{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GKHIHSRDN3H7W6IGMKGD6SS7KG","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":"e8686859d7ac6deb3e2a37a8ae32cfbb8ffb8c88401392cce5e123775cf4f2a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T18:04:43Z","title_canon_sha256":"38f50e2a739013331af140e573ec0b3b9d8d5a8f11ca519f203a347e76d780d8"},"schema_version":"1.0","source":{"id":"2206.00695","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00695","created_at":"2026-07-05T04:28:32Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00695v1","created_at":"2026-07-05T04:28:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00695","created_at":"2026-07-05T04:28:32Z"},{"alias_kind":"pith_short_12","alias_value":"GKHIHSRDN3H7","created_at":"2026-07-05T04:28:32Z"},{"alias_kind":"pith_short_16","alias_value":"GKHIHSRDN3H7W6IG","created_at":"2026-07-05T04:28:32Z"},{"alias_kind":"pith_short_8","alias_value":"GKHIHSRD","created_at":"2026-07-05T04:28:32Z"}],"graph_snapshots":[{"event_id":"sha256:d968a1f778a47b9714f41a9b27ac191fd887592a0a6846b7515d2931be75bce7","target":"graph","created_at":"2026-07-05T04:28:32Z","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/2206.00695/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce an offline reinforcement learning (RL) algorithm that explicitly clones a behavior policy to constrain value learning. In offline RL, it is often important to prevent a policy from selecting unobserved actions, since the consequence of these actions cannot be presumed without additional information about the environment. One straightforward way to implement such a constraint is to explicitly model a given data distribution via behavior cloning and directly force a policy not to select uncertain actions. However, many offline RL methods instantiate the constraint indirectly -- for ","authors_text":"Scott Niekum, Wonjoon Goo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T18:04:43Z","title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00695","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":"sha256:14b1968b852ad762a92ae732f14ac2975fe0688f5a7436813be856fb93adbb73","target":"record","created_at":"2026-07-05T04:28:32Z","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":"e8686859d7ac6deb3e2a37a8ae32cfbb8ffb8c88401392cce5e123775cf4f2a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T18:04:43Z","title_canon_sha256":"38f50e2a739013331af140e573ec0b3b9d8d5a8f11ca519f203a347e76d780d8"},"schema_version":"1.0","source":{"id":"2206.00695","kind":"arxiv","version":1}},"canonical_sha256":"328e83ca236ecffb7906628c3f4a5f51a5030a0e388abc4eedbd9b0b7843f49c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"328e83ca236ecffb7906628c3f4a5f51a5030a0e388abc4eedbd9b0b7843f49c","first_computed_at":"2026-07-05T04:28:32.691352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:32.691352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jehjmS3rPmRs/Qo6pnmH2TWpqRL+9Zo07kjhgvGKn9jXK6zcGU6PKa0HQsZMiOvkX9SFgOROZDjhYYFBqo/MAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:32.691838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00695","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14b1968b852ad762a92ae732f14ac2975fe0688f5a7436813be856fb93adbb73","sha256:d968a1f778a47b9714f41a9b27ac191fd887592a0a6846b7515d2931be75bce7"],"state_sha256":"7326d40e7b46e7131048fbe5b77a9c758c877e1a5b26338d984894540bf20479"}