{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FNZM4IX3E6YBUUHE67SSDHKK52","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":"9d0ec5bde469854a8418ede8c75f69e25340a402731763a49355d05d2bfc39ff","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T06:47:36Z","title_canon_sha256":"2c34e2b5d7fa8bd2c13319cacc6b9b64877cd31b99c483f8efd3b89c56821eeb"},"schema_version":"1.0","source":{"id":"2505.19002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19002","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19002v1","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19002","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"FNZM4IX3E6YB","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_16","alias_value":"FNZM4IX3E6YBUUHE","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_8","alias_value":"FNZM4IX3","created_at":"2026-07-05T11:09:23Z"}],"graph_snapshots":[{"event_id":"sha256:01dfd1c4555af8aeaf926f8bcc413165dc423fbde0fa03c03bab5787b0e85c80","target":"graph","created_at":"2026-07-05T11:09:23Z","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/2505.19002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected data. However, it faces challenges of distributional shift, where the learned policy may encounter unseen scenarios not covered in the offline data. Additionally, numerous applications suffer from a scarcity of labeled reward data. Relying on labeled data alone often leads to a narrow state-action distribution, further amplifying the distributional shift, and resulting in suboptimal policy learning. To address these issues, we first recognize that the volume of unlabeled data is typically substantially large","authors_text":"Chengchun Shi, Gholamali Aminian, Jiaang Yao, Jin Zhu, Lexin Li, Omar Rivasplata, Simon Little, Xin Zhou","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T06:47:36Z","title":"Semi-pessimistic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19002","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":"sha256:0fca4b399c9237877cb2a0129ba574e86fa4892ce42719b91dd2c21905cfdc38","target":"record","created_at":"2026-07-05T11:09:23Z","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":"9d0ec5bde469854a8418ede8c75f69e25340a402731763a49355d05d2bfc39ff","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T06:47:36Z","title_canon_sha256":"2c34e2b5d7fa8bd2c13319cacc6b9b64877cd31b99c483f8efd3b89c56821eeb"},"schema_version":"1.0","source":{"id":"2505.19002","kind":"arxiv","version":1}},"canonical_sha256":"2b72ce22fb27b01a50e4f7e5219d4aee879e51a4d5da0b8480012623bff560a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b72ce22fb27b01a50e4f7e5219d4aee879e51a4d5da0b8480012623bff560a6","first_computed_at":"2026-07-05T11:09:23.370347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:23.370347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+7eLWmFA2/piHt00wPwMCD1qSRlo6PDBw1s/iKbvBJztzPrraIudfzpgU3x9v2EAJIyhmlGDVV/a13MiqvCdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:23.370923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fca4b399c9237877cb2a0129ba574e86fa4892ce42719b91dd2c21905cfdc38","sha256:01dfd1c4555af8aeaf926f8bcc413165dc423fbde0fa03c03bab5787b0e85c80"],"state_sha256":"fc1c198865ebc2fe3a0140e3923aa1111832f66087663d636cbee2ba7f43f178"}