{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7QS6WNZFHGGZ2H4VUJ4CFSYKON","short_pith_number":"pith:7QS6WNZF","schema_version":"1.0","canonical_sha256":"fc25eb3725398d9d1f95a27822cb0a7348cfeca3f29631ba552a8123daface74","source":{"kind":"arxiv","id":"2209.08112","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Industrial HVAC Systems with Hierarchical Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Cosmin Paduraru, Jerry Luo, Octavian Voicu, Praneet Dutta, William Wong, Yuri Chervonyi","submitted_at":"2022-09-16T18:00:46Z","abstract_excerpt":"Reinforcement learning (RL) techniques have been developed to optimize industrial cooling systems, offering substantial energy savings compared to traditional heuristic policies. A major challenge in industrial control involves learning behaviors that are feasible in the real world due to machinery constraints. For example, certain actions can only be executed every few hours while other actions can be taken more frequently. Without extensive reward engineering and experimentation, an RL agent may not learn realistic operation of machinery. To address this, we use hierarchical reinforcement le"},"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":"2209.08112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-16T18:00:46Z","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"228b7aa353217e6bb01255106ac7367e14c35005418fe1f1747ef751082b6a02","abstract_canon_sha256":"8f095933521e01f71df77f437a4b526805a8623198f1c5c01c108e3e3948eea5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:17.561611Z","signature_b64":"sGhIkAdKj9A1Eh61L7NNGH8zFdMJcOaHbvRc7f8xhcL6tWcvvG+K86H5Vyof8WhmtjsZ5vmgwJ77wQeeARJVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc25eb3725398d9d1f95a27822cb0a7348cfeca3f29631ba552a8123daface74","last_reissued_at":"2026-07-05T04:58:17.561233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:17.561233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Industrial HVAC Systems with Hierarchical Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Cosmin Paduraru, Jerry Luo, Octavian Voicu, Praneet Dutta, William Wong, Yuri Chervonyi","submitted_at":"2022-09-16T18:00:46Z","abstract_excerpt":"Reinforcement learning (RL) techniques have been developed to optimize industrial cooling systems, offering substantial energy savings compared to traditional heuristic policies. A major challenge in industrial control involves learning behaviors that are feasible in the real world due to machinery constraints. For example, certain actions can only be executed every few hours while other actions can be taken more frequently. Without extensive reward engineering and experimentation, an RL agent may not learn realistic operation of machinery. To address this, we use hierarchical reinforcement le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08112","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/2209.08112/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":"2209.08112","created_at":"2026-07-05T04:58:17.561287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08112v1","created_at":"2026-07-05T04:58:17.561287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08112","created_at":"2026-07-05T04:58:17.561287+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QS6WNZFHGGZ","created_at":"2026-07-05T04:58:17.561287+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QS6WNZFHGGZ2H4V","created_at":"2026-07-05T04:58:17.561287+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QS6WNZF","created_at":"2026-07-05T04:58:17.561287+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/7QS6WNZFHGGZ2H4VUJ4CFSYKON","json":"https://pith.science/pith/7QS6WNZFHGGZ2H4VUJ4CFSYKON.json","graph_json":"https://pith.science/api/pith-number/7QS6WNZFHGGZ2H4VUJ4CFSYKON/graph.json","events_json":"https://pith.science/api/pith-number/7QS6WNZFHGGZ2H4VUJ4CFSYKON/events.json","paper":"https://pith.science/paper/7QS6WNZF"},"agent_actions":{"view_html":"https://pith.science/pith/7QS6WNZFHGGZ2H4VUJ4CFSYKON","download_json":"https://pith.science/pith/7QS6WNZFHGGZ2H4VUJ4CFSYKON.json","view_paper":"https://pith.science/paper/7QS6WNZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08112&json=true","fetch_graph":"https://pith.science/api/pith-number/7QS6WNZFHGGZ2H4VUJ4CFSYKON/graph.json","fetch_events":"https://pith.science/api/pith-number/7QS6WNZFHGGZ2H4VUJ4CFSYKON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QS6WNZFHGGZ2H4VUJ4CFSYKON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QS6WNZFHGGZ2H4VUJ4CFSYKON/action/storage_attestation","attest_author":"https://pith.science/pith/7QS6WNZFHGGZ2H4VUJ4CFSYKON/action/author_attestation","sign_citation":"https://pith.science/pith/7QS6WNZFHGGZ2H4VUJ4CFSYKON/action/citation_signature","submit_replication":"https://pith.science/pith/7QS6WNZFHGGZ2H4VUJ4CFSYKON/action/replication_record"}},"created_at":"2026-07-05T04:58:17.561287+00:00","updated_at":"2026-07-05T04:58:17.561287+00:00"}