{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6DM2OEY5BEHBXDP2OA7WC6X2XF","short_pith_number":"pith:6DM2OEY5","schema_version":"1.0","canonical_sha256":"f0d9a7131d090e1b8dfa703f617afab9737ab5496a037762c74969bada1aedbe","source":{"kind":"arxiv","id":"1901.02199","version":1},"attestation_state":"computed","paper":{"title":"FIGR: Few-shot Image Generation with Reptile","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Louis Clou\\^atre, Marc Demers","submitted_at":"2019-01-08T08:15:08Z","abstract_excerpt":"Generative Adversarial Networks (GAN) boast impressive capacity to generate realistic images. However, like much of the field of deep learning, they require an inordinate amount of data to produce results, thereby limiting their usefulness in generating novelty. In the same vein, recent advances in meta-learning have opened the door to many few-shot learning applications. In the present work, we propose Few-shot Image Generation using Reptile (FIGR), a GAN meta-trained with Reptile. Our model successfully generates novel images on both MNIST and Omniglot with as little as 4 images from an unse"},"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":"1901.02199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T08:15:08Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"e128a3d863306ff6ace4eb112c6db9c4ea2b508cccd99ce3fa99395a0e2ffa76","abstract_canon_sha256":"c0039785b2b617814709ef59bbdfc388e359ea4a8a4647d6556d30dd6679ba57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:43.788076Z","signature_b64":"gwk+CplgDNBAmUzZEn6+hEgngBZ03VfGFJAzJlmDDMV9fUFzHv9spQKvhvzcSM21WxUGvyHZW9weSv0xfrF0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d9a7131d090e1b8dfa703f617afab9737ab5496a037762c74969bada1aedbe","last_reissued_at":"2026-05-17T23:56:43.787729Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:43.787729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FIGR: Few-shot Image Generation with Reptile","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Louis Clou\\^atre, Marc Demers","submitted_at":"2019-01-08T08:15:08Z","abstract_excerpt":"Generative Adversarial Networks (GAN) boast impressive capacity to generate realistic images. However, like much of the field of deep learning, they require an inordinate amount of data to produce results, thereby limiting their usefulness in generating novelty. In the same vein, recent advances in meta-learning have opened the door to many few-shot learning applications. In the present work, we propose Few-shot Image Generation using Reptile (FIGR), a GAN meta-trained with Reptile. Our model successfully generates novel images on both MNIST and Omniglot with as little as 4 images from an unse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02199","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":""},"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":"1901.02199","created_at":"2026-05-17T23:56:43.787783+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.02199v1","created_at":"2026-05-17T23:56:43.787783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02199","created_at":"2026-05-17T23:56:43.787783+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DM2OEY5BEHB","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DM2OEY5BEHBXDP2","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DM2OEY5","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10437","citing_title":"SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01517","citing_title":"VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08615","citing_title":"MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF","json":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF.json","graph_json":"https://pith.science/api/pith-number/6DM2OEY5BEHBXDP2OA7WC6X2XF/graph.json","events_json":"https://pith.science/api/pith-number/6DM2OEY5BEHBXDP2OA7WC6X2XF/events.json","paper":"https://pith.science/paper/6DM2OEY5"},"agent_actions":{"view_html":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF","download_json":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF.json","view_paper":"https://pith.science/paper/6DM2OEY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.02199&json=true","fetch_graph":"https://pith.science/api/pith-number/6DM2OEY5BEHBXDP2OA7WC6X2XF/graph.json","fetch_events":"https://pith.science/api/pith-number/6DM2OEY5BEHBXDP2OA7WC6X2XF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF/action/storage_attestation","attest_author":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF/action/author_attestation","sign_citation":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF/action/citation_signature","submit_replication":"https://pith.science/pith/6DM2OEY5BEHBXDP2OA7WC6X2XF/action/replication_record"}},"created_at":"2026-05-17T23:56:43.787783+00:00","updated_at":"2026-05-17T23:56:43.787783+00:00"}