{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2VMMODIUXYVB6KEYKIKCTUC6B5","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":"47353f89eb18bde598ef7efc54d5af1cbcd6b26bd22373586be57314d58cac95","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-16T21:17:03Z","title_canon_sha256":"0e406ac236a0a1a2110837eabbcecfc811b9b05558e0ed27c22537b8aa0c1796"},"schema_version":"1.0","source":{"id":"2203.08949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08949","created_at":"2026-07-05T04:06:05Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08949v1","created_at":"2026-07-05T04:06:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08949","created_at":"2026-07-05T04:06:05Z"},{"alias_kind":"pith_short_12","alias_value":"2VMMODIUXYVB","created_at":"2026-07-05T04:06:05Z"},{"alias_kind":"pith_short_16","alias_value":"2VMMODIUXYVB6KEY","created_at":"2026-07-05T04:06:05Z"},{"alias_kind":"pith_short_8","alias_value":"2VMMODIU","created_at":"2026-07-05T04:06:05Z"}],"graph_snapshots":[{"event_id":"sha256:3ccb2b903b3acddd54342cbb4d27185496b95b4b40998b1b4574d74c9724a7a3","target":"graph","created_at":"2026-07-05T04:06:05Z","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/2203.08949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic applications for which online data collection based on trial-and-error is costly and potentially unsafe. In practice, offline datasets are often heterogeneous, i.e., collected in a variety of scenarios, such as data from several human demonstrators or from policies that act with different purposes. Unfortunately, such datasets can exacerbate the distribution","authors_text":"Ali Ghadirzadeh, Bin Liang, Chelsea Finn, Chongjie Zhang, Jianhao Wang, Tianhe Yu, Wenzhe Li, Xi Chen, Yuan Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-16T21:17:03Z","title":"Latent-Variable Advantage-Weighted Policy Optimization for Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08949","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":"sha256:813abd1ce2676d518c79a58b013a7a4ecb76d568ec67ce49f6893dd34ef58911","target":"record","created_at":"2026-07-05T04:06:05Z","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":"47353f89eb18bde598ef7efc54d5af1cbcd6b26bd22373586be57314d58cac95","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-16T21:17:03Z","title_canon_sha256":"0e406ac236a0a1a2110837eabbcecfc811b9b05558e0ed27c22537b8aa0c1796"},"schema_version":"1.0","source":{"id":"2203.08949","kind":"arxiv","version":1}},"canonical_sha256":"d558c70d14be2a1f2898521429d05e0f78a155540cb5ae91a67f27ab517b890e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d558c70d14be2a1f2898521429d05e0f78a155540cb5ae91a67f27ab517b890e","first_computed_at":"2026-07-05T04:06:05.185627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:05.185627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aOtcseY3cMpW0mWqjeNBD2x5aBTI/9aRqhy0k+99Pv4NKY1Op1HvHObdL2FfIqr5HcIx2LJfwyT+mq2MMdfQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:05.186089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:813abd1ce2676d518c79a58b013a7a4ecb76d568ec67ce49f6893dd34ef58911","sha256:3ccb2b903b3acddd54342cbb4d27185496b95b4b40998b1b4574d74c9724a7a3"],"state_sha256":"4c95aa9beee9e38f67851ce6d7e15ce46bf2c9fd8e4d5499181b95672ee89908"}