{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:23GR6VAQXFYNLUQIFC7MC2BWMN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e8e9fb04bbcb6198056ee82903f67456ac486cfa615c16415bced2214d538929","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T14:05:23Z","title_canon_sha256":"7dee84e9b6682d35d1fe09e5b7a330522b4cbd615a231b62f30da353f4dc4421"},"schema_version":"1.0","source":{"id":"2505.13484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13484","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13484v1","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13484","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"23GR6VAQXFYN","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"23GR6VAQXFYNLUQI","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"23GR6VAQ","created_at":"2026-07-05T11:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:86b069db20e2515f6f800714de4713bd2eef2f619c3067fe73ad5167991ddbf2","target":"graph","created_at":"2026-07-05T11:05:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.13484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are transformative not only for daily activities but also for engineering tasks. However, current evaluations of LLMs in engineering exhibit two critical shortcomings: (i) the reliance on simplified use cases, often adapted from examination materials where correctness is easily verifiable, and (ii) the use of ad hoc scenarios that insufficiently capture critical engineering competencies. Consequently, the assessment of LLMs on complex, real-world engineering problems remains largely unexplored. This paper addresses this gap by introducing a curated database compris","authors_text":"Alexander Diedrich, Alexander Windmann, Oliver Niggemann, Philipp Rosenthal, Rene Heesch, Sebastian Eilermann","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T14:05:23Z","title":"Evaluating Large Language Models for Real-World Engineering Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13484","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6c8f9703f48aa53620acccf7a93ccda4b4db48e2408036a9ac075d98244161bd","target":"record","created_at":"2026-07-05T11:05:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e8e9fb04bbcb6198056ee82903f67456ac486cfa615c16415bced2214d538929","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T14:05:23Z","title_canon_sha256":"7dee84e9b6682d35d1fe09e5b7a330522b4cbd615a231b62f30da353f4dc4421"},"schema_version":"1.0","source":{"id":"2505.13484","kind":"arxiv","version":1}},"canonical_sha256":"d6cd1f5410b970d5d20828bec16836635be3d4b2c99698c12f2b056278e164ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6cd1f5410b970d5d20828bec16836635be3d4b2c99698c12f2b056278e164ca","first_computed_at":"2026-07-05T11:05:46.535797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:46.535797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LKBIf7XhvMCgqmudemVRyr2eSq97bEv1vo6C6qdJwM+DUzWFRJvhG2l48AdUJ59h1fDBfZnlOSaLXr3bk03xDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:46.536228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c8f9703f48aa53620acccf7a93ccda4b4db48e2408036a9ac075d98244161bd","sha256:86b069db20e2515f6f800714de4713bd2eef2f619c3067fe73ad5167991ddbf2"],"state_sha256":"1f4833fb2fcebab9cefc804874372543d7c7f39248a6011b37e5eecf86dcb127"}