{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PWBQTRXSUBWUDUMIGWQXUME734","short_pith_number":"pith:PWBQTRXS","schema_version":"1.0","canonical_sha256":"7d8309c6f2a06d41d18835a17a309fdf053fc198fadf40023be8fc68c325f2ab","source":{"kind":"arxiv","id":"2503.14301","version":2},"attestation_state":"computed","paper":{"title":"FeNeC: Enhancing Continual Learning via Feature Clustering with Neighbor- or Logit-Based Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bartosz Trojan, Hubert Jastrz\\k{e}bski, Jacek Tabor, Kamil Ksi\\k{a}\\.zek, Krzysztof Pniaczek, Micha{\\l} Karp","submitted_at":"2025-03-18T14:42:38Z","abstract_excerpt":"The ability of deep learning models to learn continuously is essential for adapting to new data categories and evolving data distributions. In recent years, approaches leveraging frozen feature extractors after an initial learning phase have been extensively studied. Many of these methods estimate per-class covariance matrices and prototypes based on backbone-derived feature representations. Within this paradigm, we introduce FeNeC (Feature Neighborhood Classifier) and FeNeC-Log, its variant based on the log-likelihood function. Our approach generalizes the existing concept by incorporating da"},"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":"2503.14301","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-18T14:42:38Z","cross_cats_sorted":[],"title_canon_sha256":"4e525e71bd7c8afc8cbcf5646e8bd795fabda0a24e5ebb5e7caecd8dedc98c9d","abstract_canon_sha256":"7099bb6ce07fb74416954f803b53dc81b8c3cac912e88f7711126492de8e4c56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:27.293276Z","signature_b64":"hkDXDndXSOr6XSVWjB6RNm+hqodnyS33oCnT62d0mW8oH6FiskFafegk9SH6FqEEw/rPWhHThYn76llUAijSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d8309c6f2a06d41d18835a17a309fdf053fc198fadf40023be8fc68c325f2ab","last_reissued_at":"2026-07-05T10:48:27.292748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:27.292748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FeNeC: Enhancing Continual Learning via Feature Clustering with Neighbor- or Logit-Based Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bartosz Trojan, Hubert Jastrz\\k{e}bski, Jacek Tabor, Kamil Ksi\\k{a}\\.zek, Krzysztof Pniaczek, Micha{\\l} Karp","submitted_at":"2025-03-18T14:42:38Z","abstract_excerpt":"The ability of deep learning models to learn continuously is essential for adapting to new data categories and evolving data distributions. In recent years, approaches leveraging frozen feature extractors after an initial learning phase have been extensively studied. Many of these methods estimate per-class covariance matrices and prototypes based on backbone-derived feature representations. Within this paradigm, we introduce FeNeC (Feature Neighborhood Classifier) and FeNeC-Log, its variant based on the log-likelihood function. Our approach generalizes the existing concept by incorporating da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14301","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/2503.14301/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":"2503.14301","created_at":"2026-07-05T10:48:27.292807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14301v2","created_at":"2026-07-05T10:48:27.292807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14301","created_at":"2026-07-05T10:48:27.292807+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWBQTRXSUBWU","created_at":"2026-07-05T10:48:27.292807+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWBQTRXSUBWUDUMI","created_at":"2026-07-05T10:48:27.292807+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWBQTRXS","created_at":"2026-07-05T10:48:27.292807+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/PWBQTRXSUBWUDUMIGWQXUME734","json":"https://pith.science/pith/PWBQTRXSUBWUDUMIGWQXUME734.json","graph_json":"https://pith.science/api/pith-number/PWBQTRXSUBWUDUMIGWQXUME734/graph.json","events_json":"https://pith.science/api/pith-number/PWBQTRXSUBWUDUMIGWQXUME734/events.json","paper":"https://pith.science/paper/PWBQTRXS"},"agent_actions":{"view_html":"https://pith.science/pith/PWBQTRXSUBWUDUMIGWQXUME734","download_json":"https://pith.science/pith/PWBQTRXSUBWUDUMIGWQXUME734.json","view_paper":"https://pith.science/paper/PWBQTRXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14301&json=true","fetch_graph":"https://pith.science/api/pith-number/PWBQTRXSUBWUDUMIGWQXUME734/graph.json","fetch_events":"https://pith.science/api/pith-number/PWBQTRXSUBWUDUMIGWQXUME734/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWBQTRXSUBWUDUMIGWQXUME734/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWBQTRXSUBWUDUMIGWQXUME734/action/storage_attestation","attest_author":"https://pith.science/pith/PWBQTRXSUBWUDUMIGWQXUME734/action/author_attestation","sign_citation":"https://pith.science/pith/PWBQTRXSUBWUDUMIGWQXUME734/action/citation_signature","submit_replication":"https://pith.science/pith/PWBQTRXSUBWUDUMIGWQXUME734/action/replication_record"}},"created_at":"2026-07-05T10:48:27.292807+00:00","updated_at":"2026-07-05T10:48:27.292807+00:00"}