{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BYPP36SVEEYD4SXC7Q76KPUBOA","short_pith_number":"pith:BYPP36SV","schema_version":"1.0","canonical_sha256":"0e1efdfa5521303e4ae2fc3fe53e817028f0688c66cb4daedb8bdfe508882402","source":{"kind":"arxiv","id":"2403.16809","version":1},"attestation_state":"computed","paper":{"title":"An LLM-Based Digital Twin for Optimizing Human-in-the Loop Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Carlee Joe-Wong, Hanqing Yang, Marie Siew","submitted_at":"2024-03-25T14:32:28Z","abstract_excerpt":"The increasing prevalence of Cyber-Physical Systems and the Internet of Things (CPS-IoT) applications and Foundation Models are enabling new applications that leverage real-time control of the environment. For example, real-time control of Heating, Ventilation and Air-Conditioning (HVAC) systems can reduce its usage when not needed for the comfort of human occupants, hence reducing energy consumption. Collecting real-time feedback on human preferences in such human-in-the-loop (HITL) systems, however, is difficult in practice. We propose the use of large language models (LLMs) to deal with the"},"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":"2403.16809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-03-25T14:32:28Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY"],"title_canon_sha256":"772995d920fa423347effd260e9d5a0b80fa80ac30de585260211b44e8fac732","abstract_canon_sha256":"72f37e06734246cdd0932a6de46c14ecab537b56943e570eb2c2c78caad9e752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:21.388389Z","signature_b64":"3zJWlG07NwXoW7Hh/E029JN8gZIsni1hKEnmTPDzcmT6L0FEF0JFXqp+E0JyR/QXjuGOE1zkkhAonWPG7TIOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e1efdfa5521303e4ae2fc3fe53e817028f0688c66cb4daedb8bdfe508882402","last_reissued_at":"2026-07-05T08:00:21.388019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:21.388019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An LLM-Based Digital Twin for Optimizing Human-in-the Loop Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Carlee Joe-Wong, Hanqing Yang, Marie Siew","submitted_at":"2024-03-25T14:32:28Z","abstract_excerpt":"The increasing prevalence of Cyber-Physical Systems and the Internet of Things (CPS-IoT) applications and Foundation Models are enabling new applications that leverage real-time control of the environment. For example, real-time control of Heating, Ventilation and Air-Conditioning (HVAC) systems can reduce its usage when not needed for the comfort of human occupants, hence reducing energy consumption. Collecting real-time feedback on human preferences in such human-in-the-loop (HITL) systems, however, is difficult in practice. We propose the use of large language models (LLMs) to deal with the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16809","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/2403.16809/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":"2403.16809","created_at":"2026-07-05T08:00:21.388076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16809v1","created_at":"2026-07-05T08:00:21.388076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16809","created_at":"2026-07-05T08:00:21.388076+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYPP36SVEEYD","created_at":"2026-07-05T08:00:21.388076+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYPP36SVEEYD4SXC","created_at":"2026-07-05T08:00:21.388076+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYPP36SV","created_at":"2026-07-05T08:00:21.388076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11354","citing_title":"A Zero-Shot Multi-Agent Framework for Human-Building Interaction via Programmatic Reasoning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02592","citing_title":"Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA","json":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA.json","graph_json":"https://pith.science/api/pith-number/BYPP36SVEEYD4SXC7Q76KPUBOA/graph.json","events_json":"https://pith.science/api/pith-number/BYPP36SVEEYD4SXC7Q76KPUBOA/events.json","paper":"https://pith.science/paper/BYPP36SV"},"agent_actions":{"view_html":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA","download_json":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA.json","view_paper":"https://pith.science/paper/BYPP36SV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16809&json=true","fetch_graph":"https://pith.science/api/pith-number/BYPP36SVEEYD4SXC7Q76KPUBOA/graph.json","fetch_events":"https://pith.science/api/pith-number/BYPP36SVEEYD4SXC7Q76KPUBOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA/action/storage_attestation","attest_author":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA/action/author_attestation","sign_citation":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA/action/citation_signature","submit_replication":"https://pith.science/pith/BYPP36SVEEYD4SXC7Q76KPUBOA/action/replication_record"}},"created_at":"2026-07-05T08:00:21.388076+00:00","updated_at":"2026-07-05T08:00:21.388076+00:00"}