{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YEGPDM6FEKK6MIGALUICEHHM6B","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":"f06cde4ae38a430fc0b487387bf534d5a2d247fa42190e68261770d6f2c5e3fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T10:41:03Z","title_canon_sha256":"24ec79880ef4172457ee420e88a300e275b8219e0447b2cb3da8c722d8eea4da"},"schema_version":"1.0","source":{"id":"2406.00079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00079","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00079v1","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00079","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_12","alias_value":"YEGPDM6FEKK6","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_16","alias_value":"YEGPDM6FEKK6MIGA","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_8","alias_value":"YEGPDM6F","created_at":"2026-07-05T08:26:27Z"}],"graph_snapshots":[{"event_id":"sha256:7316317b09db9ff4629c276b29c0f50c09d03501e27f6d9f968ed748ac7e978f","target":"graph","created_at":"2026-07-05T08:26:27Z","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/2406.00079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Yang, Hechang Chen, Jifeng Hu, Lichao Sun, Liwei Yang, Sili Huang, Tao Luo, Zhejian Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T10:41:03Z","title":"Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00079","kind":"arxiv","version":1},"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":"sha256:1cbccda7bffdef43481502897f9a641538bedde413724dde375edfeee9c7748c","target":"record","created_at":"2026-07-05T08:26:27Z","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":"f06cde4ae38a430fc0b487387bf534d5a2d247fa42190e68261770d6f2c5e3fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T10:41:03Z","title_canon_sha256":"24ec79880ef4172457ee420e88a300e275b8219e0447b2cb3da8c722d8eea4da"},"schema_version":"1.0","source":{"id":"2406.00079","kind":"arxiv","version":1}},"canonical_sha256":"c10cf1b3c52295e620c05d10221cecf06add6a3e9b6e9d500c16ad7d527b4394","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c10cf1b3c52295e620c05d10221cecf06add6a3e9b6e9d500c16ad7d527b4394","first_computed_at":"2026-07-05T08:26:27.016153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:27.016153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wBLfb1QezceALqeVYczvVBy3h6yZY6b3usoLpgJXyR8wJ4SLE3lU9bwYw6xO+0B8ne1unfZYZ5t2r4uorb+0Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:27.016619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cbccda7bffdef43481502897f9a641538bedde413724dde375edfeee9c7748c","sha256:7316317b09db9ff4629c276b29c0f50c09d03501e27f6d9f968ed748ac7e978f"],"state_sha256":"53771895fb3715be9d96f9b0d7e5d8ec1cc1a77efaaaa6823ff41b3713e2c1ac"}