{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CMD7LBTF2LKYDXH5VXQ3MPZMAK","short_pith_number":"pith:CMD7LBTF","schema_version":"1.0","canonical_sha256":"1307f58665d2d581dcfdade1b63f2c02be4aa4e1a5893b94592b914ba68f8957","source":{"kind":"arxiv","id":"2410.08893","version":4},"attestation_state":"computed","paper":{"title":"Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ivana Dusparic, Ke Zhang, Vinny Cahill, Wenlong Wang, Yucheng Shi","submitted_at":"2024-10-11T15:10:40Z","abstract_excerpt":"Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often requires complex and deep architectures, which are computationally expensive and challenging to train. Within the world model, sequence models play a critical role in accurate predictions, and various architectures have been explored, each with its own challenges. Currently, recurrent neural network (RNN)-based world models struggle with vanishing gradients and capturing long-term dependencies. Transformers, on the other han"},"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":"2410.08893","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T15:10:40Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"2ffa24d1323eb9be52b2633bef5ec8deccfe720f4355e634ceb859fbca847945","abstract_canon_sha256":"69c2eb0d71a04660454d70c0ec89cb6349bde10afc847057aa0da6b749ddeeee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:52.471557Z","signature_b64":"paRZ7AtXLDz/8hOdEgu3pvYnEVAkszigxx2B4dTG5O1zBMKFlTseGMRnCrvxQyeAzGUOF3d6pUWai49osYMLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1307f58665d2d581dcfdade1b63f2c02be4aa4e1a5893b94592b914ba68f8957","last_reissued_at":"2026-07-05T11:03:52.471056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:52.471056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ivana Dusparic, Ke Zhang, Vinny Cahill, Wenlong Wang, Yucheng Shi","submitted_at":"2024-10-11T15:10:40Z","abstract_excerpt":"Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often requires complex and deep architectures, which are computationally expensive and challenging to train. Within the world model, sequence models play a critical role in accurate predictions, and various architectures have been explored, each with its own challenges. Currently, recurrent neural network (RNN)-based world models struggle with vanishing gradients and capturing long-term dependencies. Transformers, on the other han"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08893","kind":"arxiv","version":4},"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/2410.08893/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":"2410.08893","created_at":"2026-07-05T11:03:52.471110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08893v4","created_at":"2026-07-05T11:03:52.471110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08893","created_at":"2026-07-05T11:03:52.471110+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMD7LBTF2LKY","created_at":"2026-07-05T11:03:52.471110+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMD7LBTF2LKYDXH5","created_at":"2026-07-05T11:03:52.471110+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMD7LBTF","created_at":"2026-07-05T11:03:52.471110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00466","citing_title":"EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK","json":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK.json","graph_json":"https://pith.science/api/pith-number/CMD7LBTF2LKYDXH5VXQ3MPZMAK/graph.json","events_json":"https://pith.science/api/pith-number/CMD7LBTF2LKYDXH5VXQ3MPZMAK/events.json","paper":"https://pith.science/paper/CMD7LBTF"},"agent_actions":{"view_html":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK","download_json":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK.json","view_paper":"https://pith.science/paper/CMD7LBTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08893&json=true","fetch_graph":"https://pith.science/api/pith-number/CMD7LBTF2LKYDXH5VXQ3MPZMAK/graph.json","fetch_events":"https://pith.science/api/pith-number/CMD7LBTF2LKYDXH5VXQ3MPZMAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK/action/storage_attestation","attest_author":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK/action/author_attestation","sign_citation":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK/action/citation_signature","submit_replication":"https://pith.science/pith/CMD7LBTF2LKYDXH5VXQ3MPZMAK/action/replication_record"}},"created_at":"2026-07-05T11:03:52.471110+00:00","updated_at":"2026-07-05T11:03:52.471110+00:00"}