{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4IRWAZKCHHGE7FR4ROADMKFYYV","short_pith_number":"pith:4IRWAZKC","schema_version":"1.0","canonical_sha256":"e22360654239cc4f963c8b803628b8c55f9493b748a505bbd9cc3c647101a783","source":{"kind":"arxiv","id":"2304.08130","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Few-Shot Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Ran, Lusi Li, Prayag Tiwari, Songsong Tian, Weijun Li, Xin Ning","submitted_at":"2023-04-17T10:15:08Z","abstract_excerpt":"Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper prov"},"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":"2304.08130","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-17T10:15:08Z","cross_cats_sorted":[],"title_canon_sha256":"3dc1abba506a78a3d8958e3f6cc09488868d01774fa35b66f974e5506e113d2a","abstract_canon_sha256":"02843689df1350adec6d0e9dd763f3e63f18af7faf38513699796ad2e4be4e71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:14.455539Z","signature_b64":"8edTJPvytj9emg2z8rEYTnXvSw3ghz3e58N1GjJAZvDKmCQUJ2JXNF37pTtzMzNuj6h0EVkd2efV0JGLEyBNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e22360654239cc4f963c8b803628b8c55f9493b748a505bbd9cc3c647101a783","last_reissued_at":"2026-07-05T07:04:14.455130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:14.455130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Few-Shot Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Ran, Lusi Li, Prayag Tiwari, Songsong Tian, Weijun Li, Xin Ning","submitted_at":"2023-04-17T10:15:08Z","abstract_excerpt":"Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper prov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08130","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/2304.08130/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":"2304.08130","created_at":"2026-07-05T07:04:14.455181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08130v2","created_at":"2026-07-05T07:04:14.455181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08130","created_at":"2026-07-05T07:04:14.455181+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IRWAZKCHHGE","created_at":"2026-07-05T07:04:14.455181+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IRWAZKCHHGE7FR4","created_at":"2026-07-05T07:04:14.455181+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IRWAZKC","created_at":"2026-07-05T07:04:14.455181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06642","citing_title":"Class Balance Matters to Active Class-Incremental Learning","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV","json":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV.json","graph_json":"https://pith.science/api/pith-number/4IRWAZKCHHGE7FR4ROADMKFYYV/graph.json","events_json":"https://pith.science/api/pith-number/4IRWAZKCHHGE7FR4ROADMKFYYV/events.json","paper":"https://pith.science/paper/4IRWAZKC"},"agent_actions":{"view_html":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV","download_json":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV.json","view_paper":"https://pith.science/paper/4IRWAZKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08130&json=true","fetch_graph":"https://pith.science/api/pith-number/4IRWAZKCHHGE7FR4ROADMKFYYV/graph.json","fetch_events":"https://pith.science/api/pith-number/4IRWAZKCHHGE7FR4ROADMKFYYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV/action/storage_attestation","attest_author":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV/action/author_attestation","sign_citation":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV/action/citation_signature","submit_replication":"https://pith.science/pith/4IRWAZKCHHGE7FR4ROADMKFYYV/action/replication_record"}},"created_at":"2026-07-05T07:04:14.455181+00:00","updated_at":"2026-07-05T07:04:14.455181+00:00"}