{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZWP4ZVTPDASR4VMYYGJKNLPM63","short_pith_number":"pith:ZWP4ZVTP","schema_version":"1.0","canonical_sha256":"cd9fccd66f18251e5598c192a6adecf6f9473ecaa119ae7efe8b34d917d6f453","source":{"kind":"arxiv","id":"2405.17022","version":1},"attestation_state":"computed","paper":{"title":"Compositional Few-Shot Class-Incremental Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haichen Zhou, Ruixuan Li, Shanghang Zhang, Yixiong Zou, Yuhua Li","submitted_at":"2024-05-27T10:21:38Z","abstract_excerpt":"Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge. In contrast, humans can easily recognize novel classes with a few samples. Cognitive science demonstrates that an important component of such human capability is compositional learning. This involves identifying visual primitives from learned knowledge and then composing new concepts using these transferred primitives, making incremental learning both effective and interpretable."},"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":"2405.17022","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T10:21:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9d00b1862aa4eddb43f2ac2d7a839f56aa59a6600fbd215d12669b7ca25da5c7","abstract_canon_sha256":"c9339cc457f31cd34dfcda82d27c87fc2cecb3f011fd5cdf3ef603051ce1693c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:38.824585Z","signature_b64":"ExpftZ44g+2r15uCSIotqQunZVgFxppdKtxxjaOAb0Hgei/PWwJ268L8zp1MaF/dfcyeoU5cvLUiv3LYbmZwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd9fccd66f18251e5598c192a6adecf6f9473ecaa119ae7efe8b34d917d6f453","last_reissued_at":"2026-07-05T08:23:38.824145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:38.824145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Few-Shot Class-Incremental Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haichen Zhou, Ruixuan Li, Shanghang Zhang, Yixiong Zou, Yuhua Li","submitted_at":"2024-05-27T10:21:38Z","abstract_excerpt":"Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge. In contrast, humans can easily recognize novel classes with a few samples. Cognitive science demonstrates that an important component of such human capability is compositional learning. This involves identifying visual primitives from learned knowledge and then composing new concepts using these transferred primitives, making incremental learning both effective and interpretable."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17022","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/2405.17022/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":"2405.17022","created_at":"2026-07-05T08:23:38.824201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17022v1","created_at":"2026-07-05T08:23:38.824201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17022","created_at":"2026-07-05T08:23:38.824201+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWP4ZVTPDASR","created_at":"2026-07-05T08:23:38.824201+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWP4ZVTPDASR4VMY","created_at":"2026-07-05T08:23:38.824201+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWP4ZVTP","created_at":"2026-07-05T08:23:38.824201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25799","citing_title":"Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63","json":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63.json","graph_json":"https://pith.science/api/pith-number/ZWP4ZVTPDASR4VMYYGJKNLPM63/graph.json","events_json":"https://pith.science/api/pith-number/ZWP4ZVTPDASR4VMYYGJKNLPM63/events.json","paper":"https://pith.science/paper/ZWP4ZVTP"},"agent_actions":{"view_html":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63","download_json":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63.json","view_paper":"https://pith.science/paper/ZWP4ZVTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17022&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWP4ZVTPDASR4VMYYGJKNLPM63/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWP4ZVTPDASR4VMYYGJKNLPM63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63/action/storage_attestation","attest_author":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63/action/author_attestation","sign_citation":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63/action/citation_signature","submit_replication":"https://pith.science/pith/ZWP4ZVTPDASR4VMYYGJKNLPM63/action/replication_record"}},"created_at":"2026-07-05T08:23:38.824201+00:00","updated_at":"2026-07-05T08:23:38.824201+00:00"}