{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YHOST4Y2W2E3GNLTWO7Y5KPHBJ","short_pith_number":"pith:YHOST4Y2","schema_version":"1.0","canonical_sha256":"c1dd29f31ab689b33573b3bf8ea9e70a659d2994119a827ad443e01d8e833306","source":{"kind":"arxiv","id":"2506.20986","version":1},"attestation_state":"computed","paper":{"title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haodong Jing, Nanning Zheng, Xiao Zhang, Yongqiang Ma","submitted_at":"2025-06-26T04:00:55Z","abstract_excerpt":"Compositional Zero-Shot Learning (CZSL) investigates compositional generalization capacity to recognize unknown state-object pairs based on learned primitive concepts. Existing CZSL methods typically derive primitives features through a simple composition-prototype mapping, which is suboptimal for a set of individuals that can be divided into distinct semantic subsets. Moreover, the all-to-one cross-modal primitives matching neglects compositional divergence within identical states or objects, limiting fine-grained image-composition alignment. In this study, we propose EVA, a Mixture-of-Expert"},"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":"2506.20986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T04:00:55Z","cross_cats_sorted":[],"title_canon_sha256":"9eaf9fb99b8c27de8a7294fe0843376a4abe26c78fd4b172c3d37381dfa6036b","abstract_canon_sha256":"f121736a168c3df7156845fa23f0126826e5fb90e5393a1d9991a100b60ee3a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:37.201729Z","signature_b64":"3oHo2JBj8uAjC3iggYdC4WS1KGwkHPTaBX5dN8PA2GTp1dLnHeGB7gL+66NT9kQsfWHdR74ORJUB+n8/igLiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1dd29f31ab689b33573b3bf8ea9e70a659d2994119a827ad443e01d8e833306","last_reissued_at":"2026-07-05T11:27:37.201251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:37.201251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haodong Jing, Nanning Zheng, Xiao Zhang, Yongqiang Ma","submitted_at":"2025-06-26T04:00:55Z","abstract_excerpt":"Compositional Zero-Shot Learning (CZSL) investigates compositional generalization capacity to recognize unknown state-object pairs based on learned primitive concepts. Existing CZSL methods typically derive primitives features through a simple composition-prototype mapping, which is suboptimal for a set of individuals that can be divided into distinct semantic subsets. Moreover, the all-to-one cross-modal primitives matching neglects compositional divergence within identical states or objects, limiting fine-grained image-composition alignment. In this study, we propose EVA, a Mixture-of-Expert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20986","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/2506.20986/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":"2506.20986","created_at":"2026-07-05T11:27:37.201304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20986v1","created_at":"2026-07-05T11:27:37.201304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20986","created_at":"2026-07-05T11:27:37.201304+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHOST4Y2W2E3","created_at":"2026-07-05T11:27:37.201304+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHOST4Y2W2E3GNLT","created_at":"2026-07-05T11:27:37.201304+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHOST4Y2","created_at":"2026-07-05T11:27:37.201304+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/YHOST4Y2W2E3GNLTWO7Y5KPHBJ","json":"https://pith.science/pith/YHOST4Y2W2E3GNLTWO7Y5KPHBJ.json","graph_json":"https://pith.science/api/pith-number/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/graph.json","events_json":"https://pith.science/api/pith-number/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/events.json","paper":"https://pith.science/paper/YHOST4Y2"},"agent_actions":{"view_html":"https://pith.science/pith/YHOST4Y2W2E3GNLTWO7Y5KPHBJ","download_json":"https://pith.science/pith/YHOST4Y2W2E3GNLTWO7Y5KPHBJ.json","view_paper":"https://pith.science/paper/YHOST4Y2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20986&json=true","fetch_graph":"https://pith.science/api/pith-number/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/action/storage_attestation","attest_author":"https://pith.science/pith/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/action/author_attestation","sign_citation":"https://pith.science/pith/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/action/citation_signature","submit_replication":"https://pith.science/pith/YHOST4Y2W2E3GNLTWO7Y5KPHBJ/action/replication_record"}},"created_at":"2026-07-05T11:27:37.201304+00:00","updated_at":"2026-07-05T11:27:37.201304+00:00"}