{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GT7Q7ZRTJ6NGLAXAAVSSWGZUCV","short_pith_number":"pith:GT7Q7ZRT","schema_version":"1.0","canonical_sha256":"34ff0fe6334f9a6582e005652b1b34155a351e97063c11171a53508eddee65ba","source":{"kind":"arxiv","id":"2502.16902","version":2},"attestation_state":"computed","paper":{"title":"Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Inseong Choi, Jihie Kim, Suchae Jeong, Youngsik Yun","submitted_at":"2025-02-24T06:56:56Z","abstract_excerpt":"Text-to-Image models, including Stable Diffusion, have significantly improved in generating images that are highly semantically aligned with the given prompts. However, existing models may fail to produce appropriate images for the cultural concepts or objects that are not well known or underrepresented in western cultures, such as `hangari' (Korean utensil). In this paper, we propose a novel approach, Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement (Culture-TRIP), which refines the prompt in order to improve the alignment of the image with such culture nouns in text"},"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":"2502.16902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T06:56:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c096dbf20d8c0361357ebaefff85719ca2e2c569843ef3c005d387fc5525a1b","abstract_canon_sha256":"b2dd6046c0e349993ae9d02d0824a4982d3bb0e5176a70f928fb64652da8c90b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:46.232666Z","signature_b64":"EZWKq3tmgZc07xBzr5J3KofsRXiz9V68jaPlmYgNaf0EfpWArTQSIfRf50GTuoZSGRZEqtmtDj++mfkOuxqoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34ff0fe6334f9a6582e005652b1b34155a351e97063c11171a53508eddee65ba","last_reissued_at":"2026-07-05T11:04:46.232056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:46.232056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Inseong Choi, Jihie Kim, Suchae Jeong, Youngsik Yun","submitted_at":"2025-02-24T06:56:56Z","abstract_excerpt":"Text-to-Image models, including Stable Diffusion, have significantly improved in generating images that are highly semantically aligned with the given prompts. However, existing models may fail to produce appropriate images for the cultural concepts or objects that are not well known or underrepresented in western cultures, such as `hangari' (Korean utensil). In this paper, we propose a novel approach, Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement (Culture-TRIP), which refines the prompt in order to improve the alignment of the image with such culture nouns in text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16902","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/2502.16902/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":"2502.16902","created_at":"2026-07-05T11:04:46.232141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16902v2","created_at":"2026-07-05T11:04:46.232141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16902","created_at":"2026-07-05T11:04:46.232141+00:00"},{"alias_kind":"pith_short_12","alias_value":"GT7Q7ZRTJ6NG","created_at":"2026-07-05T11:04:46.232141+00:00"},{"alias_kind":"pith_short_16","alias_value":"GT7Q7ZRTJ6NGLAXA","created_at":"2026-07-05T11:04:46.232141+00:00"},{"alias_kind":"pith_short_8","alias_value":"GT7Q7ZRT","created_at":"2026-07-05T11:04:46.232141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30800","citing_title":"Computer-Aided Tagging on Wikimedia Commons: Designing for Human-AI Collaboration in Open Knowledge Work","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV","json":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV.json","graph_json":"https://pith.science/api/pith-number/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/graph.json","events_json":"https://pith.science/api/pith-number/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/events.json","paper":"https://pith.science/paper/GT7Q7ZRT"},"agent_actions":{"view_html":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV","download_json":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV.json","view_paper":"https://pith.science/paper/GT7Q7ZRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16902&json=true","fetch_graph":"https://pith.science/api/pith-number/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/graph.json","fetch_events":"https://pith.science/api/pith-number/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/action/storage_attestation","attest_author":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/action/author_attestation","sign_citation":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/action/citation_signature","submit_replication":"https://pith.science/pith/GT7Q7ZRTJ6NGLAXAAVSSWGZUCV/action/replication_record"}},"created_at":"2026-07-05T11:04:46.232141+00:00","updated_at":"2026-07-05T11:04:46.232141+00:00"}