{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:K7STYXFUO2EJXUKJ3UNSUB7FY2","short_pith_number":"pith:K7STYXFU","canonical_record":{"source":{"id":"2212.08131","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-15T20:36:10Z","cross_cats_sorted":[],"title_canon_sha256":"932d946969b816a4c74b479b351f89aba5b4a31907e7b994952d9a6da80d1213","abstract_canon_sha256":"35562de7f3c7310fd4c3d4397c6f034ff9b5039e45f89f7e9f34a2ad8a5e4d18"},"schema_version":"1.0"},"canonical_sha256":"57e53c5cb476889bd149dd1b2a07e5c69bcdac0d91aead5604455ca55c41874f","source":{"kind":"arxiv","id":"2212.08131","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08131","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08131v2","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08131","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"K7STYXFUO2EJ","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"K7STYXFUO2EJXUKJ","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"K7STYXFU","created_at":"2026-07-05T07:15:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:K7STYXFUO2EJXUKJ3UNSUB7FY2","target":"record","payload":{"canonical_record":{"source":{"id":"2212.08131","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-15T20:36:10Z","cross_cats_sorted":[],"title_canon_sha256":"932d946969b816a4c74b479b351f89aba5b4a31907e7b994952d9a6da80d1213","abstract_canon_sha256":"35562de7f3c7310fd4c3d4397c6f034ff9b5039e45f89f7e9f34a2ad8a5e4d18"},"schema_version":"1.0"},"canonical_sha256":"57e53c5cb476889bd149dd1b2a07e5c69bcdac0d91aead5604455ca55c41874f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:12.926831Z","signature_b64":"pL21U+60KDnsLj4tjzP7Qx01k+eIOE/Ci/B1AkawSRQ18IszHNWrkQWjR/ZkMPETqpIrwDUDz63TWXxKyeErCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57e53c5cb476889bd149dd1b2a07e5c69bcdac0d91aead5604455ca55c41874f","last_reissued_at":"2026-07-05T07:15:12.926423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:12.926423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.08131","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":"2026-07-05T07:15:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+BL0JhKbiEO4BtpcLkG1EfjxS+CFsLcQ0fYAbchx5YHPGWrzuwP/yFIwlGMAvISkHAsCYGNRu9JyYmaJkezxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:12:14.550518Z"},"content_sha256":"d25d9db621cf2cb2485f400ca59530e1a84344e4e42249c2d9733ea18d85a173","schema_version":"1.0","event_id":"sha256:d25d9db621cf2cb2485f400ca59530e1a84344e4e42249c2d9733ea18d85a173"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:K7STYXFUO2EJXUKJ3UNSUB7FY2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jorg Bornschein, Pedro H. M. Braga, Samira Ebrahimi Kahou, Shivakanth Sujit","submitted_at":"2022-12-15T20:36:10Z","abstract_excerpt":"Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a tremendous amount of environment interactions for learning. This can be infeasible in situations where such interactions are expensive; such as in robotics. Offline RL algorithms try to address this issue by bootstrapping the learning process from existing logged data without needing to interact with the environment from the very beginning. While online RL algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08131","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/2212.08131/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":"2026-07-05T07:15:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pPMNN/kgf2S+Amsoj2/pZ6QLpviG6o3tu2Yt0MaX8neKW5Ew+WWA7lQBcI+pY27pt6m/AQaL7gEHi+i1QGMeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:12:14.550897Z"},"content_sha256":"688fb7ba503a61b24bc1abefeb9c0bad1ba69679b876e80d930feb070aded337","schema_version":"1.0","event_id":"sha256:688fb7ba503a61b24bc1abefeb9c0bad1ba69679b876e80d930feb070aded337"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K7STYXFUO2EJXUKJ3UNSUB7FY2/bundle.json","state_url":"https://pith.science/pith/K7STYXFUO2EJXUKJ3UNSUB7FY2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K7STYXFUO2EJXUKJ3UNSUB7FY2/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":"2026-07-06T16:12:14Z","links":{"resolver":"https://pith.science/pith/K7STYXFUO2EJXUKJ3UNSUB7FY2","bundle":"https://pith.science/pith/K7STYXFUO2EJXUKJ3UNSUB7FY2/bundle.json","state":"https://pith.science/pith/K7STYXFUO2EJXUKJ3UNSUB7FY2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K7STYXFUO2EJXUKJ3UNSUB7FY2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:K7STYXFUO2EJXUKJ3UNSUB7FY2","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":"35562de7f3c7310fd4c3d4397c6f034ff9b5039e45f89f7e9f34a2ad8a5e4d18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-15T20:36:10Z","title_canon_sha256":"932d946969b816a4c74b479b351f89aba5b4a31907e7b994952d9a6da80d1213"},"schema_version":"1.0","source":{"id":"2212.08131","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08131","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08131v2","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08131","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"K7STYXFUO2EJ","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"K7STYXFUO2EJXUKJ","created_at":"2026-07-05T07:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"K7STYXFU","created_at":"2026-07-05T07:15:12Z"}],"graph_snapshots":[{"event_id":"sha256:688fb7ba503a61b24bc1abefeb9c0bad1ba69679b876e80d930feb070aded337","target":"graph","created_at":"2026-07-05T07:15:12Z","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/2212.08131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a tremendous amount of environment interactions for learning. This can be infeasible in situations where such interactions are expensive; such as in robotics. Offline RL algorithms try to address this issue by bootstrapping the learning process from existing logged data without needing to interact with the environment from the very beginning. While online RL algo","authors_text":"Jorg Bornschein, Pedro H. M. Braga, Samira Ebrahimi Kahou, Shivakanth Sujit","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-15T20:36:10Z","title":"Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08131","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:d25d9db621cf2cb2485f400ca59530e1a84344e4e42249c2d9733ea18d85a173","target":"record","created_at":"2026-07-05T07:15:12Z","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":"35562de7f3c7310fd4c3d4397c6f034ff9b5039e45f89f7e9f34a2ad8a5e4d18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-15T20:36:10Z","title_canon_sha256":"932d946969b816a4c74b479b351f89aba5b4a31907e7b994952d9a6da80d1213"},"schema_version":"1.0","source":{"id":"2212.08131","kind":"arxiv","version":2}},"canonical_sha256":"57e53c5cb476889bd149dd1b2a07e5c69bcdac0d91aead5604455ca55c41874f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57e53c5cb476889bd149dd1b2a07e5c69bcdac0d91aead5604455ca55c41874f","first_computed_at":"2026-07-05T07:15:12.926423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:15:12.926423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pL21U+60KDnsLj4tjzP7Qx01k+eIOE/Ci/B1AkawSRQ18IszHNWrkQWjR/ZkMPETqpIrwDUDz63TWXxKyeErCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:15:12.926831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08131","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d25d9db621cf2cb2485f400ca59530e1a84344e4e42249c2d9733ea18d85a173","sha256:688fb7ba503a61b24bc1abefeb9c0bad1ba69679b876e80d930feb070aded337"],"state_sha256":"ed15f061c91471584825c76a981a159710c459f151fc66d114ab7867facc00eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CeEa/7UzEQfo46d5hgYX+PyoM3+aygGu1SvT6ADGefVFEMX9Zx9EH1nzfnqh9SAFw0zYA5yb9QOeWoqmb6pWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:12:14.552865Z","bundle_sha256":"355a4e3dfde6a7c63d8e3e0bbc028b750bc1f225c1e050e582c613ea094c31a0"}}