{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5UM2DXQWOW4YOHDCTC5WFQAD76","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":"2dab74a71f7b5b3e34cfb25c75d4e65664b70eb76147c1d98a680521f0290925","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-08T13:52:40Z","title_canon_sha256":"b6e88e63504e3f0563a32c5e6dfb33492a33001178eea32822ca0cc0133bd808"},"schema_version":"1.0","source":{"id":"2310.05167","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05167","created_at":"2026-07-05T07:46:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05167v3","created_at":"2026-07-05T07:46:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05167","created_at":"2026-07-05T07:46:24Z"},{"alias_kind":"pith_short_12","alias_value":"5UM2DXQWOW4Y","created_at":"2026-07-05T07:46:24Z"},{"alias_kind":"pith_short_16","alias_value":"5UM2DXQWOW4YOHDC","created_at":"2026-07-05T07:46:24Z"},{"alias_kind":"pith_short_8","alias_value":"5UM2DXQW","created_at":"2026-07-05T07:46:24Z"}],"graph_snapshots":[{"event_id":"sha256:2a3e77cfeaba81d42021d74dfd050a01dce8cd79b3d5f4575cbdace606f5a136","target":"graph","created_at":"2026-07-05T07:46:24Z","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/2310.05167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the biggest challenges to modern deep reinforcement learning (DRL) algorithms is sample efficiency. Many approaches learn a world model in order to train an agent entirely in imagination, eliminating the need for direct environment interaction during training. However, these methods often suffer from either a lack of imagination accuracy, exploration capabilities, or runtime efficiency. We propose Hieros, a hierarchical policy that learns time abstracted world representations and imagines trajectories at multiple time scales in latent space. Hieros uses an S5 layer-based world model, wh","authors_text":"Paul Mattes, Rainer Schlosser, Ralf Herbrich","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-08T13:52:40Z","title":"Hieros: Hierarchical Imagination on Structured State Space Sequence World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05167","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":"sha256:6952837d2a0219370de588e8ea46bc0dec82ca436b3cc694c062cdc195c02ee2","target":"record","created_at":"2026-07-05T07:46:24Z","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":"2dab74a71f7b5b3e34cfb25c75d4e65664b70eb76147c1d98a680521f0290925","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-08T13:52:40Z","title_canon_sha256":"b6e88e63504e3f0563a32c5e6dfb33492a33001178eea32822ca0cc0133bd808"},"schema_version":"1.0","source":{"id":"2310.05167","kind":"arxiv","version":3}},"canonical_sha256":"ed19a1de1675b9871c6298bb62c003ff846db397cc48ba2dd10dd5cd0622e2ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed19a1de1675b9871c6298bb62c003ff846db397cc48ba2dd10dd5cd0622e2ee","first_computed_at":"2026-07-05T07:46:24.027142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:24.027142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LMWTAuA7zPPjRQOMAFLp/D/QLECTGx405RMobJqEPsbMlJPBdqyQDpjZxWX4jrfP7L5bjfy+FjH2i+jlIolsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:24.027611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05167","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6952837d2a0219370de588e8ea46bc0dec82ca436b3cc694c062cdc195c02ee2","sha256:2a3e77cfeaba81d42021d74dfd050a01dce8cd79b3d5f4575cbdace606f5a136"],"state_sha256":"9a51bdef17b9b9bc7a9c75082a177d39086601c829ab239337d47e6a28d9b6a4"}