{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UFYM3T3RYOHR46IMSYWWUAVLOM","short_pith_number":"pith:UFYM3T3R","canonical_record":{"source":{"id":"2406.05427","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-08T10:12:00Z","cross_cats_sorted":[],"title_canon_sha256":"484f33693c9566002a29375aa5b0f39f49e97a87670bee75afe73e9ea5def04f","abstract_canon_sha256":"13f5347fe631a1c21476c5a779413ecd4f220bda08e9c5442e1e26a5ec2a5a2f"},"schema_version":"1.0"},"canonical_sha256":"a170cdcf71c38f1e790c962d6a02ab73359d2cec60f931e8f34e42dffaa0f191","source":{"kind":"arxiv","id":"2406.05427","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UFYM3T3RYOHR46IMSYWWUAVLOM","target":"record","payload":{"canonical_record":{"source":{"id":"2406.05427","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-08T10:12:00Z","cross_cats_sorted":[],"title_canon_sha256":"484f33693c9566002a29375aa5b0f39f49e97a87670bee75afe73e9ea5def04f","abstract_canon_sha256":"13f5347fe631a1c21476c5a779413ecd4f220bda08e9c5442e1e26a5ec2a5a2f"},"schema_version":"1.0"},"canonical_sha256":"a170cdcf71c38f1e790c962d6a02ab73359d2cec60f931e8f34e42dffaa0f191","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:43.610764Z","signature_b64":"W1gN6o2Dmt9nZZ6tNlLqvH8rIEUx4HVu2B/ruCQB43EXMsvkasCTmnv8CBjcQ0lz/r9HJc4CjjkI3zQiwIGbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a170cdcf71c38f1e790c962d6a02ab73359d2cec60f931e8f34e42dffaa0f191","last_reissued_at":"2026-07-05T10:03:43.610272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:43.610272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.05427","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zbnfq5wUAz7NrTJiImG6Ksed5sprGtj+M3zRV4cLVNZq7yI64uN7d2s7zE2q86wVWVlo5KyUvK5E64GBZF5wDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:41:11.301875Z"},"content_sha256":"84f9cd638b08ca6ac494490bf34ad33c3d63a6fde1744287d74f35ae326846e3","schema_version":"1.0","event_id":"sha256:84f9cd638b08ca6ac494490bf34ad33c3d63a6fde1744287d74f35ae326846e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UFYM3T3RYOHR46IMSYWWUAVLOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gongwei Chen, Liqiang Nie, Michael Yu Wang, Qi Lv, Xiang Deng","submitted_at":"2024-06-08T10:12:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05427","kind":"arxiv","version":3},"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/2406.05427/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CF0nNWXgV/hfrYocfR09k3fI/pSTjgkZuOHdmFg4YFptJ12ZNIDFCBH1ZkhGX4RoEyUGL+L5hj28AoRIUb6KCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:41:11.302795Z"},"content_sha256":"baa6c3b84623e7ff6f91c9097c9cacf8ccfc9a9d104f03a8cadb3210f0d8e572","schema_version":"1.0","event_id":"sha256:baa6c3b84623e7ff6f91c9097c9cacf8ccfc9a9d104f03a8cadb3210f0d8e572"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFYM3T3RYOHR46IMSYWWUAVLOM/bundle.json","state_url":"https://pith.science/pith/UFYM3T3RYOHR46IMSYWWUAVLOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFYM3T3RYOHR46IMSYWWUAVLOM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T21:41:11Z","links":{"resolver":"https://pith.science/pith/UFYM3T3RYOHR46IMSYWWUAVLOM","bundle":"https://pith.science/pith/UFYM3T3RYOHR46IMSYWWUAVLOM/bundle.json","state":"https://pith.science/pith/UFYM3T3RYOHR46IMSYWWUAVLOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFYM3T3RYOHR46IMSYWWUAVLOM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Csn+hTmCkMkkJ2poLyzpCauznmFH1/+a0pUqmN8B4dMO4YYlfnlSKcNzfE5KJ+fzS1m5+w0N14JGfTRS1YZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:41:11.309879Z","bundle_sha256":"5c1ca1bb51842398a783976b869d9711d8314b9fbd05815e12b781f6396fd79f"}}