{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KDB6VJXDW62XKFVOIDX2YRDXXT","short_pith_number":"pith:KDB6VJXD","schema_version":"1.0","canonical_sha256":"50c3eaa6e3b7b57516ae40efac4477bcee7bc8b27a8d0200262bace597769be2","source":{"kind":"arxiv","id":"2310.09615","version":1},"attestation_state":"computed","paper":{"title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Wang, Gao Huang, Jian Sun, Weipu Zhang, Yetian Yuan","submitted_at":"2023-10-14T16:42:02Z","abstract_excerpt":"Recently, model-based reinforcement learning algorithms have demonstrated remarkable efficacy in visual input environments. These approaches begin by constructing a parameterized simulation world model of the real environment through self-supervised learning. By leveraging the imagination of the world model, the agent's policy is enhanced without the constraints of sampling from the real environment. The performance of these algorithms heavily relies on the sequence modeling and generation capabilities of the world model. However, constructing a perfectly accurate model of a complex unknown en"},"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":"2310.09615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-14T16:42:02Z","cross_cats_sorted":[],"title_canon_sha256":"cd3827ebea53a010eeef6edee5a79557b1b887258eca928340e51d08733f8ba7","abstract_canon_sha256":"f92696d9444a47e26c68c367d1fd07b137a246040627b977f8b72c80ece0f8c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:51.456961Z","signature_b64":"5tZETuWKL/CwL9X7234jntbJCN4wRDBHVNduuJn0ehaqprmPFJDv6TDRa2v1YTIoJ/UnhtwNe7eNyvRE0PO/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50c3eaa6e3b7b57516ae40efac4477bcee7bc8b27a8d0200262bace597769be2","last_reissued_at":"2026-07-05T07:27:51.456481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:51.456481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Wang, Gao Huang, Jian Sun, Weipu Zhang, Yetian Yuan","submitted_at":"2023-10-14T16:42:02Z","abstract_excerpt":"Recently, model-based reinforcement learning algorithms have demonstrated remarkable efficacy in visual input environments. These approaches begin by constructing a parameterized simulation world model of the real environment through self-supervised learning. By leveraging the imagination of the world model, the agent's policy is enhanced without the constraints of sampling from the real environment. The performance of these algorithms heavily relies on the sequence modeling and generation capabilities of the world model. However, constructing a perfectly accurate model of a complex unknown en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09615","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.09615/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":"2310.09615","created_at":"2026-07-05T07:27:51.456544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09615v1","created_at":"2026-07-05T07:27:51.456544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09615","created_at":"2026-07-05T07:27:51.456544+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDB6VJXDW62X","created_at":"2026-07-05T07:27:51.456544+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDB6VJXDW62XKFVO","created_at":"2026-07-05T07:27:51.456544+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDB6VJXD","created_at":"2026-07-05T07:27:51.456544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23220","citing_title":"WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT","json":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT.json","graph_json":"https://pith.science/api/pith-number/KDB6VJXDW62XKFVOIDX2YRDXXT/graph.json","events_json":"https://pith.science/api/pith-number/KDB6VJXDW62XKFVOIDX2YRDXXT/events.json","paper":"https://pith.science/paper/KDB6VJXD"},"agent_actions":{"view_html":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT","download_json":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT.json","view_paper":"https://pith.science/paper/KDB6VJXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09615&json=true","fetch_graph":"https://pith.science/api/pith-number/KDB6VJXDW62XKFVOIDX2YRDXXT/graph.json","fetch_events":"https://pith.science/api/pith-number/KDB6VJXDW62XKFVOIDX2YRDXXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT/action/storage_attestation","attest_author":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT/action/author_attestation","sign_citation":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT/action/citation_signature","submit_replication":"https://pith.science/pith/KDB6VJXDW62XKFVOIDX2YRDXXT/action/replication_record"}},"created_at":"2026-07-05T07:27:51.456544+00:00","updated_at":"2026-07-05T07:27:51.456544+00:00"}