{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KJY6PWNQLXASFYRNQ5C4DLTVQK","short_pith_number":"pith:KJY6PWNQ","schema_version":"1.0","canonical_sha256":"5271e7d9b05dc122e22d8745c1ae7582abb5974fad32f85ae00dd4b30881d1aa","source":{"kind":"arxiv","id":"1812.05083","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Learning of Semantic Relevance in Text to Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"H.T. Kung, Miriam Cha, Youngjune L. Gwon","submitted_at":"2018-12-12T18:44:23Z","abstract_excerpt":"We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previous work leveraging an auxiliary task in the discriminator. Our generated images are not limited to certain classes and do not suffer from mode collapse while semantically matching the text input. A key to our training methods is how to form positive and negative training examples with respect to the class label of a given image. Instead of selecting random training examples, w"},"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":"1812.05083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-12T18:44:23Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5c80b54ae6fce8029081737e9b0ed6c15b61a5bbd60f1f4510d7501a25cb33a4","abstract_canon_sha256":"7be86c0fb90c9f51d42edef5bae235339a6f4bdc9522fabd4e7a6b3a38556a05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:38.941706Z","signature_b64":"ZjQHFG0VAE7eAOmCJndwgo09sn8HDHBP2unDzW+nSvzmKN8zQ9opOSFc8dV4cvuAVkjS7UlgMy5P1sWfvY//CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5271e7d9b05dc122e22d8745c1ae7582abb5974fad32f85ae00dd4b30881d1aa","last_reissued_at":"2026-05-17T23:54:38.940916Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:38.940916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Learning of Semantic Relevance in Text to Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"H.T. Kung, Miriam Cha, Youngjune L. Gwon","submitted_at":"2018-12-12T18:44:23Z","abstract_excerpt":"We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previous work leveraging an auxiliary task in the discriminator. Our generated images are not limited to certain classes and do not suffer from mode collapse while semantically matching the text input. A key to our training methods is how to form positive and negative training examples with respect to the class label of a given image. Instead of selecting random training examples, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.05083","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":"1812.05083","created_at":"2026-05-17T23:54:38.941064+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.05083v2","created_at":"2026-05-17T23:54:38.941064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05083","created_at":"2026-05-17T23:54:38.941064+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJY6PWNQLXAS","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJY6PWNQLXASFYRN","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJY6PWNQ","created_at":"2026-05-18T12:32:33.847187+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/KJY6PWNQLXASFYRNQ5C4DLTVQK","json":"https://pith.science/pith/KJY6PWNQLXASFYRNQ5C4DLTVQK.json","graph_json":"https://pith.science/api/pith-number/KJY6PWNQLXASFYRNQ5C4DLTVQK/graph.json","events_json":"https://pith.science/api/pith-number/KJY6PWNQLXASFYRNQ5C4DLTVQK/events.json","paper":"https://pith.science/paper/KJY6PWNQ"},"agent_actions":{"view_html":"https://pith.science/pith/KJY6PWNQLXASFYRNQ5C4DLTVQK","download_json":"https://pith.science/pith/KJY6PWNQLXASFYRNQ5C4DLTVQK.json","view_paper":"https://pith.science/paper/KJY6PWNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.05083&json=true","fetch_graph":"https://pith.science/api/pith-number/KJY6PWNQLXASFYRNQ5C4DLTVQK/graph.json","fetch_events":"https://pith.science/api/pith-number/KJY6PWNQLXASFYRNQ5C4DLTVQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJY6PWNQLXASFYRNQ5C4DLTVQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJY6PWNQLXASFYRNQ5C4DLTVQK/action/storage_attestation","attest_author":"https://pith.science/pith/KJY6PWNQLXASFYRNQ5C4DLTVQK/action/author_attestation","sign_citation":"https://pith.science/pith/KJY6PWNQLXASFYRNQ5C4DLTVQK/action/citation_signature","submit_replication":"https://pith.science/pith/KJY6PWNQLXASFYRNQ5C4DLTVQK/action/replication_record"}},"created_at":"2026-05-17T23:54:38.941064+00:00","updated_at":"2026-05-17T23:54:38.941064+00:00"}