{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6WG4GEWESMZ6B4H6XX52R4ZIDJ","short_pith_number":"pith:6WG4GEWE","schema_version":"1.0","canonical_sha256":"f58dc312c49333e0f0febdfba8f3281a5c171327da71492ea295c6fed23d8230","source":{"kind":"arxiv","id":"2309.03904","version":1},"attestation_state":"computed","paper":{"title":"Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ceyuan Yang, Jiapeng Zhu, Kecheng Zheng, Yinghao Xu, Yujun Shen, Zifan Shi","submitted_at":"2023-09-07T17:59:43Z","abstract_excerpt":"Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling from grace on the task of text-conditioned image synthesis. Sparsely-activated mixture-of-experts (MoE) has recently been demonstrated as a valid solution to training large-scale models with limited computational resources. Inspired by such a philosophy, we present Aurora, a GAN-based text-to-image generator that employs a collection of experts to learn feature processing, together with a sparse router to help select the most suitable expert for each feature point. To faithfully decode the sampling s"},"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":"2309.03904","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T17:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"ec38014f3b78892741bf05414f52d3a6e1f1e1203e1f10213efca6e846d4da9f","abstract_canon_sha256":"cce0799460a856d5425286f49beccaffaa3331d8d8a2a323b3aa6f6c566f1775"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:43.589289Z","signature_b64":"pPVJ22RJZOqDzS6d9NbMWtsK/p+btgvrcueclJrXM6x2pFvgUYPKLL0FIt/ROwX2qGlZ4R60TmAxwfRSy/8AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f58dc312c49333e0f0febdfba8f3281a5c171327da71492ea295c6fed23d8230","last_reissued_at":"2026-07-05T06:48:43.588688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:43.588688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ceyuan Yang, Jiapeng Zhu, Kecheng Zheng, Yinghao Xu, Yujun Shen, Zifan Shi","submitted_at":"2023-09-07T17:59:43Z","abstract_excerpt":"Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling from grace on the task of text-conditioned image synthesis. Sparsely-activated mixture-of-experts (MoE) has recently been demonstrated as a valid solution to training large-scale models with limited computational resources. Inspired by such a philosophy, we present Aurora, a GAN-based text-to-image generator that employs a collection of experts to learn feature processing, together with a sparse router to help select the most suitable expert for each feature point. To faithfully decode the sampling s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03904","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/2309.03904/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":"2309.03904","created_at":"2026-07-05T06:48:43.588750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.03904v1","created_at":"2026-07-05T06:48:43.588750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03904","created_at":"2026-07-05T06:48:43.588750+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WG4GEWESMZ6","created_at":"2026-07-05T06:48:43.588750+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WG4GEWESMZ6B4H6","created_at":"2026-07-05T06:48:43.588750+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WG4GEWE","created_at":"2026-07-05T06:48:43.588750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14641","citing_title":"Towards Scalable Topological Regularizers","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ","json":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ.json","graph_json":"https://pith.science/api/pith-number/6WG4GEWESMZ6B4H6XX52R4ZIDJ/graph.json","events_json":"https://pith.science/api/pith-number/6WG4GEWESMZ6B4H6XX52R4ZIDJ/events.json","paper":"https://pith.science/paper/6WG4GEWE"},"agent_actions":{"view_html":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ","download_json":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ.json","view_paper":"https://pith.science/paper/6WG4GEWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.03904&json=true","fetch_graph":"https://pith.science/api/pith-number/6WG4GEWESMZ6B4H6XX52R4ZIDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6WG4GEWESMZ6B4H6XX52R4ZIDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ/action/storage_attestation","attest_author":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ/action/author_attestation","sign_citation":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ/action/citation_signature","submit_replication":"https://pith.science/pith/6WG4GEWESMZ6B4H6XX52R4ZIDJ/action/replication_record"}},"created_at":"2026-07-05T06:48:43.588750+00:00","updated_at":"2026-07-05T06:48:43.588750+00:00"}