{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HVFHYFTOTZEF2YAQE6S6PAM2JV","short_pith_number":"pith:HVFHYFTO","schema_version":"1.0","canonical_sha256":"3d4a7c166e9e485d601027a5e7819a4d5035523661fd7cd806fd85ef0aadc7e4","source":{"kind":"arxiv","id":"2404.00417","version":1},"attestation_state":"computed","paper":{"title":"Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hongwei Yan, Kaisheng Ma, Liyuan Wang, Yi Zhong","submitted_at":"2024-03-30T16:53:10Z","abstract_excerpt":"To accommodate real-world dynamics, artificial intelligence systems need to cope with sequentially arriving content in an online manner. Beyond regular Continual Learning (CL) attempting to address catastrophic forgetting with offline training of each task, Online Continual Learning (OCL) is a more challenging yet realistic setting that performs CL in a one-pass data stream. Current OCL methods primarily rely on memory replay of old training samples. However, a notable gap from CL to OCL stems from the additional overfitting-underfitting dilemma associated with the use of rehearsal buffers: th"},"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":"2404.00417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-30T16:53:10Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"22e0c32d218f3a847dfe111698dcdd6b567af26277ad335036ce82ad402accc6","abstract_canon_sha256":"45f60f9e7ef4e6fa5f5613fa9580e64429c4420871697ba5d92b341c8c9e2648"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:32.967768Z","signature_b64":"sZl53GRCVAjxrC0cPgxfUBoN1Oiy//XqgQXj8e/HuKuP9RFE1NlFozLYoMqzh0vaTnw5Q+pE0hYakMbpBP0BCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d4a7c166e9e485d601027a5e7819a4d5035523661fd7cd806fd85ef0aadc7e4","last_reissued_at":"2026-07-05T08:02:32.967282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:32.967282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hongwei Yan, Kaisheng Ma, Liyuan Wang, Yi Zhong","submitted_at":"2024-03-30T16:53:10Z","abstract_excerpt":"To accommodate real-world dynamics, artificial intelligence systems need to cope with sequentially arriving content in an online manner. Beyond regular Continual Learning (CL) attempting to address catastrophic forgetting with offline training of each task, Online Continual Learning (OCL) is a more challenging yet realistic setting that performs CL in a one-pass data stream. Current OCL methods primarily rely on memory replay of old training samples. However, a notable gap from CL to OCL stems from the additional overfitting-underfitting dilemma associated with the use of rehearsal buffers: th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00417","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/2404.00417/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":"2404.00417","created_at":"2026-07-05T08:02:32.967347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00417v1","created_at":"2026-07-05T08:02:32.967347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00417","created_at":"2026-07-05T08:02:32.967347+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVFHYFTOTZEF","created_at":"2026-07-05T08:02:32.967347+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVFHYFTOTZEF2YAQ","created_at":"2026-07-05T08:02:32.967347+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVFHYFTO","created_at":"2026-07-05T08:02:32.967347+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06192","citing_title":"Right Time to Learn:Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV","json":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV.json","graph_json":"https://pith.science/api/pith-number/HVFHYFTOTZEF2YAQE6S6PAM2JV/graph.json","events_json":"https://pith.science/api/pith-number/HVFHYFTOTZEF2YAQE6S6PAM2JV/events.json","paper":"https://pith.science/paper/HVFHYFTO"},"agent_actions":{"view_html":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV","download_json":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV.json","view_paper":"https://pith.science/paper/HVFHYFTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00417&json=true","fetch_graph":"https://pith.science/api/pith-number/HVFHYFTOTZEF2YAQE6S6PAM2JV/graph.json","fetch_events":"https://pith.science/api/pith-number/HVFHYFTOTZEF2YAQE6S6PAM2JV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV/action/storage_attestation","attest_author":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV/action/author_attestation","sign_citation":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV/action/citation_signature","submit_replication":"https://pith.science/pith/HVFHYFTOTZEF2YAQE6S6PAM2JV/action/replication_record"}},"created_at":"2026-07-05T08:02:32.967347+00:00","updated_at":"2026-07-05T08:02:32.967347+00:00"}