{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4NSPAS7GLVKEQ72UUZOOXTW3IZ","short_pith_number":"pith:4NSPAS7G","schema_version":"1.0","canonical_sha256":"e364f04be65d54487f54a65cebcedb46493865f77084931a139e04d6bd45ad9e","source":{"kind":"arxiv","id":"2605.17571","version":1},"attestation_state":"computed","paper":{"title":"Stable Routing for Mixture-of-Experts in Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da-Wei Zhou, Lijun Zhang, Quan Cheng, Zirui Guo","submitted_at":"2026-05-17T17:59:03Z","abstract_excerpt":"Class-incremental learning (CIL) requires models to learn new classes sequentially while preserving prior knowledge. Recently, approaches that combine pre-trained models with mixture-of-experts (MoE) have received increasing attention in CIL: they typically expand experts during learning and employ a router to assign weights across experts. However, existing MoE methods often overlook routing drift induced by expert expansion. Once new experts are introduced, the router may reassign samples from earlier classes to newly added experts, thereby perturbing previously established expert compositio"},"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":"2605.17571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-17T17:59:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de3894ad7de7a25d44dc5f5cba654988c7008a9044546d1f0b573f0827942ae1","abstract_canon_sha256":"f87e1f02b278178bb90d5f2377e32a5dc395754add692ee2ba4f94f5328d22e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:46.534059Z","signature_b64":"3sDKFFg35PrexTzTUR1lXZcA1Un7Ul3mEpEQUC80Ks/fqEh16kPQci2U6nDUH90EIld4wOcswHl9KJ0fbH3JDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e364f04be65d54487f54a65cebcedb46493865f77084931a139e04d6bd45ad9e","last_reissued_at":"2026-05-20T00:04:46.533206Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:46.533206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Routing for Mixture-of-Experts in Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da-Wei Zhou, Lijun Zhang, Quan Cheng, Zirui Guo","submitted_at":"2026-05-17T17:59:03Z","abstract_excerpt":"Class-incremental learning (CIL) requires models to learn new classes sequentially while preserving prior knowledge. Recently, approaches that combine pre-trained models with mixture-of-experts (MoE) have received increasing attention in CIL: they typically expand experts during learning and employ a router to assign weights across experts. However, existing MoE methods often overlook routing drift induced by expert expansion. Once new experts are introduced, the router may reassign samples from earlier classes to newly added experts, thereby perturbing previously established expert compositio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17571","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/2605.17571/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.594741Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.526192Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"24b7d39fc2681294b2f2f5a4bd0591e358e8c374d321acb72d8854161fc66a3b"},"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":"2605.17571","created_at":"2026-05-20T00:04:46.533337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17571v1","created_at":"2026-05-20T00:04:46.533337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17571","created_at":"2026-05-20T00:04:46.533337+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NSPAS7GLVKE","created_at":"2026-05-20T00:04:46.533337+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NSPAS7GLVKEQ72U","created_at":"2026-05-20T00:04:46.533337+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NSPAS7G","created_at":"2026-05-20T00:04:46.533337+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/4NSPAS7GLVKEQ72UUZOOXTW3IZ","json":"https://pith.science/pith/4NSPAS7GLVKEQ72UUZOOXTW3IZ.json","graph_json":"https://pith.science/api/pith-number/4NSPAS7GLVKEQ72UUZOOXTW3IZ/graph.json","events_json":"https://pith.science/api/pith-number/4NSPAS7GLVKEQ72UUZOOXTW3IZ/events.json","paper":"https://pith.science/paper/4NSPAS7G"},"agent_actions":{"view_html":"https://pith.science/pith/4NSPAS7GLVKEQ72UUZOOXTW3IZ","download_json":"https://pith.science/pith/4NSPAS7GLVKEQ72UUZOOXTW3IZ.json","view_paper":"https://pith.science/paper/4NSPAS7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17571&json=true","fetch_graph":"https://pith.science/api/pith-number/4NSPAS7GLVKEQ72UUZOOXTW3IZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4NSPAS7GLVKEQ72UUZOOXTW3IZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NSPAS7GLVKEQ72UUZOOXTW3IZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NSPAS7GLVKEQ72UUZOOXTW3IZ/action/storage_attestation","attest_author":"https://pith.science/pith/4NSPAS7GLVKEQ72UUZOOXTW3IZ/action/author_attestation","sign_citation":"https://pith.science/pith/4NSPAS7GLVKEQ72UUZOOXTW3IZ/action/citation_signature","submit_replication":"https://pith.science/pith/4NSPAS7GLVKEQ72UUZOOXTW3IZ/action/replication_record"}},"created_at":"2026-05-20T00:04:46.533337+00:00","updated_at":"2026-05-20T00:04:46.533337+00:00"}