{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SSG4ARERQEB4TI3ZHVXCTQYVLF","short_pith_number":"pith:SSG4ARER","schema_version":"1.0","canonical_sha256":"948dc044918103c9a3793d6e29c315597f79b5635b770b2ddf7cc4878ab77327","source":{"kind":"arxiv","id":"2406.02596","version":2},"attestation_state":"computed","paper":{"title":"Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Clare Lyle, Donghu Kim, Dugki Min, Hojoon Lee, Hyeonseo Cho, Hyunseung Kim, Jaegul Choo","submitted_at":"2024-06-01T05:55:15Z","abstract_excerpt":"This study investigates the loss of generalization ability in neural networks, revisiting warm-starting experiments from Ash & Adams. Our empirical analysis reveals that common methods designed to enhance plasticity by maintaining trainability provide limited benefits to generalization. While reinitializing the network can be effective, it also risks losing valuable prior knowledge. To this end, we introduce the Hare & Tortoise, inspired by the brain's complementary learning system. Hare & Tortoise consists of two components: the Hare network, which rapidly adapts to new information analogousl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.02596","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-01T05:55:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1619ad434fcdf537b1dad6176e28fbd638ff19eef2fb06a3f083d154db1e9027","abstract_canon_sha256":"168436ea2f0b1a29c197f759e3349b27597c9e63107d909c79058a043cf3a912"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:04.818966Z","signature_b64":"w6QUfa9qCazyZ2UtW47UaMRDsquYEUTA8OYvmBlnQn6uSp5izx6PxIOFVJS+zNQCdRZqmk/lZFF6Ebq8+GuFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"948dc044918103c9a3793d6e29c315597f79b5635b770b2ddf7cc4878ab77327","last_reissued_at":"2026-07-05T10:09:04.818488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:04.818488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Clare Lyle, Donghu Kim, Dugki Min, Hojoon Lee, Hyeonseo Cho, Hyunseung Kim, Jaegul Choo","submitted_at":"2024-06-01T05:55:15Z","abstract_excerpt":"This study investigates the loss of generalization ability in neural networks, revisiting warm-starting experiments from Ash & Adams. Our empirical analysis reveals that common methods designed to enhance plasticity by maintaining trainability provide limited benefits to generalization. While reinitializing the network can be effective, it also risks losing valuable prior knowledge. To this end, we introduce the Hare & Tortoise, inspired by the brain's complementary learning system. Hare & Tortoise consists of two components: the Hare network, which rapidly adapts to new information analogousl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02596","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/2406.02596/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.02596","created_at":"2026-07-05T10:09:04.818549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02596v2","created_at":"2026-07-05T10:09:04.818549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02596","created_at":"2026-07-05T10:09:04.818549+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSG4ARERQEB4","created_at":"2026-07-05T10:09:04.818549+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSG4ARERQEB4TI3Z","created_at":"2026-07-05T10:09:04.818549+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSG4ARER","created_at":"2026-07-05T10:09:04.818549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23995","citing_title":"EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26357","citing_title":"Balancing Plasticity and Stability with Fast and Slow Successor Features","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04539","citing_title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09028","citing_title":"Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04539","citing_title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13521","citing_title":"C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF","json":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF.json","graph_json":"https://pith.science/api/pith-number/SSG4ARERQEB4TI3ZHVXCTQYVLF/graph.json","events_json":"https://pith.science/api/pith-number/SSG4ARERQEB4TI3ZHVXCTQYVLF/events.json","paper":"https://pith.science/paper/SSG4ARER"},"agent_actions":{"view_html":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF","download_json":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF.json","view_paper":"https://pith.science/paper/SSG4ARER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02596&json=true","fetch_graph":"https://pith.science/api/pith-number/SSG4ARERQEB4TI3ZHVXCTQYVLF/graph.json","fetch_events":"https://pith.science/api/pith-number/SSG4ARERQEB4TI3ZHVXCTQYVLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF/action/storage_attestation","attest_author":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF/action/author_attestation","sign_citation":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF/action/citation_signature","submit_replication":"https://pith.science/pith/SSG4ARERQEB4TI3ZHVXCTQYVLF/action/replication_record"}},"created_at":"2026-07-05T10:09:04.818549+00:00","updated_at":"2026-07-05T10:09:04.818549+00:00"}