{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TSKKZMILPUJSC6QH6NJC7OEL6W","short_pith_number":"pith:TSKKZMIL","schema_version":"1.0","canonical_sha256":"9c94acb10b7d13217a07f3522fb88bf592794ef74457e0514792c1e72c7b9cba","source":{"kind":"arxiv","id":"2402.18086","version":4},"attestation_state":"computed","paper":{"title":"Generalizable Two-Branch Framework for Image Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Wu, Ruixuan Wang, Xiaobin Chang","submitted_at":"2024-02-28T06:18:33Z","abstract_excerpt":"Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and achieved substantial improvements. In this paper, a novel two-branch continual learning framework is proposed to further enhance most existing CL methods. Specifically, the main branch can be any existing CL model and the newly introduced side branch is a lightweight convolutional network. The output of each main branch block is modulated by the output of the"},"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":"2402.18086","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T06:18:33Z","cross_cats_sorted":[],"title_canon_sha256":"47029ca8ed855b732b743eb4d33b4888d4ec8783a25cab624cf084cb298bd49f","abstract_canon_sha256":"1b35bfaecddc16a90574e4310c395d42c7ea18cb8a99480fab1c4cf3c2eb0b8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:28.779498Z","signature_b64":"aj5b6BUBxPQerMYADQDPq1h2ePP2NVU7KGOaFRMKoWJYJoficJtcFo+KoOPhlTaZX6qxRz8IHrE16BWyfbwGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c94acb10b7d13217a07f3522fb88bf592794ef74457e0514792c1e72c7b9cba","last_reissued_at":"2026-07-05T07:55:28.779029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:28.779029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizable Two-Branch Framework for Image Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Wu, Ruixuan Wang, Xiaobin Chang","submitted_at":"2024-02-28T06:18:33Z","abstract_excerpt":"Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and achieved substantial improvements. In this paper, a novel two-branch continual learning framework is proposed to further enhance most existing CL methods. Specifically, the main branch can be any existing CL model and the newly introduced side branch is a lightweight convolutional network. The output of each main branch block is modulated by the output of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18086","kind":"arxiv","version":4},"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/2402.18086/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":"2402.18086","created_at":"2026-07-05T07:55:28.779087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18086v4","created_at":"2026-07-05T07:55:28.779087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18086","created_at":"2026-07-05T07:55:28.779087+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSKKZMILPUJS","created_at":"2026-07-05T07:55:28.779087+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSKKZMILPUJSC6QH","created_at":"2026-07-05T07:55:28.779087+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSKKZMIL","created_at":"2026-07-05T07:55:28.779087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13710","citing_title":"SoftPipe: A Soft-Guided Reinforcement Learning Framework for Automated Data Preparation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W","json":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W.json","graph_json":"https://pith.science/api/pith-number/TSKKZMILPUJSC6QH6NJC7OEL6W/graph.json","events_json":"https://pith.science/api/pith-number/TSKKZMILPUJSC6QH6NJC7OEL6W/events.json","paper":"https://pith.science/paper/TSKKZMIL"},"agent_actions":{"view_html":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W","download_json":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W.json","view_paper":"https://pith.science/paper/TSKKZMIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18086&json=true","fetch_graph":"https://pith.science/api/pith-number/TSKKZMILPUJSC6QH6NJC7OEL6W/graph.json","fetch_events":"https://pith.science/api/pith-number/TSKKZMILPUJSC6QH6NJC7OEL6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W/action/storage_attestation","attest_author":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W/action/author_attestation","sign_citation":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W/action/citation_signature","submit_replication":"https://pith.science/pith/TSKKZMILPUJSC6QH6NJC7OEL6W/action/replication_record"}},"created_at":"2026-07-05T07:55:28.779087+00:00","updated_at":"2026-07-05T07:55:28.779087+00:00"}