{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JVPP4NKWU7XFLPTZUESUWKALVS","short_pith_number":"pith:JVPP4NKW","schema_version":"1.0","canonical_sha256":"4d5efe3556a7ee55be79a1254b280bac981fa731f2a00df258de6d8f0d9ab35a","source":{"kind":"arxiv","id":"2501.15998","version":1},"attestation_state":"computed","paper":{"title":"Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eunju Yang, Jijoong Moon, Kirill Paramonov, Mete Ozay, Umberto Michieli","submitted_at":"2025-01-27T12:31:50Z","abstract_excerpt":"Class-incremental learning in the context of limited personal labeled samples (few-shot) is critical for numerous real-world applications, such as smart home devices. A key challenge in these scenarios is balancing the trade-off between adapting to new, personalized classes and maintaining the performance of the model on the original, base classes. Fine-tuning the model on novel classes often leads to the phenomenon of catastrophic forgetting, where the accuracy of base classes declines unpredictably and significantly. In this paper, we propose a simple yet effective mechanism to address this "},"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":"2501.15998","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T12:31:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ce3e11d5587b85a739ea7eb2c7af41206527836a4f54ae5c22cd571073a6cc79","abstract_canon_sha256":"3ac4075574fe961dd78f84250294cc687332bde1d922a74b3d21da80d5e6b169"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:53.575257Z","signature_b64":"PBQTBsAu6xl9Svu6SFyBsPxcFPOe5ocrB497Z9Y5GNSXabf/rMiFNuFjPWioZPLzC47zPNQe3e+uk4RYaQeVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d5efe3556a7ee55be79a1254b280bac981fa731f2a00df258de6d8f0d9ab35a","last_reissued_at":"2026-07-05T10:05:53.574742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:53.574742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eunju Yang, Jijoong Moon, Kirill Paramonov, Mete Ozay, Umberto Michieli","submitted_at":"2025-01-27T12:31:50Z","abstract_excerpt":"Class-incremental learning in the context of limited personal labeled samples (few-shot) is critical for numerous real-world applications, such as smart home devices. A key challenge in these scenarios is balancing the trade-off between adapting to new, personalized classes and maintaining the performance of the model on the original, base classes. Fine-tuning the model on novel classes often leads to the phenomenon of catastrophic forgetting, where the accuracy of base classes declines unpredictably and significantly. In this paper, we propose a simple yet effective mechanism to address this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15998","kind":"arxiv","version":1},"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/2501.15998/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":"2501.15998","created_at":"2026-07-05T10:05:53.574812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15998v1","created_at":"2026-07-05T10:05:53.574812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15998","created_at":"2026-07-05T10:05:53.574812+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVPP4NKWU7XF","created_at":"2026-07-05T10:05:53.574812+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVPP4NKWU7XFLPTZ","created_at":"2026-07-05T10:05:53.574812+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVPP4NKW","created_at":"2026-07-05T10:05:53.574812+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/JVPP4NKWU7XFLPTZUESUWKALVS","json":"https://pith.science/pith/JVPP4NKWU7XFLPTZUESUWKALVS.json","graph_json":"https://pith.science/api/pith-number/JVPP4NKWU7XFLPTZUESUWKALVS/graph.json","events_json":"https://pith.science/api/pith-number/JVPP4NKWU7XFLPTZUESUWKALVS/events.json","paper":"https://pith.science/paper/JVPP4NKW"},"agent_actions":{"view_html":"https://pith.science/pith/JVPP4NKWU7XFLPTZUESUWKALVS","download_json":"https://pith.science/pith/JVPP4NKWU7XFLPTZUESUWKALVS.json","view_paper":"https://pith.science/paper/JVPP4NKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15998&json=true","fetch_graph":"https://pith.science/api/pith-number/JVPP4NKWU7XFLPTZUESUWKALVS/graph.json","fetch_events":"https://pith.science/api/pith-number/JVPP4NKWU7XFLPTZUESUWKALVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVPP4NKWU7XFLPTZUESUWKALVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVPP4NKWU7XFLPTZUESUWKALVS/action/storage_attestation","attest_author":"https://pith.science/pith/JVPP4NKWU7XFLPTZUESUWKALVS/action/author_attestation","sign_citation":"https://pith.science/pith/JVPP4NKWU7XFLPTZUESUWKALVS/action/citation_signature","submit_replication":"https://pith.science/pith/JVPP4NKWU7XFLPTZUESUWKALVS/action/replication_record"}},"created_at":"2026-07-05T10:05:53.574812+00:00","updated_at":"2026-07-05T10:05:53.574812+00:00"}