{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OBZ2JNO2AD5LDQWC2MGW67XH5C","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":"4ee45aaf7508f029ca9500ba9f1c1d4db25ccb162540caa5afab87484a358667","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T17:58:38Z","title_canon_sha256":"0b1213a9c5acbe93c95a8671bf2e659453669bf0e17f3a947947f322b5f76376"},"schema_version":"1.0","source":{"id":"2404.03647","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03647","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03647v1","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03647","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"OBZ2JNO2AD5L","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"OBZ2JNO2AD5LDQWC","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"OBZ2JNO2","created_at":"2026-07-05T08:04:28Z"}],"graph_snapshots":[{"event_id":"sha256:4891f90bb214984952cba43bbd3c4d54ccb75493cde60f5440d4d5a233f42426","target":"graph","created_at":"2026-07-05T08:04:28Z","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/2404.03647/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra in solving undergraduate-level control problems. Controls provides an interesting case study for LLM reasoning due to its combination of mathematical theory and engineering design. We introduce ControlBench, a benchmark dataset tailored to reflect the breadth, depth, and complexity of classical control design. We use this dataset to study and evaluate the problem-solving abilities of these LLMs in the context of control engineering. We present evaluatio","authors_text":"Aaron Havens, Bin Hu, Darioush Kevian, Geir Dullerud, Lianhui Qin, Peter Seiler, Usman Syed, Xingang Guo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T17:58:38Z","title":"Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03647","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":"sha256:3fb6c78d7c0da52ba48476b072c600ea39f487fb1e682245ab3f74e9e701020d","target":"record","created_at":"2026-07-05T08:04:28Z","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":"4ee45aaf7508f029ca9500ba9f1c1d4db25ccb162540caa5afab87484a358667","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T17:58:38Z","title_canon_sha256":"0b1213a9c5acbe93c95a8671bf2e659453669bf0e17f3a947947f322b5f76376"},"schema_version":"1.0","source":{"id":"2404.03647","kind":"arxiv","version":1}},"canonical_sha256":"7073a4b5da00fab1c2c2d30d6f7ee7e8ab0cc2f62a32727825e747332e6952b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7073a4b5da00fab1c2c2d30d6f7ee7e8ab0cc2f62a32727825e747332e6952b6","first_computed_at":"2026-07-05T08:04:28.742789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:28.742789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gzr8hIpMCFw8EvxFkhRM48eYXdkhylraCyuwK6YSUh/WYrKTMN7NPEW+w1dmBh7JNuBP0XyyJgSDSwMP49SsCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:28.743275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03647","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fb6c78d7c0da52ba48476b072c600ea39f487fb1e682245ab3f74e9e701020d","sha256:4891f90bb214984952cba43bbd3c4d54ccb75493cde60f5440d4d5a233f42426"],"state_sha256":"2cd2632e80ffd0d8806ab31adf7a9a8d0d1d58f95b8af2c4cab83d8273fcb030"}