{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WCW5TLDKICMPCENUSVA2SGTVKA","short_pith_number":"pith:WCW5TLDK","canonical_record":{"source":{"id":"2312.05742","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T03:40:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e436d275e8f9a154e0b6079e1360bf461631584c3c2143e36f8d4fa237a997c3","abstract_canon_sha256":"59ae89b722fa3e3a287786c3f4c37cf8b45983dfda6751729075f4243fcbe9bd"},"schema_version":"1.0"},"canonical_sha256":"b0add9ac6a4098f111b49541a91a75501ce5bc614de67497059f1743635a0d4f","source":{"kind":"arxiv","id":"2312.05742","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05742","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05742v2","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05742","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"pith_short_12","alias_value":"WCW5TLDKICMP","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"pith_short_16","alias_value":"WCW5TLDKICMPCENU","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"pith_short_8","alias_value":"WCW5TLDK","created_at":"2026-07-05T07:56:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WCW5TLDKICMPCENUSVA2SGTVKA","target":"record","payload":{"canonical_record":{"source":{"id":"2312.05742","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T03:40:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e436d275e8f9a154e0b6079e1360bf461631584c3c2143e36f8d4fa237a997c3","abstract_canon_sha256":"59ae89b722fa3e3a287786c3f4c37cf8b45983dfda6751729075f4243fcbe9bd"},"schema_version":"1.0"},"canonical_sha256":"b0add9ac6a4098f111b49541a91a75501ce5bc614de67497059f1743635a0d4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:19.578261Z","signature_b64":"+G7fvai6oGPlhAIb6/wdIuD3zAAawupIZMDHDruT+quxStvoy4rbuMgrSGJdC1HNFKgxSaXfo01WiGYtobnOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0add9ac6a4098f111b49541a91a75501ce5bc614de67497059f1743635a0d4f","last_reissued_at":"2026-07-05T07:56:19.577725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:19.577725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.05742","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":"2026-07-05T07:56:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vAFU0MxAnI426v8hlmGMKd4XV5drarOyEqa+Nt70otx5CN+dCPXzoN38A3vp4agV/XuDnnHWs3cIlEGQp+SBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:13:48.423349Z"},"content_sha256":"7bfe10cef3a29eae9892c4a4804515827ecda07a6bf2a202ddd8922591bc1418","schema_version":"1.0","event_id":"sha256:7bfe10cef3a29eae9892c4a4804515827ecda07a6bf2a202ddd8922591bc1418"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WCW5TLDKICMPCENUSVA2SGTVKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Generalization Gap in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ishita Mediratta, Minqi Jiang, Qingfei You, Roberta Raileanu","submitted_at":"2023-12-10T03:40:52Z","abstract_excerpt":"Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization abilities of widely used online and offline learning methods such as online reinforcement learning (RL), offline RL, sequence modeling, and behavioral cloning. Our experiments show that offline learning algorithms perform worse on new environments than online learning ones. We also introduce the first benchmark for evaluating generalization in offline learning, collecting datasets of varying sizes and skill-levels from Procgen (2D video g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05742","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/2312.05742/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":"2026-07-05T07:56:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rd0nn0jB05qqs0D5xQJ50loiA7yCTm0Eok/mMDpO76zJtdPGcHyHWS5nkZpvwYm2DdOwiUm56olaLpYfSLf/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:13:48.423904Z"},"content_sha256":"eefcdaabfddeb341386a9144a9732f91789ce15c9d42a98326eb640ad4ec6ffd","schema_version":"1.0","event_id":"sha256:eefcdaabfddeb341386a9144a9732f91789ce15c9d42a98326eb640ad4ec6ffd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCW5TLDKICMPCENUSVA2SGTVKA/bundle.json","state_url":"https://pith.science/pith/WCW5TLDKICMPCENUSVA2SGTVKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCW5TLDKICMPCENUSVA2SGTVKA/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":"2026-08-11T08:13:48Z","links":{"resolver":"https://pith.science/pith/WCW5TLDKICMPCENUSVA2SGTVKA","bundle":"https://pith.science/pith/WCW5TLDKICMPCENUSVA2SGTVKA/bundle.json","state":"https://pith.science/pith/WCW5TLDKICMPCENUSVA2SGTVKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCW5TLDKICMPCENUSVA2SGTVKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WCW5TLDKICMPCENUSVA2SGTVKA","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":"59ae89b722fa3e3a287786c3f4c37cf8b45983dfda6751729075f4243fcbe9bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T03:40:52Z","title_canon_sha256":"e436d275e8f9a154e0b6079e1360bf461631584c3c2143e36f8d4fa237a997c3"},"schema_version":"1.0","source":{"id":"2312.05742","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05742","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05742v2","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05742","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"pith_short_12","alias_value":"WCW5TLDKICMP","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"pith_short_16","alias_value":"WCW5TLDKICMPCENU","created_at":"2026-07-05T07:56:19Z"},{"alias_kind":"pith_short_8","alias_value":"WCW5TLDK","created_at":"2026-07-05T07:56:19Z"}],"graph_snapshots":[{"event_id":"sha256:eefcdaabfddeb341386a9144a9732f91789ce15c9d42a98326eb640ad4ec6ffd","target":"graph","created_at":"2026-07-05T07:56:19Z","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/2312.05742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization abilities of widely used online and offline learning methods such as online reinforcement learning (RL), offline RL, sequence modeling, and behavioral cloning. Our experiments show that offline learning algorithms perform worse on new environments than online learning ones. We also introduce the first benchmark for evaluating generalization in offline learning, collecting datasets of varying sizes and skill-levels from Procgen (2D video g","authors_text":"Ishita Mediratta, Minqi Jiang, Qingfei You, Roberta Raileanu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T03:40:52Z","title":"The Generalization Gap in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05742","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":"sha256:7bfe10cef3a29eae9892c4a4804515827ecda07a6bf2a202ddd8922591bc1418","target":"record","created_at":"2026-07-05T07:56:19Z","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":"59ae89b722fa3e3a287786c3f4c37cf8b45983dfda6751729075f4243fcbe9bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T03:40:52Z","title_canon_sha256":"e436d275e8f9a154e0b6079e1360bf461631584c3c2143e36f8d4fa237a997c3"},"schema_version":"1.0","source":{"id":"2312.05742","kind":"arxiv","version":2}},"canonical_sha256":"b0add9ac6a4098f111b49541a91a75501ce5bc614de67497059f1743635a0d4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0add9ac6a4098f111b49541a91a75501ce5bc614de67497059f1743635a0d4f","first_computed_at":"2026-07-05T07:56:19.577725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:19.577725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+G7fvai6oGPlhAIb6/wdIuD3zAAawupIZMDHDruT+quxStvoy4rbuMgrSGJdC1HNFKgxSaXfo01WiGYtobnOAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:19.578261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.05742","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bfe10cef3a29eae9892c4a4804515827ecda07a6bf2a202ddd8922591bc1418","sha256:eefcdaabfddeb341386a9144a9732f91789ce15c9d42a98326eb640ad4ec6ffd"],"state_sha256":"dcdc428ca77a9772fb923992cf7bc52e53c6c9c59f05700fbdf2d73d4025ad6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6o3OUmULEgMz1VrgIWdmp33yZ4I4Rz2xX7ogcLMUerG7xa9tlRBORoo+OC7TsHkbLvLCKszexObwAFaRgNPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:13:48.428462Z","bundle_sha256":"efa9af9edee44062a688115792734f16b83ed2f9b8f3848be42f952220d32ade"}}