{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7GBIHAEO2VINCGUR6KWYYIXUSD","short_pith_number":"pith:7GBIHAEO","schema_version":"1.0","canonical_sha256":"f98283808ed550d11a91f2ad8c22f490fd0d6e6b9d5bcdbf73d3247ce5fd648e","source":{"kind":"arxiv","id":"2410.02312","version":1},"attestation_state":"computed","paper":{"title":"Federated Reinforcement Learning to Optimize Teleoperated Driving Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Filippo Bragato, Marco Giordani, Michele Zorzi","submitted_at":"2024-10-03T08:51:32Z","abstract_excerpt":"Several sixth generation (6G) use cases have tight requirements in terms of reliability and latency, in particular teleoperated driving (TD). To address those requirements, Predictive Quality of Service (PQoS), possibly combined with reinforcement learning (RL), has emerged as a valid approach to dynamically adapt the configuration of the TD application (e.g., the level of compression of automotive data) to the experienced network conditions. In this work, we explore different classes of RL algorithms for PQoS, namely MAB (stateless), SARSA (stateful on-policy), Q-Learning (stateful off-policy"},"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":"2410.02312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2024-10-03T08:51:32Z","cross_cats_sorted":[],"title_canon_sha256":"2061fb934bb8ada083664e4c182368b13ed984924f58220653d24b34d760f7f4","abstract_canon_sha256":"8a3fc0da21813c51072a105ac25306dd95c9ca1d34a4128d3619f4fc3822de7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:19.103152Z","signature_b64":"9JmBF4btE4oFu2Y5M8IBOyJioaaB44/zBWBEzJpiajz77EO+536YqFdUvBPz0ltORNnKlzjkL10GdbMwAvcyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f98283808ed550d11a91f2ad8c22f490fd0d6e6b9d5bcdbf73d3247ce5fd648e","last_reissued_at":"2026-07-05T09:15:19.102774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:19.102774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Reinforcement Learning to Optimize Teleoperated Driving Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Filippo Bragato, Marco Giordani, Michele Zorzi","submitted_at":"2024-10-03T08:51:32Z","abstract_excerpt":"Several sixth generation (6G) use cases have tight requirements in terms of reliability and latency, in particular teleoperated driving (TD). To address those requirements, Predictive Quality of Service (PQoS), possibly combined with reinforcement learning (RL), has emerged as a valid approach to dynamically adapt the configuration of the TD application (e.g., the level of compression of automotive data) to the experienced network conditions. In this work, we explore different classes of RL algorithms for PQoS, namely MAB (stateless), SARSA (stateful on-policy), Q-Learning (stateful off-policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02312","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/2410.02312/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":"2410.02312","created_at":"2026-07-05T09:15:19.102828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02312v1","created_at":"2026-07-05T09:15:19.102828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02312","created_at":"2026-07-05T09:15:19.102828+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GBIHAEO2VIN","created_at":"2026-07-05T09:15:19.102828+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GBIHAEO2VINCGUR","created_at":"2026-07-05T09:15:19.102828+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GBIHAEO","created_at":"2026-07-05T09:15:19.102828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03558","citing_title":"Multi-Agent Reinforcement Learning Scheduling to Support Low Latency in Teleoperated Driving","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD","json":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD.json","graph_json":"https://pith.science/api/pith-number/7GBIHAEO2VINCGUR6KWYYIXUSD/graph.json","events_json":"https://pith.science/api/pith-number/7GBIHAEO2VINCGUR6KWYYIXUSD/events.json","paper":"https://pith.science/paper/7GBIHAEO"},"agent_actions":{"view_html":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD","download_json":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD.json","view_paper":"https://pith.science/paper/7GBIHAEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02312&json=true","fetch_graph":"https://pith.science/api/pith-number/7GBIHAEO2VINCGUR6KWYYIXUSD/graph.json","fetch_events":"https://pith.science/api/pith-number/7GBIHAEO2VINCGUR6KWYYIXUSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD/action/storage_attestation","attest_author":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD/action/author_attestation","sign_citation":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD/action/citation_signature","submit_replication":"https://pith.science/pith/7GBIHAEO2VINCGUR6KWYYIXUSD/action/replication_record"}},"created_at":"2026-07-05T09:15:19.102828+00:00","updated_at":"2026-07-05T09:15:19.102828+00:00"}