{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NM6XOWWSJZYCC5WZEC4TZHVYH5","short_pith_number":"pith:NM6XOWWS","schema_version":"1.0","canonical_sha256":"6b3d775ad24e702176d920b93c9eb83f44131cdecbe4d3e64ad178fce33bb6fd","source":{"kind":"arxiv","id":"2110.06976","version":3},"attestation_state":"computed","paper":{"title":"Representational Continuity for Unsupervised Continual Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Divyam Madaan, Jaehong Yoon, Sung Ju Hwang, Yuanchun Li, Yunxin Liu","submitted_at":"2021-10-13T18:38:06Z","abstract_excerpt":"Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable to real-world applications where the data distribution is often biased and unannotated. In this work, we focus on unsupervised continual learning (UCL), where we learn the feature representations on an unlabelled sequence of tasks and show that reliance on annotated data is not necessary for continual learning. We conduct a systematic study analyzing the le"},"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":"2110.06976","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-13T18:38:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0bc71d444bc779107f6be7ce07686f9fb54f1372fe5ee346e5df8e109afe802b","abstract_canon_sha256":"66f2e63744e4c4c0cd9b5e3c03f2cff01d025123b0543b8277bd5f5477db89a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:27.634880Z","signature_b64":"A3QWt+2+KqHWXAf/y0hHIFF9m2U2LyJML/M1kKGSYVpaioT8qzrX+gm1RaI2GFX4gZyBkVDDWVGuh35M0B/2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b3d775ad24e702176d920b93c9eb83f44131cdecbe4d3e64ad178fce33bb6fd","last_reissued_at":"2026-07-05T04:11:27.634419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:27.634419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representational Continuity for Unsupervised Continual Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Divyam Madaan, Jaehong Yoon, Sung Ju Hwang, Yuanchun Li, Yunxin Liu","submitted_at":"2021-10-13T18:38:06Z","abstract_excerpt":"Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable to real-world applications where the data distribution is often biased and unannotated. In this work, we focus on unsupervised continual learning (UCL), where we learn the feature representations on an unlabelled sequence of tasks and show that reliance on annotated data is not necessary for continual learning. We conduct a systematic study analyzing the le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06976","kind":"arxiv","version":3},"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/2110.06976/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":"2110.06976","created_at":"2026-07-05T04:11:27.634472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06976v3","created_at":"2026-07-05T04:11:27.634472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06976","created_at":"2026-07-05T04:11:27.634472+00:00"},{"alias_kind":"pith_short_12","alias_value":"NM6XOWWSJZYC","created_at":"2026-07-05T04:11:27.634472+00:00"},{"alias_kind":"pith_short_16","alias_value":"NM6XOWWSJZYCC5WZ","created_at":"2026-07-05T04:11:27.634472+00:00"},{"alias_kind":"pith_short_8","alias_value":"NM6XOWWS","created_at":"2026-07-05T04:11:27.634472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07474","citing_title":"Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32016","citing_title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14364","citing_title":"MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14364","citing_title":"MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14364","citing_title":"MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5","json":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5.json","graph_json":"https://pith.science/api/pith-number/NM6XOWWSJZYCC5WZEC4TZHVYH5/graph.json","events_json":"https://pith.science/api/pith-number/NM6XOWWSJZYCC5WZEC4TZHVYH5/events.json","paper":"https://pith.science/paper/NM6XOWWS"},"agent_actions":{"view_html":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5","download_json":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5.json","view_paper":"https://pith.science/paper/NM6XOWWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06976&json=true","fetch_graph":"https://pith.science/api/pith-number/NM6XOWWSJZYCC5WZEC4TZHVYH5/graph.json","fetch_events":"https://pith.science/api/pith-number/NM6XOWWSJZYCC5WZEC4TZHVYH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5/action/storage_attestation","attest_author":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5/action/author_attestation","sign_citation":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5/action/citation_signature","submit_replication":"https://pith.science/pith/NM6XOWWSJZYCC5WZEC4TZHVYH5/action/replication_record"}},"created_at":"2026-07-05T04:11:27.634472+00:00","updated_at":"2026-07-05T04:11:27.634472+00:00"}