{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R6L4T6NBQR7CK5OBAEZY3CNHQ4","short_pith_number":"pith:R6L4T6NB","schema_version":"1.0","canonical_sha256":"8f97c9f9a1847e2575c101338d89a7872710d7d9600d33a9eac4f0b094ca955e","source":{"kind":"arxiv","id":"2412.01839","version":1},"attestation_state":"computed","paper":{"title":"Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Amine Abouaomar, Manal Mehdaoui","submitted_at":"2024-11-17T17:46:40Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) is a powerful tool used for addressing complex challenges in mobile networks. This paper investigates the application of two DRL models, on-policy and off-policy, in the field of resource allocation for Open Radio Access Networks (O-RAN). The on-policy model is the Proximal Policy Optimization (PPO), and the off-policy model is the Sample Efficient Actor-Critic with Experience Replay (ACER), which focuses on resolving the challenges of resource allocation associated with a Quality of Service (QoS) application that has strict requirements. Motivated by the orig"},"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":"2412.01839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2024-11-17T17:46:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9bc3af80d8a1a56c4abe0d64404cc354a65abf22a57f81eb214eb71548f2c5c0","abstract_canon_sha256":"dc74d3ac8b6a4ba833b26fb6618dbbae7938f5fc5ae517a5499e041a181cdfed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:39.267412Z","signature_b64":"o4sSWLqymN/TpgWmStnViW2L/141Etol7BHLKLMIaqA7OorZI9u5KASPbUuBsN9r0+Rz9iqCUFkaoaV+yokIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f97c9f9a1847e2575c101338d89a7872710d7d9600d33a9eac4f0b094ca955e","last_reissued_at":"2026-07-05T09:43:39.266843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:39.266843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Amine Abouaomar, Manal Mehdaoui","submitted_at":"2024-11-17T17:46:40Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) is a powerful tool used for addressing complex challenges in mobile networks. This paper investigates the application of two DRL models, on-policy and off-policy, in the field of resource allocation for Open Radio Access Networks (O-RAN). The on-policy model is the Proximal Policy Optimization (PPO), and the off-policy model is the Sample Efficient Actor-Critic with Experience Replay (ACER), which focuses on resolving the challenges of resource allocation associated with a Quality of Service (QoS) application that has strict requirements. Motivated by the orig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01839","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/2412.01839/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":"2412.01839","created_at":"2026-07-05T09:43:39.266895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01839v1","created_at":"2026-07-05T09:43:39.266895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01839","created_at":"2026-07-05T09:43:39.266895+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6L4T6NBQR7C","created_at":"2026-07-05T09:43:39.266895+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6L4T6NBQR7CK5OB","created_at":"2026-07-05T09:43:39.266895+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6L4T6NB","created_at":"2026-07-05T09:43:39.266895+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/R6L4T6NBQR7CK5OBAEZY3CNHQ4","json":"https://pith.science/pith/R6L4T6NBQR7CK5OBAEZY3CNHQ4.json","graph_json":"https://pith.science/api/pith-number/R6L4T6NBQR7CK5OBAEZY3CNHQ4/graph.json","events_json":"https://pith.science/api/pith-number/R6L4T6NBQR7CK5OBAEZY3CNHQ4/events.json","paper":"https://pith.science/paper/R6L4T6NB"},"agent_actions":{"view_html":"https://pith.science/pith/R6L4T6NBQR7CK5OBAEZY3CNHQ4","download_json":"https://pith.science/pith/R6L4T6NBQR7CK5OBAEZY3CNHQ4.json","view_paper":"https://pith.science/paper/R6L4T6NB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01839&json=true","fetch_graph":"https://pith.science/api/pith-number/R6L4T6NBQR7CK5OBAEZY3CNHQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/R6L4T6NBQR7CK5OBAEZY3CNHQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6L4T6NBQR7CK5OBAEZY3CNHQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6L4T6NBQR7CK5OBAEZY3CNHQ4/action/storage_attestation","attest_author":"https://pith.science/pith/R6L4T6NBQR7CK5OBAEZY3CNHQ4/action/author_attestation","sign_citation":"https://pith.science/pith/R6L4T6NBQR7CK5OBAEZY3CNHQ4/action/citation_signature","submit_replication":"https://pith.science/pith/R6L4T6NBQR7CK5OBAEZY3CNHQ4/action/replication_record"}},"created_at":"2026-07-05T09:43:39.266895+00:00","updated_at":"2026-07-05T09:43:39.266895+00:00"}