{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PJRM3FJTCWPRWGGQ4ZJ6NHXAHY","short_pith_number":"pith:PJRM3FJT","canonical_record":{"source":{"id":"2102.00714","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T09:19:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b02bb77bc1f336efd392f24aa0fc5fc7768cdcd2465c4d79be44306a06226b87","abstract_canon_sha256":"29a647bfbb9615c87754d792063277b9db0909cc30b9fbf83e464504ad0ade68"},"schema_version":"1.0"},"canonical_sha256":"7a62cd9533159f1b18d0e653e69ee03e1e13e8b1c8f9468ca6bca5d017a2a4b9","source":{"kind":"arxiv","id":"2102.00714","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.00714","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"arxiv_version","alias_value":"2102.00714v2","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00714","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_12","alias_value":"PJRM3FJTCWPR","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_16","alias_value":"PJRM3FJTCWPRWGGQ","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_8","alias_value":"PJRM3FJT","created_at":"2026-07-05T02:13:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PJRM3FJTCWPRWGGQ4ZJ6NHXAHY","target":"record","payload":{"canonical_record":{"source":{"id":"2102.00714","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T09:19:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b02bb77bc1f336efd392f24aa0fc5fc7768cdcd2465c4d79be44306a06226b87","abstract_canon_sha256":"29a647bfbb9615c87754d792063277b9db0909cc30b9fbf83e464504ad0ade68"},"schema_version":"1.0"},"canonical_sha256":"7a62cd9533159f1b18d0e653e69ee03e1e13e8b1c8f9468ca6bca5d017a2a4b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:22.506156Z","signature_b64":"kSQgjkrzHjgr41myG9ZWkcfC4VC/0ne6ebhHIwjUngqn6MFRQyhZwk6BWFUUHqv7TsVDrJirt/FZZoR/wjJ6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a62cd9533159f1b18d0e653e69ee03e1e13e8b1c8f9468ca6bca5d017a2a4b9","last_reissued_at":"2026-07-05T02:13:22.505726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:22.505726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.00714","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":"2026-07-05T02:13:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HmuxzZ6SC05F1MqsKUQB126pW7M/6aMKQpE7MRJSokfTI0NmOpR1DSVdHhaDAVLsDVZ8EwqXzIbe3+l08yTSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:26:53.391960Z"},"content_sha256":"7e209a095fed2ee6aeedea7a85e0ae41085eb822dfabb2fa1cf4d1cb8cf3047d","schema_version":"1.0","event_id":"sha256:7e209a095fed2ee6aeedea7a85e0ae41085eb822dfabb2fa1cf4d1cb8cf3047d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PJRM3FJTCWPRWGGQ4ZJ6NHXAHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Rongjun Qin, Shengkai Huang, Songyi Gao, Weinan Zhang, Xingyuan Zhang, Yang Yu, Zewen Li, Zhen Xu","submitted_at":"2021-02-01T09:19:10Z","abstract_excerpt":"Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a large reality gap, because they involve large datasets collected by highly exploratory policies, and the trained policy is directly evaluated in the environment. In real-world situations, running a highly exploratory policy is prohibited to ensure system safety, the data is commonly very limited, and a trained policy should be well validated before deployment. In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00714","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/2102.00714/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":"2026-07-05T02:13:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nju18g8fZ4XTog1ScRaq8JzX+Bp6s9fOs8PUviTVhJTgJ6scAxYaiIq/NHIas/UVeZ19bht8Onuorw6ULB9HCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:26:53.392356Z"},"content_sha256":"81154a339971c1f58f0ba37cd2f2839ce068640eeb4e03466a98780d2829a05c","schema_version":"1.0","event_id":"sha256:81154a339971c1f58f0ba37cd2f2839ce068640eeb4e03466a98780d2829a05c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJRM3FJTCWPRWGGQ4ZJ6NHXAHY/bundle.json","state_url":"https://pith.science/pith/PJRM3FJTCWPRWGGQ4ZJ6NHXAHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJRM3FJTCWPRWGGQ4ZJ6NHXAHY/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":"2026-07-05T10:26:53Z","links":{"resolver":"https://pith.science/pith/PJRM3FJTCWPRWGGQ4ZJ6NHXAHY","bundle":"https://pith.science/pith/PJRM3FJTCWPRWGGQ4ZJ6NHXAHY/bundle.json","state":"https://pith.science/pith/PJRM3FJTCWPRWGGQ4ZJ6NHXAHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJRM3FJTCWPRWGGQ4ZJ6NHXAHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PJRM3FJTCWPRWGGQ4ZJ6NHXAHY","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":"29a647bfbb9615c87754d792063277b9db0909cc30b9fbf83e464504ad0ade68","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T09:19:10Z","title_canon_sha256":"b02bb77bc1f336efd392f24aa0fc5fc7768cdcd2465c4d79be44306a06226b87"},"schema_version":"1.0","source":{"id":"2102.00714","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.00714","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"arxiv_version","alias_value":"2102.00714v2","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00714","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_12","alias_value":"PJRM3FJTCWPR","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_16","alias_value":"PJRM3FJTCWPRWGGQ","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_8","alias_value":"PJRM3FJT","created_at":"2026-07-05T02:13:22Z"}],"graph_snapshots":[{"event_id":"sha256:81154a339971c1f58f0ba37cd2f2839ce068640eeb4e03466a98780d2829a05c","target":"graph","created_at":"2026-07-05T02:13:22Z","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/2102.00714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a large reality gap, because they involve large datasets collected by highly exploratory policies, and the trained policy is directly evaluated in the environment. In real-world situations, running a highly exploratory policy is prohibited to ensure system safety, the data is commonly very limited, and a trained policy should be well validated before deployment. In this paper, we ","authors_text":"Rongjun Qin, Shengkai Huang, Songyi Gao, Weinan Zhang, Xingyuan Zhang, Yang Yu, Zewen Li, Zhen Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T09:19:10Z","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00714","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":"sha256:7e209a095fed2ee6aeedea7a85e0ae41085eb822dfabb2fa1cf4d1cb8cf3047d","target":"record","created_at":"2026-07-05T02:13:22Z","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":"29a647bfbb9615c87754d792063277b9db0909cc30b9fbf83e464504ad0ade68","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T09:19:10Z","title_canon_sha256":"b02bb77bc1f336efd392f24aa0fc5fc7768cdcd2465c4d79be44306a06226b87"},"schema_version":"1.0","source":{"id":"2102.00714","kind":"arxiv","version":2}},"canonical_sha256":"7a62cd9533159f1b18d0e653e69ee03e1e13e8b1c8f9468ca6bca5d017a2a4b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a62cd9533159f1b18d0e653e69ee03e1e13e8b1c8f9468ca6bca5d017a2a4b9","first_computed_at":"2026-07-05T02:13:22.505726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:22.505726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kSQgjkrzHjgr41myG9ZWkcfC4VC/0ne6ebhHIwjUngqn6MFRQyhZwk6BWFUUHqv7TsVDrJirt/FZZoR/wjJ6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:22.506156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.00714","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e209a095fed2ee6aeedea7a85e0ae41085eb822dfabb2fa1cf4d1cb8cf3047d","sha256:81154a339971c1f58f0ba37cd2f2839ce068640eeb4e03466a98780d2829a05c"],"state_sha256":"c5741660ddf6c7f2f50d08c1331bb38499c4d80f2e8729adf3e194aa8f826db3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5JsySWKWDCqZjFQqHGabAgySUf2cFHx40kdwU6G/wSw9Pr1Scet76QrsJLWipRepNW6Dh07glqA3CuWZFBsqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T10:26:53.394325Z","bundle_sha256":"c6abf4f6aa303e8e297fd5988d9e812ffb7596d20ee75599dd1b4d2fecaaca80"}}