{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5KM5FDGJSE6WO43VQXT5LPMU2R","short_pith_number":"pith:5KM5FDGJ","canonical_record":{"source":{"id":"2506.21899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T04:36:05Z","cross_cats_sorted":[],"title_canon_sha256":"89dbbd5f8b53678f295588f6ea95ee9db2e76626befd1d9dcb3b3e8c2c6ce9a2","abstract_canon_sha256":"19ab3954c2e08a41eb42eb395fc573f8939bcb9a72dd77b6de1714406a9adccc"},"schema_version":"1.0"},"canonical_sha256":"ea99d28cc9913d67737585e7d5bd94d4584767a0006e5af00d11944815238062","source":{"kind":"arxiv","id":"2506.21899","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21899","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21899v1","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21899","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"5KM5FDGJSE6W","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"5KM5FDGJSE6WO43V","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"5KM5FDGJ","created_at":"2026-07-05T11:28:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5KM5FDGJSE6WO43VQXT5LPMU2R","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T04:36:05Z","cross_cats_sorted":[],"title_canon_sha256":"89dbbd5f8b53678f295588f6ea95ee9db2e76626befd1d9dcb3b3e8c2c6ce9a2","abstract_canon_sha256":"19ab3954c2e08a41eb42eb395fc573f8939bcb9a72dd77b6de1714406a9adccc"},"schema_version":"1.0"},"canonical_sha256":"ea99d28cc9913d67737585e7d5bd94d4584767a0006e5af00d11944815238062","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:03.671070Z","signature_b64":"ZbB/woRhkpvIaJPoShtfDZOskRscJnBKPzhZMpSPL/aUdi1scNowHzhRrCXBvG2paCgfcSO6WN6tKayXmLmKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea99d28cc9913d67737585e7d5bd94d4584767a0006e5af00d11944815238062","last_reissued_at":"2026-07-05T11:28:03.670618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:03.670618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21899","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ygqUovL76JdbyN8n8YmyHIHQSvHsMj0EGNJPIfnJcEk0esbdXp7juFmHkW++rSJ4cDU0M1hS5dNGdJeGZUntDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:12:08.602886Z"},"content_sha256":"49a3395b8884fa2a2dbe1e5ea58ebfe209b6936ee6f355694fa08f5257fb2648","schema_version":"1.0","event_id":"sha256:49a3395b8884fa2a2dbe1e5ea58ebfe209b6936ee6f355694fa08f5257fb2648"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5KM5FDGJSE6WO43VQXT5LPMU2R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancements and Challenges in Continual Reinforcement Learning: A Comprehensive Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amara Zuffer, Mehrtash Harandi, Michael Burke","submitted_at":"2025-06-27T04:36:05Z","abstract_excerpt":"The diversity of tasks and dynamic nature of reinforcement learning (RL) require RL agents to be able to learn sequentially and continuously, a learning paradigm known as continuous reinforcement learning. This survey reviews how continual learning transforms RL agents into dynamic continual learners. This enables RL agents to acquire and retain useful and reusable knowledge seamlessly. The paper delves into fundamental aspects of continual reinforcement learning, exploring key concepts, significant challenges, and novel methodologies. Special emphasis is placed on recent advancements in conti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21899","kind":"arxiv","version":1},"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/2506.21899/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":"2026-07-05T11:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ie4SSn4jIKoefxneB/kno+IH+fS+P1t+S0rAwKTxSKHu+MOn52hVhIZ2VsWANvcUXBdRm9YDP7xCB3iv3pWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:12:08.603564Z"},"content_sha256":"4356f9bfd6540b3b23a26778c145ee7f4529f89b96e4fe16f80ce530bc0dc82e","schema_version":"1.0","event_id":"sha256:4356f9bfd6540b3b23a26778c145ee7f4529f89b96e4fe16f80ce530bc0dc82e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5KM5FDGJSE6WO43VQXT5LPMU2R/bundle.json","state_url":"https://pith.science/pith/5KM5FDGJSE6WO43VQXT5LPMU2R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5KM5FDGJSE6WO43VQXT5LPMU2R/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":"2026-08-07T20:12:08Z","links":{"resolver":"https://pith.science/pith/5KM5FDGJSE6WO43VQXT5LPMU2R","bundle":"https://pith.science/pith/5KM5FDGJSE6WO43VQXT5LPMU2R/bundle.json","state":"https://pith.science/pith/5KM5FDGJSE6WO43VQXT5LPMU2R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5KM5FDGJSE6WO43VQXT5LPMU2R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5KM5FDGJSE6WO43VQXT5LPMU2R","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":"19ab3954c2e08a41eb42eb395fc573f8939bcb9a72dd77b6de1714406a9adccc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T04:36:05Z","title_canon_sha256":"89dbbd5f8b53678f295588f6ea95ee9db2e76626befd1d9dcb3b3e8c2c6ce9a2"},"schema_version":"1.0","source":{"id":"2506.21899","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21899","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21899v1","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21899","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"5KM5FDGJSE6W","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"5KM5FDGJSE6WO43V","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"5KM5FDGJ","created_at":"2026-07-05T11:28:03Z"}],"graph_snapshots":[{"event_id":"sha256:4356f9bfd6540b3b23a26778c145ee7f4529f89b96e4fe16f80ce530bc0dc82e","target":"graph","created_at":"2026-07-05T11:28:03Z","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/2506.21899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The diversity of tasks and dynamic nature of reinforcement learning (RL) require RL agents to be able to learn sequentially and continuously, a learning paradigm known as continuous reinforcement learning. This survey reviews how continual learning transforms RL agents into dynamic continual learners. This enables RL agents to acquire and retain useful and reusable knowledge seamlessly. The paper delves into fundamental aspects of continual reinforcement learning, exploring key concepts, significant challenges, and novel methodologies. Special emphasis is placed on recent advancements in conti","authors_text":"Amara Zuffer, Mehrtash Harandi, Michael Burke","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T04:36:05Z","title":"Advancements and Challenges in Continual Reinforcement Learning: A Comprehensive Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21899","kind":"arxiv","version":1},"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":"sha256:49a3395b8884fa2a2dbe1e5ea58ebfe209b6936ee6f355694fa08f5257fb2648","target":"record","created_at":"2026-07-05T11:28:03Z","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":"19ab3954c2e08a41eb42eb395fc573f8939bcb9a72dd77b6de1714406a9adccc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T04:36:05Z","title_canon_sha256":"89dbbd5f8b53678f295588f6ea95ee9db2e76626befd1d9dcb3b3e8c2c6ce9a2"},"schema_version":"1.0","source":{"id":"2506.21899","kind":"arxiv","version":1}},"canonical_sha256":"ea99d28cc9913d67737585e7d5bd94d4584767a0006e5af00d11944815238062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea99d28cc9913d67737585e7d5bd94d4584767a0006e5af00d11944815238062","first_computed_at":"2026-07-05T11:28:03.670618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:03.670618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZbB/woRhkpvIaJPoShtfDZOskRscJnBKPzhZMpSPL/aUdi1scNowHzhRrCXBvG2paCgfcSO6WN6tKayXmLmKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:03.671070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21899","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49a3395b8884fa2a2dbe1e5ea58ebfe209b6936ee6f355694fa08f5257fb2648","sha256:4356f9bfd6540b3b23a26778c145ee7f4529f89b96e4fe16f80ce530bc0dc82e"],"state_sha256":"67f57ef0eec8109cf4c2d14b928206a70a65d71d6475439cf5842ee895035d5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XGkyOH8x94ZcX7pey3xj4yyCPgJwu8e7wXI6qV0xR+g2iwjAtdHPfXtilH5wJ8dQSu3LxiT3z878X3aCG+htCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:12:08.609761Z","bundle_sha256":"72e98ea40da29a2d419f1f48b03a1c2e8b64212f31087bfd55d6cc32007746da"}}