{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:K74ISTEGZ2GM6YZFS5MPG22QJT","short_pith_number":"pith:K74ISTEG","canonical_record":{"source":{"id":"2205.11027","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T04:01:11Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"324c00503e3fe2f6c4312e213e77b6ae66b54f569b654d2f69a0e60ae1e1a092","abstract_canon_sha256":"294738af4fd2f23801ed7b41343f5ab881833dff6d5dbebe90f5c8ded80b3b9e"},"schema_version":"1.0"},"canonical_sha256":"57f8894c86ce8ccf63259758f36b504cd44cd9d15110163a133a18f2135cc1c2","source":{"kind":"arxiv","id":"2205.11027","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11027","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11027v3","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11027","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"K74ISTEGZ2GM","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_16","alias_value":"K74ISTEGZ2GM6YZF","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_8","alias_value":"K74ISTEG","created_at":"2026-07-05T05:46:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:K74ISTEGZ2GM6YZFS5MPG22QJT","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11027","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T04:01:11Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"324c00503e3fe2f6c4312e213e77b6ae66b54f569b654d2f69a0e60ae1e1a092","abstract_canon_sha256":"294738af4fd2f23801ed7b41343f5ab881833dff6d5dbebe90f5c8ded80b3b9e"},"schema_version":"1.0"},"canonical_sha256":"57f8894c86ce8ccf63259758f36b504cd44cd9d15110163a133a18f2135cc1c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:51.521769Z","signature_b64":"LYpveNaGz/cA0zUNgFGHPBQnvg3mjocvSmz5FbymlQ6iZvon+af+hu1XwO1cqOztavzmm9HGCzfm43TXxNwmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57f8894c86ce8ccf63259758f36b504cd44cd9d15110163a133a18f2135cc1c2","last_reissued_at":"2026-07-05T05:46:51.521348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:51.521348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11027","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:46:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ElKLw4arVA8055KWYm/shZ7qt0cz4RpxVwUxbJcyX+epMK2oJ2cD+HH61zwhJhwHUzBW4519AIiuTJxutZP6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:30:56.672965Z"},"content_sha256":"20151c13afa5310cf28d5d0ebb884a8e80b220ed1c92c33e7842440e4eba0f2a","schema_version":"1.0","event_id":"sha256:20151c13afa5310cf28d5d0ebb884a8e80b220ed1c92c33e7842440e4eba0f2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:K74ISTEGZ2GM6YZFS5MPG22QJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Haoran Xu, Jianxiong Li, Jingjing Liu, Xiangyu Zhu, Xianyuan Zhan, Ya-Qin Zhang","submitted_at":"2022-05-23T04:01:11Z","abstract_excerpt":"In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas. Unfortunately, existing offline RL methods are often over-conservative, inevitably hurting generalization performance outside data distribution. In our study, one interesting observation is that deep Q functions approximate well inside the convex hull of training data. Inspired by this, we propose a new method, DOGE (Distance-sensitive Offline RL with better GEneralization). DOGE marries dataset geometry with deep function approximato"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11027","kind":"arxiv","version":3},"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/2205.11027/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":"2026-07-05T05:46:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cp3F8zPH0kEgXZcjX87iU47zKk2D4IC3oik3ORjxnbLYXeNmAOcFSidimaD4y9YSQzTwiy3g6hjJIuoMKoMHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:30:56.673836Z"},"content_sha256":"01f0ec561ba980bd00902c170315de7be200bd109c78d375d795552e93d56233","schema_version":"1.0","event_id":"sha256:01f0ec561ba980bd00902c170315de7be200bd109c78d375d795552e93d56233"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K74ISTEGZ2GM6YZFS5MPG22QJT/bundle.json","state_url":"https://pith.science/pith/K74ISTEGZ2GM6YZFS5MPG22QJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K74ISTEGZ2GM6YZFS5MPG22QJT/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":"2026-08-08T21:30:56Z","links":{"resolver":"https://pith.science/pith/K74ISTEGZ2GM6YZFS5MPG22QJT","bundle":"https://pith.science/pith/K74ISTEGZ2GM6YZFS5MPG22QJT/bundle.json","state":"https://pith.science/pith/K74ISTEGZ2GM6YZFS5MPG22QJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K74ISTEGZ2GM6YZFS5MPG22QJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:K74ISTEGZ2GM6YZFS5MPG22QJT","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":"294738af4fd2f23801ed7b41343f5ab881833dff6d5dbebe90f5c8ded80b3b9e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T04:01:11Z","title_canon_sha256":"324c00503e3fe2f6c4312e213e77b6ae66b54f569b654d2f69a0e60ae1e1a092"},"schema_version":"1.0","source":{"id":"2205.11027","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11027","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11027v3","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11027","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"K74ISTEGZ2GM","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_16","alias_value":"K74ISTEGZ2GM6YZF","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_8","alias_value":"K74ISTEG","created_at":"2026-07-05T05:46:51Z"}],"graph_snapshots":[{"event_id":"sha256:01f0ec561ba980bd00902c170315de7be200bd109c78d375d795552e93d56233","target":"graph","created_at":"2026-07-05T05:46:51Z","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/2205.11027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas. Unfortunately, existing offline RL methods are often over-conservative, inevitably hurting generalization performance outside data distribution. In our study, one interesting observation is that deep Q functions approximate well inside the convex hull of training data. Inspired by this, we propose a new method, DOGE (Distance-sensitive Offline RL with better GEneralization). DOGE marries dataset geometry with deep function approximato","authors_text":"Haoran Xu, Jianxiong Li, Jingjing Liu, Xiangyu Zhu, Xianyuan Zhan, Ya-Qin Zhang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T04:01:11Z","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11027","kind":"arxiv","version":3},"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":"sha256:20151c13afa5310cf28d5d0ebb884a8e80b220ed1c92c33e7842440e4eba0f2a","target":"record","created_at":"2026-07-05T05:46:51Z","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":"294738af4fd2f23801ed7b41343f5ab881833dff6d5dbebe90f5c8ded80b3b9e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T04:01:11Z","title_canon_sha256":"324c00503e3fe2f6c4312e213e77b6ae66b54f569b654d2f69a0e60ae1e1a092"},"schema_version":"1.0","source":{"id":"2205.11027","kind":"arxiv","version":3}},"canonical_sha256":"57f8894c86ce8ccf63259758f36b504cd44cd9d15110163a133a18f2135cc1c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57f8894c86ce8ccf63259758f36b504cd44cd9d15110163a133a18f2135cc1c2","first_computed_at":"2026-07-05T05:46:51.521348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:51.521348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LYpveNaGz/cA0zUNgFGHPBQnvg3mjocvSmz5FbymlQ6iZvon+af+hu1XwO1cqOztavzmm9HGCzfm43TXxNwmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:51.521769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11027","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20151c13afa5310cf28d5d0ebb884a8e80b220ed1c92c33e7842440e4eba0f2a","sha256:01f0ec561ba980bd00902c170315de7be200bd109c78d375d795552e93d56233"],"state_sha256":"240e64f876b6e3479a2d6d1902de4689c87cd1a169525aaa344af2a0a4a19530"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ay5Kv9B6umH565tarIGfjUUsarr/Bw57EJffl6HUtF3VNoIjkSaLb3NyFdq1dwU2BUekaDtAUJpL8+wxiXHBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:30:56.678674Z","bundle_sha256":"cad11fc1f875c079ef9faa2a4fb67910565652c46233dc2f26698675f06edc6a"}}