{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KAIBQQMBQTGKYWZGTWSD4GT4DW","short_pith_number":"pith:KAIBQQMB","schema_version":"1.0","canonical_sha256":"501018418184ccac5b269da43e1a7c1db2062bed83f0f31b635ac240327f8cea","source":{"kind":"arxiv","id":"2206.03846","version":1},"attestation_state":"computed","paper":{"title":"Sim2real for Reinforcement Learning Driven Next Generation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI"],"primary_cat":"cs.LG","authors_text":"Abdelrahim Ahmad, Angela Doufexi, Arjun Parekh, Arman Shojaeifard, Hakan Erdol, Jonathan Thomas, Peizheng Li, Robert Piechocki, Rui Inacio, Shipra Kapoor, Xiaoyang Wang","submitted_at":"2022-06-08T12:40:24Z","abstract_excerpt":"The next generation of networks will actively embrace artificial intelligence (AI) and machine learning (ML) technologies for automation networks and optimal network operation strategies. The emerging network structure represented by Open RAN (O-RAN) conforms to this trend, and the radio intelligent controller (RIC) at the centre of its specification serves as an ML applications host. Various ML models, especially Reinforcement Learning (RL) models, are regarded as the key to solving RAN-related multi-objective optimization problems. However, it should be recognized that most of the current RL"},"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":"2206.03846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T12:40:24Z","cross_cats_sorted":["cs.NI"],"title_canon_sha256":"09242d50c38744f6966c99ed319aebfaa31d269c999f82631c8d9b0d7a9590db","abstract_canon_sha256":"ecb7ea6e745d934d4b71ff99d47a2c038168b1a369f0cdcf69ff522d684748f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:14.120665Z","signature_b64":"j4TaOajeiCFxp2gC6IX24WhGdwad0PV7ZEO4yumRPPHdzJdYqogN46XTZz1F19mLcXCez3iwBBJDQKdEVEY4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"501018418184ccac5b269da43e1a7c1db2062bed83f0f31b635ac240327f8cea","last_reissued_at":"2026-07-05T04:30:14.120222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:14.120222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sim2real for Reinforcement Learning Driven Next Generation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI"],"primary_cat":"cs.LG","authors_text":"Abdelrahim Ahmad, Angela Doufexi, Arjun Parekh, Arman Shojaeifard, Hakan Erdol, Jonathan Thomas, Peizheng Li, Robert Piechocki, Rui Inacio, Shipra Kapoor, Xiaoyang Wang","submitted_at":"2022-06-08T12:40:24Z","abstract_excerpt":"The next generation of networks will actively embrace artificial intelligence (AI) and machine learning (ML) technologies for automation networks and optimal network operation strategies. The emerging network structure represented by Open RAN (O-RAN) conforms to this trend, and the radio intelligent controller (RIC) at the centre of its specification serves as an ML applications host. Various ML models, especially Reinforcement Learning (RL) models, are regarded as the key to solving RAN-related multi-objective optimization problems. However, it should be recognized that most of the current RL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03846","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/2206.03846/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":"2206.03846","created_at":"2026-07-05T04:30:14.120286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03846v1","created_at":"2026-07-05T04:30:14.120286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03846","created_at":"2026-07-05T04:30:14.120286+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAIBQQMBQTGK","created_at":"2026-07-05T04:30:14.120286+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAIBQQMBQTGKYWZG","created_at":"2026-07-05T04:30:14.120286+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAIBQQMB","created_at":"2026-07-05T04:30:14.120286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01128","citing_title":"MORPH: Multi-Environment Orchestrated Reinforcement Learning for PRB Handling in O-RAN","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW","json":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW.json","graph_json":"https://pith.science/api/pith-number/KAIBQQMBQTGKYWZGTWSD4GT4DW/graph.json","events_json":"https://pith.science/api/pith-number/KAIBQQMBQTGKYWZGTWSD4GT4DW/events.json","paper":"https://pith.science/paper/KAIBQQMB"},"agent_actions":{"view_html":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW","download_json":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW.json","view_paper":"https://pith.science/paper/KAIBQQMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03846&json=true","fetch_graph":"https://pith.science/api/pith-number/KAIBQQMBQTGKYWZGTWSD4GT4DW/graph.json","fetch_events":"https://pith.science/api/pith-number/KAIBQQMBQTGKYWZGTWSD4GT4DW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW/action/storage_attestation","attest_author":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW/action/author_attestation","sign_citation":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW/action/citation_signature","submit_replication":"https://pith.science/pith/KAIBQQMBQTGKYWZGTWSD4GT4DW/action/replication_record"}},"created_at":"2026-07-05T04:30:14.120286+00:00","updated_at":"2026-07-05T04:30:14.120286+00:00"}