{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QAGUE6AFUYTPKQLSMNSK76UOPC","short_pith_number":"pith:QAGUE6AF","schema_version":"1.0","canonical_sha256":"800d427805a626f541726364affa8e78b2761a89e2c985872066371abb90c322","source":{"kind":"arxiv","id":"2101.04627","version":1},"attestation_state":"computed","paper":{"title":"Queue-Learning: A Reinforcement Learning Approach for Providing Quality of Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NI","cs.PF"],"primary_cat":"cs.LG","authors_text":"Alberto Leon-Garcia, Ali Tizghadam, Majid Raeis","submitted_at":"2021-01-12T17:28:57Z","abstract_excerpt":"End-to-end delay is a critical attribute of quality of service (QoS) in application domains such as cloud computing and computer networks. This metric is particularly important in tandem service systems, where the end-to-end service is provided through a chain of services. Service-rate control is a common mechanism for providing QoS guarantees in service systems. In this paper, we introduce a reinforcement learning-based (RL-based) service-rate controller that provides probabilistic upper-bounds on the end-to-end delay of the system, while preventing the overuse of service resources. In order "},"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":"2101.04627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-12T17:28:57Z","cross_cats_sorted":["cs.AI","cs.NI","cs.PF"],"title_canon_sha256":"cdeda62b994d1bfbe7e491ae89894394e764f486e94a1c4886e71a123716100b","abstract_canon_sha256":"8d82f6670f886efbd5bdd860e30c72992fb22de6e749ec3f971aeb6457809847"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:27.039557Z","signature_b64":"KDh1dwJJUca9lkcjKNbf/+4BdR1tzn7BU+vE4QO846TPlj4LzlgII9Mt+XAUKNEkw7/H4rkjtttn+A2Di5SaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"800d427805a626f541726364affa8e78b2761a89e2c985872066371abb90c322","last_reissued_at":"2026-07-05T02:06:27.039189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:27.039189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Queue-Learning: A Reinforcement Learning Approach for Providing Quality of Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NI","cs.PF"],"primary_cat":"cs.LG","authors_text":"Alberto Leon-Garcia, Ali Tizghadam, Majid Raeis","submitted_at":"2021-01-12T17:28:57Z","abstract_excerpt":"End-to-end delay is a critical attribute of quality of service (QoS) in application domains such as cloud computing and computer networks. This metric is particularly important in tandem service systems, where the end-to-end service is provided through a chain of services. Service-rate control is a common mechanism for providing QoS guarantees in service systems. In this paper, we introduce a reinforcement learning-based (RL-based) service-rate controller that provides probabilistic upper-bounds on the end-to-end delay of the system, while preventing the overuse of service resources. In order "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.04627","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/2101.04627/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":"2101.04627","created_at":"2026-07-05T02:06:27.039250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.04627v1","created_at":"2026-07-05T02:06:27.039250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.04627","created_at":"2026-07-05T02:06:27.039250+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAGUE6AFUYTP","created_at":"2026-07-05T02:06:27.039250+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAGUE6AFUYTPKQLS","created_at":"2026-07-05T02:06:27.039250+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAGUE6AF","created_at":"2026-07-05T02:06:27.039250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18111","citing_title":"Percentile-Based Deep Reinforcement Learning and Reward Based Personalization For Delay Aware RAN Slicing in O-RAN","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC","json":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC.json","graph_json":"https://pith.science/api/pith-number/QAGUE6AFUYTPKQLSMNSK76UOPC/graph.json","events_json":"https://pith.science/api/pith-number/QAGUE6AFUYTPKQLSMNSK76UOPC/events.json","paper":"https://pith.science/paper/QAGUE6AF"},"agent_actions":{"view_html":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC","download_json":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC.json","view_paper":"https://pith.science/paper/QAGUE6AF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.04627&json=true","fetch_graph":"https://pith.science/api/pith-number/QAGUE6AFUYTPKQLSMNSK76UOPC/graph.json","fetch_events":"https://pith.science/api/pith-number/QAGUE6AFUYTPKQLSMNSK76UOPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC/action/storage_attestation","attest_author":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC/action/author_attestation","sign_citation":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC/action/citation_signature","submit_replication":"https://pith.science/pith/QAGUE6AFUYTPKQLSMNSK76UOPC/action/replication_record"}},"created_at":"2026-07-05T02:06:27.039250+00:00","updated_at":"2026-07-05T02:06:27.039250+00:00"}