{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3PV3IEKNBGEEICCV4DUATBFKYC","short_pith_number":"pith:3PV3IEKN","schema_version":"1.0","canonical_sha256":"dbebb4114d0988440855e0e80984aac0ab0df3b857349cd64f51cf014b863f36","source":{"kind":"arxiv","id":"2507.13107","version":1},"attestation_state":"computed","paper":{"title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongliang Li, Lili Pan, Xiaohan Guo, Yusong Cai, Zejia Liu, Zhengning Wang","submitted_at":"2025-07-17T13:22:40Z","abstract_excerpt":"Enabling large-scale generative models to continuously learn new visual concepts is essential for personalizing pre-trained models to meet individual user preferences. Existing approaches for continual visual concept learning are constrained by two fundamental challenges: catastrophic forgetting and parameter expansion. In this paper, we propose Redundancy-Removal Mixture of Experts (R^2MoE), a parameter-efficient framework for lifelong visual concept learning that effectively learns new concepts while incurring minimal parameter overhead. Our framework includes three key innovative contributi"},"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":"2507.13107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T13:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"00e5e9e8b608f6092498249e20aa6362ba2fc8cd56db66661e011fa5d6e31b20","abstract_canon_sha256":"41114f96d480e85bb773e3180467e02908a2c3a16f7eaca58d9acd0c1191d012"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:54.831363Z","signature_b64":"61ElrOI1oDhTOp6icLl1ZCJiRfnElHwd1qVqDsgBmyB3UAhUwQ0rRevuw+6DdXBIUAx7mmANS7ng3q76HbfxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbebb4114d0988440855e0e80984aac0ab0df3b857349cd64f51cf014b863f36","last_reissued_at":"2026-07-05T11:38:54.830841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:54.830841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongliang Li, Lili Pan, Xiaohan Guo, Yusong Cai, Zejia Liu, Zhengning Wang","submitted_at":"2025-07-17T13:22:40Z","abstract_excerpt":"Enabling large-scale generative models to continuously learn new visual concepts is essential for personalizing pre-trained models to meet individual user preferences. Existing approaches for continual visual concept learning are constrained by two fundamental challenges: catastrophic forgetting and parameter expansion. In this paper, we propose Redundancy-Removal Mixture of Experts (R^2MoE), a parameter-efficient framework for lifelong visual concept learning that effectively learns new concepts while incurring minimal parameter overhead. Our framework includes three key innovative contributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13107","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/2507.13107/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":"2507.13107","created_at":"2026-07-05T11:38:54.830894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13107v1","created_at":"2026-07-05T11:38:54.830894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13107","created_at":"2026-07-05T11:38:54.830894+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PV3IEKNBGEE","created_at":"2026-07-05T11:38:54.830894+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PV3IEKNBGEEICCV","created_at":"2026-07-05T11:38:54.830894+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PV3IEKN","created_at":"2026-07-05T11:38:54.830894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC","json":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC.json","graph_json":"https://pith.science/api/pith-number/3PV3IEKNBGEEICCV4DUATBFKYC/graph.json","events_json":"https://pith.science/api/pith-number/3PV3IEKNBGEEICCV4DUATBFKYC/events.json","paper":"https://pith.science/paper/3PV3IEKN"},"agent_actions":{"view_html":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC","download_json":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC.json","view_paper":"https://pith.science/paper/3PV3IEKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13107&json=true","fetch_graph":"https://pith.science/api/pith-number/3PV3IEKNBGEEICCV4DUATBFKYC/graph.json","fetch_events":"https://pith.science/api/pith-number/3PV3IEKNBGEEICCV4DUATBFKYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC/action/storage_attestation","attest_author":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC/action/author_attestation","sign_citation":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC/action/citation_signature","submit_replication":"https://pith.science/pith/3PV3IEKNBGEEICCV4DUATBFKYC/action/replication_record"}},"created_at":"2026-07-05T11:38:54.830894+00:00","updated_at":"2026-07-05T11:38:54.830894+00:00"}