{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YZ7IIG55CZQ6GFBEH6P2UUJKK5","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":"89f250d53f4abc25708ddda9e80a2191bc4dc6ade87520bf844715690c98921d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T20:15:00Z","title_canon_sha256":"1b1c2b73dae31576855114e9ba41ef4169cc06671b0df595d3f1a9f3ac2130cf"},"schema_version":"1.0","source":{"id":"2407.14653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14653","created_at":"2026-07-05T08:46:31Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14653v1","created_at":"2026-07-05T08:46:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14653","created_at":"2026-07-05T08:46:31Z"},{"alias_kind":"pith_short_12","alias_value":"YZ7IIG55CZQ6","created_at":"2026-07-05T08:46:31Z"},{"alias_kind":"pith_short_16","alias_value":"YZ7IIG55CZQ6GFBE","created_at":"2026-07-05T08:46:31Z"},{"alias_kind":"pith_short_8","alias_value":"YZ7IIG55","created_at":"2026-07-05T08:46:31Z"}],"graph_snapshots":[{"event_id":"sha256:96b3a53de00309f63854436c0826438f5e60174679ac5c549288c67de943f2e4","target":"graph","created_at":"2026-07-05T08:46:31Z","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/2407.14653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding performance. In this paper, we introduce OASIS (cOnditionAl diStributIon Shaping), a new paradigm in offline safe RL designed to overcome these critical limitations. OASIS utilizes a conditional diffusion model to synthesize offline datasets, thus shaping the data distribution toward a beneficial target domain. Our approach makes compliance with safety constra","authors_text":"Ding Zhao, Haohong Lin, Shiqi Liu, Tingnan Zhang, Wenhao Ding, Wenhao Yu, Yihang Yao, Zhepeng Cen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T20:15:00Z","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14653","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":"sha256:40256e5d6082d58d9ffc155062f3ac8cbac7481bddf8642bb7aaafa78608b747","target":"record","created_at":"2026-07-05T08:46:31Z","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":"89f250d53f4abc25708ddda9e80a2191bc4dc6ade87520bf844715690c98921d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T20:15:00Z","title_canon_sha256":"1b1c2b73dae31576855114e9ba41ef4169cc06671b0df595d3f1a9f3ac2130cf"},"schema_version":"1.0","source":{"id":"2407.14653","kind":"arxiv","version":1}},"canonical_sha256":"c67e841bbd1661e314243f9faa512a5774cc4cc0fd0ecdecd4fb2eb7ede635d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c67e841bbd1661e314243f9faa512a5774cc4cc0fd0ecdecd4fb2eb7ede635d6","first_computed_at":"2026-07-05T08:46:31.776962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:31.776962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GrxCunRa9v9yUXpAQnIPg8ntHJ7rys/EFJ067zcOjtkrpFcZ7h77b5Bd6GBwFyDGZCGT70W9oTB9tiK73KkbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:31.777394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40256e5d6082d58d9ffc155062f3ac8cbac7481bddf8642bb7aaafa78608b747","sha256:96b3a53de00309f63854436c0826438f5e60174679ac5c549288c67de943f2e4"],"state_sha256":"1f472a4d7d66eb70e29c651a1ec87a31e2332b0c8583dfa4411e7f27b74f273d"}