{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3MQUC2ZF2BVHMA4QTZYOXW5P2G","short_pith_number":"pith:3MQUC2ZF","schema_version":"1.0","canonical_sha256":"db21416b25d06a7603909e70ebdbafd1924d1c2084bffe8b58e0c0d63ad8974a","source":{"kind":"arxiv","id":"2402.04129","version":2},"attestation_state":"computed","paper":{"title":"OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chun-Fu Chen, Hsiang Hsu, Wei-Cheng Huang","submitted_at":"2024-02-06T16:31:11Z","abstract_excerpt":"Recent works have shown that by using large pre-trained models along with learnable prompts, rehearsal-free methods for class-incremental learning (CIL) settings can achieve superior performance to prominent rehearsal-based ones. Rehearsal-free CIL methods struggle with distinguishing classes from different tasks, as those are not trained together. In this work we propose a regularization method based on virtual outliers to tighten decision boundaries of the classifier, such that confusion of classes among different tasks is mitigated. Recent prompt-based methods often require a pool of task-s"},"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":"2402.04129","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T16:31:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"49888fb3dab792ff9a2f4a2cb934f3514da7b4c5610eea8bc871ebf346809cce","abstract_canon_sha256":"efb29aa287bcf3cccd4c4d5016d722a1a845fd2dfd30f38eb66466a71beae218"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:30.042508Z","signature_b64":"ZQcxoXOt4meO64EDMXX2ZehOeXQx0q+anD5JMvkQ3RR3w9HOktk+IIJjpsbsb7zaezU1tgvZ5JHPAwbZLL63Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db21416b25d06a7603909e70ebdbafd1924d1c2084bffe8b58e0c0d63ad8974a","last_reissued_at":"2026-07-05T11:34:30.041776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:30.041776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chun-Fu Chen, Hsiang Hsu, Wei-Cheng Huang","submitted_at":"2024-02-06T16:31:11Z","abstract_excerpt":"Recent works have shown that by using large pre-trained models along with learnable prompts, rehearsal-free methods for class-incremental learning (CIL) settings can achieve superior performance to prominent rehearsal-based ones. Rehearsal-free CIL methods struggle with distinguishing classes from different tasks, as those are not trained together. In this work we propose a regularization method based on virtual outliers to tighten decision boundaries of the classifier, such that confusion of classes among different tasks is mitigated. Recent prompt-based methods often require a pool of task-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04129","kind":"arxiv","version":2},"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/2402.04129/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":"2402.04129","created_at":"2026-07-05T11:34:30.041878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04129v2","created_at":"2026-07-05T11:34:30.041878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04129","created_at":"2026-07-05T11:34:30.041878+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MQUC2ZF2BVH","created_at":"2026-07-05T11:34:30.041878+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MQUC2ZF2BVHMA4Q","created_at":"2026-07-05T11:34:30.041878+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MQUC2ZF","created_at":"2026-07-05T11:34:30.041878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05540","citing_title":"Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector","ref_index":2016,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G","json":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G.json","graph_json":"https://pith.science/api/pith-number/3MQUC2ZF2BVHMA4QTZYOXW5P2G/graph.json","events_json":"https://pith.science/api/pith-number/3MQUC2ZF2BVHMA4QTZYOXW5P2G/events.json","paper":"https://pith.science/paper/3MQUC2ZF"},"agent_actions":{"view_html":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G","download_json":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G.json","view_paper":"https://pith.science/paper/3MQUC2ZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04129&json=true","fetch_graph":"https://pith.science/api/pith-number/3MQUC2ZF2BVHMA4QTZYOXW5P2G/graph.json","fetch_events":"https://pith.science/api/pith-number/3MQUC2ZF2BVHMA4QTZYOXW5P2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G/action/storage_attestation","attest_author":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G/action/author_attestation","sign_citation":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G/action/citation_signature","submit_replication":"https://pith.science/pith/3MQUC2ZF2BVHMA4QTZYOXW5P2G/action/replication_record"}},"created_at":"2026-07-05T11:34:30.041878+00:00","updated_at":"2026-07-05T11:34:30.041878+00:00"}