{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5UIRMU4RWHO37NXFSVE7IELAVR","short_pith_number":"pith:5UIRMU4R","schema_version":"1.0","canonical_sha256":"ed11165391b1ddbfb6e59549f41160ac5a7cc7efce0635679c1a457cf7dbe713","source":{"kind":"arxiv","id":"2102.02038","version":1},"attestation_state":"computed","paper":{"title":"Isometric Propagation Network for Generalized Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Lu Liu, Tianyi Zhou, Xuanyi Dong","submitted_at":"2021-02-03T12:45:38Z","abstract_excerpt":"Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few attributes describing that class but no access to any training sample. A popular strategy is to learn a mapping between the semantic space of class attributes and the visual space of images based on the seen classes and their data. Thus, an unseen class image can be ideally mapped to its corresponding class attributes. The key challenge is how to align the representations in the two spaces. For most ZSL settings, the attributes for each seen/unseen class are only represented by a vector while the seen-class"},"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":"2102.02038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-03T12:45:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ea081dc27b233d34d08f84eec9c6d2b5c546fc2afa553a1b70338cbaf667419f","abstract_canon_sha256":"1565836986e994cd9298621af488695e9e8981aa3055d1ab14b1959c15662ec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:36.111505Z","signature_b64":"K4CRQXofAwwgPptM/ZtkMfvf4LKDnNGP0HMtUPjKzjPOQoQtkEXKA575oDqFyAtqT+JAV0WJUROC7IaaGSXxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed11165391b1ddbfb6e59549f41160ac5a7cc7efce0635679c1a457cf7dbe713","last_reissued_at":"2026-07-05T02:12:36.111139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:36.111139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Isometric Propagation Network for Generalized Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Lu Liu, Tianyi Zhou, Xuanyi Dong","submitted_at":"2021-02-03T12:45:38Z","abstract_excerpt":"Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few attributes describing that class but no access to any training sample. A popular strategy is to learn a mapping between the semantic space of class attributes and the visual space of images based on the seen classes and their data. Thus, an unseen class image can be ideally mapped to its corresponding class attributes. The key challenge is how to align the representations in the two spaces. For most ZSL settings, the attributes for each seen/unseen class are only represented by a vector while the seen-class"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02038","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/2102.02038/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":"2102.02038","created_at":"2026-07-05T02:12:36.111184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.02038v1","created_at":"2026-07-05T02:12:36.111184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02038","created_at":"2026-07-05T02:12:36.111184+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UIRMU4RWHO3","created_at":"2026-07-05T02:12:36.111184+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UIRMU4RWHO37NXF","created_at":"2026-07-05T02:12:36.111184+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UIRMU4R","created_at":"2026-07-05T02:12:36.111184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15317","citing_title":"Saving for the future: Enhancing generalization via partial logic regularization","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR","json":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR.json","graph_json":"https://pith.science/api/pith-number/5UIRMU4RWHO37NXFSVE7IELAVR/graph.json","events_json":"https://pith.science/api/pith-number/5UIRMU4RWHO37NXFSVE7IELAVR/events.json","paper":"https://pith.science/paper/5UIRMU4R"},"agent_actions":{"view_html":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR","download_json":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR.json","view_paper":"https://pith.science/paper/5UIRMU4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.02038&json=true","fetch_graph":"https://pith.science/api/pith-number/5UIRMU4RWHO37NXFSVE7IELAVR/graph.json","fetch_events":"https://pith.science/api/pith-number/5UIRMU4RWHO37NXFSVE7IELAVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR/action/storage_attestation","attest_author":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR/action/author_attestation","sign_citation":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR/action/citation_signature","submit_replication":"https://pith.science/pith/5UIRMU4RWHO37NXFSVE7IELAVR/action/replication_record"}},"created_at":"2026-07-05T02:12:36.111184+00:00","updated_at":"2026-07-05T02:12:36.111184+00:00"}