{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SUU4EJJIWF3RQNECSR4NHM6TJS","short_pith_number":"pith:SUU4EJJI","schema_version":"1.0","canonical_sha256":"9529c22528b1771834829478d3b3d34c89cead95b65566743dd21b9839edf1b1","source":{"kind":"arxiv","id":"2110.07059","version":2},"attestation_state":"computed","paper":{"title":"Subspace Regularizers for Few-Shot Class Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Afra Feyza Aky\\\"urek, Derry Tanti Wijaya, Ekin Aky\\\"urek, Jacob Andreas","submitted_at":"2021-10-13T22:19:53Z","abstract_excerpt":"Few-shot class incremental learning -- the problem of updating a trained classifier to discriminate among an expanded set of classes with limited labeled data -- is a key challenge for machine learning systems deployed in non-stationary environments. Existing approaches to the problem rely on complex model architectures and training procedures that are difficult to tune and re-use. In this paper, we present an extremely simple approach that enables the use of ordinary logistic regression classifiers for few-shot incremental learning. The key to this approach is a new family of subspace regular"},"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":"2110.07059","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-13T22:19:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41f72e072eed60ba82ec8ef58888e6b007349fc8884c91f20a6c74eecdf0d4cd","abstract_canon_sha256":"b0df148404352cc41d5c395aaaf74af19fc89c0c70d935073933684aa2465043"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:17.806152Z","signature_b64":"NZuzZ4un6d3hHOT+Rb2xppLkDEGN4h9WNlEDqShVuloZLZZV3y374Heb5pLOdNaAA6L+uKQa9B+SaoLHBEuRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9529c22528b1771834829478d3b3d34c89cead95b65566743dd21b9839edf1b1","last_reissued_at":"2026-07-05T03:58:17.805751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:17.805751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subspace Regularizers for Few-Shot Class Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Afra Feyza Aky\\\"urek, Derry Tanti Wijaya, Ekin Aky\\\"urek, Jacob Andreas","submitted_at":"2021-10-13T22:19:53Z","abstract_excerpt":"Few-shot class incremental learning -- the problem of updating a trained classifier to discriminate among an expanded set of classes with limited labeled data -- is a key challenge for machine learning systems deployed in non-stationary environments. Existing approaches to the problem rely on complex model architectures and training procedures that are difficult to tune and re-use. In this paper, we present an extremely simple approach that enables the use of ordinary logistic regression classifiers for few-shot incremental learning. The key to this approach is a new family of subspace regular"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07059","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/2110.07059/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":"2110.07059","created_at":"2026-07-05T03:58:17.805810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07059v2","created_at":"2026-07-05T03:58:17.805810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07059","created_at":"2026-07-05T03:58:17.805810+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUU4EJJIWF3R","created_at":"2026-07-05T03:58:17.805810+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUU4EJJIWF3RQNEC","created_at":"2026-07-05T03:58:17.805810+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUU4EJJI","created_at":"2026-07-05T03:58:17.805810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23744","citing_title":"Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS","json":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS.json","graph_json":"https://pith.science/api/pith-number/SUU4EJJIWF3RQNECSR4NHM6TJS/graph.json","events_json":"https://pith.science/api/pith-number/SUU4EJJIWF3RQNECSR4NHM6TJS/events.json","paper":"https://pith.science/paper/SUU4EJJI"},"agent_actions":{"view_html":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS","download_json":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS.json","view_paper":"https://pith.science/paper/SUU4EJJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07059&json=true","fetch_graph":"https://pith.science/api/pith-number/SUU4EJJIWF3RQNECSR4NHM6TJS/graph.json","fetch_events":"https://pith.science/api/pith-number/SUU4EJJIWF3RQNECSR4NHM6TJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS/action/storage_attestation","attest_author":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS/action/author_attestation","sign_citation":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS/action/citation_signature","submit_replication":"https://pith.science/pith/SUU4EJJIWF3RQNECSR4NHM6TJS/action/replication_record"}},"created_at":"2026-07-05T03:58:17.805810+00:00","updated_at":"2026-07-05T03:58:17.805810+00:00"}