{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IPBQRYLYYWUMTCRMFU2XYNULEF","short_pith_number":"pith:IPBQRYLY","schema_version":"1.0","canonical_sha256":"43c308e178c5a8c98a2c2d357c368b2171b7c7001f1a140026a40bac8bd15bee","source":{"kind":"arxiv","id":"2408.10376","version":1},"attestation_state":"computed","paper":{"title":"Self-Play Ensemble Q-learning enabled Resource Allocation for Network Slicing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.NI","authors_text":"Majid Bavand, Medhat Elsayed, Melike Erol-Kantarci, Pedro Enrique Iturria-Rivera, Raimundas Gaigalas, Shavbo Salehi, Yigit Ozcan","submitted_at":"2024-08-19T19:47:38Z","abstract_excerpt":"In 5G networks, network slicing has emerged as a pivotal paradigm to address diverse user demands and service requirements. To meet the requirements, reinforcement learning (RL) algorithms have been utilized widely, but this method has the problem of overestimation and exploration-exploitation trade-offs. To tackle these problems, this paper explores the application of self-play ensemble Q-learning, an extended version of the RL-based technique. Self-play ensemble Q-learning utilizes multiple Q-tables with various exploration-exploitation rates leading to different observations for choosing th"},"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":"2408.10376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NI","submitted_at":"2024-08-19T19:47:38Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"e3f49bab735bb542bf73461bf6648f1379d1b7427e47e6900347251470c1273c","abstract_canon_sha256":"4e4c9f4d8a0f1c0cefe2af50778900c8b8fad50011f7dc51da507162e33299e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:10.981931Z","signature_b64":"YBAyKYGpoVKmpFlwrxiE1r/UlvVKGl8RxMN8cN11R/Z72lD3+cRpmMWCky3OBUPy8zLMrkbLwcqUoHBsmlHyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43c308e178c5a8c98a2c2d357c368b2171b7c7001f1a140026a40bac8bd15bee","last_reissued_at":"2026-07-05T08:57:10.981482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:10.981482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Play Ensemble Q-learning enabled Resource Allocation for Network Slicing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.NI","authors_text":"Majid Bavand, Medhat Elsayed, Melike Erol-Kantarci, Pedro Enrique Iturria-Rivera, Raimundas Gaigalas, Shavbo Salehi, Yigit Ozcan","submitted_at":"2024-08-19T19:47:38Z","abstract_excerpt":"In 5G networks, network slicing has emerged as a pivotal paradigm to address diverse user demands and service requirements. To meet the requirements, reinforcement learning (RL) algorithms have been utilized widely, but this method has the problem of overestimation and exploration-exploitation trade-offs. To tackle these problems, this paper explores the application of self-play ensemble Q-learning, an extended version of the RL-based technique. Self-play ensemble Q-learning utilizes multiple Q-tables with various exploration-exploitation rates leading to different observations for choosing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10376","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/2408.10376/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":"2408.10376","created_at":"2026-07-05T08:57:10.981536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10376v1","created_at":"2026-07-05T08:57:10.981536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10376","created_at":"2026-07-05T08:57:10.981536+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPBQRYLYYWUM","created_at":"2026-07-05T08:57:10.981536+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPBQRYLYYWUMTCRM","created_at":"2026-07-05T08:57:10.981536+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPBQRYLY","created_at":"2026-07-05T08:57:10.981536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15734","citing_title":"Prioritized Value-Decomposition Network for Explainable AI-Enabled Network Slicing","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF","json":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF.json","graph_json":"https://pith.science/api/pith-number/IPBQRYLYYWUMTCRMFU2XYNULEF/graph.json","events_json":"https://pith.science/api/pith-number/IPBQRYLYYWUMTCRMFU2XYNULEF/events.json","paper":"https://pith.science/paper/IPBQRYLY"},"agent_actions":{"view_html":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF","download_json":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF.json","view_paper":"https://pith.science/paper/IPBQRYLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10376&json=true","fetch_graph":"https://pith.science/api/pith-number/IPBQRYLYYWUMTCRMFU2XYNULEF/graph.json","fetch_events":"https://pith.science/api/pith-number/IPBQRYLYYWUMTCRMFU2XYNULEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF/action/storage_attestation","attest_author":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF/action/author_attestation","sign_citation":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF/action/citation_signature","submit_replication":"https://pith.science/pith/IPBQRYLYYWUMTCRMFU2XYNULEF/action/replication_record"}},"created_at":"2026-07-05T08:57:10.981536+00:00","updated_at":"2026-07-05T08:57:10.981536+00:00"}