{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GS35RLPZ6SMURQMBYMPCB7SSON","short_pith_number":"pith:GS35RLPZ","schema_version":"1.0","canonical_sha256":"34b7d8adf9f49948c181c31e20fe527374420745d889c7e1055b57f4c2521823","source":{"kind":"arxiv","id":"2308.03028","version":1},"attestation_state":"computed","paper":{"title":"Pre-Trained Large Language Models for Industrial Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chuheng Zhang, Jiang Bian, Lei Song, Li Zhao","submitted_at":"2023-08-06T06:01:18Z","abstract_excerpt":"For industrial control, developing high-performance controllers with few samples and low technical debt is appealing. Foundation models, possessing rich prior knowledge obtained from pre-training with Internet-scale corpus, have the potential to be a good controller with proper prompts. In this paper, we take HVAC (Heating, Ventilation, and Air Conditioning) building control as an example to examine the ability of GPT-4 (one of the first-tier foundation models) as the controller. To control HVAC, we wrap the task as a language game by providing text including a short description for the task, "},"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":"2308.03028","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-06T06:01:18Z","cross_cats_sorted":[],"title_canon_sha256":"79bd29442efaf8c3a5c439616966240cc7afcb9b0f20c5369efb55ba6db84037","abstract_canon_sha256":"a2b04ce021b3a45245cc7b4850c16badbc188004726a9ee53e93151f07afcd62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:10.984862Z","signature_b64":"jF+PtUU6trEEHfOK363gN9DhxDrVnv1M7xU4SYcTE4LEbT4N0hubs4oxp32lJLjF+XVYSdGbwqAtJuKm1Pv7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34b7d8adf9f49948c181c31e20fe527374420745d889c7e1055b57f4c2521823","last_reissued_at":"2026-07-05T06:38:10.984399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:10.984399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-Trained Large Language Models for Industrial Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chuheng Zhang, Jiang Bian, Lei Song, Li Zhao","submitted_at":"2023-08-06T06:01:18Z","abstract_excerpt":"For industrial control, developing high-performance controllers with few samples and low technical debt is appealing. Foundation models, possessing rich prior knowledge obtained from pre-training with Internet-scale corpus, have the potential to be a good controller with proper prompts. In this paper, we take HVAC (Heating, Ventilation, and Air Conditioning) building control as an example to examine the ability of GPT-4 (one of the first-tier foundation models) as the controller. To control HVAC, we wrap the task as a language game by providing text including a short description for the task, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03028","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/2308.03028/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":"2308.03028","created_at":"2026-07-05T06:38:10.984458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.03028v1","created_at":"2026-07-05T06:38:10.984458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03028","created_at":"2026-07-05T06:38:10.984458+00:00"},{"alias_kind":"pith_short_12","alias_value":"GS35RLPZ6SMU","created_at":"2026-07-05T06:38:10.984458+00:00"},{"alias_kind":"pith_short_16","alias_value":"GS35RLPZ6SMURQMB","created_at":"2026-07-05T06:38:10.984458+00:00"},{"alias_kind":"pith_short_8","alias_value":"GS35RLPZ","created_at":"2026-07-05T06:38:10.984458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31635","citing_title":"A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31614","citing_title":"Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28011","citing_title":"From Detection to Action: Using LLM Agents for Fault-Tolerant Control","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22911","citing_title":"ThermoLLM: Thermodynamics-Aware HVAC Control with Spatial-Semantic Knowledge Graph","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON","json":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON.json","graph_json":"https://pith.science/api/pith-number/GS35RLPZ6SMURQMBYMPCB7SSON/graph.json","events_json":"https://pith.science/api/pith-number/GS35RLPZ6SMURQMBYMPCB7SSON/events.json","paper":"https://pith.science/paper/GS35RLPZ"},"agent_actions":{"view_html":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON","download_json":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON.json","view_paper":"https://pith.science/paper/GS35RLPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.03028&json=true","fetch_graph":"https://pith.science/api/pith-number/GS35RLPZ6SMURQMBYMPCB7SSON/graph.json","fetch_events":"https://pith.science/api/pith-number/GS35RLPZ6SMURQMBYMPCB7SSON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON/action/storage_attestation","attest_author":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON/action/author_attestation","sign_citation":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON/action/citation_signature","submit_replication":"https://pith.science/pith/GS35RLPZ6SMURQMBYMPCB7SSON/action/replication_record"}},"created_at":"2026-07-05T06:38:10.984458+00:00","updated_at":"2026-07-05T06:38:10.984458+00:00"}