{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEGPDM6FEKK6MIGALUICEHHM6B","short_pith_number":"pith:YEGPDM6F","schema_version":"1.0","canonical_sha256":"c10cf1b3c52295e620c05d10221cecf06add6a3e9b6e9d500c16ad7d527b4394","source":{"kind":"arxiv","id":"2406.00079","version":1},"attestation_state":"computed","paper":{"title":"Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Yang, Hechang Chen, Jifeng Hu, Lichao Sun, Liwei Yang, Sili Huang, Tao Luo, Zhejian Yang","submitted_at":"2024-05-31T10:41:03Z","abstract_excerpt":"Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to proces"},"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":"2406.00079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T10:41:03Z","cross_cats_sorted":[],"title_canon_sha256":"24ec79880ef4172457ee420e88a300e275b8219e0447b2cb3da8c722d8eea4da","abstract_canon_sha256":"f06cde4ae38a430fc0b487387bf534d5a2d247fa42190e68261770d6f2c5e3fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:27.016619Z","signature_b64":"wBLfb1QezceALqeVYczvVBy3h6yZY6b3usoLpgJXyR8wJ4SLE3lU9bwYw6xO+0B8ne1unfZYZ5t2r4uorb+0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c10cf1b3c52295e620c05d10221cecf06add6a3e9b6e9d500c16ad7d527b4394","last_reissued_at":"2026-07-05T08:26:27.016153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:27.016153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Yang, Hechang Chen, Jifeng Hu, Lichao Sun, Liwei Yang, Sili Huang, Tao Luo, Zhejian Yang","submitted_at":"2024-05-31T10:41:03Z","abstract_excerpt":"Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to proces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00079","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/2406.00079/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":"2406.00079","created_at":"2026-07-05T08:26:27.016209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00079v1","created_at":"2026-07-05T08:26:27.016209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00079","created_at":"2026-07-05T08:26:27.016209+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEGPDM6FEKK6","created_at":"2026-07-05T08:26:27.016209+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEGPDM6FEKK6MIGA","created_at":"2026-07-05T08:26:27.016209+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEGPDM6F","created_at":"2026-07-05T08:26:27.016209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00795","citing_title":"Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B","json":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B.json","graph_json":"https://pith.science/api/pith-number/YEGPDM6FEKK6MIGALUICEHHM6B/graph.json","events_json":"https://pith.science/api/pith-number/YEGPDM6FEKK6MIGALUICEHHM6B/events.json","paper":"https://pith.science/paper/YEGPDM6F"},"agent_actions":{"view_html":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B","download_json":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B.json","view_paper":"https://pith.science/paper/YEGPDM6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00079&json=true","fetch_graph":"https://pith.science/api/pith-number/YEGPDM6FEKK6MIGALUICEHHM6B/graph.json","fetch_events":"https://pith.science/api/pith-number/YEGPDM6FEKK6MIGALUICEHHM6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B/action/storage_attestation","attest_author":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B/action/author_attestation","sign_citation":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B/action/citation_signature","submit_replication":"https://pith.science/pith/YEGPDM6FEKK6MIGALUICEHHM6B/action/replication_record"}},"created_at":"2026-07-05T08:26:27.016209+00:00","updated_at":"2026-07-05T08:26:27.016209+00:00"}