{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IFQNZRLFJ2OMBMHTGKGASTB3R7","short_pith_number":"pith:IFQNZRLF","schema_version":"1.0","canonical_sha256":"4160dcc5654e9cc0b0f3328c094c3b8fe0ef03c36200b5e4e74b4d6ab7bf3d89","source":{"kind":"arxiv","id":"1810.07368","version":3},"attestation_state":"computed","paper":{"title":"Learning the Compositional Spaces for Generalized Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"HanZe Dong, Leonid Sigal, Sung Ju Hwang, Xiangyang Xue, Yanwei Fu","submitted_at":"2018-10-17T03:11:20Z","abstract_excerpt":"This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time. We propose a novel space decomposition method to solve G-ZSL. Some previous models with space decomposition operations only calibrate the confident prediction of source classes (W-SVM [46]) or take target-class instances as outliers [49]. In contrast, we propose to directly estimate and fine-tune the decision boundary between the source and the target classes. Specifically, we put forward a framework that enables to learn comp"},"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":"1810.07368","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-17T03:11:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bb9262c259adc51e4812a956f472bf921465f772a7eb878bc9ace8e4560aefdd","abstract_canon_sha256":"5a15a26c0baa49947b3c9757f7e9b22ab6a04aa5deea8d9c5ebf0e63af97bf35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:41.972207Z","signature_b64":"UJDhR86jTfQ0n3GV09TmUIvfmm1gY9cC9VvhEm0SwOEsUbMQHFBVuCsrU7rf+N9VHjEMG0N6BzWEFFS4Y+N/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4160dcc5654e9cc0b0f3328c094c3b8fe0ef03c36200b5e4e74b4d6ab7bf3d89","last_reissued_at":"2026-07-05T03:09:41.971870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:41.971870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning the Compositional Spaces for Generalized Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"HanZe Dong, Leonid Sigal, Sung Ju Hwang, Xiangyang Xue, Yanwei Fu","submitted_at":"2018-10-17T03:11:20Z","abstract_excerpt":"This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time. We propose a novel space decomposition method to solve G-ZSL. Some previous models with space decomposition operations only calibrate the confident prediction of source classes (W-SVM [46]) or take target-class instances as outliers [49]. In contrast, we propose to directly estimate and fine-tune the decision boundary between the source and the target classes. Specifically, we put forward a framework that enables to learn comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07368","kind":"arxiv","version":3},"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/1810.07368/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":"1810.07368","created_at":"2026-07-05T03:09:41.971926+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07368v3","created_at":"2026-07-05T03:09:41.971926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07368","created_at":"2026-07-05T03:09:41.971926+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFQNZRLFJ2OM","created_at":"2026-07-05T03:09:41.971926+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFQNZRLFJ2OMBMHT","created_at":"2026-07-05T03:09:41.971926+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFQNZRLF","created_at":"2026-07-05T03:09:41.971926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.03983","citing_title":"Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7","json":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7.json","graph_json":"https://pith.science/api/pith-number/IFQNZRLFJ2OMBMHTGKGASTB3R7/graph.json","events_json":"https://pith.science/api/pith-number/IFQNZRLFJ2OMBMHTGKGASTB3R7/events.json","paper":"https://pith.science/paper/IFQNZRLF"},"agent_actions":{"view_html":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7","download_json":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7.json","view_paper":"https://pith.science/paper/IFQNZRLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07368&json=true","fetch_graph":"https://pith.science/api/pith-number/IFQNZRLFJ2OMBMHTGKGASTB3R7/graph.json","fetch_events":"https://pith.science/api/pith-number/IFQNZRLFJ2OMBMHTGKGASTB3R7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7/action/storage_attestation","attest_author":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7/action/author_attestation","sign_citation":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7/action/citation_signature","submit_replication":"https://pith.science/pith/IFQNZRLFJ2OMBMHTGKGASTB3R7/action/replication_record"}},"created_at":"2026-07-05T03:09:41.971926+00:00","updated_at":"2026-07-05T03:09:41.971926+00:00"}