{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NQFS4CPK5DP6FRLNZR7C4JIJ2V","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":"eda7ed8786d64ea44a787d8d2e227af826f9c93833ce7cbce1ad37f986380e6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-17T16:34:01Z","title_canon_sha256":"6a5c450f8c7ddbb5c460f5d11d6b595ffb08f7ac17c6d0e9e23179c3ded06c63"},"schema_version":"1.0","source":{"id":"2210.09241","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09241","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09241v1","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09241","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_12","alias_value":"NQFS4CPK5DP6","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_16","alias_value":"NQFS4CPK5DP6FRLN","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_8","alias_value":"NQFS4CPK","created_at":"2026-07-05T05:07:20Z"}],"graph_snapshots":[{"event_id":"sha256:fc9dc122919ddd809637442f5f18dd66a0f622a5f4312d63619abc747cf8a9e1","target":"graph","created_at":"2026-07-05T05:07:20Z","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/2210.09241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly constrain the learned policy to be close to the behavior policy. The constraint applies not only to well-performing actions but also to inferior ones, which limits the performance upper bound of the learned policy. Instead of aligning the densities of two distributions, aligning the supports gives a relaxed constraint while still being able to avoid out-of-dist","authors_text":"Bingyi Kang, Gao Huang, Shuicheng Yan, Xiao Ma, Yang Yue, Zhongwen Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-17T16:34:01Z","title":"Boosting Offline Reinforcement Learning via Data Rebalancing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09241","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":"sha256:6ef5c1ad7dbbe6751120ff7906b31e8f76869fc70e56e607cde1d51ef4f43167","target":"record","created_at":"2026-07-05T05:07:20Z","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":"eda7ed8786d64ea44a787d8d2e227af826f9c93833ce7cbce1ad37f986380e6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-17T16:34:01Z","title_canon_sha256":"6a5c450f8c7ddbb5c460f5d11d6b595ffb08f7ac17c6d0e9e23179c3ded06c63"},"schema_version":"1.0","source":{"id":"2210.09241","kind":"arxiv","version":1}},"canonical_sha256":"6c0b2e09eae8dfe2c56dcc7e2e2509d573b4ad4d5fab0b115f075c0d6a99566e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c0b2e09eae8dfe2c56dcc7e2e2509d573b4ad4d5fab0b115f075c0d6a99566e","first_computed_at":"2026-07-05T05:07:20.431129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:20.431129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"piFluBrfk9vmvgucMM0Kp2wVGkz+ymeBZWgthlTsEWx74cgbjQ21tZMTOnJMXAdz1FurTB4Clx9NhNRXwiqKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:20.431562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.09241","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ef5c1ad7dbbe6751120ff7906b31e8f76869fc70e56e607cde1d51ef4f43167","sha256:fc9dc122919ddd809637442f5f18dd66a0f622a5f4312d63619abc747cf8a9e1"],"state_sha256":"bc7e14ebb961912dfb17e47b6904ee20361b393877c7f089beceb47badddc0e6"}