{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:US5Q5QODC5XF7TOB5K6QS7DKX2","short_pith_number":"pith:US5Q5QOD","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"},"canonical_sha256":"a4bb0ec1c3176e5fcdc1eabd097c6abea2087c29be16a7322d5bd8dbb101b0e9","source":{"kind":"arxiv","id":"2412.07196","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07196","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07196v2","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07196","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"US5Q5QODC5XF","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"US5Q5QODC5XF7TOB","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"US5Q5QOD","created_at":"2026-07-05T09:49:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:US5Q5QODC5XF7TOB5K6QS7DKX2","target":"record","payload":{"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"},"canonical_sha256":"a4bb0ec1c3176e5fcdc1eabd097c6abea2087c29be16a7322d5bd8dbb101b0e9","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"},"source_kind":"arxiv","source_id":"2412.07196","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zuHKlB5c5ptNYFFd+9atnmuZ5vlzFBrg2b/xg0/pLaBOj0CP/Riq7DoxIM5pGGKLvbHeD1vIMKVNOfLfiDlfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:17:12.430785Z"},"content_sha256":"f430efc0d174e887b36aaf8c3caa86bfc1300184f7cb55c5e18aa728aa17ed64","schema_version":"1.0","event_id":"sha256:f430efc0d174e887b36aaf8c3caa86bfc1300184f7cb55c5e18aa728aa17ed64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:US5Q5QODC5XF7TOB5K6QS7DKX2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AX4jVUnM0xggoe8sybSi3yuqBAijekp8I1wHxDJDc1Typ4HLl+xdaNpqIYW1HMAznJGoev3llXcvKoVlGVsuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:17:12.431378Z"},"content_sha256":"b390fdfbb085b023700f9dcb2946d79156b3e2a0892c03aef53a9a7b1d8896df","schema_version":"1.0","event_id":"sha256:b390fdfbb085b023700f9dcb2946d79156b3e2a0892c03aef53a9a7b1d8896df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/bundle.json","state_url":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T19:17:12Z","links":{"resolver":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2","bundle":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/bundle.json","state":"https://pith.science/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/US5Q5QODC5XF7TOB5K6QS7DKX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:US5Q5QODC5XF7TOB5K6QS7DKX2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7da43f54cf538594d132e49a6dccb115eafc08c1809b497a6e10667a6873a0c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T05:09:52Z","title_canon_sha256":"3bd0ff9d276c711b54eb13fd8ad95590259feac1ae8f8f8d4204eeb1afd93e0d"},"schema_version":"1.0","source":{"id":"2412.07196","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07196","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07196v2","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07196","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"US5Q5QODC5XF","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"US5Q5QODC5XF7TOB","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"US5Q5QOD","created_at":"2026-07-05T09:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:b390fdfbb085b023700f9dcb2946d79156b3e2a0892c03aef53a9a7b1d8896df","target":"graph","created_at":"2026-07-05T09:49:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.07196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Gady Agam, Kaiyue Zhu, Xu Ouyang, Ying Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T05:09:52Z","title":"Fine-grained Text to Image Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07196","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f430efc0d174e887b36aaf8c3caa86bfc1300184f7cb55c5e18aa728aa17ed64","target":"record","created_at":"2026-07-05T09:49:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7da43f54cf538594d132e49a6dccb115eafc08c1809b497a6e10667a6873a0c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T05:09:52Z","title_canon_sha256":"3bd0ff9d276c711b54eb13fd8ad95590259feac1ae8f8f8d4204eeb1afd93e0d"},"schema_version":"1.0","source":{"id":"2412.07196","kind":"arxiv","version":2}},"canonical_sha256":"a4bb0ec1c3176e5fcdc1eabd097c6abea2087c29be16a7322d5bd8dbb101b0e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4bb0ec1c3176e5fcdc1eabd097c6abea2087c29be16a7322d5bd8dbb101b0e9","first_computed_at":"2026-07-05T09:49:13.793402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:13.793402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GK0ji2v8Mr4cg30e95XXAubAB5TVz/5ev1eqmBGtPByZZiAlhI/3MPDZlFUDW7S9JG81KLw53p95uMK5KnGcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:13.793863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07196","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f430efc0d174e887b36aaf8c3caa86bfc1300184f7cb55c5e18aa728aa17ed64","sha256:b390fdfbb085b023700f9dcb2946d79156b3e2a0892c03aef53a9a7b1d8896df"],"state_sha256":"5879dde3ee8b3d40e4b486d5b9b3fee49e705b122388a4f071c130bf4416fa99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iX84udYbjVRk2kxy//ntplzQ1hZZ85ggbhh6Rgbcdb2MYhqC4rtSzVns61wsa5Biy0kewFHHkyYkG2tmEdY9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:17:12.436623Z","bundle_sha256":"eff6692564fde761413339914c957a8d1c28eb15634edc47648b270506e13934"}}