{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IPYSRDS64F2E6MNG543ZMKTTTA","short_pith_number":"pith:IPYSRDS6","schema_version":"1.0","canonical_sha256":"43f1288e5ee1744f31a6ef37962a739818a2b5f1ed0a9e7ce8a63f243b9cfe1b","source":{"kind":"arxiv","id":"2510.16559","version":5},"attestation_state":"computed","paper":{"title":"BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenglei Yu, Long Wei, Tailin Wu, Tianrun Gao, Tian Xia, Wenhao Deng, Xiaowei Qian","submitted_at":"2025-10-18T16:13:50Z","abstract_excerpt":"Engineering construction automation aims to transform natural language specifications into physically viable structures, requiring complex integrated reasoning under strict physical constraints. While modern LLMs possess broad knowledge and strong reasoning capabilities that make them promising candidates for this domain, their construction competencies remain largely unevaluated. To address this gap, we introduce BuildArena, the first physics-aligned interactive benchmark designed for language-driven engineering construction. It takes a first step towards engineering automation using LLMs. Te"},"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":"2510.16559","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-18T16:13:50Z","cross_cats_sorted":[],"title_canon_sha256":"2746478516e28e52875c1e7b83fe6c3d6a0a3f1a6ba7e10d9799937f3f54ef4c","abstract_canon_sha256":"544b4e520b8def9199de67e12b2412fc67c2efb2004f1f3cf069bc40784f2949"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:37.182587Z","signature_b64":"OShgJhzZE4L8yl3WrMKwul8IWYL90Kc33sTAAYXwwv14Jsdh7tpfbfjVdzf3DB3dQxQsGekJDQGszx9jWE+xDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43f1288e5ee1744f31a6ef37962a739818a2b5f1ed0a9e7ce8a63f243b9cfe1b","last_reissued_at":"2026-05-20T02:05:37.181913Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:37.181913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenglei Yu, Long Wei, Tailin Wu, Tianrun Gao, Tian Xia, Wenhao Deng, Xiaowei Qian","submitted_at":"2025-10-18T16:13:50Z","abstract_excerpt":"Engineering construction automation aims to transform natural language specifications into physically viable structures, requiring complex integrated reasoning under strict physical constraints. While modern LLMs possess broad knowledge and strong reasoning capabilities that make them promising candidates for this domain, their construction competencies remain largely unevaluated. To address this gap, we introduce BuildArena, the first physics-aligned interactive benchmark designed for language-driven engineering construction. It takes a first step towards engineering automation using LLMs. Te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.16559","kind":"arxiv","version":5},"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/2510.16559/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":"2510.16559","created_at":"2026-05-20T02:05:37.182005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.16559v5","created_at":"2026-05-20T02:05:37.182005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.16559","created_at":"2026-05-20T02:05:37.182005+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPYSRDS64F2E","created_at":"2026-05-20T02:05:37.182005+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPYSRDS64F2E6MNG","created_at":"2026-05-20T02:05:37.182005+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPYSRDS6","created_at":"2026-05-20T02:05:37.182005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.12290","citing_title":"Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA","json":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA.json","graph_json":"https://pith.science/api/pith-number/IPYSRDS64F2E6MNG543ZMKTTTA/graph.json","events_json":"https://pith.science/api/pith-number/IPYSRDS64F2E6MNG543ZMKTTTA/events.json","paper":"https://pith.science/paper/IPYSRDS6"},"agent_actions":{"view_html":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA","download_json":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA.json","view_paper":"https://pith.science/paper/IPYSRDS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.16559&json=true","fetch_graph":"https://pith.science/api/pith-number/IPYSRDS64F2E6MNG543ZMKTTTA/graph.json","fetch_events":"https://pith.science/api/pith-number/IPYSRDS64F2E6MNG543ZMKTTTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA/action/storage_attestation","attest_author":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA/action/author_attestation","sign_citation":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA/action/citation_signature","submit_replication":"https://pith.science/pith/IPYSRDS64F2E6MNG543ZMKTTTA/action/replication_record"}},"created_at":"2026-05-20T02:05:37.182005+00:00","updated_at":"2026-05-20T02:05:37.182005+00:00"}