{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MADJDFNLGOHBNAGAGESRP246R5","short_pith_number":"pith:MADJDFNL","canonical_record":{"source":{"id":"2502.06491","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T14:08:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba1f5720374354925cf44a8599e6d8fb7f6258db5a8e6c9a63592edf8275577f","abstract_canon_sha256":"575f4fe549810364dccfa29c63b87ed40590d0521b18f7200e36b0a8a3a7119b"},"schema_version":"1.0"},"canonical_sha256":"60069195ab338e1680c0312517eb9e8f58a9034a5752082bb70a4ed97e2b48f3","source":{"kind":"arxiv","id":"2502.06491","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06491","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06491v2","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06491","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"MADJDFNLGOHB","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"MADJDFNLGOHBNAGA","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"MADJDFNL","created_at":"2026-07-05T10:57:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MADJDFNLGOHBNAGAGESRP246R5","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06491","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T14:08:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba1f5720374354925cf44a8599e6d8fb7f6258db5a8e6c9a63592edf8275577f","abstract_canon_sha256":"575f4fe549810364dccfa29c63b87ed40590d0521b18f7200e36b0a8a3a7119b"},"schema_version":"1.0"},"canonical_sha256":"60069195ab338e1680c0312517eb9e8f58a9034a5752082bb70a4ed97e2b48f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:55.722309Z","signature_b64":"DjCy1Z+YUbI77sB6mpfAADTrXpMxuHZg4JO9CM1Q6SdrcrNxOExYvDAz6eikWrOsQV0yXo4IxVGsmFfMYWIYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60069195ab338e1680c0312517eb9e8f58a9034a5752082bb70a4ed97e2b48f3","last_reissued_at":"2026-07-05T10:57:55.721783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:55.721783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06491","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFdfiEqk4yBYL2hqTDUbwcU5DCPHqP8GTr4K9YrCGF5gJbNOcyq+87Y75X4MDQrpcxzpNXxFuE4H/hb1o7cAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:50:37.606843Z"},"content_sha256":"4b002576e0fb174fc19f4c5935c0f32ded449c226b936388181f75331ebe01dd","schema_version":"1.0","event_id":"sha256:4b002576e0fb174fc19f4c5935c0f32ded449c226b936388181f75331ebe01dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MADJDFNLGOHBNAGAGESRP246R5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Based Offline Reinforcement Learning with Reliability-Guaranteed Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shenghong He","submitted_at":"2025-02-10T14:08:55Z","abstract_excerpt":"Model-based offline reinforcement learning (MORL) aims to learn a policy by exploiting a dynamics model derived from an existing dataset. Applying conservative quantification to the dynamics model, most existing works on MORL generate trajectories that approximate the real data distribution to facilitate policy learning by using current information (e.g., the state and action at time step $t$). However, these works neglect the impact of historical information on environmental dynamics, leading to the generation of unreliable trajectories that may not align with the real data distribution. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06491","kind":"arxiv","version":2},"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/2502.06491/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":"2026-07-05T10:57:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DrJC7iSE8SUZObkLtCXNY6bFyjeJIYqdcibrAxspYq0P9ESjNKECmeELcboDWQqyigcP3ALSRN44V/H/llilCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:50:37.607424Z"},"content_sha256":"a2e5656ebc37e985480a49542eda6fefbd10fbac8da406f2db52d16ae5e3c41c","schema_version":"1.0","event_id":"sha256:a2e5656ebc37e985480a49542eda6fefbd10fbac8da406f2db52d16ae5e3c41c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MADJDFNLGOHBNAGAGESRP246R5/bundle.json","state_url":"https://pith.science/pith/MADJDFNLGOHBNAGAGESRP246R5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MADJDFNLGOHBNAGAGESRP246R5/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":"2026-08-10T05:50:37Z","links":{"resolver":"https://pith.science/pith/MADJDFNLGOHBNAGAGESRP246R5","bundle":"https://pith.science/pith/MADJDFNLGOHBNAGAGESRP246R5/bundle.json","state":"https://pith.science/pith/MADJDFNLGOHBNAGAGESRP246R5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MADJDFNLGOHBNAGAGESRP246R5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MADJDFNLGOHBNAGAGESRP246R5","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":"575f4fe549810364dccfa29c63b87ed40590d0521b18f7200e36b0a8a3a7119b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T14:08:55Z","title_canon_sha256":"ba1f5720374354925cf44a8599e6d8fb7f6258db5a8e6c9a63592edf8275577f"},"schema_version":"1.0","source":{"id":"2502.06491","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06491","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06491v2","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06491","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"MADJDFNLGOHB","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"MADJDFNLGOHBNAGA","created_at":"2026-07-05T10:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"MADJDFNL","created_at":"2026-07-05T10:57:55Z"}],"graph_snapshots":[{"event_id":"sha256:a2e5656ebc37e985480a49542eda6fefbd10fbac8da406f2db52d16ae5e3c41c","target":"graph","created_at":"2026-07-05T10:57:55Z","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/2502.06491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based offline reinforcement learning (MORL) aims to learn a policy by exploiting a dynamics model derived from an existing dataset. Applying conservative quantification to the dynamics model, most existing works on MORL generate trajectories that approximate the real data distribution to facilitate policy learning by using current information (e.g., the state and action at time step $t$). However, these works neglect the impact of historical information on environmental dynamics, leading to the generation of unreliable trajectories that may not align with the real data distribution. In t","authors_text":"Shenghong He","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T14:08:55Z","title":"Model-Based Offline Reinforcement Learning with Reliability-Guaranteed Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06491","kind":"arxiv","version":2},"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":"sha256:4b002576e0fb174fc19f4c5935c0f32ded449c226b936388181f75331ebe01dd","target":"record","created_at":"2026-07-05T10:57:55Z","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":"575f4fe549810364dccfa29c63b87ed40590d0521b18f7200e36b0a8a3a7119b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T14:08:55Z","title_canon_sha256":"ba1f5720374354925cf44a8599e6d8fb7f6258db5a8e6c9a63592edf8275577f"},"schema_version":"1.0","source":{"id":"2502.06491","kind":"arxiv","version":2}},"canonical_sha256":"60069195ab338e1680c0312517eb9e8f58a9034a5752082bb70a4ed97e2b48f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60069195ab338e1680c0312517eb9e8f58a9034a5752082bb70a4ed97e2b48f3","first_computed_at":"2026-07-05T10:57:55.721783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:55.721783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DjCy1Z+YUbI77sB6mpfAADTrXpMxuHZg4JO9CM1Q6SdrcrNxOExYvDAz6eikWrOsQV0yXo4IxVGsmFfMYWIYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:55.722309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06491","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b002576e0fb174fc19f4c5935c0f32ded449c226b936388181f75331ebe01dd","sha256:a2e5656ebc37e985480a49542eda6fefbd10fbac8da406f2db52d16ae5e3c41c"],"state_sha256":"0aaa6dbb6b3b054f8dcc24d2b4ce683d43705007535d70361bd2f0b92dfeafd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2HjVKGkoEa/0+rrfkEmsTZVJu9GWLu22hLiYjhEhR3vcUwvgLoevAi6tRZA0OqWBTqRNkHbvE3SjcIaGnh+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:50:37.612867Z","bundle_sha256":"a8d633edac2cfc52ac1d5bb4ee0f80b8f97542891b784692d7dba1a5d1cb8e66"}}