{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LXAB4IBDGY6M37SK66WL5M5NNH","short_pith_number":"pith:LXAB4IBD","schema_version":"1.0","canonical_sha256":"5dc01e2023363ccdfe4af7acbeb3ad69c1ea242162b5c2a00231e749e7a3628c","source":{"kind":"arxiv","id":"1612.03242","version":2},"attestation_state":"computed","paper":{"title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dimitris Metaxas, Han Zhang, Hongsheng Li, Shaoting Zhang, Tao Xu, Xiaogang Wang, Xiaolei Huang","submitted_at":"2016-12-10T03:11:37Z","abstract_excerpt":"Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) to generate 256x256 photo-realistic images conditioned on text descriptions. We decompose the hard problem into more manageable sub-problems through a sketch-refinement process. The Stage-I GAN sketches th"},"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":"1612.03242","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-10T03:11:37Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ae8600706e1a632eaecf1c764d289fc34e7234705f99e211cd781ec81bce9915","abstract_canon_sha256":"629f0700adf53829efa0edc29fafa0e6c406e3b06b9c82f8c6e310b2cf9afd5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:36.216722Z","signature_b64":"+EwRk4OXTTiaY3nAOcjGXUJ0yRv7wUl/G3ecuaGdI4uBZlEKd1qHNUW6iHzQ2BR6FhRKdAuaXVkcw5zc6AGoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dc01e2023363ccdfe4af7acbeb3ad69c1ea242162b5c2a00231e749e7a3628c","last_reissued_at":"2026-05-18T00:38:36.216114Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:36.216114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dimitris Metaxas, Han Zhang, Hongsheng Li, Shaoting Zhang, Tao Xu, Xiaogang Wang, Xiaolei Huang","submitted_at":"2016-12-10T03:11:37Z","abstract_excerpt":"Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) to generate 256x256 photo-realistic images conditioned on text descriptions. We decompose the hard problem into more manageable sub-problems through a sketch-refinement process. The Stage-I GAN sketches th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03242","kind":"arxiv","version":2},"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":"1612.03242","created_at":"2026-05-18T00:38:36.216211+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.03242v2","created_at":"2026-05-18T00:38:36.216211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03242","created_at":"2026-05-18T00:38:36.216211+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXAB4IBDGY6M","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXAB4IBDGY6M37SK","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXAB4IBD","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05671","citing_title":"Justifying Diagnosis Decisions by Deep Neural Networks","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH","json":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH.json","graph_json":"https://pith.science/api/pith-number/LXAB4IBDGY6M37SK66WL5M5NNH/graph.json","events_json":"https://pith.science/api/pith-number/LXAB4IBDGY6M37SK66WL5M5NNH/events.json","paper":"https://pith.science/paper/LXAB4IBD"},"agent_actions":{"view_html":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH","download_json":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH.json","view_paper":"https://pith.science/paper/LXAB4IBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.03242&json=true","fetch_graph":"https://pith.science/api/pith-number/LXAB4IBDGY6M37SK66WL5M5NNH/graph.json","fetch_events":"https://pith.science/api/pith-number/LXAB4IBDGY6M37SK66WL5M5NNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH/action/storage_attestation","attest_author":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH/action/author_attestation","sign_citation":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH/action/citation_signature","submit_replication":"https://pith.science/pith/LXAB4IBDGY6M37SK66WL5M5NNH/action/replication_record"}},"created_at":"2026-05-18T00:38:36.216211+00:00","updated_at":"2026-05-18T00:38:36.216211+00:00"}