{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LOBYHOY5XTGOLAPTLNT3VDHGEO","short_pith_number":"pith:LOBYHOY5","schema_version":"1.0","canonical_sha256":"5b8383bb1dbccce581f35b67ba8ce623b8ff485cb0da19b4b856cb3d420952bc","source":{"kind":"arxiv","id":"2502.06501","version":2},"attestation_state":"computed","paper":{"title":"Learning Clustering-based Prototypes for Compositional Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Qu, Jianan Wei, Wenguan Wang, Xiangbo Shu","submitted_at":"2025-02-10T14:20:01Z","abstract_excerpt":"Learning primitive (i.e., attribute and object) concepts from seen compositions is the primary challenge of Compositional Zero-Shot Learning (CZSL). Existing CZSL solutions typically rely on oversimplified data assumptions, e.g., modeling each primitive with a single centroid primitive representation, ignoring the natural diversities of the attribute (resp. object) when coupled with different objects (resp. attribute). In this work, we develop ClusPro, a robust clustering-based prototype mining framework for CZSL that defines the conceptual boundaries of primitives through a set of diversified"},"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":"2502.06501","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T14:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"0b2b4d3817339bc7e0e635a77da0d9903d0dccc47357bb169f1a88c3422a44d6","abstract_canon_sha256":"68f8f241083c2d78ebc4a4d4e11b4a7ff13e993e5047feecd6fbef79f00e9028"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:13.278353Z","signature_b64":"jIoeqv8cvbjNxNyXarQNPFjzFOdX7MAaCAW1SiBK+2xAdcMclS5cmLfNBKt5136UeVRZA7lI5cU6WqqHml9mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b8383bb1dbccce581f35b67ba8ce623b8ff485cb0da19b4b856cb3d420952bc","last_reissued_at":"2026-07-05T10:18:13.277804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:13.277804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Clustering-based Prototypes for Compositional Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Qu, Jianan Wei, Wenguan Wang, Xiangbo Shu","submitted_at":"2025-02-10T14:20:01Z","abstract_excerpt":"Learning primitive (i.e., attribute and object) concepts from seen compositions is the primary challenge of Compositional Zero-Shot Learning (CZSL). Existing CZSL solutions typically rely on oversimplified data assumptions, e.g., modeling each primitive with a single centroid primitive representation, ignoring the natural diversities of the attribute (resp. object) when coupled with different objects (resp. attribute). In this work, we develop ClusPro, a robust clustering-based prototype mining framework for CZSL that defines the conceptual boundaries of primitives through a set of diversified"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06501","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/2502.06501/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":"2502.06501","created_at":"2026-07-05T10:18:13.277864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06501v2","created_at":"2026-07-05T10:18:13.277864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06501","created_at":"2026-07-05T10:18:13.277864+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOBYHOY5XTGO","created_at":"2026-07-05T10:18:13.277864+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOBYHOY5XTGOLAPT","created_at":"2026-07-05T10:18:13.277864+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOBYHOY5","created_at":"2026-07-05T10:18:13.277864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.23370","citing_title":"GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO","json":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO.json","graph_json":"https://pith.science/api/pith-number/LOBYHOY5XTGOLAPTLNT3VDHGEO/graph.json","events_json":"https://pith.science/api/pith-number/LOBYHOY5XTGOLAPTLNT3VDHGEO/events.json","paper":"https://pith.science/paper/LOBYHOY5"},"agent_actions":{"view_html":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO","download_json":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO.json","view_paper":"https://pith.science/paper/LOBYHOY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06501&json=true","fetch_graph":"https://pith.science/api/pith-number/LOBYHOY5XTGOLAPTLNT3VDHGEO/graph.json","fetch_events":"https://pith.science/api/pith-number/LOBYHOY5XTGOLAPTLNT3VDHGEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO/action/storage_attestation","attest_author":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO/action/author_attestation","sign_citation":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO/action/citation_signature","submit_replication":"https://pith.science/pith/LOBYHOY5XTGOLAPTLNT3VDHGEO/action/replication_record"}},"created_at":"2026-07-05T10:18:13.277864+00:00","updated_at":"2026-07-05T10:18:13.277864+00:00"}