{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7IBV63RTPFSEVSCCBFYOLYSFQN","short_pith_number":"pith:7IBV63RT","schema_version":"1.0","canonical_sha256":"fa035f6e3379644ac8420970e5e24583678063b7fada6a464e8289448ab0c1a9","source":{"kind":"arxiv","id":"2408.12161","version":1},"attestation_state":"computed","paper":{"title":"Rebalancing Multi-Label Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Lyu, Fuyuan Hu, Guangcan Liu, Junzhou Xie, Kaile Du, Yifan Zhou, Yixi Shen, Yuyang Li","submitted_at":"2024-08-22T07:04:22Z","abstract_excerpt":"Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only achieve suboptimal performance due to the oversight of the positive-negative imbalance problem, which manifests at both the label and loss levels because of the task-level partial label issue. The imbalance at the label level arises from the substantial absence of negative labels, while the imbalance at the loss level stems from the asymmetric contributions of"},"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":"2408.12161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T07:04:22Z","cross_cats_sorted":[],"title_canon_sha256":"608be47c365eeea3e7218e41882190ab59bad04817694a9e78d62ccaac079b2a","abstract_canon_sha256":"3bf23487cc9a6625fb5198fb0e99b44e804c00bfc83e780386d592fa2f8b56ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:05.036626Z","signature_b64":"a4lJHbL3yavLnrH/ob9+IHwUH+NUvwbkQKS5ZA0oxiflhtPoFNWrNqpMPdU8uavlYH1+QWzw1MrRsXwiydfcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa035f6e3379644ac8420970e5e24583678063b7fada6a464e8289448ab0c1a9","last_reissued_at":"2026-07-05T08:58:05.036198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:05.036198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rebalancing Multi-Label Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Lyu, Fuyuan Hu, Guangcan Liu, Junzhou Xie, Kaile Du, Yifan Zhou, Yixi Shen, Yuyang Li","submitted_at":"2024-08-22T07:04:22Z","abstract_excerpt":"Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only achieve suboptimal performance due to the oversight of the positive-negative imbalance problem, which manifests at both the label and loss levels because of the task-level partial label issue. The imbalance at the label level arises from the substantial absence of negative labels, while the imbalance at the loss level stems from the asymmetric contributions of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12161","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/2408.12161/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":"2408.12161","created_at":"2026-07-05T08:58:05.036256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12161v1","created_at":"2026-07-05T08:58:05.036256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12161","created_at":"2026-07-05T08:58:05.036256+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IBV63RTPFSE","created_at":"2026-07-05T08:58:05.036256+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IBV63RTPFSEVSCC","created_at":"2026-07-05T08:58:05.036256+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IBV63RT","created_at":"2026-07-05T08:58:05.036256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19680","citing_title":"Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN","json":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN.json","graph_json":"https://pith.science/api/pith-number/7IBV63RTPFSEVSCCBFYOLYSFQN/graph.json","events_json":"https://pith.science/api/pith-number/7IBV63RTPFSEVSCCBFYOLYSFQN/events.json","paper":"https://pith.science/paper/7IBV63RT"},"agent_actions":{"view_html":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN","download_json":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN.json","view_paper":"https://pith.science/paper/7IBV63RT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12161&json=true","fetch_graph":"https://pith.science/api/pith-number/7IBV63RTPFSEVSCCBFYOLYSFQN/graph.json","fetch_events":"https://pith.science/api/pith-number/7IBV63RTPFSEVSCCBFYOLYSFQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN/action/storage_attestation","attest_author":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN/action/author_attestation","sign_citation":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN/action/citation_signature","submit_replication":"https://pith.science/pith/7IBV63RTPFSEVSCCBFYOLYSFQN/action/replication_record"}},"created_at":"2026-07-05T08:58:05.036256+00:00","updated_at":"2026-07-05T08:58:05.036256+00:00"}