{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C7RKJMQD5NI3YYGNR6Z7ZS5S65","short_pith_number":"pith:C7RKJMQD","schema_version":"1.0","canonical_sha256":"17e2a4b203eb51bc60cd8fb3fccbb2f75a74be6bbdc623e198fc2b94e44218df","source":{"kind":"arxiv","id":"2501.09361","version":1},"attestation_state":"computed","paper":{"title":"Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Parinita Nema, Vinod K Kurmi","submitted_at":"2025-01-16T08:17:32Z","abstract_excerpt":"Few-shot class incremental learning implies the model to learn new classes while retaining knowledge of previously learned classes with a small number of training instances. Existing frameworks typically freeze the parameters of the previously learned classes during the incorporation of new classes. However, this approach often results in suboptimal class separation of previously learned classes, leading to overlap between old and new classes. Consequently, the performance of old classes degrades on new classes. To address these challenges, we propose a novel feature augmentation driven contra"},"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":"2501.09361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T08:17:32Z","cross_cats_sorted":[],"title_canon_sha256":"d3683e2957599b8ffd96eda8867514d03b9b71994ca9e74a99831389f9a8eed0","abstract_canon_sha256":"6cfcfa6699ccb6cb1adc7d13e1a3241fe17f357c1b34c1c05ccc1cad32448065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:45.790603Z","signature_b64":"sqtspx8D6ilw8z8EZCYJUAq63cYHWyx/2qRkYO+kkTTmyjAyVKancmRXyfQlIlCItk0JPkVMzNFzc24Us4NgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17e2a4b203eb51bc60cd8fb3fccbb2f75a74be6bbdc623e198fc2b94e44218df","last_reissued_at":"2026-07-05T10:01:45.790153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:45.790153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Parinita Nema, Vinod K Kurmi","submitted_at":"2025-01-16T08:17:32Z","abstract_excerpt":"Few-shot class incremental learning implies the model to learn new classes while retaining knowledge of previously learned classes with a small number of training instances. Existing frameworks typically freeze the parameters of the previously learned classes during the incorporation of new classes. However, this approach often results in suboptimal class separation of previously learned classes, leading to overlap between old and new classes. Consequently, the performance of old classes degrades on new classes. To address these challenges, we propose a novel feature augmentation driven contra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09361","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/2501.09361/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":"2501.09361","created_at":"2026-07-05T10:01:45.790215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09361v1","created_at":"2026-07-05T10:01:45.790215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09361","created_at":"2026-07-05T10:01:45.790215+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7RKJMQD5NI3","created_at":"2026-07-05T10:01:45.790215+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7RKJMQD5NI3YYGN","created_at":"2026-07-05T10:01:45.790215+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7RKJMQD","created_at":"2026-07-05T10:01:45.790215+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/C7RKJMQD5NI3YYGNR6Z7ZS5S65","json":"https://pith.science/pith/C7RKJMQD5NI3YYGNR6Z7ZS5S65.json","graph_json":"https://pith.science/api/pith-number/C7RKJMQD5NI3YYGNR6Z7ZS5S65/graph.json","events_json":"https://pith.science/api/pith-number/C7RKJMQD5NI3YYGNR6Z7ZS5S65/events.json","paper":"https://pith.science/paper/C7RKJMQD"},"agent_actions":{"view_html":"https://pith.science/pith/C7RKJMQD5NI3YYGNR6Z7ZS5S65","download_json":"https://pith.science/pith/C7RKJMQD5NI3YYGNR6Z7ZS5S65.json","view_paper":"https://pith.science/paper/C7RKJMQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09361&json=true","fetch_graph":"https://pith.science/api/pith-number/C7RKJMQD5NI3YYGNR6Z7ZS5S65/graph.json","fetch_events":"https://pith.science/api/pith-number/C7RKJMQD5NI3YYGNR6Z7ZS5S65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7RKJMQD5NI3YYGNR6Z7ZS5S65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7RKJMQD5NI3YYGNR6Z7ZS5S65/action/storage_attestation","attest_author":"https://pith.science/pith/C7RKJMQD5NI3YYGNR6Z7ZS5S65/action/author_attestation","sign_citation":"https://pith.science/pith/C7RKJMQD5NI3YYGNR6Z7ZS5S65/action/citation_signature","submit_replication":"https://pith.science/pith/C7RKJMQD5NI3YYGNR6Z7ZS5S65/action/replication_record"}},"created_at":"2026-07-05T10:01:45.790215+00:00","updated_at":"2026-07-05T10:01:45.790215+00:00"}