{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZC5SCYKNUEPWZR4RLSOQVV57JO","short_pith_number":"pith:ZC5SCYKN","schema_version":"1.0","canonical_sha256":"c8bb21614da11f6cc7915c9d0ad7bf4b99aeb9585aa413fc9d39a27d9922e395","source":{"kind":"arxiv","id":"2606.31635","version":1},"attestation_state":"computed","paper":{"title":"A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SY"],"primary_cat":"eess.SY","authors_text":"Artan Markaj, Felix Gehlhoff, Javal Vyas, Mehmet Mercang\\\"oz, Milapji Singh Gill","submitted_at":"2026-06-30T13:19:45Z","abstract_excerpt":"Fault recovery in process plants still relies heavily on plant operators, especially when faults fall outside predefined supervisory logic. Operators interpret alarms, procedures, P\\&IDs, interlocks, and process trends, then decide how to move the plant to a safe operating mode without triggering a shutdown. This paper examines how Large Language Model (LLM) agents can support such recovery decisions. The proposed framework treats the LLM as a constrained supervisory planner. It uses plant-specific knowledge to propose recovery actions, and every proposal is checked by an external validator (s"},"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":"2606.31635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2026-06-30T13:19:45Z","cross_cats_sorted":["cs.AI","cs.MA","cs.SY"],"title_canon_sha256":"4bd6847eaa43bc92c7ac493ebeff2a0e17c13c65935c2d96645aa6bfd0d5fcc1","abstract_canon_sha256":"5355a8921b2d9c99d77667b4ac5ae5e60294a4a628b02b3b966e25006eb42844"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:09.949370Z","signature_b64":"A5I10IbxhK3G0RFgMGhG0X6pJgAIwPhy7SkkRQiC8HX2pjgt6sbrRMjJASWd/+DkdkarfgNB6sgyffKTCc4lDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8bb21614da11f6cc7915c9d0ad7bf4b99aeb9585aa413fc9d39a27d9922e395","last_reissued_at":"2026-07-01T01:18:09.948960Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:09.948960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SY"],"primary_cat":"eess.SY","authors_text":"Artan Markaj, Felix Gehlhoff, Javal Vyas, Mehmet Mercang\\\"oz, Milapji Singh Gill","submitted_at":"2026-06-30T13:19:45Z","abstract_excerpt":"Fault recovery in process plants still relies heavily on plant operators, especially when faults fall outside predefined supervisory logic. Operators interpret alarms, procedures, P\\&IDs, interlocks, and process trends, then decide how to move the plant to a safe operating mode without triggering a shutdown. This paper examines how Large Language Model (LLM) agents can support such recovery decisions. The proposed framework treats the LLM as a constrained supervisory planner. It uses plant-specific knowledge to propose recovery actions, and every proposal is checked by an external validator (s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31635","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/2606.31635/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":"2606.31635","created_at":"2026-07-01T01:18:09.949012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31635v1","created_at":"2026-07-01T01:18:09.949012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31635","created_at":"2026-07-01T01:18:09.949012+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZC5SCYKNUEPW","created_at":"2026-07-01T01:18:09.949012+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZC5SCYKNUEPWZR4R","created_at":"2026-07-01T01:18:09.949012+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZC5SCYKN","created_at":"2026-07-01T01:18:09.949012+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/ZC5SCYKNUEPWZR4RLSOQVV57JO","json":"https://pith.science/pith/ZC5SCYKNUEPWZR4RLSOQVV57JO.json","graph_json":"https://pith.science/api/pith-number/ZC5SCYKNUEPWZR4RLSOQVV57JO/graph.json","events_json":"https://pith.science/api/pith-number/ZC5SCYKNUEPWZR4RLSOQVV57JO/events.json","paper":"https://pith.science/paper/ZC5SCYKN"},"agent_actions":{"view_html":"https://pith.science/pith/ZC5SCYKNUEPWZR4RLSOQVV57JO","download_json":"https://pith.science/pith/ZC5SCYKNUEPWZR4RLSOQVV57JO.json","view_paper":"https://pith.science/paper/ZC5SCYKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31635&json=true","fetch_graph":"https://pith.science/api/pith-number/ZC5SCYKNUEPWZR4RLSOQVV57JO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZC5SCYKNUEPWZR4RLSOQVV57JO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZC5SCYKNUEPWZR4RLSOQVV57JO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZC5SCYKNUEPWZR4RLSOQVV57JO/action/storage_attestation","attest_author":"https://pith.science/pith/ZC5SCYKNUEPWZR4RLSOQVV57JO/action/author_attestation","sign_citation":"https://pith.science/pith/ZC5SCYKNUEPWZR4RLSOQVV57JO/action/citation_signature","submit_replication":"https://pith.science/pith/ZC5SCYKNUEPWZR4RLSOQVV57JO/action/replication_record"}},"created_at":"2026-07-01T01:18:09.949012+00:00","updated_at":"2026-07-01T01:18:09.949012+00:00"}