{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GKHIHSRDN3H7W6IGMKGD6SS7KG","short_pith_number":"pith:GKHIHSRD","canonical_record":{"source":{"id":"2206.00695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T18:04:43Z","cross_cats_sorted":[],"title_canon_sha256":"38f50e2a739013331af140e573ec0b3b9d8d5a8f11ca519f203a347e76d780d8","abstract_canon_sha256":"e8686859d7ac6deb3e2a37a8ae32cfbb8ffb8c88401392cce5e123775cf4f2a9"},"schema_version":"1.0"},"canonical_sha256":"328e83ca236ecffb7906628c3f4a5f51a5030a0e388abc4eedbd9b0b7843f49c","source":{"kind":"arxiv","id":"2206.00695","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GKHIHSRDN3H7W6IGMKGD6SS7KG","target":"record","payload":{"canonical_record":{"source":{"id":"2206.00695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T18:04:43Z","cross_cats_sorted":[],"title_canon_sha256":"38f50e2a739013331af140e573ec0b3b9d8d5a8f11ca519f203a347e76d780d8","abstract_canon_sha256":"e8686859d7ac6deb3e2a37a8ae32cfbb8ffb8c88401392cce5e123775cf4f2a9"},"schema_version":"1.0"},"canonical_sha256":"328e83ca236ecffb7906628c3f4a5f51a5030a0e388abc4eedbd9b0b7843f49c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:32.691838Z","signature_b64":"jehjmS3rPmRs/Qo6pnmH2TWpqRL+9Zo07kjhgvGKn9jXK6zcGU6PKa0HQsZMiOvkX9SFgOROZDjhYYFBqo/MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"328e83ca236ecffb7906628c3f4a5f51a5030a0e388abc4eedbd9b0b7843f49c","last_reissued_at":"2026-07-05T04:28:32.691352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:32.691352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.00695","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f6OW3uUvgREDgaT0AjJsOxC4qCIG1CF1eDmI1g0CJHi/66ohWUH3fxWh/o6xetBZE63UF2h+CuO8uZJEyS8SDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:26:36.414921Z"},"content_sha256":"14b1968b852ad762a92ae732f14ac2975fe0688f5a7436813be856fb93adbb73","schema_version":"1.0","event_id":"sha256:14b1968b852ad762a92ae732f14ac2975fe0688f5a7436813be856fb93adbb73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GKHIHSRDN3H7W6IGMKGD6SS7KG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Scott Niekum, Wonjoon Goo","submitted_at":"2022-06-01T18:04:43Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00695","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.00695/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZZvcm+BJ0ohTrQt25fzenc5rAcl0r32FuI65yDnC/rlno7yRw9LnbCNmoLfnaKu6wwLtsl+1X+tYc+/QIKNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:26:36.415502Z"},"content_sha256":"d968a1f778a47b9714f41a9b27ac191fd887592a0a6846b7515d2931be75bce7","schema_version":"1.0","event_id":"sha256:d968a1f778a47b9714f41a9b27ac191fd887592a0a6846b7515d2931be75bce7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKHIHSRDN3H7W6IGMKGD6SS7KG/bundle.json","state_url":"https://pith.science/pith/GKHIHSRDN3H7W6IGMKGD6SS7KG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKHIHSRDN3H7W6IGMKGD6SS7KG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T20:26:36Z","links":{"resolver":"https://pith.science/pith/GKHIHSRDN3H7W6IGMKGD6SS7KG","bundle":"https://pith.science/pith/GKHIHSRDN3H7W6IGMKGD6SS7KG/bundle.json","state":"https://pith.science/pith/GKHIHSRDN3H7W6IGMKGD6SS7KG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKHIHSRDN3H7W6IGMKGD6SS7KG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yt2uXkc95jcSpYOWbtyauWDwN9r5kR+89xe3J+YyqMEkMhaQd/JLM269UbNpmEQB2bWvFujQ/dxY3Gq2HJnGBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:26:36.419559Z","bundle_sha256":"ec8471fef4575d7c800b947e794d29e20d532525899dae860fb8448985d05d7c"}}