{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:THFVHA74OP2H6AM5CMY3JKQRKL","short_pith_number":"pith:THFVHA74","canonical_record":{"source":{"id":"2505.13144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T14:11:14Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"7bda7e1ed883dbbae7a481d645d92beeb05b299bfb9b27a378caa892f45f513e","abstract_canon_sha256":"d32689b9d00c64df4a209f7586d84fb842039533400846747f99742bf9cc14e8"},"schema_version":"1.0"},"canonical_sha256":"99cb5383fc73f47f019d1331b4aa1152db9f38c8e1f661d61b33f5e5c3a233d1","source":{"kind":"arxiv","id":"2505.13144","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13144","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13144v1","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13144","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"THFVHA74OP2H","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"THFVHA74OP2H6AM5","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"THFVHA74","created_at":"2026-07-05T11:05:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:THFVHA74OP2H6AM5CMY3JKQRKL","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T14:11:14Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"7bda7e1ed883dbbae7a481d645d92beeb05b299bfb9b27a378caa892f45f513e","abstract_canon_sha256":"d32689b9d00c64df4a209f7586d84fb842039533400846747f99742bf9cc14e8"},"schema_version":"1.0"},"canonical_sha256":"99cb5383fc73f47f019d1331b4aa1152db9f38c8e1f661d61b33f5e5c3a233d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:25.785108Z","signature_b64":"X0mHWmLYLxKhFyifBw7+zxg6ESiuZX3Q8S7f/1p6W1Ssk+XXJvzzFnRmnUpIw4BycRYnN9ob57oR/ZZG1kbPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99cb5383fc73f47f019d1331b4aa1152db9f38c8e1f661d61b33f5e5c3a233d1","last_reissued_at":"2026-07-05T11:05:25.784617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:25.784617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13144","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":"2026-07-05T11:05:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E0icv/f+s8ZC3TS3iqftdiP+pGo0K8+VN1VIvhSB72aeG608l+N1aA+teaBcjRoKMA/8fokR5XjQixxt7Tp3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:17:09.950010Z"},"content_sha256":"11fe151d5b30d15cc9a6cfa74f665ba44e7d26de950bc9e8b3128652753d47dc","schema_version":"1.0","event_id":"sha256:11fe151d5b30d15cc9a6cfa74f665ba44e7d26de950bc9e8b3128652753d47dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:THFVHA74OP2H6AM5CMY3JKQRKL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Dongsu Lee, Minhae Kwon","submitted_at":"2025-05-19T14:11:14Z","abstract_excerpt":"The goal of offline reinforcement learning (RL) is to extract a high-performance policy from the fixed datasets, minimizing performance degradation due to out-of-distribution (OOD) samples. Offline model-based RL (MBRL) is a promising approach that ameliorates OOD issues by enriching state-action transitions with augmentations synthesized via a learned dynamics model. Unfortunately, seminal offline MBRL methods often struggle in sparse-reward, long-horizon tasks. In this work, we introduce a novel MBRL framework, dubbed Temporal Distance-Aware Transition Augmentation (TempDATA), that generates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13144","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/2505.13144/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":"2026-07-05T11:05:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLZVV6WkKj0puCkmLFCToB3ReAFrsxKiN1N2yC/1Awq/Dty5uUoMGnpdeq0FVWPwCwZRkNenPB4h43rCLENcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:17:09.950527Z"},"content_sha256":"63245721d68371c85becd7628f95e4ce19cfa2b830c8fdff49a98f6cda8a60e9","schema_version":"1.0","event_id":"sha256:63245721d68371c85becd7628f95e4ce19cfa2b830c8fdff49a98f6cda8a60e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THFVHA74OP2H6AM5CMY3JKQRKL/bundle.json","state_url":"https://pith.science/pith/THFVHA74OP2H6AM5CMY3JKQRKL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THFVHA74OP2H6AM5CMY3JKQRKL/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":"2026-08-18T13:17:09Z","links":{"resolver":"https://pith.science/pith/THFVHA74OP2H6AM5CMY3JKQRKL","bundle":"https://pith.science/pith/THFVHA74OP2H6AM5CMY3JKQRKL/bundle.json","state":"https://pith.science/pith/THFVHA74OP2H6AM5CMY3JKQRKL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THFVHA74OP2H6AM5CMY3JKQRKL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:THFVHA74OP2H6AM5CMY3JKQRKL","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":"d32689b9d00c64df4a209f7586d84fb842039533400846747f99742bf9cc14e8","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T14:11:14Z","title_canon_sha256":"7bda7e1ed883dbbae7a481d645d92beeb05b299bfb9b27a378caa892f45f513e"},"schema_version":"1.0","source":{"id":"2505.13144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13144","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13144v1","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13144","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"THFVHA74OP2H","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"THFVHA74OP2H6AM5","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"THFVHA74","created_at":"2026-07-05T11:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:63245721d68371c85becd7628f95e4ce19cfa2b830c8fdff49a98f6cda8a60e9","target":"graph","created_at":"2026-07-05T11:05:25Z","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/2505.13144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of offline reinforcement learning (RL) is to extract a high-performance policy from the fixed datasets, minimizing performance degradation due to out-of-distribution (OOD) samples. Offline model-based RL (MBRL) is a promising approach that ameliorates OOD issues by enriching state-action transitions with augmentations synthesized via a learned dynamics model. Unfortunately, seminal offline MBRL methods often struggle in sparse-reward, long-horizon tasks. In this work, we introduce a novel MBRL framework, dubbed Temporal Distance-Aware Transition Augmentation (TempDATA), that generates","authors_text":"Dongsu Lee, Minhae Kwon","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T14:11:14Z","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13144","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":"sha256:11fe151d5b30d15cc9a6cfa74f665ba44e7d26de950bc9e8b3128652753d47dc","target":"record","created_at":"2026-07-05T11:05:25Z","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":"d32689b9d00c64df4a209f7586d84fb842039533400846747f99742bf9cc14e8","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T14:11:14Z","title_canon_sha256":"7bda7e1ed883dbbae7a481d645d92beeb05b299bfb9b27a378caa892f45f513e"},"schema_version":"1.0","source":{"id":"2505.13144","kind":"arxiv","version":1}},"canonical_sha256":"99cb5383fc73f47f019d1331b4aa1152db9f38c8e1f661d61b33f5e5c3a233d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99cb5383fc73f47f019d1331b4aa1152db9f38c8e1f661d61b33f5e5c3a233d1","first_computed_at":"2026-07-05T11:05:25.784617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:25.784617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X0mHWmLYLxKhFyifBw7+zxg6ESiuZX3Q8S7f/1p6W1Ssk+XXJvzzFnRmnUpIw4BycRYnN9ob57oR/ZZG1kbPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:25.785108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11fe151d5b30d15cc9a6cfa74f665ba44e7d26de950bc9e8b3128652753d47dc","sha256:63245721d68371c85becd7628f95e4ce19cfa2b830c8fdff49a98f6cda8a60e9"],"state_sha256":"734f94a7c822157c21cf77e3a3be2b253cb419886b22d85b2a1d84d3d85fb0ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQxk1/7fOGLMpdQ2qT23bMwR2MElEyaI01H56AEt/7cHZUF3iF17yInMySHnTRIx1xILgHp9EdszRPdgr7qGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T13:17:09.954957Z","bundle_sha256":"ec13f5a18edbda88b0cc344acba0d022d0589c8e53a6d3fd3f20c2547aa7eee4"}}