{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JUOMH4S3ONWUGGEEGV6KPDYBHA","short_pith_number":"pith:JUOMH4S3","canonical_record":{"source":{"id":"2311.11423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2023-11-19T21:02:17Z","cross_cats_sorted":["cs.LG","cs.NI","eess.SP","math.IT"],"title_canon_sha256":"040186652992efed01e799a1a12bc85191fde6c0ed754e1076f43e085675f73d","abstract_canon_sha256":"d4468292dd3765a632c74a830fa31f574e96b2197ecf90fd36ea32cff872ce90"},"schema_version":"1.0"},"canonical_sha256":"4d1cc3f25b736d431884357ca78f01380d04ed5e2e1d28fc3f197f6103599406","source":{"kind":"arxiv","id":"2311.11423","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11423","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11423v1","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11423","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"JUOMH4S3ONWU","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"JUOMH4S3ONWUGGEE","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"JUOMH4S3","created_at":"2026-07-05T07:14:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JUOMH4S3ONWUGGEEGV6KPDYBHA","target":"record","payload":{"canonical_record":{"source":{"id":"2311.11423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2023-11-19T21:02:17Z","cross_cats_sorted":["cs.LG","cs.NI","eess.SP","math.IT"],"title_canon_sha256":"040186652992efed01e799a1a12bc85191fde6c0ed754e1076f43e085675f73d","abstract_canon_sha256":"d4468292dd3765a632c74a830fa31f574e96b2197ecf90fd36ea32cff872ce90"},"schema_version":"1.0"},"canonical_sha256":"4d1cc3f25b736d431884357ca78f01380d04ed5e2e1d28fc3f197f6103599406","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:32.853436Z","signature_b64":"3w56PTPkw7x1ftq+FPjzJN8i/fa7349WQF2SRKrJ9hukHvfa1JdggPkZYNQjjY0Do3gqBWbBfYMFQBJuC97qDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d1cc3f25b736d431884357ca78f01380d04ed5e2e1d28fc3f197f6103599406","last_reissued_at":"2026-07-05T07:14:32.852959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:32.852959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.11423","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":"2026-07-05T07:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0CuKoxow6H8ed3H2Y5bl1xXjaayAk0i7jVzg7nZOxkiHVKtx1AawiZa2WuxwHRsiulpKjynMZ0JrTL10/6TwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:45:30.145989Z"},"content_sha256":"9e5d90d1b9c162d462245a78155c6c721ffded5fca9fb7bec88a485a460c80f6","schema_version":"1.0","event_id":"sha256:9e5d90d1b9c162d462245a78155c6c721ffded5fca9fb7bec88a485a460c80f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JUOMH4S3ONWUGGEEGV6KPDYBHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NI","eess.SP","math.IT"],"primary_cat":"cs.IT","authors_text":"Cong Shen, Jerry Sydir, Jing Yang, Kun Yang, Shu-ping Yeh","submitted_at":"2023-11-19T21:02:17Z","abstract_excerpt":"The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be undesirable given the potential performance loss due to the unavoidable exploration in RL. In this work, we first investigate the use of \\emph{offline} RL algorithms in solving the RRM problem. We evaluate several state-of-the-art offline RL algorithms, including behavior constrained Q-learning (BCQ), conservative Q-learning (CQL), and implicit Q-learning (IQL), for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11423","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/2311.11423/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":"2026-07-05T07:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+trmBVIWsHTYO8Ui8yAOSDbCKvPHqkyhKWOkKqAGYkyPCDjcY8ZPq3Z9u4B819o4o99Higj2cC0mj7s5I4/HAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:45:30.146489Z"},"content_sha256":"ccacb21386df60577de32c153fe61b3820ccd3726b8f64fa8e3d5c1f354383be","schema_version":"1.0","event_id":"sha256:ccacb21386df60577de32c153fe61b3820ccd3726b8f64fa8e3d5c1f354383be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/bundle.json","state_url":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/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":"2026-08-16T22:45:30Z","links":{"resolver":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA","bundle":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/bundle.json","state":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JUOMH4S3ONWUGGEEGV6KPDYBHA","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":"d4468292dd3765a632c74a830fa31f574e96b2197ecf90fd36ea32cff872ce90","cross_cats_sorted":["cs.LG","cs.NI","eess.SP","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2023-11-19T21:02:17Z","title_canon_sha256":"040186652992efed01e799a1a12bc85191fde6c0ed754e1076f43e085675f73d"},"schema_version":"1.0","source":{"id":"2311.11423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11423","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11423v1","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11423","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"JUOMH4S3ONWU","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"JUOMH4S3ONWUGGEE","created_at":"2026-07-05T07:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"JUOMH4S3","created_at":"2026-07-05T07:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:ccacb21386df60577de32c153fe61b3820ccd3726b8f64fa8e3d5c1f354383be","target":"graph","created_at":"2026-07-05T07:14:32Z","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/2311.11423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be undesirable given the potential performance loss due to the unavoidable exploration in RL. In this work, we first investigate the use of \\emph{offline} RL algorithms in solving the RRM problem. We evaluate several state-of-the-art offline RL algorithms, including behavior constrained Q-learning (BCQ), conservative Q-learning (CQL), and implicit Q-learning (IQL), for ","authors_text":"Cong Shen, Jerry Sydir, Jing Yang, Kun Yang, Shu-ping Yeh","cross_cats":["cs.LG","cs.NI","eess.SP","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2023-11-19T21:02:17Z","title":"Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11423","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":"sha256:9e5d90d1b9c162d462245a78155c6c721ffded5fca9fb7bec88a485a460c80f6","target":"record","created_at":"2026-07-05T07:14:32Z","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":"d4468292dd3765a632c74a830fa31f574e96b2197ecf90fd36ea32cff872ce90","cross_cats_sorted":["cs.LG","cs.NI","eess.SP","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2023-11-19T21:02:17Z","title_canon_sha256":"040186652992efed01e799a1a12bc85191fde6c0ed754e1076f43e085675f73d"},"schema_version":"1.0","source":{"id":"2311.11423","kind":"arxiv","version":1}},"canonical_sha256":"4d1cc3f25b736d431884357ca78f01380d04ed5e2e1d28fc3f197f6103599406","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d1cc3f25b736d431884357ca78f01380d04ed5e2e1d28fc3f197f6103599406","first_computed_at":"2026-07-05T07:14:32.852959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:32.852959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3w56PTPkw7x1ftq+FPjzJN8i/fa7349WQF2SRKrJ9hukHvfa1JdggPkZYNQjjY0Do3gqBWbBfYMFQBJuC97qDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:32.853436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.11423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e5d90d1b9c162d462245a78155c6c721ffded5fca9fb7bec88a485a460c80f6","sha256:ccacb21386df60577de32c153fe61b3820ccd3726b8f64fa8e3d5c1f354383be"],"state_sha256":"b0e842a60551f40815456957a077206e26e1bcd24b404b451879c47f5ea301d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JR7JVk72VtjwPqqNEQXKvgTw9d0aE1veZtw4woozYDeDNZ0bYoAL7uEzn1dole8TxSxbsFC/eSnRsNs6oG7yBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:45:30.149731Z","bundle_sha256":"0b2740a4a82c194ebc64d8ef774efdc43b634a66e6b356f50360ad48a6c00d4b"}}