{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3EMNA4U2AJ4AAMOVOJ65K5T2OJ","short_pith_number":"pith:3EMNA4U2","schema_version":"1.0","canonical_sha256":"d918d0729a02780031d5727dd5767a72740ccaa789c71c337137c7697802a89c","source":{"kind":"arxiv","id":"2406.02929","version":2},"attestation_state":"computed","paper":{"title":"ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haotian Xu, Kaizhu Huang, Shreyank N. Gowda, Xiaobo Jin, Xiaowei Huang, Yaochu Jin, Zihan Ye","submitted_at":"2024-06-05T04:37:06Z","abstract_excerpt":"Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is typically achieved by generating visual features for unseen classes based on learned visual-semantic correlations from seen classes. However, most current generative approaches heavily rely on having a sufficient number of samples from seen classes. Our study reveals that a scarcity of seen class samples results in a marked decrease in performance across many generative ZSL techniques. We argue, quantify, and empirically demonstrate that this decline is largely attributable to spurious visual-semantic corre"},"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":"2406.02929","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T04:37:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f362df6a3d96d8620e405559936936d8d443ce592e4a0477c905a343ab1cba73","abstract_canon_sha256":"36c80c453139bc39ed010abb9dc1d2ca35aa695c5fac0262aba4d5ea42d86d65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:16.796462Z","signature_b64":"fuw8rg1GQ+z72Vd8Tul6sH+Uprt5cU4cnkLtsRN6SdiHjtDbvot/E1GMrG4T9a6LSzF4suQpTJ/mFB9jPUC0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d918d0729a02780031d5727dd5767a72740ccaa789c71c337137c7697802a89c","last_reissued_at":"2026-07-05T10:12:16.795982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:16.795982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haotian Xu, Kaizhu Huang, Shreyank N. Gowda, Xiaobo Jin, Xiaowei Huang, Yaochu Jin, Zihan Ye","submitted_at":"2024-06-05T04:37:06Z","abstract_excerpt":"Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is typically achieved by generating visual features for unseen classes based on learned visual-semantic correlations from seen classes. However, most current generative approaches heavily rely on having a sufficient number of samples from seen classes. Our study reveals that a scarcity of seen class samples results in a marked decrease in performance across many generative ZSL techniques. We argue, quantify, and empirically demonstrate that this decline is largely attributable to spurious visual-semantic corre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02929","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/2406.02929/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":"2406.02929","created_at":"2026-07-05T10:12:16.796036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02929v2","created_at":"2026-07-05T10:12:16.796036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02929","created_at":"2026-07-05T10:12:16.796036+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EMNA4U2AJ4A","created_at":"2026-07-05T10:12:16.796036+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EMNA4U2AJ4AAMOV","created_at":"2026-07-05T10:12:16.796036+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EMNA4U2","created_at":"2026-07-05T10:12:16.796036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18282","citing_title":"Improved Feature Generating Framework for Transductive Zero-shot Learning","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ","json":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ.json","graph_json":"https://pith.science/api/pith-number/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/graph.json","events_json":"https://pith.science/api/pith-number/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/events.json","paper":"https://pith.science/paper/3EMNA4U2"},"agent_actions":{"view_html":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ","download_json":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ.json","view_paper":"https://pith.science/paper/3EMNA4U2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02929&json=true","fetch_graph":"https://pith.science/api/pith-number/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/action/storage_attestation","attest_author":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/action/author_attestation","sign_citation":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/action/citation_signature","submit_replication":"https://pith.science/pith/3EMNA4U2AJ4AAMOVOJ65K5T2OJ/action/replication_record"}},"created_at":"2026-07-05T10:12:16.796036+00:00","updated_at":"2026-07-05T10:12:16.796036+00:00"}