{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2UGLEFB6BCLQLX4WBQGLYL33ZM","short_pith_number":"pith:2UGLEFB6","schema_version":"1.0","canonical_sha256":"d50cb2143e089705df960c0cbc2f7bcb1b14cf584c84964cf0061607a53703b5","source":{"kind":"arxiv","id":"2210.15235","version":3},"attestation_state":"computed","paper":{"title":"SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Kaizhu Huang, Qiufeng Wang, Xi Yang, Yuyao Yan, Zhaorui Tan, Zihan Ye","submitted_at":"2022-10-27T07:47:47Z","abstract_excerpt":"Generating consistent and high-quality images from given texts is essential for visual-language understanding. Although impressive results have been achieved in generating high-quality images, text-image consistency is still a major concern in existing GAN-based methods. Particularly, the most popular metric $R$-precision may not accurately reflect the text-image consistency, often resulting in very misleading semantics in the generated images. Albeit its significance, how to design a better text-image consistency metric surprisingly remains under-explored in the community. In this paper, we m"},"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":"2210.15235","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-27T07:47:47Z","cross_cats_sorted":[],"title_canon_sha256":"a9082b42d63176d5fbbc29fab3d684ff1a3d334860cade58f4fe5d35cde1e7a9","abstract_canon_sha256":"29546953d4ac454dcb7114c7358f22b457c96dcf2435c78fb604e24127b107db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:54.338086Z","signature_b64":"Q6h768GdkCEaVwBsGQaFrNRbLTtULN8n7NRZ/FN4LTNA5liJu7jU/e26Kx3D9vS0KpYU4HHTIDUpLCO6slzyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d50cb2143e089705df960c0cbc2f7bcb1b14cf584c84964cf0061607a53703b5","last_reissued_at":"2026-07-05T05:21:54.337679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:54.337679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Kaizhu Huang, Qiufeng Wang, Xi Yang, Yuyao Yan, Zhaorui Tan, Zihan Ye","submitted_at":"2022-10-27T07:47:47Z","abstract_excerpt":"Generating consistent and high-quality images from given texts is essential for visual-language understanding. Although impressive results have been achieved in generating high-quality images, text-image consistency is still a major concern in existing GAN-based methods. Particularly, the most popular metric $R$-precision may not accurately reflect the text-image consistency, often resulting in very misleading semantics in the generated images. Albeit its significance, how to design a better text-image consistency metric surprisingly remains under-explored in the community. In this paper, we m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15235","kind":"arxiv","version":3},"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/2210.15235/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":"2210.15235","created_at":"2026-07-05T05:21:54.337735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15235v3","created_at":"2026-07-05T05:21:54.337735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15235","created_at":"2026-07-05T05:21:54.337735+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UGLEFB6BCLQ","created_at":"2026-07-05T05:21:54.337735+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UGLEFB6BCLQLX4W","created_at":"2026-07-05T05:21:54.337735+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UGLEFB6","created_at":"2026-07-05T05:21:54.337735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24211","citing_title":"Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM","json":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM.json","graph_json":"https://pith.science/api/pith-number/2UGLEFB6BCLQLX4WBQGLYL33ZM/graph.json","events_json":"https://pith.science/api/pith-number/2UGLEFB6BCLQLX4WBQGLYL33ZM/events.json","paper":"https://pith.science/paper/2UGLEFB6"},"agent_actions":{"view_html":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM","download_json":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM.json","view_paper":"https://pith.science/paper/2UGLEFB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15235&json=true","fetch_graph":"https://pith.science/api/pith-number/2UGLEFB6BCLQLX4WBQGLYL33ZM/graph.json","fetch_events":"https://pith.science/api/pith-number/2UGLEFB6BCLQLX4WBQGLYL33ZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM/action/storage_attestation","attest_author":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM/action/author_attestation","sign_citation":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM/action/citation_signature","submit_replication":"https://pith.science/pith/2UGLEFB6BCLQLX4WBQGLYL33ZM/action/replication_record"}},"created_at":"2026-07-05T05:21:54.337735+00:00","updated_at":"2026-07-05T05:21:54.337735+00:00"}