{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N6UJE3IIUCAWOCUSS4RRRZUQD4","short_pith_number":"pith:N6UJE3II","schema_version":"1.0","canonical_sha256":"6fa8926d08a081670a92972318e6901f3a421b9c2ada067c73976b9093820f99","source":{"kind":"arxiv","id":"2004.03109","version":1},"attestation_state":"computed","paper":{"title":"Generative Adversarial Zero-shot Learning via Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huajun Chen, Jiaoyan Chen, Yantao Jia, Yuxia Geng, Zhiquan Ye, Zhuo Chen, Zonggang Yuan","submitted_at":"2020-04-07T03:55:26Z","abstract_excerpt":"Zero-shot learning (ZSL) is to handle the prediction of those unseen classes that have no labeled training data. Recently, generative methods like Generative Adversarial Networks (GANs) are being widely investigated for ZSL due to their high accuracy, generalization capability and so on. However, the side information of classes used now is limited to text descriptions and attribute annotations, which are in short of semantics of the classes. In this paper, we introduce a new generative ZSL method named KG-GAN by incorporating rich semantics in a knowledge graph (KG) into GANs. Specifically, we"},"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":"2004.03109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-07T03:55:26Z","cross_cats_sorted":[],"title_canon_sha256":"79de9094f1450b09774fa912a72af29254b86fdb0beb89ae09f529d447fd954e","abstract_canon_sha256":"44de75dc5c12136de1b2cd4ff8f33d9236b1d92a66d986ae7cb345fc450fb037"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:23.331088Z","signature_b64":"4T8n2OIdGA0/xkD599yRnXIPCV1YiQfmZPs4av7NCXN6uh66R8t71vbDbLt8GhUd1RaG30CV/ZIlt8ftstv9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa8926d08a081670a92972318e6901f3a421b9c2ada067c73976b9093820f99","last_reissued_at":"2026-07-05T00:53:23.330644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:23.330644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Adversarial Zero-shot Learning via Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huajun Chen, Jiaoyan Chen, Yantao Jia, Yuxia Geng, Zhiquan Ye, Zhuo Chen, Zonggang Yuan","submitted_at":"2020-04-07T03:55:26Z","abstract_excerpt":"Zero-shot learning (ZSL) is to handle the prediction of those unseen classes that have no labeled training data. Recently, generative methods like Generative Adversarial Networks (GANs) are being widely investigated for ZSL due to their high accuracy, generalization capability and so on. However, the side information of classes used now is limited to text descriptions and attribute annotations, which are in short of semantics of the classes. In this paper, we introduce a new generative ZSL method named KG-GAN by incorporating rich semantics in a knowledge graph (KG) into GANs. Specifically, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03109","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/2004.03109/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":"2004.03109","created_at":"2026-07-05T00:53:23.330703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03109v1","created_at":"2026-07-05T00:53:23.330703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03109","created_at":"2026-07-05T00:53:23.330703+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6UJE3IIUCAW","created_at":"2026-07-05T00:53:23.330703+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6UJE3IIUCAWOCUS","created_at":"2026-07-05T00:53:23.330703+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6UJE3II","created_at":"2026-07-05T00:53:23.330703+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/N6UJE3IIUCAWOCUSS4RRRZUQD4","json":"https://pith.science/pith/N6UJE3IIUCAWOCUSS4RRRZUQD4.json","graph_json":"https://pith.science/api/pith-number/N6UJE3IIUCAWOCUSS4RRRZUQD4/graph.json","events_json":"https://pith.science/api/pith-number/N6UJE3IIUCAWOCUSS4RRRZUQD4/events.json","paper":"https://pith.science/paper/N6UJE3II"},"agent_actions":{"view_html":"https://pith.science/pith/N6UJE3IIUCAWOCUSS4RRRZUQD4","download_json":"https://pith.science/pith/N6UJE3IIUCAWOCUSS4RRRZUQD4.json","view_paper":"https://pith.science/paper/N6UJE3II","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03109&json=true","fetch_graph":"https://pith.science/api/pith-number/N6UJE3IIUCAWOCUSS4RRRZUQD4/graph.json","fetch_events":"https://pith.science/api/pith-number/N6UJE3IIUCAWOCUSS4RRRZUQD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6UJE3IIUCAWOCUSS4RRRZUQD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6UJE3IIUCAWOCUSS4RRRZUQD4/action/storage_attestation","attest_author":"https://pith.science/pith/N6UJE3IIUCAWOCUSS4RRRZUQD4/action/author_attestation","sign_citation":"https://pith.science/pith/N6UJE3IIUCAWOCUSS4RRRZUQD4/action/citation_signature","submit_replication":"https://pith.science/pith/N6UJE3IIUCAWOCUSS4RRRZUQD4/action/replication_record"}},"created_at":"2026-07-05T00:53:23.330703+00:00","updated_at":"2026-07-05T00:53:23.330703+00:00"}