{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NFE7VJOJ6TUAYF6QKUHTS6WG6C","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":"f65cb7c7d33f0c9efa51ba832e5c632436b193bcdba189b59b25147cc7fb7a02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T09:58:42Z","title_canon_sha256":"df354fd644ef8283d57ba0308bf2a652b7a75e8115f913b0c59f09dba50b73ae"},"schema_version":"1.0","source":{"id":"2402.02429","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02429","created_at":"2026-07-05T09:59:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02429v3","created_at":"2026-07-05T09:59:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02429","created_at":"2026-07-05T09:59:43Z"},{"alias_kind":"pith_short_12","alias_value":"NFE7VJOJ6TUA","created_at":"2026-07-05T09:59:43Z"},{"alias_kind":"pith_short_16","alias_value":"NFE7VJOJ6TUAYF6Q","created_at":"2026-07-05T09:59:43Z"},{"alias_kind":"pith_short_8","alias_value":"NFE7VJOJ","created_at":"2026-07-05T09:59:43Z"}],"graph_snapshots":[{"event_id":"sha256:767cd783c863ea4d67bbe076a23da3b150d5c4739dd377302d0fb9a2626b3642","target":"graph","created_at":"2026-07-05T09:59:43Z","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/2402.02429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly adapt while acquiring knowledge safely. Among which, context-based OMRL (COMRL) as a popular paradigm, aims to learn a universal policy conditioned on effective task representations. In this work, by examining several key milestones in the field of COMRL, we propose to integrate these seemingly independent methodologies into a unified framework. Most importantly, we show that the pre-existing COMRL algorithms are essentia","authors_text":"Hai Zhang, Junqiao Zhao, Lanqing Li, Pheng-Ann Heng, Shatong Zhu, Xinyu Zhang, Yang Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T09:58:42Z","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02429","kind":"arxiv","version":3},"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":"sha256:747fd09e36c55841270302f686409821978b8c5cfa7d6367c173dff8ce65b037","target":"record","created_at":"2026-07-05T09:59:43Z","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":"f65cb7c7d33f0c9efa51ba832e5c632436b193bcdba189b59b25147cc7fb7a02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T09:58:42Z","title_canon_sha256":"df354fd644ef8283d57ba0308bf2a652b7a75e8115f913b0c59f09dba50b73ae"},"schema_version":"1.0","source":{"id":"2402.02429","kind":"arxiv","version":3}},"canonical_sha256":"6949faa5c9f4e80c17d0550f397ac6f0bbc16ddbef4849a6febb4fa7a3764d28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6949faa5c9f4e80c17d0550f397ac6f0bbc16ddbef4849a6febb4fa7a3764d28","first_computed_at":"2026-07-05T09:59:43.782676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:43.782676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ozr0+CwcIRFrTv3+SexczvAAttPDrQSqw20HblMfRUVSulx1lNJz8FTWSBpZnziiKuUZze9Q5jisFq1Bq/osBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:43.783165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02429","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:747fd09e36c55841270302f686409821978b8c5cfa7d6367c173dff8ce65b037","sha256:767cd783c863ea4d67bbe076a23da3b150d5c4739dd377302d0fb9a2626b3642"],"state_sha256":"57657bb6cd9c2503dc991994e6e840924cb01e92f173d50a70c1a4d47637a2cf"}