{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HRQIYAXBZMT4JGKYDGADXMOFHI","short_pith_number":"pith:HRQIYAXB","canonical_record":{"source":{"id":"2605.22454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T13:19:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"979304454219ff838786614f12383c794bb0b35e9a3ce59893e8d97654792274","abstract_canon_sha256":"b1595da6a04411285ec1c5df694564f3c47a63475f30420522c45bfccf793996"},"schema_version":"1.0"},"canonical_sha256":"3c608c02e1cb27c4995819803bb1c53a0b55d62de4f7906157849186e7e9af12","source":{"kind":"arxiv","id":"2605.22454","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22454","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22454v1","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22454","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"HRQIYAXBZMT4","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"HRQIYAXBZMT4JGKY","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"HRQIYAXB","created_at":"2026-05-22T01:04:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HRQIYAXBZMT4JGKYDGADXMOFHI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T13:19:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"979304454219ff838786614f12383c794bb0b35e9a3ce59893e8d97654792274","abstract_canon_sha256":"b1595da6a04411285ec1c5df694564f3c47a63475f30420522c45bfccf793996"},"schema_version":"1.0"},"canonical_sha256":"3c608c02e1cb27c4995819803bb1c53a0b55d62de4f7906157849186e7e9af12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:43.721831Z","signature_b64":"p7P3cmUoa/dVHAD2qUc90aRtvEe0SUUjGoKGXFJAuiRFS0Fea2XeiEtpzdrk7R0ndKVezSkMxYyfYaM21D4QBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c608c02e1cb27c4995819803bb1c53a0b55d62de4f7906157849186e7e9af12","last_reissued_at":"2026-05-22T01:04:43.721157Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:43.721157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22454","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":"2026-05-22T01:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SKuO5tk3JNJxxwtwjBqFl32cIvKliJkOhd+lMtg5bocYpN0sFRplxUdq4tMAgXZ9tiGx2kOEnT9AmL43eEFZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T17:33:27.202018Z"},"content_sha256":"3127d02db052d106cf108ed0ed0c40681e1d9ace7dcb9c86ab8a4cb5d1a5ef6c","schema_version":"1.0","event_id":"sha256:3127d02db052d106cf108ed0ed0c40681e1d9ace7dcb9c86ab8a4cb5d1a5ef6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HRQIYAXBZMT4JGKYDGADXMOFHI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrew Quinn, Benjamin Poole, Li Yang, Minwoo Lee","submitted_at":"2026-05-21T13:19:50Z","abstract_excerpt":"Data rehearsal has emerged as a leading approach for mitigating catastrophic forgetting in Continual Reinforcement Learning (CRL). However, existing work remains confined to policy gradient frameworks, regularizing only actors due to the performance degradation incurred by critic regularization. This actor-centric approach overlooks the potential of data rehearsal for value function approximation. Moreover, existing evaluations in CRL rarely consider multi-cyclic environments where task sequences repeat, a critical real-world scenario that exacerbates forgetting and plasticity. We investigate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22454","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/2605.22454/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":"2026-05-22T01:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rQmVQsKpkUYHPNVpFYz7WjTplvMaPLAj9d7fctk/UqlmBkRWTMuewW0/NZS3BXcp9dJFQyoXtfr7y3IqXLiSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T17:33:27.202415Z"},"content_sha256":"80ae2706af96c9da4a33fe09dbc1424ef36284ce9f506589569cea45d3c60352","schema_version":"1.0","event_id":"sha256:80ae2706af96c9da4a33fe09dbc1424ef36284ce9f506589569cea45d3c60352"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRQIYAXBZMT4JGKYDGADXMOFHI/bundle.json","state_url":"https://pith.science/pith/HRQIYAXBZMT4JGKYDGADXMOFHI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRQIYAXBZMT4JGKYDGADXMOFHI/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":"2026-06-05T17:33:27Z","links":{"resolver":"https://pith.science/pith/HRQIYAXBZMT4JGKYDGADXMOFHI","bundle":"https://pith.science/pith/HRQIYAXBZMT4JGKYDGADXMOFHI/bundle.json","state":"https://pith.science/pith/HRQIYAXBZMT4JGKYDGADXMOFHI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRQIYAXBZMT4JGKYDGADXMOFHI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HRQIYAXBZMT4JGKYDGADXMOFHI","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":"b1595da6a04411285ec1c5df694564f3c47a63475f30420522c45bfccf793996","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T13:19:50Z","title_canon_sha256":"979304454219ff838786614f12383c794bb0b35e9a3ce59893e8d97654792274"},"schema_version":"1.0","source":{"id":"2605.22454","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22454","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22454v1","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22454","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"HRQIYAXBZMT4","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"HRQIYAXBZMT4JGKY","created_at":"2026-05-22T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"HRQIYAXB","created_at":"2026-05-22T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:80ae2706af96c9da4a33fe09dbc1424ef36284ce9f506589569cea45d3c60352","target":"graph","created_at":"2026-05-22T01:04:43Z","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/2605.22454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data rehearsal has emerged as a leading approach for mitigating catastrophic forgetting in Continual Reinforcement Learning (CRL). However, existing work remains confined to policy gradient frameworks, regularizing only actors due to the performance degradation incurred by critic regularization. This actor-centric approach overlooks the potential of data rehearsal for value function approximation. Moreover, existing evaluations in CRL rarely consider multi-cyclic environments where task sequences repeat, a critical real-world scenario that exacerbates forgetting and plasticity. We investigate ","authors_text":"Andrew Quinn, Benjamin Poole, Li Yang, Minwoo Lee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T13:19:50Z","title":"Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22454","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":"sha256:3127d02db052d106cf108ed0ed0c40681e1d9ace7dcb9c86ab8a4cb5d1a5ef6c","target":"record","created_at":"2026-05-22T01:04:43Z","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":"b1595da6a04411285ec1c5df694564f3c47a63475f30420522c45bfccf793996","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T13:19:50Z","title_canon_sha256":"979304454219ff838786614f12383c794bb0b35e9a3ce59893e8d97654792274"},"schema_version":"1.0","source":{"id":"2605.22454","kind":"arxiv","version":1}},"canonical_sha256":"3c608c02e1cb27c4995819803bb1c53a0b55d62de4f7906157849186e7e9af12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c608c02e1cb27c4995819803bb1c53a0b55d62de4f7906157849186e7e9af12","first_computed_at":"2026-05-22T01:04:43.721157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:43.721157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p7P3cmUoa/dVHAD2qUc90aRtvEe0SUUjGoKGXFJAuiRFS0Fea2XeiEtpzdrk7R0ndKVezSkMxYyfYaM21D4QBA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:43.721831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22454","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3127d02db052d106cf108ed0ed0c40681e1d9ace7dcb9c86ab8a4cb5d1a5ef6c","sha256:80ae2706af96c9da4a33fe09dbc1424ef36284ce9f506589569cea45d3c60352"],"state_sha256":"ec920e0f7fc5e42503d2d2ec79ee4ca7e00ee80e6e0bd0225ed3fca623130027"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8iWmD+iMprrc3jYA9pGy+K19EoOv5nRzHLgOlR8fMGfSQQQRS1PfymkjAIReoLHyo+tjovTz0JcFvAfRnWfAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T17:33:27.204787Z","bundle_sha256":"50e834ef9c3cb1628546ebbada47b20ad435c64999899c0b6299bf1530d8ba99"}}