{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:US5Q5QODC5XF7TOB5K6QS7DKX2","short_pith_number":"pith:US5Q5QOD","schema_version":"1.0","canonical_sha256":"a4bb0ec1c3176e5fcdc1eabd097c6abea2087c29be16a7322d5bd8dbb101b0e9","source":{"kind":"arxiv","id":"2412.07196","version":2},"attestation_state":"computed","paper":{"title":"Fine-grained Text to Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gady Agam, Kaiyue Zhu, Xu Ouyang, Ying Chen","submitted_at":"2024-12-10T05:09:52Z","abstract_excerpt":"Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different subclasses, and there may be linguistic discrepancy among texts describing the same image. Recent Generative Adversarial Networks (GAN), such as the Recurrent Affine Transformation (RAT) GAN model, are able to synthesize clear and realistic images from texts. However, GAN models ignore fine-grained level information. In this paper we propose an approach that "},"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":"2412.07196","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T05:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"3bd0ff9d276c711b54eb13fd8ad95590259feac1ae8f8f8d4204eeb1afd93e0d","abstract_canon_sha256":"7da43f54cf538594d132e49a6dccb115eafc08c1809b497a6e10667a6873a0c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:13.793863Z","signature_b64":"GK0ji2v8Mr4cg30e95XXAubAB5TVz/5ev1eqmBGtPByZZiAlhI/3MPDZlFUDW7S9JG81KLw53p95uMK5KnGcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4bb0ec1c3176e5fcdc1eabd097c6abea2087c29be16a7322d5bd8dbb101b0e9","last_reissued_at":"2026-07-05T09:49:13.793402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:13.793402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-grained Text to Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gady Agam, Kaiyue Zhu, Xu Ouyang, Ying Chen","submitted_at":"2024-12-10T05:09:52Z","abstract_excerpt":"Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different subclasses, and there may be linguistic discrepancy among texts describing the same image. Recent Generative Adversarial Networks (GAN), such as the Recurrent Affine Transformation (RAT) GAN model, are able to synthesize clear and realistic images from texts. However, GAN models ignore fine-grained level information. In this paper we propose an approach that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07196","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.07196/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":"2412.07196","created_at":"2026-07-05T09:49:13.793459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07196v2","created_at":"2026-07-05T09:49:13.793459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07196","created_at":"2026-07-05T09:49:13.793459+00:00"},{"alias_kind":"pith_short_12","alias_value":"US5Q5QODC5XF","created_at":"2026-07-05T09:49:13.793459+00:00"},{"alias_kind":"pith_short_16","alias_value":"US5Q5QODC5XF7TOB","created_at":"2026-07-05T09:49:13.793459+00:00"},{"alias_kind":"pith_short_8","alias_value":"US5Q5QOD","created_at":"2026-07-05T09:49:13.793459+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/US5Q5QODC5XF7TOB5K6QS7DKX2","json":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2.json","graph_json":"https://pith.science/api/pith-number/US5Q5QODC5XF7TOB5K6QS7DKX2/graph.json","events_json":"https://pith.science/api/pith-number/US5Q5QODC5XF7TOB5K6QS7DKX2/events.json","paper":"https://pith.science/paper/US5Q5QOD"},"agent_actions":{"view_html":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2","download_json":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2.json","view_paper":"https://pith.science/paper/US5Q5QOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07196&json=true","fetch_graph":"https://pith.science/api/pith-number/US5Q5QODC5XF7TOB5K6QS7DKX2/graph.json","fetch_events":"https://pith.science/api/pith-number/US5Q5QODC5XF7TOB5K6QS7DKX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/action/storage_attestation","attest_author":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/action/author_attestation","sign_citation":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/action/citation_signature","submit_replication":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/action/replication_record"}},"created_at":"2026-07-05T09:49:13.793459+00:00","updated_at":"2026-07-05T09:49:13.793459+00:00"}