{"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"}