{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CQAYZICCRY22DLF7JBSKF7HFMQ","short_pith_number":"pith:CQAYZICC","schema_version":"1.0","canonical_sha256":"14018ca0428e35a1acbf4864a2fce5642bf5c0ec6327a524784a18832df37865","source":{"kind":"arxiv","id":"2311.13321","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Supervision for Continual Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bart{\\l}omiej Twardowski, Daniel Marczak, Sebastian Cygert, Tomasz Trzci\\'nski","submitted_at":"2023-11-22T11:24:04Z","abstract_excerpt":"In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use of the vast amounts of unlabeled data. Recent studies have highlighted the strengths of unsupervised methods, particularly self-supervised learning, in providing robust representations. The improved transferability of those representations built with self-supervised methods is often associated with the role played by the multi-layer perceptron projector. In t"},"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":"2311.13321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T11:24:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1b8f8b2e2d37626c8b8fe1a2f78a269ebb2d0b6e9807aa3cc6fb019e9ad78e51","abstract_canon_sha256":"9235475e70b0445f002060a76c5e70ad9290d05386384cc5a34e7e3d88b37780"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:49.068492Z","signature_b64":"n7jYmocF6qtMRGmzSX6gCVxYKn776REK4nLzUapmspfT5TuHnCV6O+xW3aNGoDBlyUKYSADCsMDuh/WtGS9XBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14018ca0428e35a1acbf4864a2fce5642bf5c0ec6327a524784a18832df37865","last_reissued_at":"2026-07-05T08:44:49.068087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:49.068087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Supervision for Continual Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bart{\\l}omiej Twardowski, Daniel Marczak, Sebastian Cygert, Tomasz Trzci\\'nski","submitted_at":"2023-11-22T11:24:04Z","abstract_excerpt":"In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use of the vast amounts of unlabeled data. Recent studies have highlighted the strengths of unsupervised methods, particularly self-supervised learning, in providing robust representations. The improved transferability of those representations built with self-supervised methods is often associated with the role played by the multi-layer perceptron projector. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13321","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/2311.13321/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":"2311.13321","created_at":"2026-07-05T08:44:49.068144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13321v2","created_at":"2026-07-05T08:44:49.068144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13321","created_at":"2026-07-05T08:44:49.068144+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQAYZICCRY22","created_at":"2026-07-05T08:44:49.068144+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQAYZICCRY22DLF7","created_at":"2026-07-05T08:44:49.068144+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQAYZICC","created_at":"2026-07-05T08:44:49.068144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ","json":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ.json","graph_json":"https://pith.science/api/pith-number/CQAYZICCRY22DLF7JBSKF7HFMQ/graph.json","events_json":"https://pith.science/api/pith-number/CQAYZICCRY22DLF7JBSKF7HFMQ/events.json","paper":"https://pith.science/paper/CQAYZICC"},"agent_actions":{"view_html":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ","download_json":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ.json","view_paper":"https://pith.science/paper/CQAYZICC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13321&json=true","fetch_graph":"https://pith.science/api/pith-number/CQAYZICCRY22DLF7JBSKF7HFMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CQAYZICCRY22DLF7JBSKF7HFMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ/action/storage_attestation","attest_author":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ/action/author_attestation","sign_citation":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ/action/citation_signature","submit_replication":"https://pith.science/pith/CQAYZICCRY22DLF7JBSKF7HFMQ/action/replication_record"}},"created_at":"2026-07-05T08:44:49.068144+00:00","updated_at":"2026-07-05T08:44:49.068144+00:00"}