{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:N2WPA75STIQUVVBMJEBTTIQ7YV","short_pith_number":"pith:N2WPA75S","schema_version":"1.0","canonical_sha256":"6eacf07fb29a214ad42c490339a21fc56553efefa9098d54d0d6b032a8a5aef3","source":{"kind":"arxiv","id":"1611.07725","version":2},"attestation_state":"computed","paper":{"title":"iCaRL: Incremental Classifier and Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexander Kolesnikov, Christoph H. Lampert, Georg Sperl, Sylvestre-Alvise Rebuffi","submitted_at":"2016-11-23T10:24:11Z","abstract_excerpt":"A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data represen"},"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":"1611.07725","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-23T10:24:11Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9374c164192be23f781d7f7266a5660704ffa361bccd5b09875f75d273118e39","abstract_canon_sha256":"6bf1d0ec5aaa0aba62085b813753ed3a1a4674d48033c584d8e0a74f0c4ea188"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:22.413553Z","signature_b64":"FmQ44vYXQ7ucj7unw9EyrIz9n5cflIJyAJkaeJ7HW3xqPwWHiL6c7PQKsQ2Z8DPsqIwfd8+bZxPeVpw44yHEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eacf07fb29a214ad42c490339a21fc56553efefa9098d54d0d6b032a8a5aef3","last_reissued_at":"2026-05-18T00:46:22.413090Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:22.413090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iCaRL: Incremental Classifier and Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexander Kolesnikov, Christoph H. Lampert, Georg Sperl, Sylvestre-Alvise Rebuffi","submitted_at":"2016-11-23T10:24:11Z","abstract_excerpt":"A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07725","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":""},"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":"1611.07725","created_at":"2026-05-18T00:46:22.413165+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.07725v2","created_at":"2026-05-18T00:46:22.413165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07725","created_at":"2026-05-18T00:46:22.413165+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2WPA75STIQU","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2WPA75STIQUVVBM","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2WPA75S","created_at":"2026-05-18T12:30:32.724797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19080","citing_title":"MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06477","citing_title":"GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV","json":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV.json","graph_json":"https://pith.science/api/pith-number/N2WPA75STIQUVVBMJEBTTIQ7YV/graph.json","events_json":"https://pith.science/api/pith-number/N2WPA75STIQUVVBMJEBTTIQ7YV/events.json","paper":"https://pith.science/paper/N2WPA75S"},"agent_actions":{"view_html":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV","download_json":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV.json","view_paper":"https://pith.science/paper/N2WPA75S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.07725&json=true","fetch_graph":"https://pith.science/api/pith-number/N2WPA75STIQUVVBMJEBTTIQ7YV/graph.json","fetch_events":"https://pith.science/api/pith-number/N2WPA75STIQUVVBMJEBTTIQ7YV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV/action/storage_attestation","attest_author":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV/action/author_attestation","sign_citation":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV/action/citation_signature","submit_replication":"https://pith.science/pith/N2WPA75STIQUVVBMJEBTTIQ7YV/action/replication_record"}},"created_at":"2026-05-18T00:46:22.413165+00:00","updated_at":"2026-05-18T00:46:22.413165+00:00"}