{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HLBZF6WZC3QCI6XN2TQ4SEFPST","short_pith_number":"pith:HLBZF6WZ","canonical_record":{"source":{"id":"2110.01548","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T16:40:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2c884f8f36fbced71a4a15b4706ccd2a62e1acb4c6c2706c93c44c84dc71ee9","abstract_canon_sha256":"fe9a9f627591f10c98b0792ace00662e98a9b4bd6467474824520a6ea7afd053"},"schema_version":"1.0"},"canonical_sha256":"3ac392fad916e0247aedd4e1c910af94cfa49a991362a9361d8ca4372e3e696d","source":{"kind":"arxiv","id":"2110.01548","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01548","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01548v2","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01548","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"HLBZF6WZC3QC","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"HLBZF6WZC3QCI6XN","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"HLBZF6WZ","created_at":"2026-07-05T03:20:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HLBZF6WZC3QCI6XN2TQ4SEFPST","target":"record","payload":{"canonical_record":{"source":{"id":"2110.01548","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T16:40:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2c884f8f36fbced71a4a15b4706ccd2a62e1acb4c6c2706c93c44c84dc71ee9","abstract_canon_sha256":"fe9a9f627591f10c98b0792ace00662e98a9b4bd6467474824520a6ea7afd053"},"schema_version":"1.0"},"canonical_sha256":"3ac392fad916e0247aedd4e1c910af94cfa49a991362a9361d8ca4372e3e696d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:04.260649Z","signature_b64":"uirNgS+fqHsTq6RVHxS0IHJX5ui58kecEiGNF9hLQtZeIYIZyPGkix4fXuSWKObmuhLZJq8YHbdIcqh44klUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ac392fad916e0247aedd4e1c910af94cfa49a991362a9361d8ca4372e3e696d","last_reissued_at":"2026-07-05T03:20:04.260207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:04.260207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.01548","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HjwCj1a5438Qc+acxWrM8ZVYoQ32XEW9fMPdFcF5jJV0PVJbfZBknmvIuG8brEcKmoTt8TlkSRnkwUBvVMzoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:06:56.912191Z"},"content_sha256":"b1ceb99bb1e717a5b37a2105967e38e2ba3c61ffd79e5d2a647e91ad1ec91d3f","schema_version":"1.0","event_id":"sha256:b1ceb99bb1e717a5b37a2105967e38e2ba3c61ffd79e5d2a647e91ad1ec91d3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HLBZF6WZC3QCI6XN2TQ4SEFPST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaon An, Hyun Oh Song, Jang-Hyun Kim, Seungyong Moon","submitted_at":"2021-10-04T16:40:13Z","abstract_excerpt":"Offline reinforcement learning (offline RL), which aims to find an optimal policy from a previously collected static dataset, bears algorithmic difficulties due to function approximation errors from out-of-distribution (OOD) data points. To this end, offline RL algorithms adopt either a constraint or a penalty term that explicitly guides the policy to stay close to the given dataset. However, prior methods typically require accurate estimation of the behavior policy or sampling from OOD data points, which themselves can be a non-trivial problem. Moreover, these methods under-utilize the genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01548","kind":"arxiv","version":2},"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/2110.01548/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":"2026-07-05T03:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zm1mKHa3UGrAtyk39GYTXrhrWsG8aRI43oJ8JtsFaAXiwIYoPkjNcH7cHe/tMW2Xx10gkMAc3lHr+t4Nq/jBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:06:56.912722Z"},"content_sha256":"995774bd929857361b13f37e1d776eab3628baf3c14ff71690b731b1293bcff3","schema_version":"1.0","event_id":"sha256:995774bd929857361b13f37e1d776eab3628baf3c14ff71690b731b1293bcff3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLBZF6WZC3QCI6XN2TQ4SEFPST/bundle.json","state_url":"https://pith.science/pith/HLBZF6WZC3QCI6XN2TQ4SEFPST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLBZF6WZC3QCI6XN2TQ4SEFPST/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":"2026-08-11T12:06:56Z","links":{"resolver":"https://pith.science/pith/HLBZF6WZC3QCI6XN2TQ4SEFPST","bundle":"https://pith.science/pith/HLBZF6WZC3QCI6XN2TQ4SEFPST/bundle.json","state":"https://pith.science/pith/HLBZF6WZC3QCI6XN2TQ4SEFPST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLBZF6WZC3QCI6XN2TQ4SEFPST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HLBZF6WZC3QCI6XN2TQ4SEFPST","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":"fe9a9f627591f10c98b0792ace00662e98a9b4bd6467474824520a6ea7afd053","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T16:40:13Z","title_canon_sha256":"e2c884f8f36fbced71a4a15b4706ccd2a62e1acb4c6c2706c93c44c84dc71ee9"},"schema_version":"1.0","source":{"id":"2110.01548","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01548","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01548v2","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01548","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"HLBZF6WZC3QC","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"HLBZF6WZC3QCI6XN","created_at":"2026-07-05T03:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"HLBZF6WZ","created_at":"2026-07-05T03:20:04Z"}],"graph_snapshots":[{"event_id":"sha256:995774bd929857361b13f37e1d776eab3628baf3c14ff71690b731b1293bcff3","target":"graph","created_at":"2026-07-05T03:20:04Z","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/2110.01548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (offline RL), which aims to find an optimal policy from a previously collected static dataset, bears algorithmic difficulties due to function approximation errors from out-of-distribution (OOD) data points. To this end, offline RL algorithms adopt either a constraint or a penalty term that explicitly guides the policy to stay close to the given dataset. However, prior methods typically require accurate estimation of the behavior policy or sampling from OOD data points, which themselves can be a non-trivial problem. Moreover, these methods under-utilize the genera","authors_text":"Gaon An, Hyun Oh Song, Jang-Hyun Kim, Seungyong Moon","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T16:40:13Z","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01548","kind":"arxiv","version":2},"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:b1ceb99bb1e717a5b37a2105967e38e2ba3c61ffd79e5d2a647e91ad1ec91d3f","target":"record","created_at":"2026-07-05T03:20:04Z","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":"fe9a9f627591f10c98b0792ace00662e98a9b4bd6467474824520a6ea7afd053","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T16:40:13Z","title_canon_sha256":"e2c884f8f36fbced71a4a15b4706ccd2a62e1acb4c6c2706c93c44c84dc71ee9"},"schema_version":"1.0","source":{"id":"2110.01548","kind":"arxiv","version":2}},"canonical_sha256":"3ac392fad916e0247aedd4e1c910af94cfa49a991362a9361d8ca4372e3e696d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ac392fad916e0247aedd4e1c910af94cfa49a991362a9361d8ca4372e3e696d","first_computed_at":"2026-07-05T03:20:04.260207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:04.260207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uirNgS+fqHsTq6RVHxS0IHJX5ui58kecEiGNF9hLQtZeIYIZyPGkix4fXuSWKObmuhLZJq8YHbdIcqh44klUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:04.260649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.01548","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1ceb99bb1e717a5b37a2105967e38e2ba3c61ffd79e5d2a647e91ad1ec91d3f","sha256:995774bd929857361b13f37e1d776eab3628baf3c14ff71690b731b1293bcff3"],"state_sha256":"643bf7646ca4276046474c61602e27f91f78e5dd231f9584e082634bb610353a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fxdf/vSCCWDPmS7N0FuOdyl5q5wRNSNC7gqYgPZ/93xEUV6ZCPCMPrrj2OI+ut1r64Y0he6zm5f1WMG/3pwhDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:06:56.917705Z","bundle_sha256":"be5a36fcf9ed1293cd5ab1bf70f50f29a90b89ae3dc8cb02e3c0aaba6191e264"}}