{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZCKDVONGDPVB3GQMA4ZBDCNJVH","short_pith_number":"pith:ZCKDVONG","canonical_record":{"source":{"id":"1802.06416","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-18T18:03:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4a6b3c0390ed5f28b5d56d9d488515d9b699b9fd57157d2f6ab9122a26e4d701","abstract_canon_sha256":"dfa71c0fe56fac77af163208de476f42607bfb16765d88b06c4313e34e5c4d83"},"schema_version":"1.0"},"canonical_sha256":"c8943ab9a61bea1d9a0c07321189a9a9ee666d56c0535b8aa940e8e0e9cb093e","source":{"kind":"arxiv","id":"1802.06416","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06416","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06416v3","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06416","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"pith_short_12","alias_value":"ZCKDVONGDPVB","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZCKDVONGDPVB3GQM","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZCKDVONG","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZCKDVONGDPVB3GQMA4ZBDCNJVH","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06416","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-18T18:03:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4a6b3c0390ed5f28b5d56d9d488515d9b699b9fd57157d2f6ab9122a26e4d701","abstract_canon_sha256":"dfa71c0fe56fac77af163208de476f42607bfb16765d88b06c4313e34e5c4d83"},"schema_version":"1.0"},"canonical_sha256":"c8943ab9a61bea1d9a0c07321189a9a9ee666d56c0535b8aa940e8e0e9cb093e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:56.148392Z","signature_b64":"ftEN1ZW83Oi4NBNHkhJ/lwsCtfMBjurRYgSDyEbW9SYLOqzt+2MwVupHF3Ipmj99M4qtUW5NUe3a3MNoaGJKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8943ab9a61bea1d9a0c07321189a9a9ee666d56c0535b8aa940e8e0e9cb093e","last_reissued_at":"2026-05-17T23:58:56.147948Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:56.147948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06416","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hhrcmx75XUrRMj2TgATVhREdyDpR6S6jZQUc7ReRB5ehKfE2aMYOXuoGtdSyd1xLWvQnN9QuMMxIoJNPx2ZHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:15:58.628889Z"},"content_sha256":"a25ad5d942f168e15ec32b73a66eae370c7b377e7da006c3b6b5ce7461858a6c","schema_version":"1.0","event_id":"sha256:a25ad5d942f168e15ec32b73a66eae370c7b377e7da006c3b6b5ce7461858a6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZCKDVONGDPVB3GQMA4ZBDCNJVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sim-to-Real Optimization of Complex Real World Mobile Network with Imperfect Information via Deep Reinforcement Learning from Self-play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Jin Yang, Qitao Song, Xin Chen, Yongxi Tan, Yunjun Chen, Zhangxiang Ye, Zhenqiang Su","submitted_at":"2018-02-18T18:03:39Z","abstract_excerpt":"Mobile network that millions of people use every day is one of the most complex systems in the world. Optimization of mobile network to meet exploding customer demand and reduce capital/operation expenditures poses great challenges. Despite recent progress, application of deep reinforcement learning (DRL) to complex real world problem still remains unsolved, given data scarcity, partial observability, risk and complex rules/dynamics in real world, as well as the huge reality gap between simulation and real world. To bridge the reality gap, we introduce a Sim-to-Real framework to directly trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06416","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tuaXJR8FqtvY71PUHxIIZvypBO9uxJRExwdnFno3twC3YSV+nqP8gqD4ktEZQUomsWZwpH3bK9uZgwTUCSuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:15:58.629589Z"},"content_sha256":"176a32723ab5becd5eeb38cc5f8cf0865664fc8a0c5163690ab2c7f6903bcb70","schema_version":"1.0","event_id":"sha256:176a32723ab5becd5eeb38cc5f8cf0865664fc8a0c5163690ab2c7f6903bcb70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZCKDVONGDPVB3GQMA4ZBDCNJVH/bundle.json","state_url":"https://pith.science/pith/ZCKDVONGDPVB3GQMA4ZBDCNJVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZCKDVONGDPVB3GQMA4ZBDCNJVH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T21:15:58Z","links":{"resolver":"https://pith.science/pith/ZCKDVONGDPVB3GQMA4ZBDCNJVH","bundle":"https://pith.science/pith/ZCKDVONGDPVB3GQMA4ZBDCNJVH/bundle.json","state":"https://pith.science/pith/ZCKDVONGDPVB3GQMA4ZBDCNJVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZCKDVONGDPVB3GQMA4ZBDCNJVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZCKDVONGDPVB3GQMA4ZBDCNJVH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dfa71c0fe56fac77af163208de476f42607bfb16765d88b06c4313e34e5c4d83","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-18T18:03:39Z","title_canon_sha256":"4a6b3c0390ed5f28b5d56d9d488515d9b699b9fd57157d2f6ab9122a26e4d701"},"schema_version":"1.0","source":{"id":"1802.06416","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06416","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06416v3","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06416","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"pith_short_12","alias_value":"ZCKDVONGDPVB","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZCKDVONGDPVB3GQM","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZCKDVONG","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:176a32723ab5becd5eeb38cc5f8cf0865664fc8a0c5163690ab2c7f6903bcb70","target":"graph","created_at":"2026-05-17T23:58:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Mobile network that millions of people use every day is one of the most complex systems in the world. Optimization of mobile network to meet exploding customer demand and reduce capital/operation expenditures poses great challenges. Despite recent progress, application of deep reinforcement learning (DRL) to complex real world problem still remains unsolved, given data scarcity, partial observability, risk and complex rules/dynamics in real world, as well as the huge reality gap between simulation and real world. To bridge the reality gap, we introduce a Sim-to-Real framework to directly trans","authors_text":"Jin Yang, Qitao Song, Xin Chen, Yongxi Tan, Yunjun Chen, Zhangxiang Ye, Zhenqiang Su","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-18T18:03:39Z","title":"Sim-to-Real Optimization of Complex Real World Mobile Network with Imperfect Information via Deep Reinforcement Learning from Self-play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06416","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a25ad5d942f168e15ec32b73a66eae370c7b377e7da006c3b6b5ce7461858a6c","target":"record","created_at":"2026-05-17T23:58:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dfa71c0fe56fac77af163208de476f42607bfb16765d88b06c4313e34e5c4d83","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-18T18:03:39Z","title_canon_sha256":"4a6b3c0390ed5f28b5d56d9d488515d9b699b9fd57157d2f6ab9122a26e4d701"},"schema_version":"1.0","source":{"id":"1802.06416","kind":"arxiv","version":3}},"canonical_sha256":"c8943ab9a61bea1d9a0c07321189a9a9ee666d56c0535b8aa940e8e0e9cb093e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8943ab9a61bea1d9a0c07321189a9a9ee666d56c0535b8aa940e8e0e9cb093e","first_computed_at":"2026-05-17T23:58:56.147948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:56.147948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ftEN1ZW83Oi4NBNHkhJ/lwsCtfMBjurRYgSDyEbW9SYLOqzt+2MwVupHF3Ipmj99M4qtUW5NUe3a3MNoaGJKCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:56.148392Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06416","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a25ad5d942f168e15ec32b73a66eae370c7b377e7da006c3b6b5ce7461858a6c","sha256:176a32723ab5becd5eeb38cc5f8cf0865664fc8a0c5163690ab2c7f6903bcb70"],"state_sha256":"dc281ec882fc2c0ae0c435a1ddb727fd50a4aad1de2f2d97ecb6060d983a3ba4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u6cfIAUPDMm+7cHSV57CowCku5Gay4a8/1RX7kACYJ3CcLHp6qDwXTr/ViHX3P1V2Yj6vOTY+cvD1ou+X2bOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:15:58.633027Z","bundle_sha256":"f56d6abe177d03495bb9c7d7d9a1922f99f11a85ab12a93a79c601d445c39d3f"}}