{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:B6ACLNIW5CPBZUMRWHZYJZYFUE","short_pith_number":"pith:B6ACLNIW","canonical_record":{"source":{"id":"2307.11046","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:28:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"91e714b4b40414d1d7cabb3c6500282bf57a5fe372da0d8f6fc56733c9b767e8","abstract_canon_sha256":"5eb0da7738952c5ea1a1e56a1b2fb021df7323de609e4773b8f0acad3f1a0d32"},"schema_version":"1.0"},"canonical_sha256":"0f8025b516e89e1cd191b1f384e705a12f67442acec9b50e0ed1cf968a00bcaf","source":{"kind":"arxiv","id":"2307.11046","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11046","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11046v2","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11046","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"B6ACLNIW5CPB","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"B6ACLNIW5CPBZUMR","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"B6ACLNIW","created_at":"2026-07-05T07:18:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:B6ACLNIW5CPBZUMRWHZYJZYFUE","target":"record","payload":{"canonical_record":{"source":{"id":"2307.11046","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:28:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"91e714b4b40414d1d7cabb3c6500282bf57a5fe372da0d8f6fc56733c9b767e8","abstract_canon_sha256":"5eb0da7738952c5ea1a1e56a1b2fb021df7323de609e4773b8f0acad3f1a0d32"},"schema_version":"1.0"},"canonical_sha256":"0f8025b516e89e1cd191b1f384e705a12f67442acec9b50e0ed1cf968a00bcaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:59.166726Z","signature_b64":"Pc4MBUGuyLcV2GaWSU8O8gmDtrhs9ACdxxO4nxRl9EtQSC0NH/40KJ7d5T1dU652iIRL9ZIO4XVFyOXnPZNPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f8025b516e89e1cd191b1f384e705a12f67442acec9b50e0ed1cf968a00bcaf","last_reissued_at":"2026-07-05T07:18:59.166202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:59.166202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.11046","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":"2026-07-05T07:18:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r/W81slBA/MA8eUQjTqWMIhGP8YcT2I6MQoiLnDqdx7OoX2Z7UT6DswfC8JLm+/gGyBP+OKrv8AdTTedU6dzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:44:20.263110Z"},"content_sha256":"5d755c2a669fd017f297791d4dd3737a4062a714dc95a7018cefcd0550c7a504","schema_version":"1.0","event_id":"sha256:5d755c2a669fd017f297791d4dd3737a4062a714dc95a7018cefcd0550c7a504"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:B6ACLNIW5CPBZUMRWHZYJZYFUE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Definition of Continual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Benjamin Van Roy, David Abel, Doina Precup, Hado van Hasselt, Satinder Singh","submitted_at":"2023-07-20T17:28:01Z","abstract_excerpt":"In a standard view of the reinforcement learning problem, an agent's goal is to efficiently identify a policy that maximizes long-term reward. However, this perspective is based on a restricted view of learning as finding a solution, rather than treating learning as endless adaptation. In contrast, continual reinforcement learning refers to the setting in which the best agents never stop learning. Despite the importance of continual reinforcement learning, the community lacks a simple definition of the problem that highlights its commitments and makes its primary concepts precise and clear. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11046","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/2307.11046/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":"2026-07-05T07:18:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXBw9He0Hn0w7nyjw4PTS+OmzHy0h7WCt+1/3fpinoE06WiDiW+Da3eAskW5FsmVLcftjEcGK8urJ50vwWINDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:44:20.264323Z"},"content_sha256":"488f8c44a918077f35d309c24b7880aadfa2a4f4112af1eff6575c6c290e39ff","schema_version":"1.0","event_id":"sha256:488f8c44a918077f35d309c24b7880aadfa2a4f4112af1eff6575c6c290e39ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B6ACLNIW5CPBZUMRWHZYJZYFUE/bundle.json","state_url":"https://pith.science/pith/B6ACLNIW5CPBZUMRWHZYJZYFUE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B6ACLNIW5CPBZUMRWHZYJZYFUE/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":"2026-08-10T12:44:20Z","links":{"resolver":"https://pith.science/pith/B6ACLNIW5CPBZUMRWHZYJZYFUE","bundle":"https://pith.science/pith/B6ACLNIW5CPBZUMRWHZYJZYFUE/bundle.json","state":"https://pith.science/pith/B6ACLNIW5CPBZUMRWHZYJZYFUE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B6ACLNIW5CPBZUMRWHZYJZYFUE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B6ACLNIW5CPBZUMRWHZYJZYFUE","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":"5eb0da7738952c5ea1a1e56a1b2fb021df7323de609e4773b8f0acad3f1a0d32","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:28:01Z","title_canon_sha256":"91e714b4b40414d1d7cabb3c6500282bf57a5fe372da0d8f6fc56733c9b767e8"},"schema_version":"1.0","source":{"id":"2307.11046","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11046","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11046v2","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11046","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"B6ACLNIW5CPB","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"B6ACLNIW5CPBZUMR","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"B6ACLNIW","created_at":"2026-07-05T07:18:59Z"}],"graph_snapshots":[{"event_id":"sha256:488f8c44a918077f35d309c24b7880aadfa2a4f4112af1eff6575c6c290e39ff","target":"graph","created_at":"2026-07-05T07:18:59Z","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/2307.11046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In a standard view of the reinforcement learning problem, an agent's goal is to efficiently identify a policy that maximizes long-term reward. However, this perspective is based on a restricted view of learning as finding a solution, rather than treating learning as endless adaptation. In contrast, continual reinforcement learning refers to the setting in which the best agents never stop learning. Despite the importance of continual reinforcement learning, the community lacks a simple definition of the problem that highlights its commitments and makes its primary concepts precise and clear. To","authors_text":"Andr\\'e Barreto, Benjamin Van Roy, David Abel, Doina Precup, Hado van Hasselt, Satinder Singh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:28:01Z","title":"A Definition of Continual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11046","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":"sha256:5d755c2a669fd017f297791d4dd3737a4062a714dc95a7018cefcd0550c7a504","target":"record","created_at":"2026-07-05T07:18:59Z","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":"5eb0da7738952c5ea1a1e56a1b2fb021df7323de609e4773b8f0acad3f1a0d32","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:28:01Z","title_canon_sha256":"91e714b4b40414d1d7cabb3c6500282bf57a5fe372da0d8f6fc56733c9b767e8"},"schema_version":"1.0","source":{"id":"2307.11046","kind":"arxiv","version":2}},"canonical_sha256":"0f8025b516e89e1cd191b1f384e705a12f67442acec9b50e0ed1cf968a00bcaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f8025b516e89e1cd191b1f384e705a12f67442acec9b50e0ed1cf968a00bcaf","first_computed_at":"2026-07-05T07:18:59.166202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:59.166202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pc4MBUGuyLcV2GaWSU8O8gmDtrhs9ACdxxO4nxRl9EtQSC0NH/40KJ7d5T1dU652iIRL9ZIO4XVFyOXnPZNPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:59.166726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.11046","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d755c2a669fd017f297791d4dd3737a4062a714dc95a7018cefcd0550c7a504","sha256:488f8c44a918077f35d309c24b7880aadfa2a4f4112af1eff6575c6c290e39ff"],"state_sha256":"ec00454604f2b35c48009642754688de1cb8d49ae0923664c1f779b246d12c23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z9EMloScCieyrXhWNDZHATEDL4OOjv0SVEU4MsWvsu+4mlVc5b1klE4NY/9pSNaSqFOydWZAI5jDn1g0SMFUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:44:20.270520Z","bundle_sha256":"e27cfcb4ccd90c48b7a4aa307ac5f579a79183cbee5007e1f5eec0a99c010aa7"}}