{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ERKIUPG7UZTXKZVNQHXOY3X2GL","short_pith_number":"pith:ERKIUPG7","canonical_record":{"source":{"id":"2305.13804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"1ed515ab6fc6166c7b86e20cb34a6d860e004dfd94ed10193381c6e7204716be","abstract_canon_sha256":"206b851a0058fef1a89849bb9be751d3ad19f8c4e063b3348e1d51a5e4239ade"},"schema_version":"1.0"},"canonical_sha256":"24548a3cdfa6677566ad81eeec6efa32c1199b614b7ab1e0cdab28e11d4fa4df","source":{"kind":"arxiv","id":"2305.13804","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13804","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13804v2","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13804","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"ERKIUPG7UZTX","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_16","alias_value":"ERKIUPG7UZTXKZVN","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_8","alias_value":"ERKIUPG7","created_at":"2026-07-05T08:10:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ERKIUPG7UZTXKZVNQHXOY3X2GL","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"1ed515ab6fc6166c7b86e20cb34a6d860e004dfd94ed10193381c6e7204716be","abstract_canon_sha256":"206b851a0058fef1a89849bb9be751d3ad19f8c4e063b3348e1d51a5e4239ade"},"schema_version":"1.0"},"canonical_sha256":"24548a3cdfa6677566ad81eeec6efa32c1199b614b7ab1e0cdab28e11d4fa4df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:14.056870Z","signature_b64":"IhSEpHg5xonRYyK/UqW4nDN1PaDGKCif4QBIGY23ptcQxev5t1yIM+WBNWGSuuJcnT41sBXPYgRzyb79zBgyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24548a3cdfa6677566ad81eeec6efa32c1199b614b7ab1e0cdab28e11d4fa4df","last_reissued_at":"2026-07-05T08:10:14.056455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:14.056455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13804","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":"2026-07-05T08:10:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIBxUHthGhMuXNsDGysslaoDXEwy0og7dTPQvhTu7OQpydXTWbYsNjOdFBljH2OMMDUU0MornEVqIcPmZzP9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:36:26.580407Z"},"content_sha256":"180cc18231d807b0d0d0f646c1f3d34dbeb34739609a14bd640c7b566cb27d9a","schema_version":"1.0","event_id":"sha256:180cc18231d807b0d0d0f646c1f3d34dbeb34739609a14bd640c7b566cb27d9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ERKIUPG7UZTXKZVNQHXOY3X2GL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OER: Offline Experience Replay for Continual Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Li He, Sibo Gai","submitted_at":"2023-05-23T08:16:44Z","abstract_excerpt":"The capability of continuously learning new skills via a sequence of pre-collected offline datasets is desired for an agent. However, consecutively learning a sequence of offline tasks likely leads to the catastrophic forgetting issue under resource-limited scenarios. In this paper, we formulate a new setting, continual offline reinforcement learning (CORL), where an agent learns a sequence of offline reinforcement learning tasks and pursues good performance on all learned tasks with a small replay buffer without exploring any of the environments of all the sequential tasks. For consistently l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13804","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/2305.13804/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":"2026-07-05T08:10:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3DVmAEsijct9fLR3JKJdUG9iSim+20Tj+bwnqD8nw0g0XGInxaax7OwWVJ3fIEMkzt9ZVmzagYCeRlj1T/CPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:36:26.581374Z"},"content_sha256":"de2541179cbfe47a60bef47a7cf159f67ae104333e1d77477d284aaa210d3e53","schema_version":"1.0","event_id":"sha256:de2541179cbfe47a60bef47a7cf159f67ae104333e1d77477d284aaa210d3e53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERKIUPG7UZTXKZVNQHXOY3X2GL/bundle.json","state_url":"https://pith.science/pith/ERKIUPG7UZTXKZVNQHXOY3X2GL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERKIUPG7UZTXKZVNQHXOY3X2GL/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":"2026-08-17T16:36:26Z","links":{"resolver":"https://pith.science/pith/ERKIUPG7UZTXKZVNQHXOY3X2GL","bundle":"https://pith.science/pith/ERKIUPG7UZTXKZVNQHXOY3X2GL/bundle.json","state":"https://pith.science/pith/ERKIUPG7UZTXKZVNQHXOY3X2GL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERKIUPG7UZTXKZVNQHXOY3X2GL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ERKIUPG7UZTXKZVNQHXOY3X2GL","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":"206b851a0058fef1a89849bb9be751d3ad19f8c4e063b3348e1d51a5e4239ade","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:16:44Z","title_canon_sha256":"1ed515ab6fc6166c7b86e20cb34a6d860e004dfd94ed10193381c6e7204716be"},"schema_version":"1.0","source":{"id":"2305.13804","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13804","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13804v2","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13804","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"ERKIUPG7UZTX","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_16","alias_value":"ERKIUPG7UZTXKZVN","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_8","alias_value":"ERKIUPG7","created_at":"2026-07-05T08:10:14Z"}],"graph_snapshots":[{"event_id":"sha256:de2541179cbfe47a60bef47a7cf159f67ae104333e1d77477d284aaa210d3e53","target":"graph","created_at":"2026-07-05T08:10:14Z","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/2305.13804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The capability of continuously learning new skills via a sequence of pre-collected offline datasets is desired for an agent. However, consecutively learning a sequence of offline tasks likely leads to the catastrophic forgetting issue under resource-limited scenarios. In this paper, we formulate a new setting, continual offline reinforcement learning (CORL), where an agent learns a sequence of offline reinforcement learning tasks and pursues good performance on all learned tasks with a small replay buffer without exploring any of the environments of all the sequential tasks. For consistently l","authors_text":"Donglin Wang, Li He, Sibo Gai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:16:44Z","title":"OER: Offline Experience Replay for Continual Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13804","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":"sha256:180cc18231d807b0d0d0f646c1f3d34dbeb34739609a14bd640c7b566cb27d9a","target":"record","created_at":"2026-07-05T08:10:14Z","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":"206b851a0058fef1a89849bb9be751d3ad19f8c4e063b3348e1d51a5e4239ade","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:16:44Z","title_canon_sha256":"1ed515ab6fc6166c7b86e20cb34a6d860e004dfd94ed10193381c6e7204716be"},"schema_version":"1.0","source":{"id":"2305.13804","kind":"arxiv","version":2}},"canonical_sha256":"24548a3cdfa6677566ad81eeec6efa32c1199b614b7ab1e0cdab28e11d4fa4df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24548a3cdfa6677566ad81eeec6efa32c1199b614b7ab1e0cdab28e11d4fa4df","first_computed_at":"2026-07-05T08:10:14.056455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:14.056455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IhSEpHg5xonRYyK/UqW4nDN1PaDGKCif4QBIGY23ptcQxev5t1yIM+WBNWGSuuJcnT41sBXPYgRzyb79zBgyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:14.056870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13804","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:180cc18231d807b0d0d0f646c1f3d34dbeb34739609a14bd640c7b566cb27d9a","sha256:de2541179cbfe47a60bef47a7cf159f67ae104333e1d77477d284aaa210d3e53"],"state_sha256":"d41c4ac2d244cd56be0137ba4d8110dd95d159867710a7d77055cd8c0cdcf22e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NdKrRCnJLssLQMqlhiDNbDFcax3Zv6gUuAPJQJIbDmLUJwnO0oX69Yf+AvK6z7mzlR62tjQNsi1ZOF2S9cc6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:36:26.663523Z","bundle_sha256":"263cb79f8c30f7fba30832b593679bbafb53c57ed7fab90ba38fe73490f78b6d"}}