{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MBY7YGDELDUASR6UNTGTPO7OVN","short_pith_number":"pith:MBY7YGDE","schema_version":"1.0","canonical_sha256":"6071fc186458e80947d46ccd37bbeeab77c5decbab3044d3df02c2911b6992e9","source":{"kind":"arxiv","id":"2407.07468","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Few-shot Class-incremental Learning: Learning from Yourself","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingke Meng, Wei-Shi Zheng, Yi-Xing Peng, Yu-Ming Tang","submitted_at":"2024-07-10T08:52:56Z","abstract_excerpt":"Few-shot class-incremental learning (FSCIL) aims to learn sequential classes with limited samples in a few-shot fashion. Inherited from the classical class-incremental learning setting, the popular benchmark of FSCIL uses averaged accuracy (aAcc) and last-task averaged accuracy (lAcc) as the evaluation metrics. However, we reveal that such evaluation metrics may not provide adequate emphasis on the novel class performance, and the continual learning ability of FSCIL methods could be ignored under this benchmark. In this work, as a complement to existing metrics, we offer a new metric called ge"},"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":"2407.07468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T08:52:56Z","cross_cats_sorted":[],"title_canon_sha256":"c421aa5f3bfae0a6b70759049b3eabe4cef32e1191a0926cd34328ce26c2f1f3","abstract_canon_sha256":"cb5981204dab7394b887e786e12a44136ddaaace06f90b5cc6f7e7c339ef7850"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:12.343417Z","signature_b64":"TQeSeT41Ky02mK2rWcZGrn9AtFNQpUHzGThDuGDzIpxRgu4LDR3SXrQXVNeosWdWesvFQiFRpNbhc/M+kEwyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6071fc186458e80947d46ccd37bbeeab77c5decbab3044d3df02c2911b6992e9","last_reissued_at":"2026-07-05T08:42:12.343032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:12.343032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Few-shot Class-incremental Learning: Learning from Yourself","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingke Meng, Wei-Shi Zheng, Yi-Xing Peng, Yu-Ming Tang","submitted_at":"2024-07-10T08:52:56Z","abstract_excerpt":"Few-shot class-incremental learning (FSCIL) aims to learn sequential classes with limited samples in a few-shot fashion. Inherited from the classical class-incremental learning setting, the popular benchmark of FSCIL uses averaged accuracy (aAcc) and last-task averaged accuracy (lAcc) as the evaluation metrics. However, we reveal that such evaluation metrics may not provide adequate emphasis on the novel class performance, and the continual learning ability of FSCIL methods could be ignored under this benchmark. In this work, as a complement to existing metrics, we offer a new metric called ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07468","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/2407.07468/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":"2407.07468","created_at":"2026-07-05T08:42:12.343100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07468v1","created_at":"2026-07-05T08:42:12.343100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07468","created_at":"2026-07-05T08:42:12.343100+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBY7YGDELDUA","created_at":"2026-07-05T08:42:12.343100+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBY7YGDELDUASR6U","created_at":"2026-07-05T08:42:12.343100+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBY7YGDE","created_at":"2026-07-05T08:42:12.343100+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/MBY7YGDELDUASR6UNTGTPO7OVN","json":"https://pith.science/pith/MBY7YGDELDUASR6UNTGTPO7OVN.json","graph_json":"https://pith.science/api/pith-number/MBY7YGDELDUASR6UNTGTPO7OVN/graph.json","events_json":"https://pith.science/api/pith-number/MBY7YGDELDUASR6UNTGTPO7OVN/events.json","paper":"https://pith.science/paper/MBY7YGDE"},"agent_actions":{"view_html":"https://pith.science/pith/MBY7YGDELDUASR6UNTGTPO7OVN","download_json":"https://pith.science/pith/MBY7YGDELDUASR6UNTGTPO7OVN.json","view_paper":"https://pith.science/paper/MBY7YGDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07468&json=true","fetch_graph":"https://pith.science/api/pith-number/MBY7YGDELDUASR6UNTGTPO7OVN/graph.json","fetch_events":"https://pith.science/api/pith-number/MBY7YGDELDUASR6UNTGTPO7OVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBY7YGDELDUASR6UNTGTPO7OVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBY7YGDELDUASR6UNTGTPO7OVN/action/storage_attestation","attest_author":"https://pith.science/pith/MBY7YGDELDUASR6UNTGTPO7OVN/action/author_attestation","sign_citation":"https://pith.science/pith/MBY7YGDELDUASR6UNTGTPO7OVN/action/citation_signature","submit_replication":"https://pith.science/pith/MBY7YGDELDUASR6UNTGTPO7OVN/action/replication_record"}},"created_at":"2026-07-05T08:42:12.343100+00:00","updated_at":"2026-07-05T08:42:12.343100+00:00"}