{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HC3I5F7RC3VDR6RNSZX2T6E623","short_pith_number":"pith:HC3I5F7R","schema_version":"1.0","canonical_sha256":"38b68e97f116ea38fa2d966fa9f89ed6ea002c2d948ed36f6405b4b9017ee36d","source":{"kind":"arxiv","id":"2605.28809","version":1},"attestation_state":"computed","paper":{"title":"AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da-Wei Zhou, Yu-Cheng Shi, Zhen-Hao Xie","submitted_at":"2026-05-27T17:58:16Z","abstract_excerpt":"Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g., ``a photo of a [CLASS]''. This seemingly monolithic matching process can be decomposed into two conceptually distinct stages: attribute extraction and attribute aggregation. For example, a model may recognize cat using attributes such as fur texture and whiskers. When learning a new class like car, the model must extract additional attributes like wheels and"},"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":"2605.28809","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T17:58:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5d428a24ce19ae6af36e7abf7469cb127dd5a0bc2681ad004831dc095820c933","abstract_canon_sha256":"89aadf085d0fdd8763bf4550e9380318504adee82b2ab449d1628adea331c232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:04.270193Z","signature_b64":"C53V9ZfInLmRdxdN9NOyyivNIUHnG2HELx/IbZlbXMVTVjhPSyOD4jdZ15GynY/s5l4iaAlw+vHLUwnGvpCHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38b68e97f116ea38fa2d966fa9f89ed6ea002c2d948ed36f6405b4b9017ee36d","last_reissued_at":"2026-05-28T02:05:04.269764Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:04.269764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da-Wei Zhou, Yu-Cheng Shi, Zhen-Hao Xie","submitted_at":"2026-05-27T17:58:16Z","abstract_excerpt":"Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g., ``a photo of a [CLASS]''. This seemingly monolithic matching process can be decomposed into two conceptually distinct stages: attribute extraction and attribute aggregation. For example, a model may recognize cat using attributes such as fur texture and whiskers. When learning a new class like car, the model must extract additional attributes like wheels and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28809","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/2605.28809/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":"2605.28809","created_at":"2026-05-28T02:05:04.269824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28809v1","created_at":"2026-05-28T02:05:04.269824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28809","created_at":"2026-05-28T02:05:04.269824+00:00"},{"alias_kind":"pith_short_12","alias_value":"HC3I5F7RC3VD","created_at":"2026-05-28T02:05:04.269824+00:00"},{"alias_kind":"pith_short_16","alias_value":"HC3I5F7RC3VDR6RN","created_at":"2026-05-28T02:05:04.269824+00:00"},{"alias_kind":"pith_short_8","alias_value":"HC3I5F7R","created_at":"2026-05-28T02:05:04.269824+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/HC3I5F7RC3VDR6RNSZX2T6E623","json":"https://pith.science/pith/HC3I5F7RC3VDR6RNSZX2T6E623.json","graph_json":"https://pith.science/api/pith-number/HC3I5F7RC3VDR6RNSZX2T6E623/graph.json","events_json":"https://pith.science/api/pith-number/HC3I5F7RC3VDR6RNSZX2T6E623/events.json","paper":"https://pith.science/paper/HC3I5F7R"},"agent_actions":{"view_html":"https://pith.science/pith/HC3I5F7RC3VDR6RNSZX2T6E623","download_json":"https://pith.science/pith/HC3I5F7RC3VDR6RNSZX2T6E623.json","view_paper":"https://pith.science/paper/HC3I5F7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28809&json=true","fetch_graph":"https://pith.science/api/pith-number/HC3I5F7RC3VDR6RNSZX2T6E623/graph.json","fetch_events":"https://pith.science/api/pith-number/HC3I5F7RC3VDR6RNSZX2T6E623/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HC3I5F7RC3VDR6RNSZX2T6E623/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HC3I5F7RC3VDR6RNSZX2T6E623/action/storage_attestation","attest_author":"https://pith.science/pith/HC3I5F7RC3VDR6RNSZX2T6E623/action/author_attestation","sign_citation":"https://pith.science/pith/HC3I5F7RC3VDR6RNSZX2T6E623/action/citation_signature","submit_replication":"https://pith.science/pith/HC3I5F7RC3VDR6RNSZX2T6E623/action/replication_record"}},"created_at":"2026-05-28T02:05:04.269824+00:00","updated_at":"2026-05-28T02:05:04.269824+00:00"}