{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DK3E7SSR6IGDRJ6XMHKSAPUO7U","short_pith_number":"pith:DK3E7SSR","schema_version":"1.0","canonical_sha256":"1ab64fca51f20c38a7d761d5203e8efd337df51f52de3c51ce1462f1346ab5f9","source":{"kind":"arxiv","id":"2406.02428","version":1},"attestation_state":"computed","paper":{"title":"Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Depeng Li, Junwei Chen, Tianqi Wang, Wei Dai, Zhigang Zeng","submitted_at":"2024-06-04T15:47:03Z","abstract_excerpt":"Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. In this paper, we propose a new kind of connectionist model by tailoring neural unit dynamics that adapt the behavior of neural networks for CIL. In each training session, it introduces a supervisory mechanism to guide network expansion whose growth size is compactly commensurate with the intrinsic complexity of a newly arriving task. This constructs a near-minimal network while allowing the model to expand its capacity when cannot sufficiently hold new clas"},"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":"2406.02428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T15:47:03Z","cross_cats_sorted":[],"title_canon_sha256":"3c9f2284755cd22be9afb2d2016c93f5c5ef9ff71d7a0b3fad286564658a296b","abstract_canon_sha256":"b9df21e33fd98059b0fdd23f2a2c63c3dc0ec6b59cc27c1ddc720abc2b22cef5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:19.631947Z","signature_b64":"OXj6Sn7AQy+z5PWWg2x2/Jgu22/btTbfrbr8C+andfzAu4xH6kExbCFW5JrRtCHZdREO9GGLV2/em7GF3RZaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ab64fca51f20c38a7d761d5203e8efd337df51f52de3c51ce1462f1346ab5f9","last_reissued_at":"2026-07-05T08:27:19.631477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:19.631477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Depeng Li, Junwei Chen, Tianqi Wang, Wei Dai, Zhigang Zeng","submitted_at":"2024-06-04T15:47:03Z","abstract_excerpt":"Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. In this paper, we propose a new kind of connectionist model by tailoring neural unit dynamics that adapt the behavior of neural networks for CIL. In each training session, it introduces a supervisory mechanism to guide network expansion whose growth size is compactly commensurate with the intrinsic complexity of a newly arriving task. This constructs a near-minimal network while allowing the model to expand its capacity when cannot sufficiently hold new clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02428","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/2406.02428/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":"2406.02428","created_at":"2026-07-05T08:27:19.631534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02428v1","created_at":"2026-07-05T08:27:19.631534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02428","created_at":"2026-07-05T08:27:19.631534+00:00"},{"alias_kind":"pith_short_12","alias_value":"DK3E7SSR6IGD","created_at":"2026-07-05T08:27:19.631534+00:00"},{"alias_kind":"pith_short_16","alias_value":"DK3E7SSR6IGDRJ6X","created_at":"2026-07-05T08:27:19.631534+00:00"},{"alias_kind":"pith_short_8","alias_value":"DK3E7SSR","created_at":"2026-07-05T08:27:19.631534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15454","citing_title":"On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U","json":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U.json","graph_json":"https://pith.science/api/pith-number/DK3E7SSR6IGDRJ6XMHKSAPUO7U/graph.json","events_json":"https://pith.science/api/pith-number/DK3E7SSR6IGDRJ6XMHKSAPUO7U/events.json","paper":"https://pith.science/paper/DK3E7SSR"},"agent_actions":{"view_html":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U","download_json":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U.json","view_paper":"https://pith.science/paper/DK3E7SSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02428&json=true","fetch_graph":"https://pith.science/api/pith-number/DK3E7SSR6IGDRJ6XMHKSAPUO7U/graph.json","fetch_events":"https://pith.science/api/pith-number/DK3E7SSR6IGDRJ6XMHKSAPUO7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U/action/storage_attestation","attest_author":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U/action/author_attestation","sign_citation":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U/action/citation_signature","submit_replication":"https://pith.science/pith/DK3E7SSR6IGDRJ6XMHKSAPUO7U/action/replication_record"}},"created_at":"2026-07-05T08:27:19.631534+00:00","updated_at":"2026-07-05T08:27:19.631534+00:00"}