{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PNBXQEFRDE35JUXFNB3UOX2426","short_pith_number":"pith:PNBXQEFR","schema_version":"1.0","canonical_sha256":"7b437810b11937d4d2e56877475f5cd7b66d4a3ae788f98637784b10e7dd5499","source":{"kind":"arxiv","id":"2507.01026","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Inspired Generative Zero-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Farhad Pourpanah, Md Shakil Ahamed Shohag, Q. M. Jonathan Wu","submitted_at":"2025-06-18T02:39:36Z","abstract_excerpt":"Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require substantial computational resources and extensive synthetic data, thereby relaxing the original ZSL assumptions. In this paper, we propose FSIGenZ, a few-shot-inspired generative ZSL framework that reduces reliance on large-scale feature synthesis. Our key insight is that class-level attributes exhibit instance-level variability, i.e., some attributes may be "},"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":"2507.01026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T02:39:36Z","cross_cats_sorted":[],"title_canon_sha256":"c0a0e1d799786dbb575342830c4e0674de9560b903a0580821389a5676d29317","abstract_canon_sha256":"dccc69f382a8dc6605de75c40e5305bde6359f3487c572c84d84a5d4cc99a286"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:23.972412Z","signature_b64":"DkFxpIuaMpmkLjAfgb9mACup1E/R0lPpcOzJsJVFobyxrVD5WxYBDgIyyPz5WlnXgnmRzsPSf80hH1mO+lkZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b437810b11937d4d2e56877475f5cd7b66d4a3ae788f98637784b10e7dd5499","last_reissued_at":"2026-07-05T11:30:23.971967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:23.971967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Inspired Generative Zero-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Farhad Pourpanah, Md Shakil Ahamed Shohag, Q. M. Jonathan Wu","submitted_at":"2025-06-18T02:39:36Z","abstract_excerpt":"Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require substantial computational resources and extensive synthetic data, thereby relaxing the original ZSL assumptions. In this paper, we propose FSIGenZ, a few-shot-inspired generative ZSL framework that reduces reliance on large-scale feature synthesis. Our key insight is that class-level attributes exhibit instance-level variability, i.e., some attributes may be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01026","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/2507.01026/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":"2507.01026","created_at":"2026-07-05T11:30:23.972022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01026v1","created_at":"2026-07-05T11:30:23.972022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01026","created_at":"2026-07-05T11:30:23.972022+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNBXQEFRDE35","created_at":"2026-07-05T11:30:23.972022+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNBXQEFRDE35JUXF","created_at":"2026-07-05T11:30:23.972022+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNBXQEFR","created_at":"2026-07-05T11:30:23.972022+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/PNBXQEFRDE35JUXFNB3UOX2426","json":"https://pith.science/pith/PNBXQEFRDE35JUXFNB3UOX2426.json","graph_json":"https://pith.science/api/pith-number/PNBXQEFRDE35JUXFNB3UOX2426/graph.json","events_json":"https://pith.science/api/pith-number/PNBXQEFRDE35JUXFNB3UOX2426/events.json","paper":"https://pith.science/paper/PNBXQEFR"},"agent_actions":{"view_html":"https://pith.science/pith/PNBXQEFRDE35JUXFNB3UOX2426","download_json":"https://pith.science/pith/PNBXQEFRDE35JUXFNB3UOX2426.json","view_paper":"https://pith.science/paper/PNBXQEFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01026&json=true","fetch_graph":"https://pith.science/api/pith-number/PNBXQEFRDE35JUXFNB3UOX2426/graph.json","fetch_events":"https://pith.science/api/pith-number/PNBXQEFRDE35JUXFNB3UOX2426/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNBXQEFRDE35JUXFNB3UOX2426/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNBXQEFRDE35JUXFNB3UOX2426/action/storage_attestation","attest_author":"https://pith.science/pith/PNBXQEFRDE35JUXFNB3UOX2426/action/author_attestation","sign_citation":"https://pith.science/pith/PNBXQEFRDE35JUXFNB3UOX2426/action/citation_signature","submit_replication":"https://pith.science/pith/PNBXQEFRDE35JUXFNB3UOX2426/action/replication_record"}},"created_at":"2026-07-05T11:30:23.972022+00:00","updated_at":"2026-07-05T11:30:23.972022+00:00"}