{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:637QYM7BV4MHAML3SH7ZMGGZL5","short_pith_number":"pith:637QYM7B","canonical_record":{"source":{"id":"1812.09968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T19:25:23Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"a81501325768b2b647a7c51490c996b7226e479ceba0b1d3d3862b532d816d99","abstract_canon_sha256":"af5f247f2d76c10129465f243794dec83ce25d8517bea82cf1f736806f739f15"},"schema_version":"1.0"},"canonical_sha256":"f6ff0c33e1af1870317b91ff9618d95f42628dfddf7aff72457ffd4bd7bad17b","source":{"kind":"arxiv","id":"1812.09968","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.09968","created_at":"2026-05-17T23:57:26Z"},{"alias_kind":"arxiv_version","alias_value":"1812.09968v1","created_at":"2026-05-17T23:57:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09968","created_at":"2026-05-17T23:57:26Z"},{"alias_kind":"pith_short_12","alias_value":"637QYM7BV4MH","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"637QYM7BV4MHAML3","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"637QYM7B","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:637QYM7BV4MHAML3SH7ZMGGZL5","target":"record","payload":{"canonical_record":{"source":{"id":"1812.09968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T19:25:23Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"a81501325768b2b647a7c51490c996b7226e479ceba0b1d3d3862b532d816d99","abstract_canon_sha256":"af5f247f2d76c10129465f243794dec83ce25d8517bea82cf1f736806f739f15"},"schema_version":"1.0"},"canonical_sha256":"f6ff0c33e1af1870317b91ff9618d95f42628dfddf7aff72457ffd4bd7bad17b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:26.241945Z","signature_b64":"2hZNvYrsUYANKS+FnY6PkGZig9BRWhqsjUQGK1hXnpncfJuWWvFTYM4C3dPsSNxrDJcf+9VVF+kLWo29e/AuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6ff0c33e1af1870317b91ff9618d95f42628dfddf7aff72457ffd4bd7bad17b","last_reissued_at":"2026-05-17T23:57:26.241472Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:26.241472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.09968","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RDTcuNqemFNB4yWSgVxMBe5IC80vCciHsL34STt3wBXMCJ7V3QKqr+lwvji6na3zKvDJ+3+1TkrFupFgHznqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:00:05.026857Z"},"content_sha256":"3ec9d5e0ed73954b790ceb798f71d02bacae49a8d8f29e2b1c2bee7d5ef38e58","schema_version":"1.0","event_id":"sha256:3ec9d5e0ed73954b790ceb798f71d02bacae49a8d8f29e2b1c2bee7d5ef38e58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:637QYM7BV4MHAML3SH7ZMGGZL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VMAV-C: A Deep Attention-based Reinforcement Learning Algorithm for Model-based Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jincai Huang, Qi Wang, Xingxing Liang, Yanghe Feng, Zhong Liu","submitted_at":"2018-12-24T19:25:23Z","abstract_excerpt":"Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this paradigm to universal complex tasks. Among them, the low efficiency of data utilization in model-free reinforcement algorithms is of great concern. In contrast, the model-based reinforcement learning algorithms can reveal underlying dynamics in learning environments and seldom suffer the data utilization problem. To address the problem, a model-based reinforcement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09968","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":""},"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":"2026-05-17T23:57:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KftmAIZ5q7uewBDuUd+/JjrEg8/WA1iAw4TW2k/hSNqpgUfu1wEwqixh8W0iORr3BrnSiHj/y75aewu23odcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:00:05.027415Z"},"content_sha256":"1d4d1c8c7d1a0c8bc9ede94215ef36e9397d7b18c3c58913770af5abfd1d1b95","schema_version":"1.0","event_id":"sha256:1d4d1c8c7d1a0c8bc9ede94215ef36e9397d7b18c3c58913770af5abfd1d1b95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/637QYM7BV4MHAML3SH7ZMGGZL5/bundle.json","state_url":"https://pith.science/pith/637QYM7BV4MHAML3SH7ZMGGZL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/637QYM7BV4MHAML3SH7ZMGGZL5/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":"2026-05-30T07:00:05Z","links":{"resolver":"https://pith.science/pith/637QYM7BV4MHAML3SH7ZMGGZL5","bundle":"https://pith.science/pith/637QYM7BV4MHAML3SH7ZMGGZL5/bundle.json","state":"https://pith.science/pith/637QYM7BV4MHAML3SH7ZMGGZL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/637QYM7BV4MHAML3SH7ZMGGZL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:637QYM7BV4MHAML3SH7ZMGGZL5","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":"af5f247f2d76c10129465f243794dec83ce25d8517bea82cf1f736806f739f15","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T19:25:23Z","title_canon_sha256":"a81501325768b2b647a7c51490c996b7226e479ceba0b1d3d3862b532d816d99"},"schema_version":"1.0","source":{"id":"1812.09968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.09968","created_at":"2026-05-17T23:57:26Z"},{"alias_kind":"arxiv_version","alias_value":"1812.09968v1","created_at":"2026-05-17T23:57:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09968","created_at":"2026-05-17T23:57:26Z"},{"alias_kind":"pith_short_12","alias_value":"637QYM7BV4MH","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"637QYM7BV4MHAML3","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"637QYM7B","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:1d4d1c8c7d1a0c8bc9ede94215ef36e9397d7b18c3c58913770af5abfd1d1b95","target":"graph","created_at":"2026-05-17T23:57:26Z","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":"Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this paradigm to universal complex tasks. Among them, the low efficiency of data utilization in model-free reinforcement algorithms is of great concern. In contrast, the model-based reinforcement learning algorithms can reveal underlying dynamics in learning environments and seldom suffer the data utilization problem. To address the problem, a model-based reinforcement ","authors_text":"Jincai Huang, Qi Wang, Xingxing Liang, Yanghe Feng, Zhong Liu","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T19:25:23Z","title":"VMAV-C: A Deep Attention-based Reinforcement Learning Algorithm for Model-based Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09968","kind":"arxiv","version":1},"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":"sha256:3ec9d5e0ed73954b790ceb798f71d02bacae49a8d8f29e2b1c2bee7d5ef38e58","target":"record","created_at":"2026-05-17T23:57:26Z","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":"af5f247f2d76c10129465f243794dec83ce25d8517bea82cf1f736806f739f15","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T19:25:23Z","title_canon_sha256":"a81501325768b2b647a7c51490c996b7226e479ceba0b1d3d3862b532d816d99"},"schema_version":"1.0","source":{"id":"1812.09968","kind":"arxiv","version":1}},"canonical_sha256":"f6ff0c33e1af1870317b91ff9618d95f42628dfddf7aff72457ffd4bd7bad17b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6ff0c33e1af1870317b91ff9618d95f42628dfddf7aff72457ffd4bd7bad17b","first_computed_at":"2026-05-17T23:57:26.241472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:26.241472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2hZNvYrsUYANKS+FnY6PkGZig9BRWhqsjUQGK1hXnpncfJuWWvFTYM4C3dPsSNxrDJcf+9VVF+kLWo29e/AuAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:26.241945Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.09968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ec9d5e0ed73954b790ceb798f71d02bacae49a8d8f29e2b1c2bee7d5ef38e58","sha256:1d4d1c8c7d1a0c8bc9ede94215ef36e9397d7b18c3c58913770af5abfd1d1b95"],"state_sha256":"1d8186f00a814d2bdbb8ac0b6438546b7e49978e18bea4d32ea5f110af9041a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2dEX1/pHcmUdnBrRSUbA7mrjO6VoI97fhiuMFNwN7F++LbiZoTebKxtBHZzZ6xtzt19KDQgC8yKmlx8oF1lpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:00:05.030370Z","bundle_sha256":"e9a1c9481dfd1c480b571d1c2ba8570b61347cbadd8c27b3729ee3d1f711ed34"}}