{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6LREWCH7RRTQRJ4SQJDSSJD5TJ","short_pith_number":"pith:6LREWCH7","schema_version":"1.0","canonical_sha256":"f2e24b08ff8c6708a792824729247d9a777514d619dc5ba1a6f84602dc475bc1","source":{"kind":"arxiv","id":"2404.00901","version":1},"attestation_state":"computed","paper":{"title":"Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanyang Gong, Hefei Mei, Heqian Qiu, Hongliang Li, Jian Jiao, Shiyuan Tang, Xinpeng Hao, Yu Dai","submitted_at":"2024-04-01T03:58:51Z","abstract_excerpt":"Recent video class-incremental learning usually excessively pursues the accuracy of the newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old classes. However, limited storage only allows storing a few representative videos. So we propose SNRO, which slightly shifts the features of new classes to remember old classes. Specifically, SNRO contains Examples Sparse(ES) and Early Break(EB). ES decimates at a lower sample rate to build memory sets and uses interpolation to align those sparse frames in the future. By this, SNRO stores more examples under the same"},"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":"2404.00901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T03:58:51Z","cross_cats_sorted":[],"title_canon_sha256":"1b0d7dbf076057cae66c99c02270bfde355f0063c0116ee16cdd033509a8a669","abstract_canon_sha256":"c52480e1f40ebc581d9938ec87e89c44d29627e6d1426dbda7b6d42c6da4f3ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:58.418590Z","signature_b64":"RitAEqsvoHvfna0c/iSXfEWMwZtUqaix/Tib7SH4gB+EFt6MeobBB/+d3Y9/mP1lPoNQSECFPDKXEQek3NncAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2e24b08ff8c6708a792824729247d9a777514d619dc5ba1a6f84602dc475bc1","last_reissued_at":"2026-07-05T08:02:58.418083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:58.418083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanyang Gong, Hefei Mei, Heqian Qiu, Hongliang Li, Jian Jiao, Shiyuan Tang, Xinpeng Hao, Yu Dai","submitted_at":"2024-04-01T03:58:51Z","abstract_excerpt":"Recent video class-incremental learning usually excessively pursues the accuracy of the newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old classes. However, limited storage only allows storing a few representative videos. So we propose SNRO, which slightly shifts the features of new classes to remember old classes. Specifically, SNRO contains Examples Sparse(ES) and Early Break(EB). ES decimates at a lower sample rate to build memory sets and uses interpolation to align those sparse frames in the future. By this, SNRO stores more examples under the same"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00901","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/2404.00901/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":"2404.00901","created_at":"2026-07-05T08:02:58.418129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00901v1","created_at":"2026-07-05T08:02:58.418129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00901","created_at":"2026-07-05T08:02:58.418129+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LREWCH7RRTQ","created_at":"2026-07-05T08:02:58.418129+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LREWCH7RRTQRJ4S","created_at":"2026-07-05T08:02:58.418129+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LREWCH7","created_at":"2026-07-05T08:02:58.418129+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/6LREWCH7RRTQRJ4SQJDSSJD5TJ","json":"https://pith.science/pith/6LREWCH7RRTQRJ4SQJDSSJD5TJ.json","graph_json":"https://pith.science/api/pith-number/6LREWCH7RRTQRJ4SQJDSSJD5TJ/graph.json","events_json":"https://pith.science/api/pith-number/6LREWCH7RRTQRJ4SQJDSSJD5TJ/events.json","paper":"https://pith.science/paper/6LREWCH7"},"agent_actions":{"view_html":"https://pith.science/pith/6LREWCH7RRTQRJ4SQJDSSJD5TJ","download_json":"https://pith.science/pith/6LREWCH7RRTQRJ4SQJDSSJD5TJ.json","view_paper":"https://pith.science/paper/6LREWCH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00901&json=true","fetch_graph":"https://pith.science/api/pith-number/6LREWCH7RRTQRJ4SQJDSSJD5TJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6LREWCH7RRTQRJ4SQJDSSJD5TJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LREWCH7RRTQRJ4SQJDSSJD5TJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LREWCH7RRTQRJ4SQJDSSJD5TJ/action/storage_attestation","attest_author":"https://pith.science/pith/6LREWCH7RRTQRJ4SQJDSSJD5TJ/action/author_attestation","sign_citation":"https://pith.science/pith/6LREWCH7RRTQRJ4SQJDSSJD5TJ/action/citation_signature","submit_replication":"https://pith.science/pith/6LREWCH7RRTQRJ4SQJDSSJD5TJ/action/replication_record"}},"created_at":"2026-07-05T08:02:58.418129+00:00","updated_at":"2026-07-05T08:02:58.418129+00:00"}