{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PAFC6XUMVQHMEKURHLTV2J2YIZ","short_pith_number":"pith:PAFC6XUM","schema_version":"1.0","canonical_sha256":"780a2f5e8cac0ec22a913ae75d2758466881dff4b18172689e8707c302ff8fe4","source":{"kind":"arxiv","id":"2606.11015","version":1},"attestation_state":"computed","paper":{"title":"Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors for Coupled MIMO Controller Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haonan Li, Jiaxuan Chen, Yang Shu","submitted_at":"2026-06-09T15:53:40Z","abstract_excerpt":"Tuning controllers for strongly coupled multi-input multi-output (MIMO) industrial processes is hard: decentralized classical auto-tuning ignores loop interaction, and local numerical optimization from natural initializations stalls in the resulting non-convex cost landscape. We ask whether on-premise open-source large language models (LLMs), which keep data on-site and need no plant model, can help. On a single-loop CSTR, classical relay-feedback tuning (IAE 0.106, near the 0.102 optimum) beats an LLM tuner (0.162): for simple loops the LLM adds nothing. The picture inverts on a strongly coup"},"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":"2606.11015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T15:53:40Z","cross_cats_sorted":[],"title_canon_sha256":"6a32480f2ed4a4a96972308e94583c9603283935b9b50ec10248655cda2c4c97","abstract_canon_sha256":"dc8d8185a7ce308794d24d4330eb6dcd54788b0059ebd5a6781e684e6f426d0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:03.795471Z","signature_b64":"7v0bHOnl03BGixkLOqjJOK5jkzzKmmGSsZNJZt+u8rxoUBKxzjJdqY+/m8fePfJ6EzkBNgrCg+GOgX5xn85/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"780a2f5e8cac0ec22a913ae75d2758466881dff4b18172689e8707c302ff8fe4","last_reissued_at":"2026-06-10T01:11:03.794534Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:03.794534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors for Coupled MIMO Controller Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haonan Li, Jiaxuan Chen, Yang Shu","submitted_at":"2026-06-09T15:53:40Z","abstract_excerpt":"Tuning controllers for strongly coupled multi-input multi-output (MIMO) industrial processes is hard: decentralized classical auto-tuning ignores loop interaction, and local numerical optimization from natural initializations stalls in the resulting non-convex cost landscape. We ask whether on-premise open-source large language models (LLMs), which keep data on-site and need no plant model, can help. On a single-loop CSTR, classical relay-feedback tuning (IAE 0.106, near the 0.102 optimum) beats an LLM tuner (0.162): for simple loops the LLM adds nothing. The picture inverts on a strongly coup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11015","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/2606.11015/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":"2606.11015","created_at":"2026-06-10T01:11:03.794715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11015v1","created_at":"2026-06-10T01:11:03.794715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11015","created_at":"2026-06-10T01:11:03.794715+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAFC6XUMVQHM","created_at":"2026-06-10T01:11:03.794715+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAFC6XUMVQHMEKUR","created_at":"2026-06-10T01:11:03.794715+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAFC6XUM","created_at":"2026-06-10T01:11:03.794715+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/PAFC6XUMVQHMEKURHLTV2J2YIZ","json":"https://pith.science/pith/PAFC6XUMVQHMEKURHLTV2J2YIZ.json","graph_json":"https://pith.science/api/pith-number/PAFC6XUMVQHMEKURHLTV2J2YIZ/graph.json","events_json":"https://pith.science/api/pith-number/PAFC6XUMVQHMEKURHLTV2J2YIZ/events.json","paper":"https://pith.science/paper/PAFC6XUM"},"agent_actions":{"view_html":"https://pith.science/pith/PAFC6XUMVQHMEKURHLTV2J2YIZ","download_json":"https://pith.science/pith/PAFC6XUMVQHMEKURHLTV2J2YIZ.json","view_paper":"https://pith.science/paper/PAFC6XUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11015&json=true","fetch_graph":"https://pith.science/api/pith-number/PAFC6XUMVQHMEKURHLTV2J2YIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PAFC6XUMVQHMEKURHLTV2J2YIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAFC6XUMVQHMEKURHLTV2J2YIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAFC6XUMVQHMEKURHLTV2J2YIZ/action/storage_attestation","attest_author":"https://pith.science/pith/PAFC6XUMVQHMEKURHLTV2J2YIZ/action/author_attestation","sign_citation":"https://pith.science/pith/PAFC6XUMVQHMEKURHLTV2J2YIZ/action/citation_signature","submit_replication":"https://pith.science/pith/PAFC6XUMVQHMEKURHLTV2J2YIZ/action/replication_record"}},"created_at":"2026-06-10T01:11:03.794715+00:00","updated_at":"2026-06-10T01:11:03.794715+00:00"}