{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JTFSN5LRROOE3O2QX4GCTZ6CB5","short_pith_number":"pith:JTFSN5LR","canonical_record":{"source":{"id":"2012.10711","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2020-12-19T15:16:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"623e442729dcc8342a0d61505cc0c0b62f34928c87e5933a3deb939ddb86e949","abstract_canon_sha256":"77ef3205e3abe7875aec8a2db2d0c917fa228eb606fa2923dea1c316afbf4345"},"schema_version":"1.0"},"canonical_sha256":"4ccb26f5718b9c4dbb50bf0c29e7c20f609634d286cfc6633e2b46556d4e7d4c","source":{"kind":"arxiv","id":"2012.10711","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.10711","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"arxiv_version","alias_value":"2012.10711v5","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10711","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"pith_short_12","alias_value":"JTFSN5LRROOE","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"pith_short_16","alias_value":"JTFSN5LRROOE3O2Q","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"pith_short_8","alias_value":"JTFSN5LR","created_at":"2026-07-05T10:33:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JTFSN5LRROOE3O2QX4GCTZ6CB5","target":"record","payload":{"canonical_record":{"source":{"id":"2012.10711","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2020-12-19T15:16:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"623e442729dcc8342a0d61505cc0c0b62f34928c87e5933a3deb939ddb86e949","abstract_canon_sha256":"77ef3205e3abe7875aec8a2db2d0c917fa228eb606fa2923dea1c316afbf4345"},"schema_version":"1.0"},"canonical_sha256":"4ccb26f5718b9c4dbb50bf0c29e7c20f609634d286cfc6633e2b46556d4e7d4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:28.189966Z","signature_b64":"CF4VMf7RvBe/619sT2U0G/RwLTbRDdoVk6SkUX+uzNXWiP4iDIJG8zGF/A4aqNt0LSK3MijUBsFuE/HKRDDlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ccb26f5718b9c4dbb50bf0c29e7c20f609634d286cfc6633e2b46556d4e7d4c","last_reissued_at":"2026-07-05T10:33:28.189472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:28.189472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.10711","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:33:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBL2N7c9NQubhQadOm/QnW05rYCh6zk60IB7i5soslHxVGMu12qpISso31UP+W7bzGSndaBr0ev4DhnoXLe4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T21:52:28.903332Z"},"content_sha256":"b52e1d687cf4fc9c9818af50b61868fd1333ddfb3f0bc1481e91a390d3455306","schema_version":"1.0","event_id":"sha256:b52e1d687cf4fc9c9818af50b61868fd1333ddfb3f0bc1481e91a390d3455306"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JTFSN5LRROOE3O2QX4GCTZ6CB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantum reinforcement learning in continuous action space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Dingding Wen, Donghong Han, Shan Jin, Shaojun Wu, Xiaoting Wang","submitted_at":"2020-12-19T15:16:17Z","abstract_excerpt":"Quantum reinforcement learning (QRL) is a promising paradigm for near-term quantum devices. While existing QRL methods have shown success in discrete action spaces, extending these techniques to continuous domains is challenging due to the curse of dimensionality introduced by discretization. To overcome this limitation, we introduce a quantum Deep Deterministic Policy Gradient (DDPG) algorithm that efficiently addresses both classical and quantum sequential decision problems in continuous action spaces. Moreover, our approach facilitates single-shot quantum state generation: a one-time optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10711","kind":"arxiv","version":5},"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/2012.10711/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:33:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0UtBuRhEk2tHzt0FEjpTLMEvM2hgqAJRMp99fKwMNNc7pMjJ34gI3ftyk/rEJwCX3t4ozhoVqtJ1BHneRL5xCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T21:52:28.903719Z"},"content_sha256":"a1d00ea78d86e0bf20ed0855d45a647bf7326d79c3d1586d2785919f85811afb","schema_version":"1.0","event_id":"sha256:a1d00ea78d86e0bf20ed0855d45a647bf7326d79c3d1586d2785919f85811afb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTFSN5LRROOE3O2QX4GCTZ6CB5/bundle.json","state_url":"https://pith.science/pith/JTFSN5LRROOE3O2QX4GCTZ6CB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTFSN5LRROOE3O2QX4GCTZ6CB5/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":"2026-07-10T21:52:28Z","links":{"resolver":"https://pith.science/pith/JTFSN5LRROOE3O2QX4GCTZ6CB5","bundle":"https://pith.science/pith/JTFSN5LRROOE3O2QX4GCTZ6CB5/bundle.json","state":"https://pith.science/pith/JTFSN5LRROOE3O2QX4GCTZ6CB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTFSN5LRROOE3O2QX4GCTZ6CB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JTFSN5LRROOE3O2QX4GCTZ6CB5","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":"77ef3205e3abe7875aec8a2db2d0c917fa228eb606fa2923dea1c316afbf4345","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2020-12-19T15:16:17Z","title_canon_sha256":"623e442729dcc8342a0d61505cc0c0b62f34928c87e5933a3deb939ddb86e949"},"schema_version":"1.0","source":{"id":"2012.10711","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.10711","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"arxiv_version","alias_value":"2012.10711v5","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10711","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"pith_short_12","alias_value":"JTFSN5LRROOE","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"pith_short_16","alias_value":"JTFSN5LRROOE3O2Q","created_at":"2026-07-05T10:33:28Z"},{"alias_kind":"pith_short_8","alias_value":"JTFSN5LR","created_at":"2026-07-05T10:33:28Z"}],"graph_snapshots":[{"event_id":"sha256:a1d00ea78d86e0bf20ed0855d45a647bf7326d79c3d1586d2785919f85811afb","target":"graph","created_at":"2026-07-05T10:33:28Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.10711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantum reinforcement learning (QRL) is a promising paradigm for near-term quantum devices. While existing QRL methods have shown success in discrete action spaces, extending these techniques to continuous domains is challenging due to the curse of dimensionality introduced by discretization. To overcome this limitation, we introduce a quantum Deep Deterministic Policy Gradient (DDPG) algorithm that efficiently addresses both classical and quantum sequential decision problems in continuous action spaces. Moreover, our approach facilitates single-shot quantum state generation: a one-time optimi","authors_text":"Dingding Wen, Donghong Han, Shan Jin, Shaojun Wu, Xiaoting Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2020-12-19T15:16:17Z","title":"Quantum reinforcement learning in continuous action space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10711","kind":"arxiv","version":5},"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:b52e1d687cf4fc9c9818af50b61868fd1333ddfb3f0bc1481e91a390d3455306","target":"record","created_at":"2026-07-05T10:33:28Z","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":"77ef3205e3abe7875aec8a2db2d0c917fa228eb606fa2923dea1c316afbf4345","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2020-12-19T15:16:17Z","title_canon_sha256":"623e442729dcc8342a0d61505cc0c0b62f34928c87e5933a3deb939ddb86e949"},"schema_version":"1.0","source":{"id":"2012.10711","kind":"arxiv","version":5}},"canonical_sha256":"4ccb26f5718b9c4dbb50bf0c29e7c20f609634d286cfc6633e2b46556d4e7d4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ccb26f5718b9c4dbb50bf0c29e7c20f609634d286cfc6633e2b46556d4e7d4c","first_computed_at":"2026-07-05T10:33:28.189472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:28.189472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CF4VMf7RvBe/619sT2U0G/RwLTbRDdoVk6SkUX+uzNXWiP4iDIJG8zGF/A4aqNt0LSK3MijUBsFuE/HKRDDlBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:28.189966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.10711","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b52e1d687cf4fc9c9818af50b61868fd1333ddfb3f0bc1481e91a390d3455306","sha256:a1d00ea78d86e0bf20ed0855d45a647bf7326d79c3d1586d2785919f85811afb"],"state_sha256":"bee80b834f0cd7b2011265a7df5793080fff83df6e93b621c12f80834a4c988f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bU+yx8B2KzwR3DPZOwQ4igTUNL/DshK/sR8O14fU7k7MD9c4UxLJHpowao2qjBW3xjIgrAYWA67GSGJS2I9ZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T21:52:28.906566Z","bundle_sha256":"c10535d7f492a490e41f4373d5f925a5278c54acf8df6a575a4c40ac16dd88f4"}}