{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VAFBEEJVAJEOYFNSFRXHL3QYQH","short_pith_number":"pith:VAFBEEJV","schema_version":"1.0","canonical_sha256":"a80a1211350248ec15b22c6e75ee1881cdf92a87f82928201849aa177f84da66","source":{"kind":"arxiv","id":"2104.00567","version":6},"attestation_state":"computed","paper":{"title":"Text to Image Generation with Semantic-Spatial Aware GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Kai Hu, Michael Ying Yang, Wentong Liao","submitted_at":"2021-04-01T15:48:01Z","abstract_excerpt":"Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an image from noise with sentence embedding, and then refine the features with fine-grained word embedding iteratively. A close inspection of their generated images reveals a major limitation: even though the generated image holistically matches the description, individual image regions or parts of somethings are often not recognizable or consistent with words"},"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":"2104.00567","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T15:48:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"902c76fba6c4b6fddf31ab8fdcb0d8b5321defc788350975be2cde602cd711be","abstract_canon_sha256":"7955051035189a16e6592da32c9367462b60d1a8a862fff3de57b0d856f629d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:15.120731Z","signature_b64":"XMNTrN18jnN65LtVCEr5nwZbAfYX5+fUDXsncf263UUzeAQBlQLgqxp+E3l/x0RLx429dZxTHjVpY/vld68FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a80a1211350248ec15b22c6e75ee1881cdf92a87f82928201849aa177f84da66","last_reissued_at":"2026-07-05T04:08:15.120229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:15.120229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text to Image Generation with Semantic-Spatial Aware GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Kai Hu, Michael Ying Yang, Wentong Liao","submitted_at":"2021-04-01T15:48:01Z","abstract_excerpt":"Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an image from noise with sentence embedding, and then refine the features with fine-grained word embedding iteratively. A close inspection of their generated images reveals a major limitation: even though the generated image holistically matches the description, individual image regions or parts of somethings are often not recognizable or consistent with words"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00567","kind":"arxiv","version":6},"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/2104.00567/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":"2104.00567","created_at":"2026-07-05T04:08:15.120287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00567v6","created_at":"2026-07-05T04:08:15.120287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00567","created_at":"2026-07-05T04:08:15.120287+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAFBEEJVAJEO","created_at":"2026-07-05T04:08:15.120287+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAFBEEJVAJEOYFNS","created_at":"2026-07-05T04:08:15.120287+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAFBEEJV","created_at":"2026-07-05T04:08:15.120287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03091","citing_title":"T2UE: Generating Unlearnable Examples from Text Descriptions","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH","json":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH.json","graph_json":"https://pith.science/api/pith-number/VAFBEEJVAJEOYFNSFRXHL3QYQH/graph.json","events_json":"https://pith.science/api/pith-number/VAFBEEJVAJEOYFNSFRXHL3QYQH/events.json","paper":"https://pith.science/paper/VAFBEEJV"},"agent_actions":{"view_html":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH","download_json":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH.json","view_paper":"https://pith.science/paper/VAFBEEJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00567&json=true","fetch_graph":"https://pith.science/api/pith-number/VAFBEEJVAJEOYFNSFRXHL3QYQH/graph.json","fetch_events":"https://pith.science/api/pith-number/VAFBEEJVAJEOYFNSFRXHL3QYQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH/action/storage_attestation","attest_author":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH/action/author_attestation","sign_citation":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH/action/citation_signature","submit_replication":"https://pith.science/pith/VAFBEEJVAJEOYFNSFRXHL3QYQH/action/replication_record"}},"created_at":"2026-07-05T04:08:15.120287+00:00","updated_at":"2026-07-05T04:08:15.120287+00:00"}