{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VR4LNWBIBPFNW4TXJKABQYVNGK","short_pith_number":"pith:VR4LNWBI","schema_version":"1.0","canonical_sha256":"ac78b6d8280bcadb72774a801862ad32a6733e9b3ec78e2896878522d62c335b","source":{"kind":"arxiv","id":"2312.07082","version":1},"attestation_state":"computed","paper":{"title":"Continual Learning through Networks Splitting and Merging with Dreaming-Meta-Weighted Model Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglei Xie, Jian Li, Qiang Fang, Xin Xu, Yifei Shi, Yi Sun","submitted_at":"2023-12-12T09:02:56Z","abstract_excerpt":"It's challenging to balance the networks stability and plasticity in continual learning scenarios, considering stability suffers from the update of model and plasticity benefits from it. Existing works usually focus more on the stability and restrict the learning plasticity of later tasks to avoid catastrophic forgetting of learned knowledge. Differently, we propose a continual learning method named Split2MetaFusion which can achieve better trade-off by employing a two-stage strategy: splitting and meta-weighted fusion. In this strategy, a slow model with better stability, and a fast model wit"},"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":"2312.07082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T09:02:56Z","cross_cats_sorted":[],"title_canon_sha256":"6d290abe9d1a4c74d1d27a600780d050a91e398e64ecd1d70b52d801cfe6fc4f","abstract_canon_sha256":"321a046bdba7a63791a84da32f449355c633c44e83a95278743ca6bc3e658796"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:14.682073Z","signature_b64":"9QyYUghoF4iNkrusvfZzc612AEZokhS/cviBPE2df2dVzzZ/oZuuFNHagWqYs29rIABTnYBBiCWU2lPsubVlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac78b6d8280bcadb72774a801862ad32a6733e9b3ec78e2896878522d62c335b","last_reissued_at":"2026-07-05T07:23:14.681496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:14.681496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning through Networks Splitting and Merging with Dreaming-Meta-Weighted Model Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglei Xie, Jian Li, Qiang Fang, Xin Xu, Yifei Shi, Yi Sun","submitted_at":"2023-12-12T09:02:56Z","abstract_excerpt":"It's challenging to balance the networks stability and plasticity in continual learning scenarios, considering stability suffers from the update of model and plasticity benefits from it. Existing works usually focus more on the stability and restrict the learning plasticity of later tasks to avoid catastrophic forgetting of learned knowledge. Differently, we propose a continual learning method named Split2MetaFusion which can achieve better trade-off by employing a two-stage strategy: splitting and meta-weighted fusion. In this strategy, a slow model with better stability, and a fast model wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07082","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/2312.07082/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":"2312.07082","created_at":"2026-07-05T07:23:14.681559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07082v1","created_at":"2026-07-05T07:23:14.681559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07082","created_at":"2026-07-05T07:23:14.681559+00:00"},{"alias_kind":"pith_short_12","alias_value":"VR4LNWBIBPFN","created_at":"2026-07-05T07:23:14.681559+00:00"},{"alias_kind":"pith_short_16","alias_value":"VR4LNWBIBPFNW4TX","created_at":"2026-07-05T07:23:14.681559+00:00"},{"alias_kind":"pith_short_8","alias_value":"VR4LNWBI","created_at":"2026-07-05T07:23:14.681559+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/VR4LNWBIBPFNW4TXJKABQYVNGK","json":"https://pith.science/pith/VR4LNWBIBPFNW4TXJKABQYVNGK.json","graph_json":"https://pith.science/api/pith-number/VR4LNWBIBPFNW4TXJKABQYVNGK/graph.json","events_json":"https://pith.science/api/pith-number/VR4LNWBIBPFNW4TXJKABQYVNGK/events.json","paper":"https://pith.science/paper/VR4LNWBI"},"agent_actions":{"view_html":"https://pith.science/pith/VR4LNWBIBPFNW4TXJKABQYVNGK","download_json":"https://pith.science/pith/VR4LNWBIBPFNW4TXJKABQYVNGK.json","view_paper":"https://pith.science/paper/VR4LNWBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07082&json=true","fetch_graph":"https://pith.science/api/pith-number/VR4LNWBIBPFNW4TXJKABQYVNGK/graph.json","fetch_events":"https://pith.science/api/pith-number/VR4LNWBIBPFNW4TXJKABQYVNGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VR4LNWBIBPFNW4TXJKABQYVNGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VR4LNWBIBPFNW4TXJKABQYVNGK/action/storage_attestation","attest_author":"https://pith.science/pith/VR4LNWBIBPFNW4TXJKABQYVNGK/action/author_attestation","sign_citation":"https://pith.science/pith/VR4LNWBIBPFNW4TXJKABQYVNGK/action/citation_signature","submit_replication":"https://pith.science/pith/VR4LNWBIBPFNW4TXJKABQYVNGK/action/replication_record"}},"created_at":"2026-07-05T07:23:14.681559+00:00","updated_at":"2026-07-05T07:23:14.681559+00:00"}