{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UFYM3T3RYOHR46IMSYWWUAVLOM","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":"13f5347fe631a1c21476c5a779413ecd4f220bda08e9c5442e1e26a5ec2a5a2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-08T10:12:00Z","title_canon_sha256":"484f33693c9566002a29375aa5b0f39f49e97a87670bee75afe73e9ea5def04f"},"schema_version":"1.0","source":{"id":"2406.05427","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05427","created_at":"2026-07-05T10:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05427v3","created_at":"2026-07-05T10:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05427","created_at":"2026-07-05T10:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"UFYM3T3RYOHR","created_at":"2026-07-05T10:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"UFYM3T3RYOHR46IM","created_at":"2026-07-05T10:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"UFYM3T3R","created_at":"2026-07-05T10:03:43Z"}],"graph_snapshots":[{"event_id":"sha256:baa6c3b84623e7ff6f91c9097c9cacf8ccfc9a9d104f03a8cadb3210f0d8e572","target":"graph","created_at":"2026-07-05T10:03:43Z","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/2406.05427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is struggle to handle out-of-distribution states and actions. Existing work attempts to address this issue by data augmentation with the learned policy or adding extra constraints with the value-based RL algorithm. However, these studies still fail to overcome the following challenges: (1) insufficiently utilizing the historical temporal information among inter-steps, (2) overlooking the local intrastep relationships among re","authors_text":"Gongwei Chen, Liqiang Nie, Michael Yu Wang, Qi Lv, Xiang Deng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-08T10:12:00Z","title":"Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05427","kind":"arxiv","version":3},"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":"sha256:84f9cd638b08ca6ac494490bf34ad33c3d63a6fde1744287d74f35ae326846e3","target":"record","created_at":"2026-07-05T10:03:43Z","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":"13f5347fe631a1c21476c5a779413ecd4f220bda08e9c5442e1e26a5ec2a5a2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-08T10:12:00Z","title_canon_sha256":"484f33693c9566002a29375aa5b0f39f49e97a87670bee75afe73e9ea5def04f"},"schema_version":"1.0","source":{"id":"2406.05427","kind":"arxiv","version":3}},"canonical_sha256":"a170cdcf71c38f1e790c962d6a02ab73359d2cec60f931e8f34e42dffaa0f191","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a170cdcf71c38f1e790c962d6a02ab73359d2cec60f931e8f34e42dffaa0f191","first_computed_at":"2026-07-05T10:03:43.610272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:43.610272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W1gN6o2Dmt9nZZ6tNlLqvH8rIEUx4HVu2B/ruCQB43EXMsvkasCTmnv8CBjcQ0lz/r9HJc4CjjkI3zQiwIGbCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:43.610764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05427","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84f9cd638b08ca6ac494490bf34ad33c3d63a6fde1744287d74f35ae326846e3","sha256:baa6c3b84623e7ff6f91c9097c9cacf8ccfc9a9d104f03a8cadb3210f0d8e572"],"state_sha256":"8b3fa62499dc29a3be378f6dd6e242ae45410eaa14ae43309403a740cc6e2060"}