{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YRRAMBCSV6N7FRBQPYXSDEKN4R","short_pith_number":"pith:YRRAMBCS","canonical_record":{"source":{"id":"2604.15414","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T17:06:54Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"6c57bfe0876c73341a1ce4467f8d84cf5f1c6262a2fbb3748ecf118c9dc27bf8","abstract_canon_sha256":"70747f82ce3b80c13704025f935cc09399e3c4d0b489caa3754d21dac4522897"},"schema_version":"1.0"},"canonical_sha256":"c462060452af9bf2c4307e2f21914de442ef06c3c7eb296a896034909f09d8aa","source":{"kind":"arxiv","id":"2604.15414","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.15414","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2604.15414v2","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.15414","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"YRRAMBCSV6N7","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"YRRAMBCSV6N7FRBQ","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"YRRAMBCS","created_at":"2026-06-10T01:08:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YRRAMBCSV6N7FRBQPYXSDEKN4R","target":"record","payload":{"canonical_record":{"source":{"id":"2604.15414","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T17:06:54Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"6c57bfe0876c73341a1ce4467f8d84cf5f1c6262a2fbb3748ecf118c9dc27bf8","abstract_canon_sha256":"70747f82ce3b80c13704025f935cc09399e3c4d0b489caa3754d21dac4522897"},"schema_version":"1.0"},"canonical_sha256":"c462060452af9bf2c4307e2f21914de442ef06c3c7eb296a896034909f09d8aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:08:35.446112Z","signature_b64":"LHArJsUHVNSTQeGzX0rfTCQAbzhDRtdo9WGKBK49W7cvXH4suHwvL/ITdae63D0OEa3I1LAPNB35NhlAFAJTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c462060452af9bf2c4307e2f21914de442ef06c3c7eb296a896034909f09d8aa","last_reissued_at":"2026-06-10T01:08:35.445009Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:08:35.445009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.15414","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":"2026-06-10T01:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOXIe36xIweq2hMquMcQXAhLEOxr4XSPUDcJrBapMULf5LbkFtxIGfulOzUSFnYupU7IY+pv7Knn7qPzkMsGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T13:12:35.656277Z"},"content_sha256":"c842cf93ddb5a820fe95e0a6ceacdca35ccad056356858b9a73b051a79014cad","schema_version":"1.0","event_id":"sha256:c842cf93ddb5a820fe95e0a6ceacdca35ccad056356858b9a73b051a79014cad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YRRAMBCSV6N7FRBQPYXSDEKN4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Maintaining archives of diverse policies in a shared latent space preserves plasticity in continual reinforcement learning.","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Lute Lillo, Nick Cheney","submitted_at":"2026-04-16T17:06:54Z","abstract_excerpt":"Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \\emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously successful policy is retained, it may no longer provide a reliable starting point for rapid adaptation after interference, reflecting a form of \\emph{loss of plasticity} that single-policy preservation cannot address. Inspired by quality-diversity methods, we introduce \\textsc{TeLAPA} (Transfer-Enabled Latent-Aligned Policy Archives), a continual RL framework"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In our MiniGrid CL setting, TeLAPA learns more tasks successfully, recovers competence faster on revisited tasks after interference, and retains higher performance across a sequence of tasks. Our analyses show that source-optimal policies are often not transfer-optimal, even within a local competent neighborhood, and that effective reuse depends on retaining and selecting among multiple nearby alternatives rather than collapsing them to one representative.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That organizing policies into behaviorally diverse neighborhoods via a shared latent space will reliably preserve plasticity and transfer better than single-model preservation across a wide range of continual RL domains and interference patterns.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Maintaining archives of diverse policies in a shared latent space preserves plasticity in continual reinforcement learning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8257ab599890b7d64ca5e74285966f095502f11f70a030cab81649447d8d2bbd"},"source":{"id":"2604.15414","kind":"arxiv","version":2},"verdict":{"id":"c9dee478-1f4a-4b6b-8206-e391795a0c0b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T10:57:09.649445Z","strongest_claim":"In our MiniGrid CL setting, TeLAPA learns more tasks successfully, recovers competence faster on revisited tasks after interference, and retains higher performance across a sequence of tasks. Our analyses show that source-optimal policies are often not transfer-optimal, even within a local competent neighborhood, and that effective reuse depends on retaining and selecting among multiple nearby alternatives rather than collapsing them to one representative.","one_line_summary":"TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That organizing policies into behaviorally diverse neighborhoods via a shared latent space will reliably preserve plasticity and transfer better than single-model preservation across a wide range of continual RL domains and interference patterns.","pith_extraction_headline":"Maintaining archives of diverse policies in a shared latent space preserves plasticity in continual reinforcement learning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.15414/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":"c9dee478-1f4a-4b6b-8206-e391795a0c0b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ScNHurfPrzRYjYYG3UPRLXWHf8rk7NufHoTtv76DoCXe2G0GRnpYzltcHADz9FTI2H6uIJG5MiPK5K7BbRspAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T13:12:35.657166Z"},"content_sha256":"f62df04e6bd1e11b5e9997c106b8603b7a61de1e6bb4b2831366531a65dfdef5","schema_version":"1.0","event_id":"sha256:f62df04e6bd1e11b5e9997c106b8603b7a61de1e6bb4b2831366531a65dfdef5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRRAMBCSV6N7FRBQPYXSDEKN4R/bundle.json","state_url":"https://pith.science/pith/YRRAMBCSV6N7FRBQPYXSDEKN4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRRAMBCSV6N7FRBQPYXSDEKN4R/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":"2026-06-11T13:12:35Z","links":{"resolver":"https://pith.science/pith/YRRAMBCSV6N7FRBQPYXSDEKN4R","bundle":"https://pith.science/pith/YRRAMBCSV6N7FRBQPYXSDEKN4R/bundle.json","state":"https://pith.science/pith/YRRAMBCSV6N7FRBQPYXSDEKN4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRRAMBCSV6N7FRBQPYXSDEKN4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YRRAMBCSV6N7FRBQPYXSDEKN4R","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":"70747f82ce3b80c13704025f935cc09399e3c4d0b489caa3754d21dac4522897","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T17:06:54Z","title_canon_sha256":"6c57bfe0876c73341a1ce4467f8d84cf5f1c6262a2fbb3748ecf118c9dc27bf8"},"schema_version":"1.0","source":{"id":"2604.15414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.15414","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2604.15414v2","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.15414","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"YRRAMBCSV6N7","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"YRRAMBCSV6N7FRBQ","created_at":"2026-06-10T01:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"YRRAMBCS","created_at":"2026-06-10T01:08:35Z"}],"graph_snapshots":[{"event_id":"sha256:f62df04e6bd1e11b5e9997c106b8603b7a61de1e6bb4b2831366531a65dfdef5","target":"graph","created_at":"2026-06-10T01:08:35Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"In our MiniGrid CL setting, TeLAPA learns more tasks successfully, recovers competence faster on revisited tasks after interference, and retains higher performance across a sequence of tasks. Our analyses show that source-optimal policies are often not transfer-optimal, even within a local competent neighborhood, and that effective reuse depends on retaining and selecting among multiple nearby alternatives rather than collapsing them to one representative."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That organizing policies into behaviorally diverse neighborhoods via a shared latent space will reliably preserve plasticity and transfer better than single-model preservation across a wide range of continual RL domains and interference patterns."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Maintaining archives of diverse policies in a shared latent space preserves plasticity in continual reinforcement learning."}],"snapshot_sha256":"8257ab599890b7d64ca5e74285966f095502f11f70a030cab81649447d8d2bbd"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.15414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \\emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously successful policy is retained, it may no longer provide a reliable starting point for rapid adaptation after interference, reflecting a form of \\emph{loss of plasticity} that single-policy preservation cannot address. Inspired by quality-diversity methods, we introduce \\textsc{TeLAPA} (Transfer-Enabled Latent-Aligned Policy Archives), a continual RL framework","authors_text":"Lute Lillo, Nick Cheney","cross_cats":["cs.AI","cs.NE"],"headline":"Maintaining archives of diverse policies in a shared latent space preserves plasticity in continual reinforcement learning.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T17:06:54Z","title":"Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.15414","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T10:57:09.649445Z","id":"c9dee478-1f4a-4b6b-8206-e391795a0c0b","model_set":{"reader":"grok-4.3"},"one_line_summary":"TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Maintaining archives of diverse policies in a shared latent space preserves plasticity in continual reinforcement learning.","strongest_claim":"In our MiniGrid CL setting, TeLAPA learns more tasks successfully, recovers competence faster on revisited tasks after interference, and retains higher performance across a sequence of tasks. Our analyses show that source-optimal policies are often not transfer-optimal, even within a local competent neighborhood, and that effective reuse depends on retaining and selecting among multiple nearby alternatives rather than collapsing them to one representative.","weakest_assumption":"That organizing policies into behaviorally diverse neighborhoods via a shared latent space will reliably preserve plasticity and transfer better than single-model preservation across a wide range of continual RL domains and interference patterns."}},"verdict_id":"c9dee478-1f4a-4b6b-8206-e391795a0c0b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c842cf93ddb5a820fe95e0a6ceacdca35ccad056356858b9a73b051a79014cad","target":"record","created_at":"2026-06-10T01:08:35Z","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":"70747f82ce3b80c13704025f935cc09399e3c4d0b489caa3754d21dac4522897","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T17:06:54Z","title_canon_sha256":"6c57bfe0876c73341a1ce4467f8d84cf5f1c6262a2fbb3748ecf118c9dc27bf8"},"schema_version":"1.0","source":{"id":"2604.15414","kind":"arxiv","version":2}},"canonical_sha256":"c462060452af9bf2c4307e2f21914de442ef06c3c7eb296a896034909f09d8aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c462060452af9bf2c4307e2f21914de442ef06c3c7eb296a896034909f09d8aa","first_computed_at":"2026-06-10T01:08:35.445009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:08:35.445009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LHArJsUHVNSTQeGzX0rfTCQAbzhDRtdo9WGKBK49W7cvXH4suHwvL/ITdae63D0OEa3I1LAPNB35NhlAFAJTDA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:08:35.446112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.15414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c842cf93ddb5a820fe95e0a6ceacdca35ccad056356858b9a73b051a79014cad","sha256:f62df04e6bd1e11b5e9997c106b8603b7a61de1e6bb4b2831366531a65dfdef5"],"state_sha256":"adb1b2aed52f1926afd25c116778b45697d41ad89cc880b02311ccc2f99f1535"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ed0/F08gjTPJQCOtAljxo+uML3MUFql9/jm0bFWmpu2avVjzIk99V59alqIl0NIGFpZqY0fCwoE+7qCTW57bCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T13:12:35.661763Z","bundle_sha256":"ccdbe7af1266d97fa5b385d2072bd329c1f2c0ab6801490d66c68f78aa67c870"}}