{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XORSTIA6OBI7JQ7SFN7RBA2Q3B","short_pith_number":"pith:XORSTIA6","schema_version":"1.0","canonical_sha256":"bba329a01e7051f4c3f22b7f108350d85262dd3184a65f220e7102f4c3a112e3","source":{"kind":"arxiv","id":"1605.05396","version":2},"attestation_state":"computed","paper":{"title":"Generative Adversarial Text to Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Bernt Schiele, Honglak Lee, Lajanugen Logeswaran, Scott Reed, Xinchen Yan, Zeynep Akata","submitted_at":"2016-05-17T23:09:15Z","abstract_excerpt":"Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been developed to learn discriminative text feature representations. Meanwhile, deep convolutional generative adversarial networks (GANs) have begun to generate highly compelling images of specific categories, such as faces, album covers, and room interiors. In this work, we develop a novel deep architecture and GAN formulation to effectively bridge these advances in text"},"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":"1605.05396","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-05-17T23:09:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"77abafa4b9c77446f3934bcc887e16bd5a4e34b4aecabdf0ea3e212efbb41bfa","abstract_canon_sha256":"59190351a999c16526e022443409d7107ce4173ce1b0b809e8a1780f4b434c46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:54.644754Z","signature_b64":"8tgDsuapGj0wnZo8Ug2SM5K58Dy2Kqx5YOj0BsKUS7XUeFVm7n4jb9Bj4Hyd6u272MgApeonHJkTKVOZPb+QBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bba329a01e7051f4c3f22b7f108350d85262dd3184a65f220e7102f4c3a112e3","last_reissued_at":"2026-05-18T01:12:54.644341Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:54.644341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Adversarial Text to Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Bernt Schiele, Honglak Lee, Lajanugen Logeswaran, Scott Reed, Xinchen Yan, Zeynep Akata","submitted_at":"2016-05-17T23:09:15Z","abstract_excerpt":"Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been developed to learn discriminative text feature representations. Meanwhile, deep convolutional generative adversarial networks (GANs) have begun to generate highly compelling images of specific categories, such as faces, album covers, and room interiors. In this work, we develop a novel deep architecture and GAN formulation to effectively bridge these advances in text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.05396","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":"1605.05396","created_at":"2026-05-18T01:12:54.644420+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.05396v2","created_at":"2026-05-18T01:12:54.644420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.05396","created_at":"2026-05-18T01:12:54.644420+00:00"},{"alias_kind":"pith_short_12","alias_value":"XORSTIA6OBI7","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XORSTIA6OBI7JQ7S","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XORSTIA6","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.11080","citing_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03426","citing_title":"Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10178","citing_title":"Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14689","citing_title":"Are Candidate Models Really Needed for Active Learning?","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21036","citing_title":"Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2101.00027","citing_title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","ref_index":166,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B","json":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B.json","graph_json":"https://pith.science/api/pith-number/XORSTIA6OBI7JQ7SFN7RBA2Q3B/graph.json","events_json":"https://pith.science/api/pith-number/XORSTIA6OBI7JQ7SFN7RBA2Q3B/events.json","paper":"https://pith.science/paper/XORSTIA6"},"agent_actions":{"view_html":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B","download_json":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B.json","view_paper":"https://pith.science/paper/XORSTIA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.05396&json=true","fetch_graph":"https://pith.science/api/pith-number/XORSTIA6OBI7JQ7SFN7RBA2Q3B/graph.json","fetch_events":"https://pith.science/api/pith-number/XORSTIA6OBI7JQ7SFN7RBA2Q3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B/action/storage_attestation","attest_author":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B/action/author_attestation","sign_citation":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B/action/citation_signature","submit_replication":"https://pith.science/pith/XORSTIA6OBI7JQ7SFN7RBA2Q3B/action/replication_record"}},"created_at":"2026-05-18T01:12:54.644420+00:00","updated_at":"2026-05-18T01:12:54.644420+00:00"}