{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F5OMLIIE7G7PDMC3RUQTFFBIZH","short_pith_number":"pith:F5OMLIIE","schema_version":"1.0","canonical_sha256":"2f5cc5a104f9bef1b05b8d21329428c9fb19c7fedf03a0b7f8194739565bb3b7","source":{"kind":"arxiv","id":"2402.10063","version":1},"attestation_state":"computed","paper":{"title":"Balancing the Causal Effects in Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chongzhi Zhang, Huawen Feng, Junhao Zheng, Qianli Ma, Ruiyan Wang","submitted_at":"2024-02-15T16:30:45Z","abstract_excerpt":"Class-Incremental Learning (CIL) is a practical and challenging problem for achieving general artificial intelligence. Recently, Pre-Trained Models (PTMs) have led to breakthroughs in both visual and natural language processing tasks. Despite recent studies showing PTMs' potential ability to learn sequentially, a plethora of work indicates the necessity of alleviating the catastrophic forgetting of PTMs. Through a pilot study and a causal analysis of CIL, we reveal that the crux lies in the imbalanced causal effects between new and old data. Specifically, the new data encourage models to adapt"},"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":"2402.10063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T16:30:45Z","cross_cats_sorted":[],"title_canon_sha256":"6835ceabcfee2b7b3242531d968292a1b84330356c9c3658bddec9e3809cd4a0","abstract_canon_sha256":"3280c488a8160ddf43711c7cca6eb3099067ad4f11c544895a221cf3b56ea7a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:40.892660Z","signature_b64":"ZJBezThDapH/nhdlC43fEnKZwQNcH94Dyj9oWSEi6buffgZIwiUShZxkj/fE7WJL7fDdXuFCtx/31mQXl8KgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f5cc5a104f9bef1b05b8d21329428c9fb19c7fedf03a0b7f8194739565bb3b7","last_reissued_at":"2026-07-05T07:45:40.892111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:40.892111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing the Causal Effects in Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chongzhi Zhang, Huawen Feng, Junhao Zheng, Qianli Ma, Ruiyan Wang","submitted_at":"2024-02-15T16:30:45Z","abstract_excerpt":"Class-Incremental Learning (CIL) is a practical and challenging problem for achieving general artificial intelligence. Recently, Pre-Trained Models (PTMs) have led to breakthroughs in both visual and natural language processing tasks. Despite recent studies showing PTMs' potential ability to learn sequentially, a plethora of work indicates the necessity of alleviating the catastrophic forgetting of PTMs. Through a pilot study and a causal analysis of CIL, we reveal that the crux lies in the imbalanced causal effects between new and old data. Specifically, the new data encourage models to adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10063","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/2402.10063/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":"2402.10063","created_at":"2026-07-05T07:45:40.892193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10063v1","created_at":"2026-07-05T07:45:40.892193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10063","created_at":"2026-07-05T07:45:40.892193+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5OMLIIE7G7P","created_at":"2026-07-05T07:45:40.892193+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5OMLIIE7G7PDMC3","created_at":"2026-07-05T07:45:40.892193+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5OMLIIE","created_at":"2026-07-05T07:45:40.892193+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/F5OMLIIE7G7PDMC3RUQTFFBIZH","json":"https://pith.science/pith/F5OMLIIE7G7PDMC3RUQTFFBIZH.json","graph_json":"https://pith.science/api/pith-number/F5OMLIIE7G7PDMC3RUQTFFBIZH/graph.json","events_json":"https://pith.science/api/pith-number/F5OMLIIE7G7PDMC3RUQTFFBIZH/events.json","paper":"https://pith.science/paper/F5OMLIIE"},"agent_actions":{"view_html":"https://pith.science/pith/F5OMLIIE7G7PDMC3RUQTFFBIZH","download_json":"https://pith.science/pith/F5OMLIIE7G7PDMC3RUQTFFBIZH.json","view_paper":"https://pith.science/paper/F5OMLIIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10063&json=true","fetch_graph":"https://pith.science/api/pith-number/F5OMLIIE7G7PDMC3RUQTFFBIZH/graph.json","fetch_events":"https://pith.science/api/pith-number/F5OMLIIE7G7PDMC3RUQTFFBIZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5OMLIIE7G7PDMC3RUQTFFBIZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5OMLIIE7G7PDMC3RUQTFFBIZH/action/storage_attestation","attest_author":"https://pith.science/pith/F5OMLIIE7G7PDMC3RUQTFFBIZH/action/author_attestation","sign_citation":"https://pith.science/pith/F5OMLIIE7G7PDMC3RUQTFFBIZH/action/citation_signature","submit_replication":"https://pith.science/pith/F5OMLIIE7G7PDMC3RUQTFFBIZH/action/replication_record"}},"created_at":"2026-07-05T07:45:40.892193+00:00","updated_at":"2026-07-05T07:45:40.892193+00:00"}