{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WPR3Y4KAGNI2W7PY7HXNLP7PRU","short_pith_number":"pith:WPR3Y4KA","schema_version":"1.0","canonical_sha256":"b3e3bc71403351ab7df8f9eed5bfef8d10885b8be4e798076311c9a8afb0e6ea","source":{"kind":"arxiv","id":"2408.16766","version":2},"attestation_state":"computed","paper":{"title":"CSGO: Content-Style Composition in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ai, Haofan Wang, Peng Xing, Qixun Wang, Renyuan Huang, Xu Bai, Yanpeng Sun, Zechao Li","submitted_at":"2024-08-29T17:59:30Z","abstract_excerpt":"The diffusion model has shown exceptional capabilities in controlled image generation, which has further fueled interest in image style transfer. Existing works mainly focus on training free-based methods (e.g., image inversion) due to the scarcity of specific data. In this study, we present a data construction pipeline for content-style-stylized image triplets that generates and automatically cleanses stylized data triplets. Based on this pipeline, we construct a dataset IMAGStyle, the first large-scale style transfer dataset containing 210k image triplets, available for the community to expl"},"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":"2408.16766","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-29T17:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"270a472dfe53a9f0022a5d755dd3e09dbc5f449679d54d329f7eed81e6ee165c","abstract_canon_sha256":"55a2fd9d1e1cace35ecc3307ddc85b702c33fa0852995086c6125a8358ab8059"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:02.575755Z","signature_b64":"dBhNyD4raM6gdZSYKIFATvQBp6tw8CZ9BvKxIcUZzsIVhUF95JqfNsjr6aWqGYjkA90CFdEXGhB2X3IqeR7BAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3e3bc71403351ab7df8f9eed5bfef8d10885b8be4e798076311c9a8afb0e6ea","last_reissued_at":"2026-07-05T09:03:02.575304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:02.575304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSGO: Content-Style Composition in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ai, Haofan Wang, Peng Xing, Qixun Wang, Renyuan Huang, Xu Bai, Yanpeng Sun, Zechao Li","submitted_at":"2024-08-29T17:59:30Z","abstract_excerpt":"The diffusion model has shown exceptional capabilities in controlled image generation, which has further fueled interest in image style transfer. Existing works mainly focus on training free-based methods (e.g., image inversion) due to the scarcity of specific data. In this study, we present a data construction pipeline for content-style-stylized image triplets that generates and automatically cleanses stylized data triplets. Based on this pipeline, we construct a dataset IMAGStyle, the first large-scale style transfer dataset containing 210k image triplets, available for the community to expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16766","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/2408.16766/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":"2408.16766","created_at":"2026-07-05T09:03:02.575369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16766v2","created_at":"2026-07-05T09:03:02.575369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16766","created_at":"2026-07-05T09:03:02.575369+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPR3Y4KAGNI2","created_at":"2026-07-05T09:03:02.575369+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPR3Y4KAGNI2W7PY","created_at":"2026-07-05T09:03:02.575369+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPR3Y4KA","created_at":"2026-07-05T09:03:02.575369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20506","citing_title":"FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01079","citing_title":"Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11051","citing_title":"NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17500","citing_title":"The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12038","citing_title":"OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08364","citing_title":"MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU","json":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU.json","graph_json":"https://pith.science/api/pith-number/WPR3Y4KAGNI2W7PY7HXNLP7PRU/graph.json","events_json":"https://pith.science/api/pith-number/WPR3Y4KAGNI2W7PY7HXNLP7PRU/events.json","paper":"https://pith.science/paper/WPR3Y4KA"},"agent_actions":{"view_html":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU","download_json":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU.json","view_paper":"https://pith.science/paper/WPR3Y4KA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16766&json=true","fetch_graph":"https://pith.science/api/pith-number/WPR3Y4KAGNI2W7PY7HXNLP7PRU/graph.json","fetch_events":"https://pith.science/api/pith-number/WPR3Y4KAGNI2W7PY7HXNLP7PRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU/action/storage_attestation","attest_author":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU/action/author_attestation","sign_citation":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU/action/citation_signature","submit_replication":"https://pith.science/pith/WPR3Y4KAGNI2W7PY7HXNLP7PRU/action/replication_record"}},"created_at":"2026-07-05T09:03:02.575369+00:00","updated_at":"2026-07-05T09:03:02.575369+00:00"}