{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5ETEFSVDKSVQ73K2FOLYRE6SCV","short_pith_number":"pith:5ETEFSVD","schema_version":"1.0","canonical_sha256":"e92642caa354ab0fed5a2b978893d2156549c0ecc09cff4adb59df0a51278933","source":{"kind":"arxiv","id":"1911.09046","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Jin, Hongyuan Zha, Junchi Yan, Junjie Wang, Wenjie Zhang, Xiangfeng Wang","submitted_at":"2019-11-20T17:20:05Z","abstract_excerpt":"Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. The key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen classes are available. However, such an assumption is unrealistic when new unseen classes appear dynamically. To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural netw"},"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":"1911.09046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T17:20:05Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"e556d3c44a9f9c230825ad5aac80d2b4c54c08c7657da98ef7294ad6d512d11b","abstract_canon_sha256":"4780d30a86968205817953d5aed516ce4eeec63661c16705a6055c93641f9a15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:49.037025Z","signature_b64":"ZpIvq6rjMiZOM7dmz0mg9oEiAURRbOZBBkfhejDdKgXXdf5AZSUfxZlViXOH4zwTt/VR5/jix1PGBc1lQ5mYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e92642caa354ab0fed5a2b978893d2156549c0ecc09cff4adb59df0a51278933","last_reissued_at":"2026-07-05T00:20:49.036641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:49.036641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Jin, Hongyuan Zha, Junchi Yan, Junjie Wang, Wenjie Zhang, Xiangfeng Wang","submitted_at":"2019-11-20T17:20:05Z","abstract_excerpt":"Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. The key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen classes are available. However, such an assumption is unrealistic when new unseen classes appear dynamically. To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09046","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/1911.09046/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":"1911.09046","created_at":"2026-07-05T00:20:49.036708+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.09046v1","created_at":"2026-07-05T00:20:49.036708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09046","created_at":"2026-07-05T00:20:49.036708+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ETEFSVDKSVQ","created_at":"2026-07-05T00:20:49.036708+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ETEFSVDKSVQ73K2","created_at":"2026-07-05T00:20:49.036708+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ETEFSVD","created_at":"2026-07-05T00:20:49.036708+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/5ETEFSVDKSVQ73K2FOLYRE6SCV","json":"https://pith.science/pith/5ETEFSVDKSVQ73K2FOLYRE6SCV.json","graph_json":"https://pith.science/api/pith-number/5ETEFSVDKSVQ73K2FOLYRE6SCV/graph.json","events_json":"https://pith.science/api/pith-number/5ETEFSVDKSVQ73K2FOLYRE6SCV/events.json","paper":"https://pith.science/paper/5ETEFSVD"},"agent_actions":{"view_html":"https://pith.science/pith/5ETEFSVDKSVQ73K2FOLYRE6SCV","download_json":"https://pith.science/pith/5ETEFSVDKSVQ73K2FOLYRE6SCV.json","view_paper":"https://pith.science/paper/5ETEFSVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.09046&json=true","fetch_graph":"https://pith.science/api/pith-number/5ETEFSVDKSVQ73K2FOLYRE6SCV/graph.json","fetch_events":"https://pith.science/api/pith-number/5ETEFSVDKSVQ73K2FOLYRE6SCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ETEFSVDKSVQ73K2FOLYRE6SCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ETEFSVDKSVQ73K2FOLYRE6SCV/action/storage_attestation","attest_author":"https://pith.science/pith/5ETEFSVDKSVQ73K2FOLYRE6SCV/action/author_attestation","sign_citation":"https://pith.science/pith/5ETEFSVDKSVQ73K2FOLYRE6SCV/action/citation_signature","submit_replication":"https://pith.science/pith/5ETEFSVDKSVQ73K2FOLYRE6SCV/action/replication_record"}},"created_at":"2026-07-05T00:20:49.036708+00:00","updated_at":"2026-07-05T00:20:49.036708+00:00"}