{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HV37WFL7D4VRVU3TKW5QKY74E4","short_pith_number":"pith:HV37WFL7","schema_version":"1.0","canonical_sha256":"3d77fb157f1f2b1ad37355bb0563fc272966517657e12b071ad35f4dc744da4a","source":{"kind":"arxiv","id":"2605.00457","version":3},"attestation_state":"computed","paper":{"title":"Policy-Driven DRL-Based TXOP Adaptation in NR-U and Wi-Fi Coexistence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A policy-driven deep reinforcement learning framework models NR-U and Wi-Fi coexistence as a Markov decision process and uses reward design to learn TXOP control policies that set explicit operating points on the fairness-throughput curve.","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.NI","authors_text":"Chiapin Wang, Po-Heng Chou, Shou-Yu Chen, Yi-Fang Yu","submitted_at":"2026-05-01T06:43:09Z","abstract_excerpt":"The coexistence of NR-U and Wi-Fi in unlicensed spectrum introduces a challenging coexistence management problem, where heterogeneous channel access mechanisms lead to a significant imbalance in spectrum utilization and degraded Wi-Fi performance. To address this challenge, we propose a policy-driven deep reinforcement learning (DRL) framework for adaptive transmission opportunity (TXOP) control, in which the coexistence process is formulated as a Markov decision process (MDP) and a deep Q-network (DQN) learns control policies through online interaction. A key contribution is the introduction "},"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":"2605.00457","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2026-05-01T06:43:09Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"5ab028d0820d5fda486924dfb0e4ff4f873c29200ed1bd7747776eb36f79a868","abstract_canon_sha256":"14187a97355e550c5fc8b686fade400d1174df56fd08762bb0a75fc4e3aa21db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:41.258116Z","signature_b64":"ns1hRP59UaiY7GgbDJuHNU78Irgp32DAPuHxYIC/wM+egVHBr6Jb/Kx7EeiJ9ZBVmv0q7E6yVzw/zbiW0T+2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d77fb157f1f2b1ad37355bb0563fc272966517657e12b071ad35f4dc744da4a","last_reissued_at":"2026-05-28T01:04:41.257608Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:41.257608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy-Driven DRL-Based TXOP Adaptation in NR-U and Wi-Fi Coexistence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A policy-driven deep reinforcement learning framework models NR-U and Wi-Fi coexistence as a Markov decision process and uses reward design to learn TXOP control policies that set explicit operating points on the fairness-throughput curve.","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.NI","authors_text":"Chiapin Wang, Po-Heng Chou, Shou-Yu Chen, Yi-Fang Yu","submitted_at":"2026-05-01T06:43:09Z","abstract_excerpt":"The coexistence of NR-U and Wi-Fi in unlicensed spectrum introduces a challenging coexistence management problem, where heterogeneous channel access mechanisms lead to a significant imbalance in spectrum utilization and degraded Wi-Fi performance. To address this challenge, we propose a policy-driven deep reinforcement learning (DRL) framework for adaptive transmission opportunity (TXOP) control, in which the coexistence process is formulated as a Markov decision process (MDP) and a deep Q-network (DQN) learns control policies through online interaction. A key contribution is the introduction "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Simulation results show that the proposed framework achieves a Jain fairness index above 0.9 under strict fairness control. Compared to absolute fairness, moderate fairness improves aggregate throughput by 68.22%, while the utility-based policy further enhances utility by 177.6%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The coexistence dynamics can be faithfully captured as a Markov decision process whose state and reward signals allow a DQN to learn stable policies that generalize beyond the simulated scenarios.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A DRL framework with tunable reward policies controls TXOP in NR-U/Wi-Fi coexistence to achieve Jain fairness above 0.9 and throughput/utility gains of 68-177% in simulations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A policy-driven deep reinforcement learning framework models NR-U and Wi-Fi coexistence as a Markov decision process and uses reward design to learn TXOP control policies that set explicit operating points on the fairness-throughput curve.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"61f81ce2fc691f971937de94da233ae318e51e273f47305bc7fc4f57deb36a6e"},"source":{"id":"2605.00457","kind":"arxiv","version":3},"verdict":{"id":"a4530fe5-9d59-410a-baf6-49cb4648f376","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T19:00:02.200119Z","strongest_claim":"Simulation results show that the proposed framework achieves a Jain fairness index above 0.9 under strict fairness control. Compared to absolute fairness, moderate fairness improves aggregate throughput by 68.22%, while the utility-based policy further enhances utility by 177.6%.","one_line_summary":"A DRL framework with tunable reward policies controls TXOP in NR-U/Wi-Fi coexistence to achieve Jain fairness above 0.9 and throughput/utility gains of 68-177% in simulations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The coexistence dynamics can be faithfully captured as a Markov decision process whose state and reward signals allow a DQN to learn stable policies that generalize beyond the simulated scenarios.","pith_extraction_headline":"A policy-driven deep reinforcement learning framework models NR-U and Wi-Fi coexistence as a Markov decision process and uses reward design to learn TXOP control policies that set explicit operating points on the fairness-throughput curve."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00457/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T19:41:44.267011Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:07:27.165103Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f550ce65b13dafbf29fe15693d7c88f410410b6578cdeec0b3b67ffbe436e3f9"},"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":"2605.00457","created_at":"2026-05-28T01:04:41.257672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.00457v3","created_at":"2026-05-28T01:04:41.257672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00457","created_at":"2026-05-28T01:04:41.257672+00:00"},{"alias_kind":"pith_short_12","alias_value":"HV37WFL7D4VR","created_at":"2026-05-28T01:04:41.257672+00:00"},{"alias_kind":"pith_short_16","alias_value":"HV37WFL7D4VRVU3T","created_at":"2026-05-28T01:04:41.257672+00:00"},{"alias_kind":"pith_short_8","alias_value":"HV37WFL7","created_at":"2026-05-28T01:04:41.257672+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/HV37WFL7D4VRVU3TKW5QKY74E4","json":"https://pith.science/pith/HV37WFL7D4VRVU3TKW5QKY74E4.json","graph_json":"https://pith.science/api/pith-number/HV37WFL7D4VRVU3TKW5QKY74E4/graph.json","events_json":"https://pith.science/api/pith-number/HV37WFL7D4VRVU3TKW5QKY74E4/events.json","paper":"https://pith.science/paper/HV37WFL7"},"agent_actions":{"view_html":"https://pith.science/pith/HV37WFL7D4VRVU3TKW5QKY74E4","download_json":"https://pith.science/pith/HV37WFL7D4VRVU3TKW5QKY74E4.json","view_paper":"https://pith.science/paper/HV37WFL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.00457&json=true","fetch_graph":"https://pith.science/api/pith-number/HV37WFL7D4VRVU3TKW5QKY74E4/graph.json","fetch_events":"https://pith.science/api/pith-number/HV37WFL7D4VRVU3TKW5QKY74E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HV37WFL7D4VRVU3TKW5QKY74E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HV37WFL7D4VRVU3TKW5QKY74E4/action/storage_attestation","attest_author":"https://pith.science/pith/HV37WFL7D4VRVU3TKW5QKY74E4/action/author_attestation","sign_citation":"https://pith.science/pith/HV37WFL7D4VRVU3TKW5QKY74E4/action/citation_signature","submit_replication":"https://pith.science/pith/HV37WFL7D4VRVU3TKW5QKY74E4/action/replication_record"}},"created_at":"2026-05-28T01:04:41.257672+00:00","updated_at":"2026-05-28T01:04:41.257672+00:00"}