{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XD3NLLTKDDZ6IVV2FRWK4T26CZ","short_pith_number":"pith:XD3NLLTK","schema_version":"1.0","canonical_sha256":"b8f6d5ae6a18f3e456ba2c6cae4f5e16525f4a29a0058f261f7032f9352db9cb","source":{"kind":"arxiv","id":"2501.11979","version":1},"attestation_state":"computed","paper":{"title":"Linear Feedback Control Systems for Iterative Prompt Optimization in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rupesh Raj Karn","submitted_at":"2025-01-21T08:52:47Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized various applications by generating outputs based on given prompts. However, achieving the desired output requires iterative prompt refinement. This paper presents a novel approach that draws parallels between the iterative prompt optimization process in LLMs and feedback control systems. We iteratively refine the prompt by treating the deviation between the LLM output and the desired result as an error term until the output criteria are met. This process is akin to a feedback control system, where the LLM, despite being non-linear and non-determ"},"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":"2501.11979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T08:52:47Z","cross_cats_sorted":[],"title_canon_sha256":"473722fed464f09cfbab6c2426ee4218de545ec7e4ce96aa283d93c5156a8ef4","abstract_canon_sha256":"cbfa37687f73121c4512247535e7f8f9a2d2c2622fe9f02f8036e73f08cb9fc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:16.972801Z","signature_b64":"/hOsFnjlwcaF1heLcLtS1VQ0dWzANfYCCKclb5oJ9g4pD2Tlow+fgkGTyc+FO/n3tApIk3DItD3y5/DDofJmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8f6d5ae6a18f3e456ba2c6cae4f5e16525f4a29a0058f261f7032f9352db9cb","last_reissued_at":"2026-07-05T10:03:16.972408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:16.972408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Feedback Control Systems for Iterative Prompt Optimization in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rupesh Raj Karn","submitted_at":"2025-01-21T08:52:47Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized various applications by generating outputs based on given prompts. However, achieving the desired output requires iterative prompt refinement. This paper presents a novel approach that draws parallels between the iterative prompt optimization process in LLMs and feedback control systems. We iteratively refine the prompt by treating the deviation between the LLM output and the desired result as an error term until the output criteria are met. This process is akin to a feedback control system, where the LLM, despite being non-linear and non-determ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11979","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/2501.11979/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":"2501.11979","created_at":"2026-07-05T10:03:16.972466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11979v1","created_at":"2026-07-05T10:03:16.972466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11979","created_at":"2026-07-05T10:03:16.972466+00:00"},{"alias_kind":"pith_short_12","alias_value":"XD3NLLTKDDZ6","created_at":"2026-07-05T10:03:16.972466+00:00"},{"alias_kind":"pith_short_16","alias_value":"XD3NLLTKDDZ6IVV2","created_at":"2026-07-05T10:03:16.972466+00:00"},{"alias_kind":"pith_short_8","alias_value":"XD3NLLTK","created_at":"2026-07-05T10:03:16.972466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ","json":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ.json","graph_json":"https://pith.science/api/pith-number/XD3NLLTKDDZ6IVV2FRWK4T26CZ/graph.json","events_json":"https://pith.science/api/pith-number/XD3NLLTKDDZ6IVV2FRWK4T26CZ/events.json","paper":"https://pith.science/paper/XD3NLLTK"},"agent_actions":{"view_html":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ","download_json":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ.json","view_paper":"https://pith.science/paper/XD3NLLTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11979&json=true","fetch_graph":"https://pith.science/api/pith-number/XD3NLLTKDDZ6IVV2FRWK4T26CZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XD3NLLTKDDZ6IVV2FRWK4T26CZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ/action/storage_attestation","attest_author":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ/action/author_attestation","sign_citation":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ/action/citation_signature","submit_replication":"https://pith.science/pith/XD3NLLTKDDZ6IVV2FRWK4T26CZ/action/replication_record"}},"created_at":"2026-07-05T10:03:16.972466+00:00","updated_at":"2026-07-05T10:03:16.972466+00:00"}