{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VT63DOYAGYTBBDFYYTC3TX7EFK","short_pith_number":"pith:VT63DOYA","canonical_record":{"source":{"id":"2408.07986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T07:25:52Z","cross_cats_sorted":[],"title_canon_sha256":"6a13d0a8e3e35fd16c3c7ded03accf45a103cf23d86913e5c8879a826ca90a45","abstract_canon_sha256":"42f73739f7c63ad516acc867b71cee31ac79a833b8879a547203b986a79fcbac"},"schema_version":"1.0"},"canonical_sha256":"acfdb1bb003626108cb8c4c5b9dfe42aa79e92fdc917396d8199aba860310d6e","source":{"kind":"arxiv","id":"2408.07986","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07986","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07986v1","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07986","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_12","alias_value":"VT63DOYAGYTB","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_16","alias_value":"VT63DOYAGYTBBDFY","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_8","alias_value":"VT63DOYA","created_at":"2026-07-05T08:55:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VT63DOYAGYTBBDFYYTC3TX7EFK","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T07:25:52Z","cross_cats_sorted":[],"title_canon_sha256":"6a13d0a8e3e35fd16c3c7ded03accf45a103cf23d86913e5c8879a826ca90a45","abstract_canon_sha256":"42f73739f7c63ad516acc867b71cee31ac79a833b8879a547203b986a79fcbac"},"schema_version":"1.0"},"canonical_sha256":"acfdb1bb003626108cb8c4c5b9dfe42aa79e92fdc917396d8199aba860310d6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:42.871175Z","signature_b64":"8AUu1ou5VxY3vV7+raiEOmKdQrCKejpz8kbm+TxRcbfgzFRUXsUF6+KSkCHQhUkyEOasCRhpyh90mpzo1HizDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acfdb1bb003626108cb8c4c5b9dfe42aa79e92fdc917396d8199aba860310d6e","last_reissued_at":"2026-07-05T08:55:42.870756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:42.870756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07986","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:55:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6uliFhundfl0+9Fu+t7xG76QOS2o5UxM8DM9ZB0CYZ13Sc0FuyMDG8r51IAe19uJmbg3KGQouwm5KBlPnVCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:01:13.540524Z"},"content_sha256":"7e61830759bd74afd0d92fc60d725baee6dd50581efd32c18079bde83ac32fac","schema_version":"1.0","event_id":"sha256:7e61830759bd74afd0d92fc60d725baee6dd50581efd32c18079bde83ac32fac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VT63DOYAGYTBBDFYYTC3TX7EFK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Experimental evaluation of offline reinforcement learning for HVAC control in buildings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jun Wang, Linyan Li, Qi Liu, Yu Yang","submitted_at":"2024-08-15T07:25:52Z","abstract_excerpt":"Reinforcement learning (RL) techniques have been increasingly investigated for dynamic HVAC control in buildings. However, most studies focus on exploring solutions in online or off-policy scenarios without discussing in detail the implementation feasibility or effectiveness of dealing with purely offline datasets or trajectories. The lack of these works limits the real-world deployment of RL-based HVAC controllers, especially considering the abundance of historical data. To this end, this paper comprehensively evaluates the strengths and limitations of state-of-the-art offline RL algorithms b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07986","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/2408.07986/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:55:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lxuPdbFkEX66bYcKQHCv73ffxw8Zk2igBjLubgp17ahGSlBKvfIi4MDicJ6PcNM8YH7ox90HLkyntt+snAM7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:01:13.541058Z"},"content_sha256":"8f17beff8238f038762dff8ac1c5b00e205472c1e03e2b3d5a2550f6c4e30d59","schema_version":"1.0","event_id":"sha256:8f17beff8238f038762dff8ac1c5b00e205472c1e03e2b3d5a2550f6c4e30d59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VT63DOYAGYTBBDFYYTC3TX7EFK/bundle.json","state_url":"https://pith.science/pith/VT63DOYAGYTBBDFYYTC3TX7EFK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VT63DOYAGYTBBDFYYTC3TX7EFK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T01:01:13Z","links":{"resolver":"https://pith.science/pith/VT63DOYAGYTBBDFYYTC3TX7EFK","bundle":"https://pith.science/pith/VT63DOYAGYTBBDFYYTC3TX7EFK/bundle.json","state":"https://pith.science/pith/VT63DOYAGYTBBDFYYTC3TX7EFK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VT63DOYAGYTBBDFYYTC3TX7EFK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VT63DOYAGYTBBDFYYTC3TX7EFK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"42f73739f7c63ad516acc867b71cee31ac79a833b8879a547203b986a79fcbac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T07:25:52Z","title_canon_sha256":"6a13d0a8e3e35fd16c3c7ded03accf45a103cf23d86913e5c8879a826ca90a45"},"schema_version":"1.0","source":{"id":"2408.07986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07986","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07986v1","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07986","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_12","alias_value":"VT63DOYAGYTB","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_16","alias_value":"VT63DOYAGYTBBDFY","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_8","alias_value":"VT63DOYA","created_at":"2026-07-05T08:55:42Z"}],"graph_snapshots":[{"event_id":"sha256:8f17beff8238f038762dff8ac1c5b00e205472c1e03e2b3d5a2550f6c4e30d59","target":"graph","created_at":"2026-07-05T08:55:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.07986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) techniques have been increasingly investigated for dynamic HVAC control in buildings. However, most studies focus on exploring solutions in online or off-policy scenarios without discussing in detail the implementation feasibility or effectiveness of dealing with purely offline datasets or trajectories. The lack of these works limits the real-world deployment of RL-based HVAC controllers, especially considering the abundance of historical data. To this end, this paper comprehensively evaluates the strengths and limitations of state-of-the-art offline RL algorithms b","authors_text":"Jun Wang, Linyan Li, Qi Liu, Yu Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T07:25:52Z","title":"Experimental evaluation of offline reinforcement learning for HVAC control in buildings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07986","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7e61830759bd74afd0d92fc60d725baee6dd50581efd32c18079bde83ac32fac","target":"record","created_at":"2026-07-05T08:55:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"42f73739f7c63ad516acc867b71cee31ac79a833b8879a547203b986a79fcbac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T07:25:52Z","title_canon_sha256":"6a13d0a8e3e35fd16c3c7ded03accf45a103cf23d86913e5c8879a826ca90a45"},"schema_version":"1.0","source":{"id":"2408.07986","kind":"arxiv","version":1}},"canonical_sha256":"acfdb1bb003626108cb8c4c5b9dfe42aa79e92fdc917396d8199aba860310d6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acfdb1bb003626108cb8c4c5b9dfe42aa79e92fdc917396d8199aba860310d6e","first_computed_at":"2026-07-05T08:55:42.870756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:42.870756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8AUu1ou5VxY3vV7+raiEOmKdQrCKejpz8kbm+TxRcbfgzFRUXsUF6+KSkCHQhUkyEOasCRhpyh90mpzo1HizDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:42.871175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e61830759bd74afd0d92fc60d725baee6dd50581efd32c18079bde83ac32fac","sha256:8f17beff8238f038762dff8ac1c5b00e205472c1e03e2b3d5a2550f6c4e30d59"],"state_sha256":"541a62d4b00f8482b8d11583d333f9e1fd494084b0ab8836576dc3f28fd2a17d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OZ/hP3AtkiUUR8tQlm43a0mN/WoWCUhkkFS6Zg8OBO43XO79TSNoFi9NwEcYN7vc/zwdXqne47Q9bVFoJNO0CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:01:13.546771Z","bundle_sha256":"44dae973115e051efc118e1c73d32357e70fcb1f0ae296aea5dbfa97903d0b01"}}