{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OBZ2JNO2AD5LDQWC2MGW67XH5C","short_pith_number":"pith:OBZ2JNO2","schema_version":"1.0","canonical_sha256":"7073a4b5da00fab1c2c2d30d6f7ee7e8ab0cc2f62a32727825e747332e6952b6","source":{"kind":"arxiv","id":"2404.03647","version":1},"attestation_state":"computed","paper":{"title":"Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"math.OC","authors_text":"Aaron Havens, Bin Hu, Darioush Kevian, Geir Dullerud, Lianhui Qin, Peter Seiler, Usman Syed, Xingang Guo","submitted_at":"2024-04-04T17:58:38Z","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"},"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":"2404.03647","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T17:58:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0b1213a9c5acbe93c95a8671bf2e659453669bf0e17f3a947947f322b5f76376","abstract_canon_sha256":"4ee45aaf7508f029ca9500ba9f1c1d4db25ccb162540caa5afab87484a358667"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:28.743275Z","signature_b64":"Gzr8hIpMCFw8EvxFkhRM48eYXdkhylraCyuwK6YSUh/WYrKTMN7NPEW+w1dmBh7JNuBP0XyyJgSDSwMP49SsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7073a4b5da00fab1c2c2d30d6f7ee7e8ab0cc2f62a32727825e747332e6952b6","last_reissued_at":"2026-07-05T08:04:28.742789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:28.742789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"math.OC","authors_text":"Aaron Havens, Bin Hu, Darioush Kevian, Geir Dullerud, Lianhui Qin, Peter Seiler, Usman Syed, Xingang Guo","submitted_at":"2024-04-04T17:58:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03647","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/2404.03647/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":"2404.03647","created_at":"2026-07-05T08:04:28.742855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03647v1","created_at":"2026-07-05T08:04:28.742855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03647","created_at":"2026-07-05T08:04:28.742855+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBZ2JNO2AD5L","created_at":"2026-07-05T08:04:28.742855+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBZ2JNO2AD5LDQWC","created_at":"2026-07-05T08:04:28.742855+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBZ2JNO2","created_at":"2026-07-05T08:04:28.742855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09819","citing_title":"FDM-Bench: A Comprehensive Benchmark for Evaluating Large Language Models in Additive Manufacturing Tasks","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06921","citing_title":"Teaching Astronomy with Large Language Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12290","citing_title":"Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C","json":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C.json","graph_json":"https://pith.science/api/pith-number/OBZ2JNO2AD5LDQWC2MGW67XH5C/graph.json","events_json":"https://pith.science/api/pith-number/OBZ2JNO2AD5LDQWC2MGW67XH5C/events.json","paper":"https://pith.science/paper/OBZ2JNO2"},"agent_actions":{"view_html":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C","download_json":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C.json","view_paper":"https://pith.science/paper/OBZ2JNO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03647&json=true","fetch_graph":"https://pith.science/api/pith-number/OBZ2JNO2AD5LDQWC2MGW67XH5C/graph.json","fetch_events":"https://pith.science/api/pith-number/OBZ2JNO2AD5LDQWC2MGW67XH5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C/action/storage_attestation","attest_author":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C/action/author_attestation","sign_citation":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C/action/citation_signature","submit_replication":"https://pith.science/pith/OBZ2JNO2AD5LDQWC2MGW67XH5C/action/replication_record"}},"created_at":"2026-07-05T08:04:28.742855+00:00","updated_at":"2026-07-05T08:04:28.742855+00:00"}