{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IONT3QVPERS527YB2AL5MGNPSK","short_pith_number":"pith:IONT3QVP","schema_version":"1.0","canonical_sha256":"439b3dc2af2465dd7f01d017d619af9296e6a25ff3554e053b0b9d288bf24af0","source":{"kind":"arxiv","id":"2501.04897","version":1},"attestation_state":"computed","paper":{"title":"Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Mohammadkhah, Faeze Hassani, Kiyan Rezaee, Maziar Salahi, Mohammad M. Ghassemi, Sadegh Eskandari, Seyed Amir Bidaki","submitted_at":"2025-01-09T01:03:14Z","abstract_excerpt":"Online Continual Learning (OCL) is a critical area in machine learning, focusing on enabling models to adapt to evolving data streams in real-time while addressing challenges such as catastrophic forgetting and the stability-plasticity trade-off. This study conducts the first comprehensive Systematic Literature Review (SLR) on OCL, analyzing 81 approaches, extracting over 1,000 features (specific tasks addressed by these approaches), and identifying more than 500 components (sub-models within approaches, including algorithms and tools). We also review 83 datasets spanning applications like ima"},"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":"2501.04897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T01:03:14Z","cross_cats_sorted":[],"title_canon_sha256":"b145232bcb1fe4ebd4f1bac16b016d2e2681c242070a62d3efa69bd86375fa58","abstract_canon_sha256":"2d5ec046aa6c93d35f5121ea02181814416d2505a8667b46363643f6e4320c69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:48.153047Z","signature_b64":"RDsCi5+neBtW6Rq14gmgoKh4t10iHtOV20zk/ao6tOu/rt1nzabIQs83jsFC8qkkWFeD/d/H4KCbS65TyfHRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"439b3dc2af2465dd7f01d017d619af9296e6a25ff3554e053b0b9d288bf24af0","last_reissued_at":"2026-07-05T09:58:48.152632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:48.152632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Mohammadkhah, Faeze Hassani, Kiyan Rezaee, Maziar Salahi, Mohammad M. Ghassemi, Sadegh Eskandari, Seyed Amir Bidaki","submitted_at":"2025-01-09T01:03:14Z","abstract_excerpt":"Online Continual Learning (OCL) is a critical area in machine learning, focusing on enabling models to adapt to evolving data streams in real-time while addressing challenges such as catastrophic forgetting and the stability-plasticity trade-off. This study conducts the first comprehensive Systematic Literature Review (SLR) on OCL, analyzing 81 approaches, extracting over 1,000 features (specific tasks addressed by these approaches), and identifying more than 500 components (sub-models within approaches, including algorithms and tools). We also review 83 datasets spanning applications like ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04897","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/2501.04897/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":"2501.04897","created_at":"2026-07-05T09:58:48.152692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04897v1","created_at":"2026-07-05T09:58:48.152692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04897","created_at":"2026-07-05T09:58:48.152692+00:00"},{"alias_kind":"pith_short_12","alias_value":"IONT3QVPERS5","created_at":"2026-07-05T09:58:48.152692+00:00"},{"alias_kind":"pith_short_16","alias_value":"IONT3QVPERS527YB","created_at":"2026-07-05T09:58:48.152692+00:00"},{"alias_kind":"pith_short_8","alias_value":"IONT3QVP","created_at":"2026-07-05T09:58:48.152692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03843","citing_title":"Re-Evaluating Continual Learning with Few-Shot Adaptation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03321","citing_title":"Validation-Gated Multi-Agent Governance for Online Adaptation of Thermal-Hydraulic Surrogate Models under Operating-Regime Shift","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01553","citing_title":"Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK","json":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK.json","graph_json":"https://pith.science/api/pith-number/IONT3QVPERS527YB2AL5MGNPSK/graph.json","events_json":"https://pith.science/api/pith-number/IONT3QVPERS527YB2AL5MGNPSK/events.json","paper":"https://pith.science/paper/IONT3QVP"},"agent_actions":{"view_html":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK","download_json":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK.json","view_paper":"https://pith.science/paper/IONT3QVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04897&json=true","fetch_graph":"https://pith.science/api/pith-number/IONT3QVPERS527YB2AL5MGNPSK/graph.json","fetch_events":"https://pith.science/api/pith-number/IONT3QVPERS527YB2AL5MGNPSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK/action/storage_attestation","attest_author":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK/action/author_attestation","sign_citation":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK/action/citation_signature","submit_replication":"https://pith.science/pith/IONT3QVPERS527YB2AL5MGNPSK/action/replication_record"}},"created_at":"2026-07-05T09:58:48.152692+00:00","updated_at":"2026-07-05T09:58:48.152692+00:00"}