approach in both accuracy and computational cost, spanning 2,947 single-round (initial guess) and 1,931 multi-round (adjustment by trial-and-error)"},"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":"2603.20253","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-03-11T05:00:48Z","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"title_canon_sha256":"7717d896c1a756ebf79ced83ef090ba039145ece4915f7b3d115ae825a2c2cad","abstract_canon_sha256":"3f1d49d204cb1ee90da2b4198c8dd64311e298f7bd276132e3bff976d86b1208"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:37.621149Z","signature_b64":"DwTxDlbHj47VBzooNShu7N1Zu3jl7wWHV++ur5orIFD1wRJvlU6y1zZ0IbVtP5QMruiSNPqMKytrAgXF5hZyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f572694037aeec3360293e486ed0b6841960b7f5cc15720e8badd364bcd46fe","last_reissued_at":"2026-06-01T01:02:37.619668Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:37.619668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.LG"],"primary_cat":"physics.comp-ph","authors_text":"Alessandro Marinoni, Alexey Arefiev, Chung-Hao Tsai, Hao Liu, Izzy F. Thomas, Jiahe Huang, Mingyun Cao, Rohan Bhakta, Rose Yu, Sicheng Lai, Yadi Cao, Yang Zhang, Yidong Zhao, Zach Lawrence, Zihao Zhou","submitted_at":"2026-03-11T05:00:48Z","abstract_excerpt":"Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental resources. As a result, metrics like pass@k become impractical under realistic budget constraints. To address this gap, we introduce SimulCost, the first benchmark targeting cost-sensitive parameter tuning in physics simulations. SimulCost compares LLM tuning cost-sensitive parameters against traditional scanning approach in both accuracy and computational cost, spanning 2,947 single-round (initial guess) and 1,931 multi-round (adjustment by trial-and-error)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.20253","kind":"arxiv","version":2},"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/2603.20253/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":"2603.20253","created_at":"2026-06-01T01:02:37.619848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.20253v2","created_at":"2026-06-01T01:02:37.619848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.20253","created_at":"2026-06-01T01:02:37.619848+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5LSNFADPLXM","created_at":"2026-06-01T01:02:37.619848+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5LSNFADPLXMGNQC","created_at":"2026-06-01T01:02:37.619848+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5LSNFAD","created_at":"2026-06-01T01:02:37.619848+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/J5LSNFADPLXMGNQCSPSIN3ILNB","json":"https://pith.science/pith/J5LSNFADPLXMGNQCSPSIN3ILNB.json","graph_json":"https://pith.science/api/pith-number/J5LSNFADPLXMGNQCSPSIN3ILNB/graph.json","events_json":"https://pith.science/api/pith-number/J5LSNFADPLXMGNQCSPSIN3ILNB/events.json","paper":"https://pith.science/paper/J5LSNFAD"},"agent_actions":{"view_html":"https://pith.science/pith/J5LSNFADPLXMGNQCSPSIN3ILNB","download_json":"https://pith.science/pith/J5LSNFADPLXMGNQCSPSIN3ILNB.json","view_paper":"https://pith.science/paper/J5LSNFAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.20253&json=true","fetch_graph":"https://pith.science/api/pith-number/J5LSNFADPLXMGNQCSPSIN3ILNB/graph.json","fetch_events":"https://pith.science/api/pith-number/J5LSNFADPLXMGNQCSPSIN3ILNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5LSNFADPLXMGNQCSPSIN3ILNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5LSNFADPLXMGNQCSPSIN3ILNB/action/storage_attestation","attest_author":"https://pith.science/pith/J5LSNFADPLXMGNQCSPSIN3ILNB/action/author_attestation","sign_citation":"https://pith.science/pith/J5LSNFADPLXMGNQCSPSIN3ILNB/action/citation_signature","submit_replication":"https://pith.science/pith/J5LSNFADPLXMGNQCSPSIN3ILNB/action/replication_record"}},"created_at":"2026-06-01T01:02:37.619848+00:00","updated_at":"2026-06-01T01:02:37.619848+00:00"}