{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HXEKJ36EG5347KXV2GJ53YVCKI","short_pith_number":"pith:HXEKJ36E","canonical_record":{"source":{"id":"2401.05899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-11T13:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"506179f15c17300648844cd3f9c93b885139a2bacde4b80d226ffad9a625aa5a","abstract_canon_sha256":"4afd89eb194ab0b0794c39e004008f2c5f026e68065c19ef87380af89dec43fa"},"schema_version":"1.0"},"canonical_sha256":"3dc8a4efc43777cfaaf5d193dde2a2520ad2f2c9d46034febe420df209466e10","source":{"kind":"arxiv","id":"2401.05899","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05899","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05899v1","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05899","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"HXEKJ36EG534","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"HXEKJ36EG5347KXV","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"HXEKJ36E","created_at":"2026-07-05T07:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HXEKJ36EG5347KXV2GJ53YVCKI","target":"record","payload":{"canonical_record":{"source":{"id":"2401.05899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-11T13:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"506179f15c17300648844cd3f9c93b885139a2bacde4b80d226ffad9a625aa5a","abstract_canon_sha256":"4afd89eb194ab0b0794c39e004008f2c5f026e68065c19ef87380af89dec43fa"},"schema_version":"1.0"},"canonical_sha256":"3dc8a4efc43777cfaaf5d193dde2a2520ad2f2c9d46034febe420df209466e10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:37.436328Z","signature_b64":"TmSb/Rcs10rKRaJM38r+sVcpQCBG9fV6C59CGFQ7woXMYDP4zligyFHc0MRz7ZEdUMDKdE1/88ZyaM+DYzsFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dc8a4efc43777cfaaf5d193dde2a2520ad2f2c9d46034febe420df209466e10","last_reissued_at":"2026-07-05T07:32:37.435881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:37.435881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.05899","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:32:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"05CzVQU1Pke67z1ybDlFi/6Gx/p3GU40U9qHsescnmcnATfC39ytfPtzuSsx3PCedIxOzIsEjwO5tt2cpwyDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:35.350605Z"},"content_sha256":"51b694c558799c6ed2df7f5ad36280de8caac5127cc915ce97d7c1b2b2aa9279","schema_version":"1.0","event_id":"sha256:51b694c558799c6ed2df7f5ad36280de8caac5127cc915ce97d7c1b2b2aa9279"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HXEKJ36EG5347KXV2GJ53YVCKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimistic Model Rollouts for Pessimistic Offline Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dawei Feng, Ding Bo, Huaimin Wang, Kele Xu, Xudong Gong, Yiying Li, Yuanzhao Zhai, Zijian Gao","submitted_at":"2024-01-11T13:19:45Z","abstract_excerpt":"Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy optimization, usually via constructing a Pessimistic Markov Decision Process (P-MDP). However, the P-MDP discourages the policies from learning in out-of-distribution (OOD) regions beyond the support of offline datasets, which can under-utilize the generalization ability of dynamics models. In contrast, we propose constructing an Optimistic MDP (O-MDP). We initia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05899","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/2401.05899/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":"2026-07-05T07:32:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xlgh+tVGpaqIivkTZdKe6N+IMTUB64WSAUELnkM9O8TLgivFOGGLke7JRMTMpOzB5MBje1rKlbIWUzkzB+6MCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:35.351131Z"},"content_sha256":"6c1baf043d2d7db618da7c440ce9a41370cadcfe04f599b9e8067b16c3f66077","schema_version":"1.0","event_id":"sha256:6c1baf043d2d7db618da7c440ce9a41370cadcfe04f599b9e8067b16c3f66077"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXEKJ36EG5347KXV2GJ53YVCKI/bundle.json","state_url":"https://pith.science/pith/HXEKJ36EG5347KXV2GJ53YVCKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXEKJ36EG5347KXV2GJ53YVCKI/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":"2026-08-07T19:52:35Z","links":{"resolver":"https://pith.science/pith/HXEKJ36EG5347KXV2GJ53YVCKI","bundle":"https://pith.science/pith/HXEKJ36EG5347KXV2GJ53YVCKI/bundle.json","state":"https://pith.science/pith/HXEKJ36EG5347KXV2GJ53YVCKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXEKJ36EG5347KXV2GJ53YVCKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HXEKJ36EG5347KXV2GJ53YVCKI","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":"4afd89eb194ab0b0794c39e004008f2c5f026e68065c19ef87380af89dec43fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-11T13:19:45Z","title_canon_sha256":"506179f15c17300648844cd3f9c93b885139a2bacde4b80d226ffad9a625aa5a"},"schema_version":"1.0","source":{"id":"2401.05899","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05899","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05899v1","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05899","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"HXEKJ36EG534","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"HXEKJ36EG5347KXV","created_at":"2026-07-05T07:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"HXEKJ36E","created_at":"2026-07-05T07:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:6c1baf043d2d7db618da7c440ce9a41370cadcfe04f599b9e8067b16c3f66077","target":"graph","created_at":"2026-07-05T07:32:37Z","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/2401.05899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy optimization, usually via constructing a Pessimistic Markov Decision Process (P-MDP). However, the P-MDP discourages the policies from learning in out-of-distribution (OOD) regions beyond the support of offline datasets, which can under-utilize the generalization ability of dynamics models. In contrast, we propose constructing an Optimistic MDP (O-MDP). We initia","authors_text":"Dawei Feng, Ding Bo, Huaimin Wang, Kele Xu, Xudong Gong, Yiying Li, Yuanzhao Zhai, Zijian Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-11T13:19:45Z","title":"Optimistic Model Rollouts for Pessimistic Offline Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05899","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":"sha256:51b694c558799c6ed2df7f5ad36280de8caac5127cc915ce97d7c1b2b2aa9279","target":"record","created_at":"2026-07-05T07:32:37Z","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":"4afd89eb194ab0b0794c39e004008f2c5f026e68065c19ef87380af89dec43fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-11T13:19:45Z","title_canon_sha256":"506179f15c17300648844cd3f9c93b885139a2bacde4b80d226ffad9a625aa5a"},"schema_version":"1.0","source":{"id":"2401.05899","kind":"arxiv","version":1}},"canonical_sha256":"3dc8a4efc43777cfaaf5d193dde2a2520ad2f2c9d46034febe420df209466e10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dc8a4efc43777cfaaf5d193dde2a2520ad2f2c9d46034febe420df209466e10","first_computed_at":"2026-07-05T07:32:37.435881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:37.435881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TmSb/Rcs10rKRaJM38r+sVcpQCBG9fV6C59CGFQ7woXMYDP4zligyFHc0MRz7ZEdUMDKdE1/88ZyaM+DYzsFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:37.436328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.05899","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51b694c558799c6ed2df7f5ad36280de8caac5127cc915ce97d7c1b2b2aa9279","sha256:6c1baf043d2d7db618da7c440ce9a41370cadcfe04f599b9e8067b16c3f66077"],"state_sha256":"e5719c3ce930427bf9a8d26ffa227f8c532f756ee4dc77b41d63667c890bae52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5KL6mnOLGYEOK4oOZHlelqjRUkT7lgix3PZ7CYZW5IPhxnce3UBYFz9f2lh5HaiYRpsgDfxFCIMbESOeug+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:52:35.356319Z","bundle_sha256":"4ca4e8084ab2437a299ed70eb3fcd2c38c49ce865de69944ab567bb2db6355ff"}}