{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5UM2DXQWOW4YOHDCTC5WFQAD76","short_pith_number":"pith:5UM2DXQW","schema_version":"1.0","canonical_sha256":"ed19a1de1675b9871c6298bb62c003ff846db397cc48ba2dd10dd5cd0622e2ee","source":{"kind":"arxiv","id":"2310.05167","version":3},"attestation_state":"computed","paper":{"title":"Hieros: Hierarchical Imagination on Structured State Space Sequence World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Paul Mattes, Rainer Schlosser, Ralf Herbrich","submitted_at":"2023-10-08T13:52:40Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.05167","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-08T13:52:40Z","cross_cats_sorted":[],"title_canon_sha256":"b6e88e63504e3f0563a32c5e6dfb33492a33001178eea32822ca0cc0133bd808","abstract_canon_sha256":"2dab74a71f7b5b3e34cfb25c75d4e65664b70eb76147c1d98a680521f0290925"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:24.027611Z","signature_b64":"LMWTAuA7zPPjRQOMAFLp/D/QLECTGx405RMobJqEPsbMlJPBdqyQDpjZxWX4jrfP7L5bjfy+FjH2i+jlIolsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed19a1de1675b9871c6298bb62c003ff846db397cc48ba2dd10dd5cd0622e2ee","last_reissued_at":"2026-07-05T07:46:24.027142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:24.027142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hieros: Hierarchical Imagination on Structured State Space Sequence World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Paul Mattes, Rainer Schlosser, Ralf Herbrich","submitted_at":"2023-10-08T13:52:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05167","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.05167/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.05167","created_at":"2026-07-05T07:46:24.027197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05167v3","created_at":"2026-07-05T07:46:24.027197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05167","created_at":"2026-07-05T07:46:24.027197+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UM2DXQWOW4Y","created_at":"2026-07-05T07:46:24.027197+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UM2DXQWOW4YOHDC","created_at":"2026-07-05T07:46:24.027197+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UM2DXQW","created_at":"2026-07-05T07:46:24.027197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11949","citing_title":"GLAM: Global-Local Variation Awareness in Mamba-based World Model","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76","json":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76.json","graph_json":"https://pith.science/api/pith-number/5UM2DXQWOW4YOHDCTC5WFQAD76/graph.json","events_json":"https://pith.science/api/pith-number/5UM2DXQWOW4YOHDCTC5WFQAD76/events.json","paper":"https://pith.science/paper/5UM2DXQW"},"agent_actions":{"view_html":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76","download_json":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76.json","view_paper":"https://pith.science/paper/5UM2DXQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05167&json=true","fetch_graph":"https://pith.science/api/pith-number/5UM2DXQWOW4YOHDCTC5WFQAD76/graph.json","fetch_events":"https://pith.science/api/pith-number/5UM2DXQWOW4YOHDCTC5WFQAD76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76/action/storage_attestation","attest_author":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76/action/author_attestation","sign_citation":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76/action/citation_signature","submit_replication":"https://pith.science/pith/5UM2DXQWOW4YOHDCTC5WFQAD76/action/replication_record"}},"created_at":"2026-07-05T07:46:24.027197+00:00","updated_at":"2026-07-05T07:46:24.027197+00:00"}