{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OJJKBIC4CA2YKHUHYPLD242YFV","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":"3885076d5d375e70ceebe4afff9d7c4a90a93b53ca1a7e9101f6d875d5c7b65d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T14:42:25Z","title_canon_sha256":"3a6aa4984e6bfb8b742a382a71fb2502c329c9e9a886c8939179882301ceb21b"},"schema_version":"1.0","source":{"id":"2403.00564","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00564","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00564v2","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00564","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"OJJKBIC4CA2Y","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"OJJKBIC4CA2YKHUH","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"OJJKBIC4","created_at":"2026-07-05T09:06:03Z"}],"graph_snapshots":[{"event_id":"sha256:4821dc377b1663f44fadb39cc6fb726bf650e7035a31747801a0f1a85c45819c","target":"graph","created_at":"2026-07-05T09:06:03Z","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/2403.00564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency remains a crucial challenge in applying Reinforcement Learning (RL) to real-world tasks. While recent algorithms have made significant strides in improving sample efficiency, none have achieved consistently superior performance across diverse domains. In this paper, we introduce EfficientZero V2, a general framework designed for sample-efficient RL algorithms. We have expanded the performance of EfficientZero to multiple domains, encompassing both continuous and discrete actions, as well as visual and low-dimensional inputs. With a series of improvements we propose, Efficient","authors_text":"Jiacheng You, Shaohuai Liu, Shengjie Wang, Weirui Ye, Yang Gao","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T14:42:25Z","title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00564","kind":"arxiv","version":2},"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":"sha256:45515d5f2319a4ea87461ed7b5f340b4e8924d6cf7691f252017beda3bc1a0a2","target":"record","created_at":"2026-07-05T09:06:03Z","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":"3885076d5d375e70ceebe4afff9d7c4a90a93b53ca1a7e9101f6d875d5c7b65d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T14:42:25Z","title_canon_sha256":"3a6aa4984e6bfb8b742a382a71fb2502c329c9e9a886c8939179882301ceb21b"},"schema_version":"1.0","source":{"id":"2403.00564","kind":"arxiv","version":2}},"canonical_sha256":"7252a0a05c1035851e87c3d63d73582d7aea465d7a12c79301aa1b29f0322665","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7252a0a05c1035851e87c3d63d73582d7aea465d7a12c79301aa1b29f0322665","first_computed_at":"2026-07-05T09:06:03.358095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:03.358095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/wpQs1qfMJyi55Y7WW+OiNMwdyizEqtvW4lLs8FOCOEdNns8gReXvIh6xNNIV7wpHyLY7jPQ+6SRTQIefKAbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:03.358543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00564","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45515d5f2319a4ea87461ed7b5f340b4e8924d6cf7691f252017beda3bc1a0a2","sha256:4821dc377b1663f44fadb39cc6fb726bf650e7035a31747801a0f1a85c45819c"],"state_sha256":"0cbd8ad103b29f28ff536dc4ce6a7a405320f518a71d87cd088aff869621709f"}